KR102830045B1 - Method, device, and program for monitoring and controlling hvac systems - Google Patents

Abstract

A method for monitoring and controlling air conditioning equipment according to various embodiments of the present invention is disclosed. The method includes a step of generating a facility digital twin model corresponding to a facility space and an air conditioning equipment based on design data of the facility space and air conditioning equipment configuration data, a step of acquiring environmental data within the facility in real time through a plurality of sensors provided within the facility space and updating the facility digital twin model based on the acquired environmental data, a step of predicting temperature changes and air flow using a simulation analysis algorithm to derive thermal comfort information within the facility space, and a step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information. The facility digital twin model may include a building model regarding the physical structure and layout of the facility space and an air conditioning equipment digital twin model regarding components and operating characteristics of the air conditioning equipment.

Description

METHOD, DEVICE, AND PROGRAM FOR MONITORING AND CONTROLLING HVAC SYSTEMS

The present invention relates to a method for monitoring and controlling the status of air conditioning equipment in real time, and more specifically, to an automated control method for detecting abnormal signs and responding thereto by analyzing data of facility space, air conditioning equipment, and process equipment.

Recently, building management systems (BMS) are evolving toward integrated management of various facilities and sensors for efficient energy management and facility maintenance. In particular, HVAC (Heating, Ventilation, and Air Conditioning) facilities account for more than 40% of building energy consumption and are considered essential elements for providing a comfortable indoor environment. Existing HVAC facility management systems control HVAC facilities based on environmental data such as temperature, humidity, and air flow, but most of them rely on pre-set rule-based control logic, which has limitations in effectively reflecting real-time data changes or abnormal conditions of facilities.

In particular, existing systems often fail to detect abnormal signs of equipment in advance, resulting in prolonged abnormal operation of equipment or significant reduction in energy efficiency. These abnormal signs are likely to lead to equipment failure, and not only worsen the environmental conditions within the building, causing inconvenience to users, but also become a major cause of increased management costs. For example, if a temperature sensor malfunctions in the cooling system of an air conditioning facility, it may fail to maintain the set temperature or cause excessive energy consumption, resulting in long-term equipment damage.

In addition, modern facility management systems are increasingly required to manage additional elements such as process facilities in addition to air conditioning facilities. Process facilities are key devices required to perform specific tasks within the facility space, and their stable operation is very important for maintaining productivity and quality assurance. However, if the interaction between process facilities and air conditioning facilities is not considered, each facility does not operate optimally, and it is difficult to accurately identify the cause of the problem when an abnormality occurs.

In addition, 3D visualization technology is attracting attention as a key tool for providing intuitive information in the field of facility management and maintenance. If the structure of facilities and space is visualized as a 3D model, the layout of the facilities, operating status, and the location and cause of abnormal signs can be quickly identified. However, existing 3D visualization technology tends to depend on high-spec hardware because it requires large-scale data processing and complex rendering work. Accordingly, the accuracy and efficiency of visualization are low on low-spec devices, and there may be limitations in updating 3D models in real time in large-scale facilities.

In addition, facility management systems that incorporate artificial intelligence (AI) technology are being introduced to analyze and respond to abnormal signs. AI technology can detect abnormal signs early through data learning and analysis, and analyze complex interactions between facilities to suggest response measures. However, existing AI-based systems are often applied only to specific facilities or environments, and the response process to abnormal signs is often fragmentary or requires user intervention. This can limit the implementation of complex interactions between facilities or rapid responses in emergency situations.

Therefore, a technology that can accurately detect abnormal signs based on real-time data, analyze their causes, and perform automated responses while comprehensively managing the entire system including air conditioning facilities and process facilities may be required. In particular, a technology that visually expresses abnormal signs to provide intuitive information to users and automatically executes responses according to predefined protocols to improve energy efficiency, extend the life of the equipment, and minimize user intervention is important. Such technology is expected to enable accident prevention and cost reduction in various environments such as data centers and factories as well as large-scale building management.

Republic of Korea Patent Publication No. 10-2020-0072765

The problem to be solved by the present invention is to provide a method, device and program capable of comprehensively monitoring the entire facility including air conditioning equipment and process equipment, detecting and analyzing abnormal signs based on real-time data, and automatically executing a response protocol, in response to the problem posed by the present invention in response to the aforementioned background technology.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

In order to solve the above-described problem, an air conditioning facility monitoring and control method according to one embodiment of the present invention is disclosed. The method includes a step of generating a facility digital twin model corresponding to a facility space and an air conditioning facility based on design data of the facility space and air conditioning facility configuration data, a step of acquiring environmental data within the facility in real time through a plurality of sensors provided within the facility space and updating the facility digital twin model based on the acquired environmental data, a step of predicting temperature change and air flow using a simulation analysis algorithm to derive thermal comfort information within the facility space, and a step of generating a control signal for controlling the air conditioning facility based on the thermal comfort information, wherein the facility digital twin model may include a building information model (BIM, Building Information Model) regarding the physical structure and layout of the facility space and an air conditioning facility digital twin model (HVAC Digital Twin Model) regarding components and operating characteristics of the air conditioning facility.

In an alternative embodiment, the step of acquiring environmental data within the facility in real time through a plurality of sensors provided within the facility space and updating the facility digital twin model based on the acquired environmental data may include the steps of: defining physical characteristics of the facility space based on design data of the facility space and the air conditioning facility configuration data; generating learning data for simulation by modeling components and operating characteristics of the air conditioning facility; and generating a facility digital twin model including the building model and the air conditioning facility digital twin model by utilizing the generated learning data.

In an alternative embodiment, the plurality of sensors may include an environmental sensor module provided in each of a plurality of sections within the facility space to obtain sensing data including information on temperature, humidity, and air flow; and a facility status sensor module to monitor facility data including whether the air conditioning facility is operating, its operating direction, and its output level.

In an alternative embodiment, the step of acquiring environmental data within the facility in real time through a plurality of sensors provided within the facility space and updating the facility digital twin model based on the acquired environmental data may include: a step of reflecting changes in temperature, humidity, and air flow within the air conditioning facility and the facility space based on the real-time environmental data acquired from the plurality of sensors to update the facility digital twin model in real time; a step of analyzing the environmental data and the facility data to simulate the operating state and environmental changes of the air conditioning facility, and identifying meaningful events from the simulation results to add them to learning data; a step of comparing and analyzing the updated environmental data with existing accumulated data to update a prediction result for the operating pattern and environmental changes of the air conditioning facility; and a step of determining to visually reflect the operating state and environmental changes of the air conditioning facility in the facility digital twin model based on the updated learning data and displaying them through a user interface.

In an alternative embodiment, the step of predicting temperature change and air flow using a simulation analysis algorithm to derive thermal comfort information within the facility space may include the steps of: setting initial conditions for performing air flow and heat transfer simulation based on physical characteristics of the facility space and the air conditioning equipment; calculating speed, pressure, and density of air flow by applying the Bernoulli equation and an air resistance model based on the initial conditions; analyzing the calculated air flow and heat transfer data to derive temperature distribution and air flow characteristics by section; and calculating thermal comfort information within the facility space based on the derived temperature distribution and air flow characteristics.

In an alternative embodiment, the step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information may include the step of determining whether thermal comfort information corresponding to each of the plurality of sections is within a predefined reference range; the step of individually generating a control signal for a section that is determined to be out of the reference range; and the step of transmitting the generated control signal to the corresponding air conditioning equipment to adjust the temperature of the section or control the air flow.

In an alternative embodiment, the step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information may include the steps of: comparing the thermal comfort information between the plurality of sections to derive a deviation of the thermal comfort information, and identifying a section requiring additional control if the deviation exceeds a predefined reference value; generating a control signal for equalizing thermal comfort between the sections based on the thermal comfort information of the identified section and a section adjacent to the identified section; and transmitting the generated control signal to a corresponding air conditioning equipment to adjust a temperature difference between the sections to within a predefined allowable range or to adjust an air flow direction and speed.

In an alternative embodiment, the step of generating a control signal for controlling the air conditioning facility based on the thermal comfort information may include the steps of: analyzing a current operating state of the air conditioning facility and thermal comfort information calculated in real time; calculating predicted thermal comfort information based on the analyzed information when the air conditioning facility continues to operate for a specific period of time; generating a control signal for correcting the operating state of the air conditioning facility when the predicted thermal comfort information is out of a predefined target range; and transmitting the generated control signal to a corresponding air conditioning facility to adjust an output level, an operating time, or an air flow direction of the air conditioning facility.

According to another embodiment of the present invention, a device for performing an air conditioning facility monitoring and control method is disclosed. The device includes a memory storing one or more instructions and a processor executing one or more instructions stored in the memory, and the processor can perform the air conditioning facility monitoring and control method described above by executing the one or more instructions.

According to another embodiment of the present invention, a computer program stored in a computer-readable recording medium is disclosed. The computer program is combined with a computer, which is hardware, to perform a method for monitoring and controlling air conditioning equipment.

Other specific details of the present invention are included in the detailed description and drawings.

According to one embodiment of the present invention, the status of the entire facility including air conditioning equipment and process equipment can be comprehensively monitored, abnormal signs can be detected based on real-time data, and a response protocol can be automatically executed, thereby improving the stability and energy efficiency of the facility.

In addition, the status of facility space, air conditioning equipment, and process equipment can be visualized as an integrated digital twin model to intuitively identify the location, cause, and impact of abnormal signs, and this visualization includes data optimization so that it can be smoothly implemented even on low-spec client terminals.

Additionally, the AI model continuously learns by utilizing automatically generated reports and saved data history when abnormal signs occur, which can improve the accuracy of abnormal sign detection and response in the future, and extend the life of equipment and reduce management costs.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

FIG. 1 is an exemplary diagram schematically illustrating a system for implementing an air conditioning facility monitoring and control method related to one embodiment of the present invention.
FIG. 2 is a hardware configuration diagram of a computing device that performs an air conditioning facility monitoring and control method related to one embodiment of the present invention.
FIG. 3 illustrates a flowchart exemplarily showing an air conditioning facility monitoring and control method related to one embodiment of the present invention.
FIGS. 4 and 5 are exemplary flowcharts for explaining a process for performing an air conditioning facility monitoring and control method related to one embodiment of the present invention.
FIGS. 6 and 7 are exemplary diagrams illustrating visual representations and analysis results of an air conditioning facility monitoring and control system related to one embodiment of the present invention.
FIG. 8 is a flowchart illustrating an exemplary 3D data optimization and facility visualization method related to one embodiment of the present invention.
FIGS. 9 to 13 are exemplary flowcharts for explaining a process of performing a 3D data optimization and facility visualization method related to one embodiment of the present invention.
FIG. 14 and FIG. 15 are exemplary diagrams showing the status monitoring and simulation result visualization of air conditioning equipment and process equipment related to one embodiment of the present invention.
FIG. 16 illustrates a flowchart exemplarily showing an AI-based process equipment abnormality detection and response automation method related to one embodiment of the present invention.
FIGS. 17 to 19 are exemplary flowcharts for explaining a process for performing an AI-based process equipment abnormality detection and response automation method related to one embodiment of the present invention.
FIGS. 20 and 21 are exemplary diagrams showing a user interface provided in an air conditioning facility and process facility monitoring system related to one embodiment of the present invention.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are set forth to provide an understanding of the invention. However, it will be apparent that these embodiments may be practiced without these specific descriptions.

The terms "component," "module," "system," and the like, as used herein, refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an execution of software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, an application running on a computing device and the computing device may both be components. One or more components may reside within a processor and/or a thread of execution. A component may be localized within a single computer. A component may be distributed between two or more computers. Furthermore, such components may execute from various computer-readable media having various data structures stored therein. The components may communicate via local and/or remote processes, for example, by means of a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, a distributed system, and/or data transmitted via a network such as the Internet to another system via the signal).

Additionally, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X employs A or B" is intended to mean either of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, "X employs A or B" can apply to any of these cases. Furthermore, the term "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the associated items listed.

Also, the terms "comprises" and/or "comprising" should be understood to mean the presence of the features and/or components. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, components, and/or groups thereof. Also, unless otherwise specified or clear from the context to refer to the singular form, the singular form as used in the specification and claims should generally be construed to mean "one or more."

Those skilled in the art should additionally recognize that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as combinations of electronic hardware, computer software, or both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The description of the disclosed embodiments is provided to enable a person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to a person skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present invention. Thus, the present invention is not limited to the disclosed embodiments. The present invention is to be construed in the widest scope consistent with the principles and novel features disclosed herein.

In this specification, a computer means any kind of hardware device including at least one processor, and may be understood to encompass software configurations operating on the hardware device according to an embodiment. For example, a computer may be understood to encompass, but is not limited to, a smartphone, a tablet PC, a desktop, a laptop, and all user clients and applications running on each device.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

Although each step described in this specification is described as being performed by a computer, the subject of each step is not limited thereto, and at least some of each step may be performed by different devices depending on the embodiment.

FIG. 1 is an exemplary diagram schematically illustrating a system for implementing an air conditioning facility monitoring and control method related to one embodiment of the present invention.

As illustrated in FIG. 1, a system according to embodiments of the present invention may include a computing device (100), a client terminal (200), an external server (300), and a network (400). The components illustrated in FIG. 1 are exemplary, and additional components may exist or some of the components illustrated in FIG. 1 may be omitted. The computing device (100), the external server (300), and the client terminal (200) according to embodiments of the present invention may mutually transmit and receive data for the system according to embodiments of the present invention through the network 400.

The network (400) according to embodiments of the present invention can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

Additionally, the network (400) presented herein can use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA), and other systems.

The network (400) according to embodiments of the present invention may be configured regardless of the communication mode, such as wired or wireless, and may be configured as various communication networks, such as a personal area network (PAN) and a wide area network (WAN). In addition, the network (400) may be the well-known World Wide Web (WWW), and may also use a wireless transmission technology used for short-distance communication, such as infrared (IrDA: Infrared Data Association) or Bluetooth. The technologies described in this specification may be used not only in the networks mentioned above, but also in other networks.

A computing device (100) (hereinafter referred to as 'computing device (100)') that performs a method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a processor and a memory for collecting, analyzing, and processing real-time data of air conditioning equipment and process equipment. The computing device (100) may create a virtual environment that reflects the physical and operational states of equipment and space in real time based on digital twin technology. To this end, the computing device (100) may be connected to a plurality of sensors through a network (400) to collect sensor data, and may perform a role of monitoring the states of air conditioning equipment and process equipment or detecting abnormal signs based on the collected data.

According to one embodiment, the computing device (100) may include a graphic processing module for generating and visualizing an integrated digital twin model, and may visually display the status and abnormal signs of the equipment through a user interface through the integrated digital twin model implemented as a digital twin. The integrated digital twin model may be configured to accurately reflect the dynamic status of the equipment and space by comprehensively integrating design data, initial operation data, and real-time sensor data.

In an embodiment, the computing device (100) utilizes the TWIN-X digital twin solution to dynamically replicate actual conditions within a virtual space based on real-time data of the equipment and space, analyze the location, cause, and impact of anomalies, and generate control signals to execute response protocols based on the analysis results to adjust the operation of the equipment or modify environmental conditions.

The TWIN-X digital twin solution dynamically reflects the status of physical facilities and spaces in a virtual environment based on real-world data, and can support the derivation of optimal operating methods through simulation and predictive analysis. In particular, TWIN-X aims to provide integrated management and optimization of air conditioning facilities and process facilities, and can provide an environment that maximizes facility performance and responds quickly to abnormal signs.

In one embodiment, the TWIN-X digital twin solution can reproduce the current and expected state of facility space and process equipment in real time in a virtual space by combining facility condition data and environmental data with simulation models. This allows for the precise identification of where facility abnormalities occur, the prediction of additional impacts that may occur at that location, and the provision of optimized response measures based on simulation results.

For example, if an overheating problem occurs in a specific process facility using the TWIN-X solution, the heat distribution and airflow around the facility can be simulated in real time to analyze the cause of the overheating, and a control signal can be generated to activate the cooling facility or adjust the airflow based on this. This method enables a quick and accurate response by simulating real-time changes in the facility and environmental conditions.

Additionally, the TWIN-X digital twin solution can analyze the status data of individual facilities and spaces to comprehensively manage the interactions between facilities and the operation of the entire system. This can provide an environment where the digital twin technology of HVAC facilities and process facilities operate complementarily rather than simply operating individually, maximizing the efficiency of the entire facility.

In other words, the TWIN-X solution operates in an integrated and organic manner at each stage of anomaly detection, simulation, predictive analysis, and response protocol execution, and can support optimized management and control by synchronizing all facility and space data in real time.

In one embodiment, the computing device (100) may include a machine learning engine for driving an artificial intelligence-based anomaly detection model. According to an embodiment, the machine learning engine may learn previously collected data and real-time data to improve the accuracy of prediction of facility status and anomaly detection. The computing device (100) may also be connected to an external server (300) and a database via a network (400) to store generated anomaly data or automatically generate additional analysis and reports.

According to an embodiment, the computing device (100) may be connected to a client terminal (200) to support interaction with a user. The client terminal (200) may provide the user with real-time monitoring information, visual and text-based notifications for abnormal signs, response protocol execution status, etc., and may control the status of a specific facility or request additional information through user input.

The computing device (100) according to the embodiment of the present invention can be equipped to ensure high accuracy and efficiency even in a complex facility environment, and can include a 3D model optimization algorithm and GPU-based texture compression technology to enable optimized data processing and visualization even in low-spec client terminals. Through this configuration, abnormal signs of air conditioning facilities and process facilities can be detected early and responded to quickly, thereby maintaining the stability of the facilities and reducing management costs.

A detailed description of a method for detecting abnormal signs of air conditioning equipment and process equipment provided by a computing device (100), a method for providing a user interface through creation and visualization of an integrated digital twin model, and an automated method for responding to abnormal signs will be described in detail later with reference to FIG. 3. This description includes the entire process of visualization of equipment status, data analysis, and abnormal sign processing in order to help clearly understand the technical features and effects of the present invention.

In the embodiment, only one computing device (100) is illustrated in FIG. 1, but it will be apparent to those skilled in the art that more computing devices may also be included within the scope of the present invention and that the computing device (100) may include additional components. That is, the computing device (100) may be composed of multiple computing devices. In other words, a set of multiple nodes may constitute the computing device (100).

According to one embodiment of the present invention, the computing device (100) may be a server providing a cloud computing service. More specifically, the computing device (100) may be a server providing a cloud computing service that processes information with another computer connected to the Internet rather than the user's computer, which is a type of Internet-based computing. The cloud computing service may be a service that stores data on the Internet and allows the user to use the data or programs required by the user anytime and anywhere through an Internet connection without having to install them on their computer, and allows the data stored on the Internet to be easily shared and transmitted with simple manipulation and clicks. In addition, the cloud computing service may be a service that not only simply stores data on a server on the Internet, but also performs desired tasks by utilizing the functions of application programs provided on the Web without having to install a separate program, and allows multiple people to simultaneously share documents and proceed with tasks. In addition, the cloud computing service may be implemented in at least one form among IaaS (Infrastructure as a Service), PaaS (Platform as a Service), SaaS (Software as a Service), a virtual machine-based cloud server, and a container-based cloud server. That is, the computing device (100) of the present invention may be implemented in at least one form among the above-described cloud computing services. The specific description of the cloud computing service described above is only an example, and may include any platform that constructs the cloud computing environment of the present invention.

A client terminal (200) according to an embodiment of the present invention may mean any type of node(s) within a system capable of communicating with a computing device (100), and serves as an interface for a user to monitor the status of air conditioning equipment and process equipment in real time and respond to abnormal signs.

For example, the client terminal (200) may be a terminal that can receive status information of air conditioning equipment and process equipment and check the operating status of the equipment, the location and cause of abnormal signs, and the progress status of the response protocol. The user can adjust the operating settings of the equipment or input or request additional information about abnormal signs through the client terminal (200).

In addition, the client terminal (200) may be a terminal used by the manager to monitor or control the equipment status of a large-scale facility. In this case, the manager can visually check the equipment status on the facility digital twin model through the client terminal (200) and manually execute or modify a response protocol for an abnormality.

In an additional embodiment, the client terminal (200) may be a mobile terminal used by a maintenance worker in the field. In this case, the worker can check real-time facility data provided from the computing device (100) through the client terminal (200) and immediately receive information necessary for facility inspection or repair. This can improve the speed and accuracy of response in the field.

The client terminal (200) is equipped with a display and an input device, and can receive user input and output visual and text-based information. The client terminal (200) can include all types of terminals that can connect to wired/wireless networks, such as a personal computer (PC), a notebook, a mobile terminal, a smartphone, a tablet PC, and a wearable device.

In addition, the client terminal (200) may be implemented by at least one of a client application, an API (Application Programming Interface), or a plug-in to support information exchange with the computing device (100). The client terminal (200) may include an application source and function optimized to efficiently process visualization data on the equipment status, thereby allowing the user to intuitively identify abnormal signs of the equipment and respond quickly.

In one embodiment, the external server (300) may be connected to the computing device (100) via a network (400), and may provide various information and data required for the computing device (100) to perform a method for monitoring and controlling air conditioning equipment and process equipment, or may store and manage result data derived during the process of performing the method. For example, the external server (300) may be a storage server separately provided outside the computing device (100) to store facility operation data for a long period of time, or to manage analyzed abnormal signs and response records in the form of a database.

The external server (300) can be implemented in various forms, and can perform the role of storing and managing learning data, verification data, and test data for learning a neural network-based abnormality detection model in the system of the present invention. Such data includes various data such as the operating status of the equipment, environmental changes, and abnormality occurrence patterns, and is essentially utilized for developing and optimizing a neural network model related to equipment management.

The learning data stored in the external server (300) is used to learn the normal and abnormal states of air conditioning equipment and process equipment and build a model that can accurately detect abnormal signs in real time. The verification data is used to evaluate and adjust the performance of the model being learned, and the test data can be used to check the generalization performance of the model based on new data. Through this, the external server (300) contributes to increasing the reliability of the method for detecting and responding to abnormal signs in the present invention and continuously improving the performance of the model.

In addition, the external server (300) can also store and manage data of the integrated digital twin model. It exchanges 3D model information including the layout and operating status of the facility and environmental data with the client terminal (200) and the computing device (100), and can be utilized as a backend system for updating visualization data.

The external server (300) is a digital device, and can be implemented in various forms such as a laptop computer, a desktop computer, a cloud server, a web server, etc., and includes all devices that can exchange data with the computing device (100) through a network. This configuration can contribute to efficiently managing large-scale facility data and improving the accuracy of detecting and responding to abnormal signs in air conditioning facilities and process facilities.

FIG. 2 is a hardware configuration diagram of a computing device that performs an air conditioning facility monitoring and control method related to one embodiment of the present invention.

Referring to FIG. 2, a computing device (100) that performs one embodiment of the present invention and an air conditioning facility monitoring and control method may include one or more processors (110), a memory (120) that loads a computer program (151) performed by the processor (110), a bus (130), a communication interface (140), and a storage (150) that stores the computer program (151). Here, only components related to the embodiment of the present invention are illustrated in FIG. 2. Therefore, a person skilled in the art to which the present invention pertains may recognize that other general components may be further included in addition to the components illustrated in FIG. 2.

According to one embodiment of the present invention, the processor (110) can typically process the overall operation of the computing device (100). The processor (110) can process signals, data, information, etc. input or output through the components described above, or can operate an application program stored in the memory (120) to provide or process appropriate information or functions to a user or client terminal.

Additionally, the processor (110) may perform operations for at least one application or program for executing a method according to embodiments of the present invention, and the computing device (100) may have one or more processors.

According to one embodiment of the present invention, the processor (110) may be composed of one or more cores and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device.

The processor (110) can read a computer program stored in the memory (120) to perform a method for monitoring and controlling air conditioning equipment according to one embodiment of the present invention.

In various embodiments, the processor (110) may further include a Random Access Memory (RAM) and a Read-Only Memory (ROM) that temporarily and/or permanently store signals (or data) processed within the processor (110). In addition, the processor (110) may be implemented in the form of a system on chip (SoC) that includes at least one of a graphics processing unit, RAM, and ROM.

The memory (120) stores various data, commands, and/or information. The memory (120) can load a computer program (151) from the storage (150) to execute a method/operation according to various embodiments of the present invention. When the computer program (151) is loaded into the memory (120), the processor (110) can perform the method/operation by executing one or more instructions constituting the computer program (151). The memory (120) may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

The bus (130) provides a communication function between components of the computing device (100). The bus (130) may be implemented as various types of buses such as an address bus, a data bus, and a control bus.

The communication interface (140) supports wired and wireless Internet communication of the computing device (100). In addition, the communication interface (140) may support various communication methods other than Internet communication. To this end, the communication interface (140) may be configured to include a communication module well known in the technical field of the present invention. In some embodiments, the communication interface (140) may be omitted.

The storage (150) can temporarily store a computer program (151). When performing an air conditioning facility monitoring and control process through a computing device (100), the storage (150) can store various types of information necessary to provide the air conditioning facility monitoring and control process.

Storage (150) may be configured to include nonvolatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention pertains.

The computer program (151) may include one or more instructions that cause the processor (110) to perform a method/operation according to various embodiments of the present invention when loaded into the memory (120). That is, the processor (110) may perform the method/operation according to various embodiments of the present invention by executing the one or more instructions.

In one embodiment, the computer program (151) may include one or more instructions that cause an air conditioning facility monitoring and control method to be performed, including the steps of generating a facility digital twin model corresponding to the facility space and the air conditioning facility based on design data of the facility space and air conditioning facility configuration data, acquiring environmental data within the facility in real time through a plurality of sensors provided within the facility space and updating the facility digital twin model based on the acquired environmental data, predicting temperature changes and air flow using a simulation analysis algorithm to derive thermal comfort information within the facility space, and generating a control signal for controlling the air conditioning facility based on the thermal comfort information.

In another embodiment, the computer program (151) may include one or more instructions for performing a 3D data optimization and facility visualization method, including the steps of acquiring facility status data from a sensor equipped in the facility, analyzing the facility status data to generate simulation data according to facility operation, generating a process facility digital twin model based on the facility status data and the simulation data, performing adjustments to the process facility digital twin model based on hardware performance of a client terminal to generate a customized process facility image, and visualizing the customized process facility image in real time through a user interface to monitor the facility status or display simulation results.

In another embodiment, the computer program (151) may include one or more instructions that cause an AI-based process facility abnormality detection and response automation method to be performed, including the steps of: generating a facility digital twin model visually representing the status of the facility space, the air conditioning facility, and the process facility based on design data and initial operation data of the facility space, the air conditioning facility, and the process facility; acquiring real-time environmental data and facility status data through a plurality of sensors provided in each of the facility space, the air conditioning facility, and the process facility; analyzing the acquired environmental data and facility status data using an AI-based abnormality detection model to detect an abnormality; and reflecting the detected abnormality into the integrated digital twin model, visually representing the location, type, cause, and impact of the abnormality, and providing the corresponding information through a user interface; and executing a predefined response protocol based on the type and impact of the abnormality.

The steps of a method or algorithm described in connection with the embodiments of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination of these. The software module may reside in a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Flash Memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) to be executed by being combined with a computer as hardware and stored on a medium. The components of the present invention may be executed as software programming or software elements, and similarly, the embodiments may be implemented in a programming or scripting language such as C, C++, Java, assembler, etc., including various algorithms implemented as a combination of data structures, processes, routines, or other programming elements. Functional aspects may be implemented as algorithms that are executed on one or more processors.

FIG. 3 is a flow chart illustrating an exemplary method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention. The steps illustrated in FIG. 3 may be changed in order as necessary, and at least one step may be omitted or added. The steps illustrated in FIG. 3 are merely one embodiment of the present invention, and the scope of the rights of the present invention is not limited thereto.

In the present invention, the facility space refers to a physical space where air conditioning equipment and process equipment are installed and operated, and such space may include an area where environmental conditions such as temperature, humidity, and air flow need to be controlled. For example, this may be a data center, a manufacturing plant, an office space, a hospital, or a specific area within other large-scale buildings. The facility space interacts with air conditioning equipment and process equipment according to the characteristics of each space, and can optimize environmental conditions and detect abnormal signs through real-time data analysis.

In addition, air conditioning equipment is a device for maintaining and controlling environmental conditions within a facility space, and may include, but is not limited to, air conditioners, heaters, air conditioners, ventilation fans, humidifiers, and dehumidifiers. For example, air conditioning equipment can adjust its operating status based on environmental data through sensors to provide optimal environmental conditions. In the present invention, when an abnormality occurs, the air conditioning equipment can operate to maintain system stability by automatically adjusting the operating status of the equipment or executing an emergency protocol.

According to one embodiment of the present invention, a method for monitoring and controlling air conditioning equipment may include a step (S110) of generating a facility digital twin model corresponding to a facility space and air conditioning equipment based on design data of the facility space and air conditioning equipment configuration data.

Specifically, the computing device (100) can define physical characteristics of the space, such as the layout structure, size, walls, ceiling, and floor, based on design data corresponding to the facility space, and model the location, connection status, and operating characteristics of the air conditioning equipment based on the air conditioning equipment configuration data to create an integrated three-dimensional virtual environment. In this process, the geometric structure of each facility and simulation data can be combined to create a model that can reflect the actual operating status of the facility.

For example, configuration data for air conditioning equipment may include physical size and layout information for air conditioners, heaters, and air conditioners, as well as their operating directions, output levels, and airflow simulation results. These data can be integrated through 3D modeling software or graphics engines, and a facility digital twin model can be implemented to visually represent interactions between equipment and changes in environmental conditions within the space.

In one embodiment, a facility digital twin model may include a building model relating to the physical structure and layout of the facility space and a HVAC digital twin model relating to the components and operational characteristics of the HVAC equipment.

Specifically, the computing device (100) can generate a facility digital twin model by integrating a building model and an air conditioning facility digital twin model. The building model models the physical characteristics and layout of walls, floors, ceilings, and openings (e.g., windows, doors) of a facility space based on design data, and can visually express the volume and usable area of the space. In addition, the air conditioning facility digital twin model can model the physical configuration and operating status of facilities such as air conditioners, heaters, and air circulators based on air conditioning facility configuration data.

These two models can be generated separately and then linked and integrated by a computing device (100) to form a facility digital twin model. The integrated model can simulate how the location and operating status of the equipment interact with the spatial structure within the building, and can visually represent the impact of the operation of the HVAC equipment on the environmental conditions within the space (e.g., temperature, humidity, air flow).

For example, if a digital twin model of an air conditioning facility on a specific floor is in operation, the facility digital twin model can simulate temperature distribution and airflow paths by linking it to the building model of that floor and provide data in 3D visualization. This allows facility managers to monitor the operating status of the facility and changes in environmental conditions within the space in real time and establish efficient facility control strategies.

In addition, in the embodiment, the facility digital twin model can also be used for detecting and responding to abnormal signs. For example, when abnormal operation of a specific facility is detected, data generated from the air conditioning facility digital twin model of the facility is reflected in the facility digital twin model, so that the space and facility where the problem occurred can be visually highlighted in the building model. Through this, cause analysis and response to abnormal signs can be performed more quickly and accurately.

In an embodiment, the facility digital twin model can be configured to be updated to reflect real-time data. To this end, real-time environmental data collected from sensors (e.g., temperature, humidity, air flow) and facility status data (e.g., operation status, output level) can be dynamically applied to the 3D model to visually display changes in the facility status and changes in environmental conditions within the space.

According to one embodiment of the present invention, a method for monitoring and controlling air conditioning equipment may include a step (S120) of acquiring environmental data within a facility in real time through a plurality of sensors provided within the facility space, and updating a facility digital twin model based on the acquired environmental data.

The computing device (100) can process environmental data acquired from a sensor and reflect the data in a facility digital twin model to provide updated status in real time.

Specifically, the computing device (100) can analyze temperature, humidity, air flow, and facility status data transmitted from the sensor to evaluate the environmental conditions within the space and the operating status of the air conditioning facility. The results of this analysis can be reflected in real time to each facility and space component of the facility digital twin model, thereby providing intuitive visual information to the user.

According to one embodiment, the plurality of sensors may include an environmental sensor module that is provided in each of a plurality of sections within the facility space and obtains sensing data including information on temperature, humidity, and air flow, and a facility status sensor module that monitors facility data including whether air conditioning equipment is operating, its operating direction, and its output level.

The environmental sensor module includes a sensor for detecting environmental conditions of each section within the facility space in real time, and may include, but is not limited to, a temperature sensor, a humidity sensor, and an airflow sensor. In an embodiment, the environmental sensor module may collect sensing data in real time and transmit the same to a computing device (100) to support analysis and visual reflection of changes in environmental conditions within the space. For example, when a temperature rise is detected in a specific area, the environmental sensor module may transmit the corresponding sensing data to the computing device (100) to reflect the environmental change within the space in the facility digital twin model.

In addition, the facility status sensor module includes a sensor for monitoring the operating status of the air conditioning facility, and may include an operating sensor for checking whether the facility is operating, a direction sensor for measuring the operating direction, and an output sensor for detecting the output level. The facility status sensor module collects operating information of the air conditioning facility in real time and transmits it to a computing device (100), and can detect status changes and abnormal signs of the air conditioning facility based on the collected information. For example, when the output level of a specific air conditioning facility is abnormally low or the operating direction is operated differently from the set value, the facility status sensor module can collect the corresponding data and transmit it to the computing device (100), and the computing device (100) can visually highlight the abnormal status on the facility digital twin model.

According to a specific embodiment, the step of acquiring environmental data within a facility in real time through a plurality of sensors installed within the facility space and updating the facility digital twin model based on the acquired environmental data may include the step of defining physical characteristics of the facility space based on design data of the facility space and air conditioning facility configuration data, the step of modeling components and operating characteristics of the air conditioning facility to generate learning data for simulation, and the step of utilizing the generated learning data to generate a facility digital twin model including a building model and an air conditioning facility digital twin model.

To explain in more detail, the computing device (100) can analyze the design data of the facility space to define physical characteristics such as the size, structure, and openings (e.g., windows, doors, etc.) of each space, and set the location, connection structure, and operating range of the facility based on the air conditioning facility configuration data. In this process, an initial 3D model is created to visualize the layout of the facility space and the interaction of the air conditioning facility.

For example, if the components of an air conditioning facility installed in a specific space are composed of a cooling unit, a heating unit, and a ventilation system, the computing device (100) can model the operating characteristics (e.g., output, operating direction, energy consumption, etc.) of these facilities to generate learning data. The learning data is used to simulate the impact of the operating state of the facility on environmental conditions, and can provide a basis for accurately predicting temperature distribution, airflow patterns, and humidity changes in the space.

The computing device (100) can update the facility digital twin model including the facility space and air conditioning equipment by utilizing the generated learning data. For example, if the temperature in a specific area exceeds a set range, the computing device (100) that receives real-time data from the sensor can reflect the data in the 3D model to highlight the problem area. In addition, the operating status of the air conditioning equipment is visually expressed on the model so that the user can intuitively understand the status of the equipment and space.

In various embodiments, the computing device (100) may include a process of verifying and analyzing sensor data to remove outliers or erroneous data in order to maintain the accuracy and reliability of real-time data. Through this, the facility digital twin model accurately reflects the actual state of the facility space and air conditioning equipment, and can provide basic information for detecting and responding to abnormal signs at a later stage.

Additionally, in an embodiment, the computing device (100) may process real-time data acquired from sensors to update the facility digital twin model to reflect the status of the facility space and air conditioning equipment.

In a specific embodiment, the step of acquiring environmental data within a facility in real time through a plurality of sensors installed within the facility space and updating the facility digital twin model based on the acquired environmental data may include a step of reflecting changes in temperature, humidity, and air flow within the air conditioning facility and the facility space based on the real-time environmental data acquired from the plurality of sensors and updating the facility digital twin model in real time, a step of analyzing the environmental data and the facility data to simulate the operating status and environmental changes of the air conditioning facility and identifying meaningful events from the simulation results and adding them to learning data, a step of comparing and analyzing the updated environmental data with existing accumulated data and updating a prediction result for the operating pattern and environmental changes of the air conditioning facility, and a step of determining to visually reflect the operating status and environmental changes of the air conditioning facility in the facility digital twin model based on the updated learning data and displaying them through a user interface.

More specifically, the computing device (100) may process real-time data collected from a plurality of sensors, analyze temperature, humidity, airflow data, etc. measured by each sensor, and update each zone of the facility digital twin model in real time based on the analyzed data. For example, if the temperature of a specific zone exceeds the set standard of 25°C and rises to 30°C, the computing device (100) may visually highlight a 3D model of the zone to warn the user. For example, the highlighting may include a color change (e.g., displaying in red) or a blinking animation. In addition, if the humidity increases rapidly or the airflow stagnates in a specific zone, the computing device (100) may update in real time the zone that requires an output level adjustment of the air conditioning equipment based on the data.

In the step of analyzing environmental data and facility data to simulate the operating status and environmental changes of air conditioning equipment and identifying meaningful events, the computing device (100) can process the collected data through a pattern analysis algorithm. For example, a pattern in which the output level of the air conditioning equipment periodically decreases or the equipment unexpectedly stops at a specific time can be detected. If such an abnormal behavior is found, the computing device (100) can identify it as a 'meaningful event' and add the event to the learning data to improve the accuracy of future simulations and predictions. For example, if high humidity is continuously detected in a specific area, it can automatically learn that a setting is needed to enhance the ventilation performance of the area.

In the step of updating the prediction results for the operation pattern of the air conditioning equipment and environmental changes by comparing the updated environmental data with the existing accumulated data, the computing device (100) can analyze the difference between the real-time data and the existing data to evaluate the efficiency of the equipment. For example, by comparing the energy consumption pattern of the air conditioning equipment and the impact of the equipment on environmental conditions, equipment that operates inefficiently in a specific area can be identified. In this process, a machine learning model can be utilized to learn past data and be utilized to predict future equipment status and environmental changes. For example, if a specific equipment does not generate sufficient airflow when operating, this may indicate that a filter replacement or equipment inspection is necessary.

In the step of visually reflecting the operating status and environmental changes of the air conditioning equipment in the facility digital twin model based on the updated learning data and displaying them through the user interface, the computing device (100) can convert real-time data into visual elements to provide intuitive information to the user. For example, an abnormality occurring in a specific area can be displayed by enlarging the area on a 3D model, or the operating status of the equipment can be expressed as a graphic element (e.g., an animation of a fan in operation). In addition, data such as temperature, humidity, and air flow can be provided in the form of a dashboard so that the user can comprehensively monitor the equipment status. Through this information, the user can quickly identify the cause of the abnormality and take appropriate measures.

According to one embodiment of the present invention, a method for monitoring and controlling air conditioning equipment may include a step (S130) of predicting temperature changes and air flow using a simulation analysis algorithm to derive thermal comfort information within a facility space.

In one embodiment, the step of predicting temperature changes and airflow using a simulation analysis algorithm to derive thermal comfort information within a facility space may include the step of setting initial conditions for performing airflow and heat transfer simulations based on physical characteristics of the facility space and air conditioning equipment.

Specifically, the computing device (100) can perform a process of setting initial conditions by analyzing the physical characteristics of the facility space and air conditioning equipment. In this process, the computing device (100) can define physical boundary conditions such as the size, shape, walls, and ceiling of the space based on the structural data of the facility space. For example, the computing device (100) can collect information on the length, width, and height of the space, and set accurate boundary conditions for simulating the air flow path by reflecting the location of the opening (e.g., window, door). Such data can be used as essential input values for calculating the air circulation and heat transfer path.

In addition, the computing device (100) can analyze the layout and operating characteristics of the air conditioning equipment and reflect them in the initial conditions. Information such as the location, output level, and operating direction of the equipment can be key factors in determining the speed and direction of the air flow. For example, if the equipment is installed near a wall, the computing device (100) can calculate the influence of the air flow and heat distribution reflected from the wall to set the initial conditions.

In addition, in an embodiment, the computing device (100) may include external environmental conditions in the initial conditions. Variables such as external temperature, humidity, wind direction and speed may be considered to increase the accuracy of the simulation as they affect the internal environment. For example, in winter conditions with low external temperatures, the initial conditions may be adjusted to reflect the possibility of increased heat loss through the walls.

Also, in the embodiment, the computing device can analyze internal heat source and heat load data to generate and define initial conditions. Factors such as electronic devices, lighting, and the number of people increase the heat load of a specific area within a space, which can directly affect airflow and temperature distribution. For example, the computing device (100) can calculate the heat load of a concentrated number of people in a specific area and include this in the simulation to adjust the output level of the air conditioning equipment by reflecting it in the initial conditions.

In an additional embodiment, the computing device (100) incorporates physical properties of air, such as temperature, density, and viscosity, into the initial conditions. For example, as the air temperature increases, the density decreases, which may affect the speed and pressure distribution of the air flow. The computing device (100) can precisely analyze these air properties and set them as the initial conditions, thereby improving the reliability of the simulation results.

The computing device (100) can reflect the physical characteristics of the air conditioning equipment and facility space by comprehensively processing various data as described above to set initial conditions. The initial conditions generated through this can maximize the accuracy of air flow and heat transfer simulations, and can support the simulation results to more precisely reproduce the state of the actual space.

In an embodiment, the step of generating thermal comfort information within a facility space may include the step of calculating air flow velocity, pressure, and density by applying the Bernoulli equation and air resistance model based on initial conditions.

More specifically, the computing device (100) can perform a fluid dynamic simulation based on the Bernoulli equation and the air resistance model to calculate the air flow and heat transfer characteristics within the facility space. The computing device (100) can calculate variables of the speed, pressure, and density of the air flow based on the initial conditions within the facility space and the air conditioning equipment. Here, the initial conditions can include boundary conditions of the air flow, the operating status of the air conditioning equipment, and the location and shape data of obstacles within the space.

The computing device (100) can calculate airflow characteristics by applying the following Bernoulli equation.

Here, is the fluid flow rate (flow velocity), is the acceleration of gravity, is the altitude, is the pressure, can represent the density of a fluid.

The equation describes the basic principle that when the velocity of a fluid is high, the pressure is low, and when the velocity of a fluid is low, the pressure is high. The computing device (100) can use the equation to calculate the distribution of air flow and model changes in pressure, velocity, and altitude at each point in space.

Additionally, the computing device (100) can utilize an air resistance model to reflect the influence of obstacles or equipment operation status on air flow. The air resistance model can be expressed by the following formula.

Here, is the acting resistance, is the direction of the velocity of the fluid flow (unit vector), is the drag coefficient, is the momentum transferred per unit time, is the fluid density, is the fluid flow velocity, can be a projected area.

The computing device (100) can simulate air flow and pressure distribution throughout the space by repeatedly calculating the above formula for all sections of the facility space. This contributes to precisely modeling changes in air flow according to the arrangement or operating status of the facility, and can provide basis data for maintaining or improving thermal comfort within the space.

That is, the computing device (100) can calculate the pressure, velocity, and density of air flow within a space by utilizing the Bernoulli equation, and can reflect the influence of obstacles and equipment operation status within the space on the air flow by applying an air resistance model. This calculation can be performed by subdividing all sections within the space, and can be performed based on the physical characteristics and equipment status data of each section.

For a specific example, the computing device (100) can divide the facility space into several sections and independently analyze the boundary conditions and physical characteristics of each section. For example, by inputting shape and location data of an obstacle (e.g., a pillar, furniture, or machine device) located within a specific section, it can simulate how the path of air flow within the section changes. In this process, the computing device (100) can calculate the distribution of pressure, velocity, and density of air flow by applying Bernoulli's equation, and predict a decrease in the velocity of the flow or the generation of eddies due to the obstacle.

In addition, when the air conditioning system is in operation, the computing device (100) can set the air output (e.g., air volume, temperature) generated from the air conditioning system as an initial condition to analyze how the air flow within the section spreads to other sections. For example, a section located directly below the air vent of the air conditioning system may be observed to have a high flow rate and low pressure, and this data can be utilized to precisely calculate the effect of spreading to the surrounding sections by applying an air resistance model.

In addition, the computing device (100) can integrate the data calculated in each section by considering the interaction of airflow between sections. For example, it can reflect the phenomenon that the speed of a high-velocity airflow decreases as it passes to an adjacent section, or the direction of the airflow changes due to a boundary condition such as a wall surface. This allows for early detection of abnormal patterns of airflow (e.g., excessive speed increase, eddies) that may occur in a specific section while maintaining the continuity and balance of the airflow within the entire facility space.

In addition, the computing device (100) compares and analyzes the calculated data to determine whether excessive changes in airflow speed or pressure difference occur in a specific area within the space and generates a facility control command to adjust it. This can help the air conditioning facility maintain an optimal operating state.

Additionally, in the embodiment, the step of calculating thermal comfort information within the facility space may include a step of analyzing the calculated airflow and heat transfer data to derive temperature distribution and airflow characteristics by section.

Specifically, the computing device (100) can derive the thermodynamic state of each section within the space based on the airflow velocity, pressure, density, and heat transfer characteristics calculated in the previous step. This analysis can be conducted by including various factors such as the spatial location of each section, the operating state of the air conditioning equipment, and the presence of obstacles.

The computing device (100) can apply a heat transfer equation to calculate the temperature distribution of each section. The heat transfer equation describes how the heat energy transferred through the air conditioning system is spread within a space, and can be expressed as follows:

Here, is the heat flux (heat energy transferred per unit area), is the thermal conductivity, can be a spatial change in temperature (temperature gradient).

The computing device (100) can calculate the thermal conductivity and temperature gradient of each section within the space to predict the temperature change and heat distribution of the corresponding section. This allows analysis of the effect of airflow on the distribution of heat energy.

To derive airflow characteristics, the computing device (100) can calculate the air velocity and direction of each section to visualize the flow pattern within the space. For example, the computing device (100) can generate a vector field to simulate the airflow direction and size of each section, which is useful for evaluating the influence of the layout and operating conditions of the facility on the airflow.

The calculated temperature distribution and airflow characteristics can be integrated and analyzed by the computing device (100) to produce a thermal comfort index within the space. The thermal comfort index can be used to evaluate whether a specific section provides a comfortable environment for the user or requires additional adjustment. For example, the temperature distribution and airflow data can be utilized to identify a condition in which a specific section is overheated or lacks ventilation.

In addition, the computing device (100) can provide the derived thermal comfort information visually through a user interface or generate data for additional facility adjustment and reflect it in the control command of the air conditioning facility. This can enable real-time feedback for maintaining or improving comfort in the space.

Additionally, in an embodiment, the step of calculating thermal comfort information within a facility space may include a step of calculating thermal comfort information within the facility space based on the derived temperature distribution and air flow characteristics.

The computing device (100) can calculate thermal comfort information for each facility space based on the derived temperature distribution and air flow characteristics. Thermal comfort information is an index that quantitatively evaluates the environmental comfort experienced by users in the space, and can maximize the operating efficiency of air conditioning equipment through this.

In an embodiment, the computing device (100) can integrate and analyze various physical variables to derive thermal comfort. For example, thermal comfort evaluation criteria can be applied based on temperature, airflow rate, and humidity measured in each section of the space. Based on this data, the computing device (100) can apply international thermal comfort models such as ASHRAE standard, PMV (Predicted Mean Vote), and PPD (Predicted Discomfort Ratio) to conduct an evaluation.

In an embodiment, the computing device (100) can generate thermal comfort information including a PMV (Partial Molar Volume) value. The computing device (100) can calculate the PMV value by utilizing environmental data collected within the facility space and air conditioning equipment, and evaluate thermal comfort based on the PMV value. The PMV value is an indicator that quantitatively represents the thermal comfort felt by a user within a space, and can be calculated by comprehensively considering various variables such as temperature, humidity, air flow rate, user activity level, and clothing insulation effect.

The computing device (100) can utilize data such as temperature (T) in the space, average radiant temperature (Tr), relative humidity (Hr), air flow rate (Va), user metabolic rate (M), and thermal resistance value (Cl) of clothing worn as input values for calculating PMV values. Based on these data, the PMV formula is applied to quantify thermal comfort in the space. For example, the computing device (100) can predict thermal comfort that a user can feel by applying the PMV calculation formula below.

Here, is the air temperature, is the reference temperature, is the average radiant temperature, is the current humidity, is the standard humidity, can represent water vapor pressure, M can represent metabolic rate, and W can represent external work.

The computing device (100) can calculate the thermal comfort information in each section within the space by segmenting it based on the input data collected to calculate the PMV value. For example, the computing device (100) can analyze the temperature, humidity, and air flow data of a specific area within the space by segmenting it and calculate the PMV value in each section individually. This allows the thermal comfort status of a specific area, rather than the entire space, to be checked in more detail.

The results derived based on the PMV value can be provided visually through a user interface, and the computing device (100) can display the thermal comfort status within the space as a color, graph, or numerical data. For example, the computing device (100) can provide visual feedback by highlighting in green an area where the thermal comfort is within a reference range (PMV -0.5 to +0.5), and in yellow or red an area outside the reference range. Such visual information helps users or managers quickly understand the environmental conditions of a specific area within the space and take necessary actions.

In addition, the computing device (100) can comprehensively analyze the environmental data within the space together with the derived PMV value to generate a control command for the air conditioning equipment. For example, if the PMV value is out of the reference range in a specific area, the computing device (100) can generate a control command to adjust the temperature setting value of the air conditioning equipment in the area or increase the air flow speed. This control command can be transmitted to the air conditioning equipment in real time to adjust the environmental conditions, thereby maintaining or improving the thermal comfort within the space.

According to one embodiment of the present invention, a method for monitoring and controlling air conditioning equipment may include a step (S140) of generating a control signal for controlling air conditioning equipment based on thermal comfort information.

That is, the computing device (100) can analyze the operation data of the air conditioning equipment to improve the thermal comfort of a specific section within the space and generate a control command for the specific equipment. In this process, the computing device (100) can simulate the change in thermal comfort within the space by utilizing a prediction algorithm based on existing data and determine the optimal equipment operating conditions.

According to one embodiment of the present invention, the computing device (100) can analyze thermal comfort information to generate a control signal for optimizing the operation of air conditioning equipment. Specifically, the computing device (100) can compare and analyze real-time data collected from a plurality of sensors with thermal comfort information to perform equipment adjustments appropriate for environmental changes occurring in a specific section within a space.

In a specific embodiment, referring to FIG. 4, the step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information may include the step of determining whether the thermal comfort information corresponding to each of the plurality of sections is within a predefined reference range (S141), the step of individually generating a control signal for a section that is determined to be out of the reference range (S142), and the step of transmitting the generated control signal to the corresponding air conditioning equipment to adjust the temperature of the section or control the air flow (S143).

More specifically, the computing device (100) may generate a control signal for adjusting a section if the section does not meet the thermal comfort criteria based on data such as the PMV value derived for each section and the temperature, humidity, and airflow rate within the space. For example, the computing device (100) may generate a control command for activating the air conditioning equipment of a specific section or adjusting the fan speed for a specific section where the PMV value exceeds the range of -0.5 to +0.5.

For example, if the temperature of a specific section is measured to be higher than a reference temperature, the computing device (100) may generate a control signal to operate the cooling device of the section or increase the amount of cooling air intake. Conversely, if the airflow speed of a specific section is insufficient, the computing device (100) may transmit a command to increase the speed of the air circulation fan or generate a signal to change the direction of the airflow.

That is, the computing device (100) can analyze the operating status of air conditioning equipment in real time to maintain thermal comfort in a space and generate an optimized control signal that can adjust environmental conditions as needed, thereby simultaneously improving equipment efficiency and user satisfaction.

In one embodiment, the computing device (100) can analyze thermal comfort within multiple sections and generate control signals to maintain balance between the sections.

In a specific embodiment, referring to FIG. 5, the step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information may include the step (S145) of comparing the thermal comfort information between a plurality of sections to derive a deviation of the thermal comfort information, and identifying a section requiring additional control if the deviation exceeds a predefined reference value, the step (S146) of generating a control signal for equalizing thermal comfort between the sections based on the thermal comfort information of the identified section and a section adjacent to the corresponding section, and the step (S147) of transmitting the generated control signal to a corresponding air conditioning equipment to adjust the temperature difference between the sections to within a predefined allowable range or to adjust the air flow direction and speed.

More specifically, the computing device (100) can divide the facility space into a plurality of sections and collect and analyze data such as PMV values, temperature, humidity, and airflow speed in real time to evaluate the thermal comfort of each section. The computing device (100) calculates a thermal comfort deviation based on the data of each section, and through this, can quantitatively evaluate the comfort difference between specific sections. For example, if the PMV value of a specific section is -0.5 or lower, making it feel relatively cold, and the PMV value of an adjacent section is +0.5 or higher, indicating a hot state, the computing device (100) can determine that the thermal comfort deviation between these sections exceeds a predefined reference value (e.g., ±0.5).

In such a situation, the computing device (100) can generate a control signal to reduce the deviation and maintain a thermal balance between the sections. For example, if the temperature of a specific section is higher than that of an adjacent section, the computing device (100) can generate a control signal to activate the cooling device of that section or increase the output of an existing cooling facility. At the same time, the airflow direction of the adjacent section can be adjusted to optimize the airflow so that the cooling air is naturally delivered to the adjacent section. This can prevent excessive cooling or overheating in a single section and increase the energy usage efficiency in the space.

As another example, if the airflow speed of a specific section is insufficient and thermal comfort is deteriorated, the computing device (100) can activate the air circulation fan installed in the section to strengthen the airflow. At the same time, the airflow direction and speed of the adjacent section can be adjusted to command the redistribution of the free airflow in the adjacent section. Such measures can contribute to maintaining the balance of airflow between the sections and minimizing stagnant areas that may occur in a specific section.

Additionally, the computing device (100) can simulate thermal comfort changes based on the operating data of the air conditioning equipment and predict the most suitable operating conditions for each section. For example, if the PMV value of a specific section is close to the reference value but is still unstable, the computing device (100) can induce subtle temperature changes through detailed adjustments of the cooling or heating equipment. This can maintain thermal comfort of the entire space while minimizing energy consumption due to excessive operation of the equipment.

That is, the computing device (100) can perform intelligent and efficient facility control to maintain thermal comfort balance between multiple sections and optimize comfort within the space by combining real-time data and predictive algorithms.

According to one embodiment, the computing device (100) can analyze the current operating status of the air conditioning equipment and the thermal comfort information calculated in real time to generate a control signal that optimizes the balance between the efficiency of the equipment and maintenance of thermal comfort.

In a specific embodiment, the step of generating a control signal for controlling an air conditioning facility based on the thermal comfort information may include the steps of analyzing a current operating state of the air conditioning facility and thermal comfort information calculated in real time, the step of calculating predicted thermal comfort information based on the analyzed information when the air conditioning facility continues to operate for a specific period of time, the step of generating a control signal for correcting the operating state of the air conditioning facility when the predicted thermal comfort information is out of a predefined target range, and the step of transmitting the generated control signal to a corresponding air conditioning facility to adjust an output level, an operating time, or an air flow direction of the air conditioning facility.

To explain in more detail, the computing device (100) collects the current status of the air conditioning equipment and the thermal comfort data within the space in real time and performs an analysis based on the collected data. During the analysis process, the computing device (100) predicts the change in the thermal comfort of each section within the space along the time axis, and calculates the expected PMV value, temperature, humidity, air flow rate, and other changes in a specific section if the current operating status of the air conditioning equipment continues. For example, if the predicted PMV value of a specific section exceeds +1.0 and is expected to cause excessive thermal discomfort, or conversely, if it falls below -1.0 and is likely to lead to an excessive cooling state, the computing device (100) can identify such a situation in advance.

Thereafter, the computing device (100) can calculate an optimal control method to adjust the predicted thermal comfort information if it is out of a predefined target range. In this process, the computing device (100) can evaluate the operation priority between the facilities if multiple facilities affect the same space, or generate a conflict-free control signal by considering the interaction between the facilities. For example, if the temperature of a specific section increases and the airflow speed of an adjacent section decreases, the computing device (100) can generate a control signal to preferentially activate the cooling device of the corresponding section and readjust the airflow to the adjacent section to equalize the thermal comfort.

The generated control signal may include detailed operating variables such as the output level of the air conditioning equipment, the operating time, and the airflow direction. For example, if the temperature of a specific section is expected to rise rapidly, the computing device (100) may transmit a control signal to temporarily increase the output of the cooling device installed in the section and simultaneously activate the blower of the adjacent section to promote air circulation. Conversely, if a specific section is excessively cooled, the computing device (100) may temporarily stop the cooling device of the section or adjust the blower direction to optimize the equipment operation so that the cooled air is distributed to other sections.

That is, the computing device (100) can perform real-time control to maximize the energy efficiency of the facility while maintaining the thermal comfort of the entire space. Such optimized control of the air conditioning facility can not only reduce energy consumption, but also contribute to improving the comfort of users in the space.

In various embodiments, the computing device (100) may utilize an artificial intelligence-based prediction algorithm based on thermal comfort information and environmental data collected in real time to predict future thermal comfort conditions within a space, and generate a control signal for pre-adjusting the operation of air conditioning equipment based on the predicted state. Such pre-adjustment may be for preventing sudden temperature changes, abnormal airflow, or sudden energy consumption that may occur under certain conditions.

In a specific embodiment, the computing device (100) can train a machine learning model by combining past sensing data and current thermal comfort information, thereby analyzing the correlation between the operating pattern of the air conditioning system and environmental changes. For example, the impact of an increase in outside temperature on a temperature increase in a specific section of the room can be predicted, and a control signal can be generated to pre-adjust the output of the cooling system or activate an additional air circulation device accordingly.

More specifically, the computing device (100) can predict temperature distribution and airflow changes after a certain point in time based on external environmental data, and dynamically adjust the operation schedule of the air conditioning equipment so that the PMV value of each section does not exceed the allowable standard. For example, if a predicted airflow shortage is detected in a certain section, the computing device (100) can generate a command to activate a fan for additional air circulation in the section and distribute airflow in an adjacent section.

Additionally, in an embodiment, the computing device (100) may proactively detect and automatically execute emergency control protocols to prevent abnormal situations (e.g., equipment overheating, pollutant accumulation due to stagnant air) that may occur in a specific area within the space based on thermal comfort information and environmental data. Such emergency control may focus on maintaining the safety of the space and preventing unexpected equipment damage or user inconvenience.

In a specific embodiment, the computing device (100) may analyze data collected from a plurality of sensors to automatically activate air conditioning equipment in a specific area or to generate a control signal to readjust airflow when a sudden increase in temperature or an abnormal increase in the concentration of a hazardous substance is detected in that area. For example, when overheating is detected in a server room of a data center, the computing device (100) may increase the output of a cooling device in that section and redistribute air from an adjacent section to quickly stabilize the temperature.

The computing device (100) can learn a new abnormal situation that has not been defined before by utilizing a machine learning-based abnormal pattern detection algorithm and generate an adaptive emergency response plan in real time. For example, if a stagnation of air flow that has not been observed before occurs in a specific area, it can detect this as an abnormal pattern and generate a new control command to activate an air circulation device.

Additionally, the computing device (100) can record and analyze the result data after executing the emergency control protocol to continuously improve the control strategy so that a more effective response can be made in the event of a similar situation in the future. This can simultaneously maintain spatial stability and energy efficiency, and provide more intelligent and autonomous control capabilities compared to existing systems.

In additional embodiments, the computing device (100) may implement an energy management strategy to optimize the efficiency of the air conditioning system based on the predicted thermal comfort state. For example, the air conditioning system output may be automatically minimized in spaces that are not in use during certain time periods, thereby maximizing energy savings. Such energy management strategies may contribute to extending the operating life of the system and reducing overall operating costs.

Through this, the computing device (100) can provide improved predictability and efficiency compared to existing air conditioning equipment control methods, and implement a comprehensive control solution that can optimize energy consumption while maintaining thermal comfort.

FIGS. 6 and 7 are exemplary diagrams illustrating visual representations and analysis results of an air conditioning facility monitoring and control system related to one embodiment of the present invention. Referring to FIGS. 6 and 7, a facility digital twin model according to an embodiment of the present invention can provide a user interface by visualizing temperature distribution and airflow characteristics across multiple sections within a facility space in the form of a color map.

In Fig. 6, the temperature distribution of each section in the facility is displayed in color, so that the cooling or heating needs of a specific area can be intuitively identified. In addition, the operating status, connection status, and air flow path of the air conditioning equipment are displayed together, so that the operating status of the equipment can be monitored in real time. The graph and dashboard in Fig. 6 quantitatively show the temperature change over time and the efficiency of the air conditioning equipment, and can be equipped to support the user in making data-based decisions.

In Fig. 7, the results of the airflow simulation in the air conditioning facility are visually displayed. The green and red flows indicate the density and direction of air circulation, and highlight areas where the airflow is not smooth. In addition, the power consumption and efficiency of each facility are additionally displayed, allowing facility managers to determine energy-saving measures. This information provides essential data for optimizing air conditioning facilities, and can improve the efficiency of maintaining thermal comfort and energy management in a space.

Fig. 8 is a flow chart exemplifying a 3D data optimization and facility visualization method related to one embodiment of the present invention. For features of the contents illustrated in Fig. 8 that overlap with features described above with respect to Figs. 3 to 7, reference should be made to the contents described in Figs. 3 to 7, and their descriptions will be omitted herein.

A method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a step (S210) of obtaining equipment status data from a sensor equipped in the equipment.

Equipment status data can include various information such as equipment operating status, temperature, pressure, flow rate, vibration, energy consumption, and wear status of parts. Equipment status data indicates the current status of the equipment and can be used to evaluate the efficiency and stability of the equipment or to detect abnormal signs.

According to an embodiment, the equipment may mean, for example, process equipment. For example, the process equipment may include, but is not limited to, reactors, heat exchangers, pumps, compressors, conveyor systems, precision machining equipment, assembly equipment, packaging equipment, etc. These process equipment play a key role in manufacturing, processing, logistics, and other industrial processes, and the stability and quality of the process can be maintained by monitoring and analyzing the status data thereof.

The computing device (100) can obtain facility status data in real time from various sensors installed in the facility. These sensors may include a temperature sensor, a pressure sensor, a flow sensor, a vibration sensor, an energy consumption measurement sensor, and a component wear detection sensor.

For example, the computing device (100) can obtain data from a pressure sensor and a flow sensor attached to the pump to monitor the operating status of the pump in real time. If the pressure or flow rate deviates from the reference value for a certain period of time, the computing device (100) can perform additional analysis to determine this as an abnormal state.

In addition, for example, the computing device (100) can collect vibration data of the conveyor system through a vibration sensor, and periodically sample and accumulate the data to identify a section where excessive vibration occurs. Through this, the computing device (100) can predict that wear of parts is occurring in a specific part of the equipment and store the corresponding data.

In one embodiment, the computing device (100) can organize facility status data by sensor and compare it with a predefined normal operation reference value to support a real-time abnormality detection process. For example, the computing device (100) can simultaneously collect temperature data and flow rate data from a heat exchanger, calculate heat transfer efficiency, and evaluate whether it is within a normal range. In this case, the acquired facility status data can be appropriately corrected or filtered for accurate comparison and abnormality detection.

That is, the computing device (100) can accurately understand the current operating status of the equipment based on equipment status data acquired from various process equipment and provide basic information for early detection of abnormal signs. This data acquisition step is an essential process for maintaining the efficiency and stability of the process equipment, and can improve the accuracy of subsequent analysis and control steps.

A method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a step (S220) of analyzing equipment status data to generate simulation data according to equipment operation.

Specifically, the computing device (100) can analyze the equipment status data to generate simulation data based on the equipment's operating status and environmental conditions. The equipment status data includes various information such as the equipment's operating status, temperature, pressure, flow rate, vibration, energy consumption, wear status of parts, etc., and in the process of generating simulation data based on this data, the equipment's dynamic characteristics and external conditions can be reflected.

The computing device (100) can first compare the equipment status data with a predefined equipment model to identify the current operating characteristics of the equipment. For example, the computing device (100) can analyze the pressure and flow rate data of the pump to calculate the current efficiency of the pump, and generate simulation data to predict the dynamic operating status of the pump based on this.

In addition, for example, the computing device (100) can utilize the temperature and flow rate data of the heat exchanger to calculate the heat transfer efficiency and predict the expected heat exchange performance of the heat exchanger. In this process, the computing device (100) can integrate the heat transfer equation and the equipment model data to generate a heat transfer simulation result according to the operating state of the equipment.

The computing device (100) can also generate integrated simulation data including the interaction between the facilities. For example, the internal pressure and temperature data of the reactor can be analyzed to simulate the operating state of the reactor, and at the same time, the flow and heat transfer performance of the fluid connected to the heat exchanger can be comprehensively calculated. Through this, the computing device (100) can generate data that predicts in advance an abnormal state that may occur due to the interaction between the facilities.

In one embodiment, the computing device (100) can predict future conditions of the equipment by simulating changes in the condition of the equipment and the resulting impact over a certain period of time. For example, the computing device (100) can predict, through simulation data, a process abnormality that may occur due to a decrease in heat exchange performance when the internal temperature of the reactor continues to rise over a certain period of time.

In the process of generating simulation data, the computing device (100) can utilize various mathematical models and algorithms. For example, the heat transfer of a heat exchanger can be calculated by applying a heat transfer model including conduction, convection, and radiation, and the fluid flow of a pump can be simulated based on the Navier-Stokes equation. The generated simulation data can be utilized as data for optimizing the operation of the facility, predicting the condition of the facility, and warning of abnormal conditions.

A method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a step (S230) of generating a process equipment digital twin model based on equipment status data and simulation data.

According to an embodiment, the computing device (100) can generate a process facility digital twin model by reflecting the physical characteristics, operating status, and environmental conditions of the facility based on the facility status data and simulation data. The process facility digital twin model visually represents the structural shape, internal operating status, and surrounding environment data of the facility, and can be configured to intuitively provide real-time status monitoring and simulation results to the user.

The computing device (100) can model the basic structure and shape of the facility by referring to the design data of the facility (e.g., CAD drawings, BIM data, etc.). In this process, the computing device (100) can generate 3D data that accurately reflects not only the external shape of the facility but also the positions and sizes of internal components. For example, the tube arrangement of a heat exchanger, the internal chamber structure of a reactor, or the internal impeller shape of a pump can be modeled.

Thereafter, the computing device (100) can integrate the equipment status data collected in real time into a 3D model to visually express the current operating status of the equipment. For example, the temperature distribution of the reactor can be expressed in color, and the flow rate and pressure changes of the pump can be displayed through animation effects. Such visual expressions support understanding the status of the equipment at a glance, and can also include a function of highlighting and displaying an area where an abnormality has occurred.

In addition, the computing device (100) can utilize simulation data to reflect the expected state in the process equipment digital twin model. For example, the expected heat transfer performance of a heat exchanger can be expressed in a graph or number, or the fluid flow changes that may occur under certain conditions can be visually reproduced. By including such predicted data in the 3D model, the user can understand the future state of the equipment in advance and determine the necessary actions.

That is, the computing device (100) can generate a process facility digital twin model reflecting real-time status and predicted data based on facility status data and simulation data, thereby providing facility operation status in a visually intuitive and clear manner. This process facility digital twin model can be utilized as an important tool for facility management, abnormality detection, and improvement of operational efficiency.

A method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a step (S240) of generating a customized process equipment image by performing adjustments to a process equipment digital twin model based on hardware performance of a client terminal.

The computing device (100) can adjust the resolution and level of detail of the process equipment digital twin model to suit the user's requirements and the performance of the client terminal. This supports smooth confirmation and manipulation of the 3D model even on low-spec client terminals. For example, it can be selected to display only the external shape of the equipment in a simplified manner or to display detailed internal components.

In an embodiment, the hardware performance of the client terminal may include performance regarding at least one of the CPU, GPU, memory size, and network bandwidth of the client terminal.

In one embodiment, the adjustment to the process facility digital twin model may be characterized by an adjustment to at least one of the resolution, level of detail (LOD), and texture quality of the process facility digital twin model based on the hardware performance.

More specifically, the computing device (100) can collect hardware performance data of the client terminal and, based on the data, determine an optimal process facility digital twin model adjustment method that can be efficiently rendered on the client terminal. The hardware performance data includes CPU and GPU processing speeds, memory free space, network bandwidth, etc. of the client terminal, and the computing device (100) can analyze the data in real time and appropriately adjust the complexity of the process facility digital twin model.

The process of adjusting the digital twin model of the process equipment can be performed dynamically according to the performance of the client terminal. For example, a high-performance terminal can generate a high-resolution model that expresses even the minute details of the equipment, and a low-performance terminal can adjust it to a simplified model that only includes essential information.

In a specific embodiment, referring to FIG. 9, the step of generating a customized process facility image by performing adjustments to a process facility digital twin model based on the hardware performance of the client terminal may include a step (S231) of calculating the expected CPU and GPU load ratio and memory usage that may occur during rendering on the client terminal based on simulation data.

In an embodiment, the computing device (100) may analyze the rendering processing range in advance based on the hardware specifications of the client terminal (e.g., the number of CPU cores, GPU operation speed, memory capacity), calculate the expected CPU and GPU load ratio and memory usage, and determine an adjustment strategy for the process equipment digital twin model. To this end, the computing device (100) may collect and analyze hardware performance data of the client terminal in real time, and predict the complexity of the rendering task that may occur in the corresponding terminal.

The computing device (100) estimates the amount of computation (e.g., texture mapping, shader processing) required for rendering the process facility digital twin model by utilizing the CPU and GPU performance data of the client terminal. For example, a process facility digital twin model with a high number of polygons or a model including a high-resolution texture requires more computational resources, so the computing device (100) can dynamically adjust the complexity of the model so as not to exceed the maximum amount of computation that can be processed by the client terminal.

In addition, the computing device (100) can utilize simulation data to evaluate the memory consumption of the client terminal. For example, the computing device (100) can calculate the texture load size, cache usage, and data transfer requirements based on the available memory size and current memory occupancy of the terminal. Through this, rendering delays or errors due to lack of memory can be prevented in advance.

Specifically, the computing device (100) can calculate the expected load ratio by analyzing the data size and rendering complexity for each component (e.g., complex structure of the facility, texture resolution, animation data) of the process facility digital twin model. For example, if a specific section includes a complex facility structure and detailed texture, the GPU computational resource requirement and memory usage of the section can be estimated, and the priority of the rendering task can be adjusted.

Additionally, the computing device (100) also considers the data streaming requirements of the process facility digital twin model based on the network bandwidth and data transmission speed of the client terminal. For example, in a terminal with limited bandwidth, optimization can be performed to reduce the amount of data transmitted by compressing texture data or excluding non-essential data.

That is, the computing device (100) comprehensively analyzes the hardware specifications, memory usage, and network bandwidth of the client terminal to optimize the rendering work of the process equipment digital twin model and generate a customized process equipment image that matches the terminal performance. Through this, the stability and efficiency of the system can be secured at the same time while maintaining the rendering quality in the client terminal.

According to one embodiment, the step of generating a customized process equipment image may include a step (S232) of comparing the calculated expected load ratio and memory usage with the hardware performance of the client terminal to identify texture and polygon density areas likely to be overloaded.

According to one embodiment, the computing device (100) can identify texture and polygon density areas that are likely to be overloaded by comparing the calculated expected load ratio and memory usage with the hardware performance of the client terminal. The step may be a process for optimizing a specific area of the process facility digital twin model so that the rendering work on the client terminal does not exceed the load.

The computing device (100) can set a threshold value for each hardware resource by referring to the performance data of the client terminal. For example, threshold values for the computational capability of the GPU, available space of the memory, network bandwidth, etc. can be set, and the threshold values can be dynamically adjusted according to the hardware specifications of the client terminal.

Thereafter, the computing device (100) can analyze each texture and polygon area within the process facility digital twin model to evaluate whether the expected load ratio and memory usage exceed a threshold value. According to an embodiment, the texture data is classified by resolution, and as the resolution increases, the memory usage and GPU load increase, so an area with many high-resolution textures can be identified as having a high possibility of being overloaded.

For the polygon density area, the computing device (100) can calculate the number of polygons of each process facility digital twin model to evaluate whether the density of a specific area exceeds the GPU processing capability of the client terminal. The computing device (100) analyzes the number of polygons for each facility section and identifies an area containing a complex geometric structure. For example, a specific section in which the internal mechanical parts of the facility are complexly designed may have a much larger number of polygons than a relatively simple exterior section. Such an over-dense area is likely to excessively consume the GPU computational resources of the client terminal, resulting in a decrease in rendering performance.

Specifically, the computing device (100) analyzes the correlation with the polygon density based on the GPU clock speed, the number of shader cores, and the memory bandwidth of the client terminal. For example, if the number of polygons in a specific section exceeds the processing capability of the terminal, the computing device (100) can identify the area as an area subject to overload and determine that additional optimization is required. This analysis is performed in real time, allowing for flexible adjustments depending on the complexity of the model.

In addition, the computing device (100) can simulate the impact of texture and high polygon density areas on the performance of the client terminal. In this process, areas with a high possibility of overload can be visually highlighted and displayed to the user, or the system can be designated to automatically perform optimization work. For example, if a specific facility section is likely to slow down the rendering speed, the computing device (100) can automatically lower the texture resolution of the section or perform a retopology work to reduce the number of polygons.

In other words, the computing device (100) can analyze the texture and polygon density areas of the process equipment digital twin model by comparing them with the hardware performance of the client terminal, and identify areas with a possibility of overload, thereby providing basic data for optimization work. Through this, stable performance can be guaranteed while maintaining the rendering quality on the client terminal.

Additionally, according to an embodiment, the step of generating a customized process equipment image may include a step (S233) of performing compression by applying a graphics processing unit (GPU)-based texture compression algorithm corresponding to the identified texture and polygon density area.

More specifically, the computing device (100) can select a GPU texture compression algorithm and apply a suitable compression method based on the hardware performance data of the client terminal and the identified texture density information. For example, in a high-performance terminal, a high-efficiency compression format (e.g., Basis Universal) that can reduce the data size while maintaining high quality can be applied, and in a low-spec terminal, a lightweight compression method that prioritizes speed (e.g., DXT or ASTC) can be applied.

The compression process is performed in a direction to optimize data transmission and rendering performance by appropriately adjusting the resolution and quality of the texture. For example, if the texture resolution is excessively high, the computing device (100) can evaluate compatibility with the available GPU memory by gradually lowering the resolution. In addition, the computing device (100) can analyze the color channel and alpha channel data of the texture to reduce or remove channels with low importance, thereby maximizing the compression efficiency.

For example, in a complex equipment section, a high-resolution texture that is likely to exceed the GPU memory allocation of the client terminal may be compressed to reduce the data size by more than half. In this process, a selective compression method may be applied to analyze the frequency domain information of the texture to preserve the detail information of the texture and maintain high-frequency areas and remove low-frequency areas so that the quality degradation after compression is minimized.

Additionally, the computing device (100) can merge the compressed texture data with existing data of the process equipment digital twin model to ultimately generate a customized process equipment image that can be efficiently rendered on a client terminal. The compressed texture data can optimize the user experience by enabling efficient use of GPU memory during the rendering process and improving data transfer speed.

Additionally, according to an embodiment, the computing device (100) can perform a Retopology process to reduce the complexity of the process facility digital twin model and improve rendering efficiency at the client terminal.

In a specific embodiment, referring to FIG. 10, the step of performing adjustments to a process facility digital twin model to generate a customized process facility image may include a step (S241) of performing a Retopology process on the process facility digital twin model to generate a first adjusted process facility digital twin model.

In one embodiment, referring to FIG. 11, the step of performing a Retopology process on a process facility digital twin model to generate a first-adjusted process facility digital twin model may include a step of analyzing original data of the process facility digital twin model to identify an excluded polygon area based on a curvature of a facility surface, a geometric change rate, or a user visual requirement (S241a), a step of identifying a polygon to be excluded from the polygon area that does not cause a structural change and can maintain shape accuracy and data consistency of the facility model and setting the polygon as a polygon to be deleted (S241b), a step of removing the polygon to be deleted or merging it with an adjacent polygon to reduce the density of the mesh (S241c), and a step of modifying a correction for the process facility digital twin model with a reduced polygon density to generate a first-adjusted process facility digital twin model (S241d).

More specifically, the computing device (100) can receive the original data of the process equipment digital twin model and comprehensively analyze the curvature of the equipment surface, the geometric change rate, and the user's visual requirements. In this process, the computing device (100) can calculate the curvature value of each part of the equipment surface by utilizing a curvature analysis algorithm, and identify a flat area with little geometric change or an area with a repetitive and uniform structure as an excluded polygon area. For example, a straight line area with little change on a cylindrical equipment surface is likely to be selected as an excluded polygon area. Such an excluded polygon area can be an optimization target for improving the rendering efficiency of a 3D model.

The computing device (100) can perform additional analysis to maintain shape accuracy and data consistency in the area identified as the excluded polygon area. In this process, the impact of each polygon on the structural feature of the equipment model can be evaluated, and polygons that do not cause structural changes can be set as polygons to be deleted. The polygons to be deleted enable data simplification while maintaining the main geometric features of the equipment. For example, polygons that are excessively distributed on a planar surface can be merged into one single plane, and monotonous areas without complex structures can have their number of polygons reduced for data efficiency.

After the polygon to be deleted is determined, the computing device (100) can perform an optimization task to remove the polygon or merge it with an adjacent polygon. In this step, an algorithm for adjusting the density of the mesh is applied, and an abnormal connection state that may be caused by the deleted polygon is corrected. According to an embodiment, in the correction task, the boundary line of the adjacent polygon can be readjusted to maintain a smooth connection and prevent distortion of the boundary line. In addition, the interval between vertices is analyzed and equalization is performed based on the average interval of the adjacent vertices. Through this, the rendering efficiency can be improved while maintaining the consistency and visual quality of the data.

In addition, in the embodiment, the step of modifying the correction for the process facility digital twin model with reduced polygon density to generate the first adjusted process facility digital twin model may include the steps of aligning boundaries of adjacent polygons included in the process facility digital twin model with reduced polygon density and verifying and modifying the continuity of the boundaries, performing interval equalization by adjusting the interval between vertices of the process facility digital twin model with reduced polygon density to the average interval of the adjacent vertices, and performing an interval equalization, and after the interval equalization, performing a correction task of removing faulty vertices and artifact surfaces generated in the deletion and merging process, or reconstructing geometrically inappropriate areas.

Specifically, the computing device (100) detects an abnormal connection state caused by a deletion and merging process in a process facility digital twin model with a reduced polygon density, and performs a correction operation to correct it. In this process, the computing device (100) analyzes a geometric mismatch of a boundary line between adjacent polygons, and may apply a boundary line alignment algorithm to ensure the continuity of the boundary line. For example, since the boundary lines of the remaining adjacent polygons in the area where the deleted polygon is located may not be interconnected, the computing device (100) readjusts the boundary lines according to the reference coordinate system to maintain a smooth connection.

After the boundary alignment is completed, the computing device (100) analyzes the spacing between the vertices of the polygon and calculates the average spacing between adjacent vertices to perform spacing uniformity. In this process, the vertex positions are optimized to prevent visual distortion and data inconsistency that may occur due to uneven spacing between vertices. For example, if the spacing between vertices in a specific area is excessively narrow or wide, the computing device (100) readjusts the coordinates of the adjacent vertices to make the spacing between the vertices uniform.

Thereafter, the computing device (100) can perform a step of detecting and removing faulty vertices and abnormal surfaces (artifact surfaces) generated during the deletion and merging process based on the gap equalization operation. These faulty vertices may be generated due to residual data of the deleted polygon or geometric inconsistencies generated during the merging process, and the computing device (100) automatically removes or corrects the faulty vertices by comparing them with data of adjacent polygons. The abnormal surfaces are polygons whose data do not match or distorted surfaces, and the computing device (100) can analyze the geometric characteristics of the corresponding surfaces and perform a reconstruction operation. In the reconstruction operation, the original shape of the deleted polygon can be restored, or a new surface can be generated based on data of the adjacent polygon to correct the abnormal area.

That is, the computing device (100) can generate a first adjusted process facility digital twin model that corrects geometric inconsistencies that may occur in the process facility digital twin model after the deletion and merge operation, maintains data consistency, and improves rendering quality.

Through this process, the first adjusted process facility digital twin model generated by the computing device (100) can be further optimized to match the hardware performance and rendering requirements of the client terminal while maintaining the core shape of the facility and reducing excessive data load.

Referring again to FIG. 10, the step of generating a customized process facility image by performing adjustments to the process facility digital twin model may include a step (S242) of setting the level of detail in multiple stages according to the hardware performance and rendering requirements of the client terminal in response to the first adjusted process facility digital twin model, and generating a second adjusted process facility digital twin model corresponding to each level of detail.

In one embodiment, referring to FIG. 12, the step of setting the level of detail in multiple stages according to the hardware performance and rendering requirements of the client terminal in response to the first-adjusted process facility digital twin model and generating the second-adjusted process facility digital twin model corresponding to each level of detail may include the step of determining customized rendering settings based on the hardware performance of the client terminal (S242a), the step of classifying each polygon group of the first-adjusted process facility digital twin model according to distance, visibility, or frequency of use based on the determined customized rendering settings (S242b), the step of setting the level of detail in multiple stages to reduce the polygon density for a group that is located far away or has a low visibility frequency among the classified polygon groups and maintain high resolution for a nearby group (S242c), and the step of generating the second-adjusted process facility digital twin model based on the process facility digital twin model with the set level of detail (S242d).

More specifically, the computing device (100) can determine customized rendering settings suitable for the rendering task based on the hardware performance data of the client terminal. In this process, the computing device (100) comprehensively analyzes the CPU and GPU processing capabilities, available memory, display resolution, network bandwidth, etc. of the client terminal. For example, in the case of a terminal equipped with a high-performance GPU, settings can be set to maintain high-resolution graphics and complex polygon details, and in the case of a low-spec terminal, settings can be applied to reduce texture quality and polygon density to reduce the rendering load.

According to the determined customized rendering settings, the computing device (100) can classify each polygon group of the first adjusted process facility digital twin model according to criteria such as distance, visibility, and usage frequency. In this process, the computing device (100) can analyze the location of each polygon group within the process facility digital twin model and calculate how close or far it is from the viewpoint of the client terminal. For example, a polygon group that is far from the user's viewpoint and has a low visibility frequency is likely to be a target for optimization. In addition, if a specific polygon group is in a location that is always visible or has a high frequency of interaction with the user, the group is classified as a group that must maintain a high resolution.

The computing device (100) sets the Level of Detail (LOD) for the classified polygon groups in multiple stages. For example, a polygon group that is far from the user's viewpoint can have its polygon density reduced or replaced with a simplified mesh to reduce the rendering load. On the other hand, a polygon group that is close to the user can maintain high resolution and maintain or reinforce its polygon density so that even fine details can be expressed. This multi-stage setting is performed not only based on distance, but also comprehensively considering visibility frequency and usage frequency. For example, a polygon group that is not normally visible, such as internal components of equipment, but is frequently accessed in a specific work situation, can be set to maintain high detail.

Finally, the computing device (100) integrates the polygon groups with the level of detail set to generate a second-order adjusted process facility digital twin model. In this case, the models are combined by reflecting the level of detail set for each polygon group, and the integrated model maximizes rendering efficiency while maintaining user experience. For example, by merging with a texture compression algorithm, high-quality textures can be maintained in areas requiring high resolution, and low-resolution textures can be applied to unnecessary areas. This second-order adjusted process facility digital twin model can provide optimal rendering performance on client terminals, while maintaining visibility and interactivity of the facility model.

Referring again to FIG. 10, the step of generating a customized process facility image by performing adjustments to the process facility digital twin model may include a step (S243) of generating a minimap (mipmap) based on the second-adjusted process facility digital twin model, and generating the customized process facility image based on the generated minimap.

Here, the minimap may be generated by layering texture data of a second-order adjusted process facility digital twin model into multiple resolutions, and configured to dynamically select and apply a texture of an appropriate resolution depending on the hardware performance of the client terminal during the rendering process.

In one embodiment, referring to FIG. 13, the step of generating a minimap based on a second-adjusted process facility digital twin model and generating a customized process facility image based on the generated minimap may include a step of analyzing texture data of the second-adjusted process facility digital twin model to evaluate the size, quality, and usage frequency of each texture (S243a), a step of dividing the evaluated texture data into multiple resolutions and generating texture blocks suitable for each resolution (S243b), a step of configuring layered texture data into a minimap structure so that texture blocks of suitable resolutions can be dynamically selected and applied according to the hardware performance and rendering environment of the client terminal (S243c), and a step of generating a customized process facility image for providing optimized rendering quality in the client terminal based on the minimap structure (S243d).

More specifically, the computing device (100) can analyze the texture data of the second-adjusted process facility digital twin model to evaluate the size, quality, and usage frequency of each texture. In this process, the computing device (100) collects pixel resolution, color quality, and usage frequency data of the texture applied to each area of the process facility digital twin model, and can analyze the influence of a specific texture on the rendering process of a client terminal based on the collected data. For example, if the texture of a specific area requires high resolution but has a low visibility frequency, optimization can be performed by lowering the priority of the corresponding texture.

The computing device (100) can divide each texture into multi-resolution levels based on the evaluated texture data and generate texture blocks suitable for each resolution. The multi-resolution levels of the texture can be set in various ways depending on the hardware performance and rendering environment of the client terminal. For example, a high-resolution texture is applied to an area that a user can see up close, and a low-resolution texture is assigned to an area that can be seen from a distance. In this process, the computing device (100) can compress or simplify the texture on a pixel basis to convert the same texture into various resolutions.

In addition, the computing device (100) hierarchizes texture data divided into multiple resolutions to generate a minimap structure. The minimap structure is designed to dynamically select and apply texture blocks of an appropriate resolution according to the hardware performance and rendering environment of the client terminal. For example, when rendering an area close to the user's viewpoint, a high-resolution texture block is applied, and when rendering an area far away, a low-resolution texture block is automatically selected and applied. This minimap structure reduces the rendering load while allowing the user to experience high visual quality.

Additionally, the computing device (100) can generate a customized process facility image based on the generated minimap structure. In this process, the resolution and quality of the texture applied to each area are optimized to match the performance of the client terminal, and the finally rendered image can be smoothly visualized on the client terminal. For example, when rendering a 3D image including a complex facility structure, the minimap structure dynamically adjusts the size and quality of the texture block so that the rendering performance and visual quality can be satisfied at the same time on the client terminal. This process can minimize the hardware load on the client terminal while maintaining the optimal rendering quality.

A method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a step (S250) of monitoring the status of equipment by visualizing a customized process equipment image in real time through a user interface or displaying simulation results.

A customized process equipment image visualized in real time through a user interface may be characterized by reflecting equipment status data such as temperature, pressure, and power consumption of the equipment in real time, and including notification information for visually indicating an abnormal state or abnormal operating condition of the equipment.

The computing device (100) can visualize the generated customized process equipment image in real time through a user interface to intuitively display the status of the equipment. Here, the customized process equipment image is dynamically updated based on the real-time status data of the equipment, and visually expresses key data such as temperature, pressure, and power consumption. For example, when a specific part of the equipment reaches a high temperature state, the corresponding area can be highlighted with a color change (e.g., red) on the user interface.

The computing device (100) not only visually displays equipment status data, but also provides notification information to the user when an abnormal condition is detected. Such notifications may be displayed in the form of text, graphic icons, or animations. For example, when the pressure in a specific equipment exceeds a reference value, a warning icon may appear on the user interface, and a text message explaining the location and cause of the equipment may be provided together.

In addition, the computing device (100) can visualize predicted information on the equipment status based on the simulation results on the user interface. For example, the temperature or pressure change expected when the load of a specific equipment is maintained in the current state can be displayed in the form of a graph, or the simulation results when the operating state of the equipment is maintained or adjusted can be compared to provide the user with selectable scenarios.

The user interface can be designed to allow intuitive operation. For example, a user can select a specific piece of equipment in a 3D image to view detailed information or enter a command to change the operating conditions of the equipment. The computing device (100) processes this input to adjust the status of the equipment or provide additional analysis results.

That is, the computing device (100) updates the customized process equipment image in real time and provides visual information based on equipment status data, thereby enabling the user to efficiently monitor the equipment status and immediately take necessary actions. This user interface can contribute to improving the reliability and efficiency of air conditioning equipment monitoring and control.

In summary, the computing device (100) visualizes customized process equipment images in real time through a user interface to support intuitive monitoring of the equipment status. To this end, the computing device (100) collects and analyzes hardware performance data of a client terminal, and dynamically generates and optimizes a 3D image suitable for the performance. For example, a high-performance terminal provides a 3D image with high resolution and detailed details, and a low-spec terminal provides a lightweight image containing only essential data, thereby optimizing the rendering performance.

In addition, the computing device (100) generates a 3D image that is dynamically updated based on the equipment status data, visually expresses key data such as the temperature, pressure, and power consumption of the equipment, and provides notification information to the user when an abnormal equipment status is detected. This prevents a decrease in rendering speed that may occur due to performance limitations of the client terminal, and allows the user to accurately check the equipment status in real time.

Accordingly, the computing device (100) provides an optimized 3D image by simultaneously considering the performance of the client terminal and the equipment status data, thereby visually conveying the real-time status and prediction information of the equipment, and allowing the user to efficiently manage the equipment and immediately respond to abnormal signs. This approach can contribute to strengthening the stability of the equipment and maximizing operational efficiency.

FIG. 14 and FIG. 15 are exemplary diagrams showing the status monitoring and simulation result visualization of air conditioning equipment and process equipment related to one embodiment of the present invention.

Referring to FIG. 14, the computing device (100) can visualize real-time data such as temperature, pressure, flow rate, and power consumption of the facility and display them on the user interface. Such data visually expresses the complex flow inside the facility and helps to intuitively understand the status of each facility component. For example, the cooling water flow path and air circulation status of the facility can be displayed with color distinction, which is useful for evaluating the efficiency inside the facility or detecting abnormal conditions in advance.

Referring to Fig. 15, the internal structure and major components of the equipment are visualized in a 3D cross-section, thereby supporting detailed analysis of the operating mechanism of the equipment. For example, if a specific equipment section exhibits a failure or abnormal operating condition, the computing device (100) highlights the location and related data of the corresponding component, thereby providing information so that the user can quickly resolve the problem. In addition, major components inside the equipment are color-coded to clearly indicate the status and role of each component.

Such visualizations can be used as important tools for monitoring facility operation status in real time and optimizing facility performance based on simulation results.

Fig. 16 illustrates a flow chart exemplarily showing an AI-based process equipment abnormality detection and response automation method related to one embodiment of the present invention. For features of the contents illustrated in Fig. 16 that overlap with features described above with respect to Figs. 3 to 15, reference should be made to the contents described in Figs. 3 to 15, and their descriptions will be omitted here.

An AI-based process facility abnormality detection and response automation method related to one embodiment of the present invention may include a step (S310) of generating an integrated digital twin model that visually expresses the status of a facility space, air conditioning equipment, and process equipment based on design data and initial operation data of the facility space, air conditioning equipment, and process equipment.

The integrated digital twin model can be updated to reflect real-time changes in anomalies, and the response protocol can be characterized by variable adjustments based on the severity of the anomaly and the condition of the equipment. For example, if a pressure anomaly occurs in a specific section of the process equipment, that section can be visually highlighted, and the associated air conditioning equipment and spatial impacts can be analyzed to provide information for the user to resolve the issue.

In an embodiment, the integrated digital twin model may be configured to include a process facility digital twin model including visual information about the layout structure and operating status of the process facility, and a facility digital twin model including spatial information and environmental data of the facility space, and visual information about the operating status of the air conditioning facility.

More specifically, the integrated digital twin model is configured to comprehensively express the status and interrelationship of each process facility, facility space, and air conditioning facility. The process facility digital twin model of the process facility is designed based on the geometric structure and physical characteristics of each facility, and can reflect data such as the status of the facility's internal components, operating status, and energy consumption in real time. For example, in the case of a heat exchanger, the flow path and temperature change of the fluid can be visually expressed, and in the case of a pump, the operating speed and flow rate data can be graphically displayed to provide clear information to the user.

The facility digital twin model, which includes spatial information and environmental data of the facility space, can reflect environmental variables such as temperature, humidity, and airflow in real time. The facility digital twin model visualizes environmental data by area of the space, allowing users to easily understand the environmental conditions of a specific area. For example, if the temperature of a specific area exceeds the standard range, the area can be highlighted in color, and the speed and direction of airflow can be animated. This data becomes the basis for evaluating and adjusting the environmental comfort of the space.

A facility digital twin model that visualizes the operating status of air conditioning equipment can include information such as the operating status, energy consumption, and operating efficiency of the equipment. For example, for cooling equipment, the operating rate is displayed in real time, and for blowers, the blowing speed and energy consumption are displayed in real time, and when an abnormality occurs, related information is highlighted along with a warning message.

These integrated digital twin models can clearly visualize the interactions and influences between facilities. For example, if an abnormal condition of a specific process facility leads to an increase in the load of an air conditioning facility, the integrated model can visually display the correlation between facilities, helping users quickly identify the cause of the problem. In addition, by integrating facility status and environmental data in real time, it can generate optimal control signals according to the operating situation and provide information for adjusting facility operations when necessary.

A method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a step (S320) of acquiring real-time environmental data and equipment status data through a plurality of sensors provided in each of a facility space, air conditioning equipment, and process equipment.

In one embodiment, the computing device (100) can obtain real-time environmental data and facility status data through a plurality of sensors installed in each of the facility space, air conditioning equipment, and process equipment. The step of obtaining environmental data and facility status data plays an essential role in maintaining real-time operation of the system and for accurate status monitoring and control.

The computing device (100) is connected to each sensor via a network (400) and can collect data from the sensor periodically or based on an event. Real-time environmental data may include temperature, humidity, air flow rate, pressure, and air quality of the facility space, and facility status data obtained from air conditioning equipment and process equipment may include various information such as equipment operating status, energy consumption, operating temperature, flow rate, vibration level, and component wear status.

Specifically, the environmental sensors installed in the facility space may include a temperature and humidity sensor that measures the temperature and humidity of each area, a wind speed sensor that measures the speed and direction of air flow, a dust sensor that detects air quality, and a _CO2 sensor. For example, the computing device (100) can detect when the air quality in a specific area deviates from a standard or the temperature rises rapidly, immediately collect data, and analyze the abnormal condition.

Sensors equipped in air conditioning equipment provide data related to the operating status of the equipment. For example, the computing device (100) can obtain status data of the air conditioning equipment through a pressure sensor that detects the operating status of the compressor of the air conditioner, a rotation speed sensor that measures the speed of the blower, a power sensor that monitors energy consumption, etc. Through this, the efficiency of the air conditioning equipment can be evaluated or abnormal operation can be detected early.

Sensors installed in process equipment monitor the operating conditions and performance of the equipment. For example, temperature and pressure sensors mounted on the reactor detect the internal operating environment in real time, and the flow sensor of the pump can check whether the equipment is operating at a constant performance. In addition, vibration sensors can be used to predict the wear status or failure of equipment parts in advance.

The computing device (100) can comprehensively analyze the status of the system by integrating the collected data. For example, if a temperature rise in a specific process facility leads to an increase in the load of the facility and a lack of cooling capacity in the air conditioning facility, the computing device (100) can detect this in real time and suggest a response measure. Data is collected at regular intervals or transmitted immediately when an abnormality occurs, thereby enhancing the real-time response capability of the system.

This sensor data acquisition process can be an important foundation for continuously monitoring the status of complex systems in which air conditioning equipment, process equipment, and facility spaces interact, maintaining equipment efficiency and stability, and optimizing environmental conditions.

A method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a step (S330) of detecting abnormal signs by analyzing acquired environmental data and equipment status data using an artificial intelligence-based abnormal sign detection model.

In an embodiment, the anomaly detection model is a machine learning-based model that analyzes environmental data and facility status data acquired from process equipment and facility space to classify normal and abnormal states, and may be characterized by learning patterns in time series data to detect abnormal states, analyzing the cause of occurrence of abnormal signs, and classifying warning levels according to occurrence frequency and severity.

Specifically, the computing device (100) may collect environmental data such as temperature, humidity, and airflow rate obtained from process equipment and facility space, and status data such as vibration, pressure, and energy consumption of the equipment, to form learning data for learning an anomaly detection model. Such learning data is labeled as a normal state and an abnormal state, and may include a preprocessing process such as missing value processing, normalization, and outlier removal to ensure data quality.

The anomaly detection model may include a deep learning-based structure, and may use a Long Short-Term Memory (LSTM) network to analyze patterns in time series data, or a Convolutional Neural Network (CNN) to effectively learn the features of the data. For example, in order to detect overheating of equipment, the model may be configured to learn the correlation between the temperature at a specific point in time and the past temperature pattern to detect anomalies.

More specifically, the computing device (100) can perform specific steps to learn an anomaly detection model by utilizing data collected from process equipment and facility space.

For example, in order to detect an overheating condition of equipment, the computing device (100) can organize temperature data of the process equipment into time series data and label each data point as normal or overheating to create a learning data set. The learning data set includes temperature change patterns over a certain period of time in the past and current temperature data, and can be used to train a model capable of predicting changes in the condition of the equipment.

During the learning process, the computing device (100) can utilize a Long Short-Term Memory (LSTM) network to effectively process the temporal dependency of time series data. For example, the LSTM model can predict the temperature change at the next point in time based on the past temperature change data of the facility, and if the predicted value exceeds a threshold, it can be classified as an anomaly.

In addition, CNN (Convolutional Neural Network) can be used to process complex condition data of equipment. For example, vibration data of equipment can be converted into a time-frequency spectrum and input into a CNN model, and patterns of normal and abnormal conditions can be learned to detect abnormal signs.

After the abnormality detection model is learned, the computing device (100) can analyze the collected data in real time to quickly detect an abnormal condition and identify the cause of the abnormality (e.g., overheating, component wear) and the location of occurrence. For example, the computing device (100) can process input data such as temperature 60°C, humidity 45%, vibration 0.5g, pressure 400kPa, and energy consumption 120kW to analyze whether the corresponding equipment is in a normal state. As a result of the analysis, the status of the equipment can be output in detail, such as a high-risk level warning is required due to an overheating state or a medium-risk level warning is generated due to excessive vibration. Such analysis results can be classified into warning levels (e.g., low-risk, medium-risk, high-risk) and provided visually through a user interface or transmitted as a response protocol.

A method for monitoring and controlling air conditioning equipment related to one embodiment of the present invention may include a step (S340) of reflecting the location, type, cause, and influence of the abnormal symptom into an integrated digital twin model and providing the result through a user interface.

In a specific embodiment, referring to FIG. 17, the step of reflecting the location, type, cause, and influence of an abnormality symptom into an integrated digital twin model and providing it through a user interface may include a step (S341) of visually highlighting the location of the facility or space where the abnormality symptom occurred on the integrated digital twin model.

The computing device (100) can utilize color, animation, or graphic elements to visually highlight the location of the equipment or space where the abnormality occurred on the integrated digital twin model. For example, if an overheating problem occurred in a specific equipment, the equipment can be highlighted in red on the 3D model or a blinking icon can be added to highlight it so that the user can immediately recognize it. This visual emphasis can be variably adjusted depending on the severity of the abnormality. For example, a method can be applied in which a minor abnormality is expressed in yellow and a serious abnormality is expressed in red.

Additionally, the computing device (100) can apply different emphasis methods depending on the type of abnormality. For example, when excessive vibration is detected, an animation indicating a vibration effect can be added, or when an airflow problem occurs, an abnormal airflow path can be visually indicated through an arrow on the 3D model.

In an embodiment, the computing device (100) may analyze the cause and effect of an abnormality and reflect it in the integrated digital twin model. For example, if it is confirmed that the cause of overheating of the facility is a failure of the cooling system, the location of the corresponding cooling system may be highlighted together on the 3D model, or detailed information related to the cause may be provided in a pop-up window. In addition, the effect of the abnormality on other facilities or spaces may be analyzed and intuitively displayed on the integrated digital twin model. For example, if a failure of a specific facility is likely to cause a temperature rise in an adjacent facility, the path may be represented as a graphic arrow, or the expected effect may be visualized and provided to the user.

In one embodiment, the computing device (100) may be configured to provide such information hierarchically through a user interface so that the user can selectively check detailed information as needed. For example, a method may be applied in which the location and basic information of an anomaly are displayed on the main screen, and additional information including detailed cause analysis and expected impact are provided upon clicking. Such a configuration may contribute to optimizing the user experience and maximizing the efficiency of responding to an anomaly.

In addition, the step provided through the user interface may include a step (S342) of displaying information describing the type, occurrence time, and cause of the abnormal symptom in the form of text or an icon corresponding to the highlighted location.

Specifically, the computing device (100) can display information explaining the type, occurrence time, and cause of the abnormal symptom in the form of text or icons corresponding to the location of the abnormal symptom highlighted on the integrated digital twin model. For example, if an overheating problem occurs in a specific facility, the computing device (100) can intuitively indicate the overheating state by adding an icon to the location of the facility, and when the icon is clicked or touched, a detailed description such as "Overheating occurred - Temperature: 85°C, Occurrence time: 14:23, Cause: Cooling system failure" can be provided in a pop-up window.

In addition, the computing device (100) can update text information in real time in connection with the equipment status. For example, when the equipment is restored to normal condition or the condition of an abnormality worsens, the information can be reflected in real time to convey the exact condition to the user. In one embodiment, the text information can be provided in the form of a notification message or an interactive pop-up to enhance the user experience.

Information in the form of icons can be designed to identify the type of abnormality at a glance. For example, overheating problems can be represented by a red icon symbolizing temperature, vibration problems by a waveform icon, and airflow problems by an arrow-shaped icon. These icons can be dynamically adjusted in size or color depending on the severity of the abnormality.

In addition, the computing device (100) can support the user to selectively check basic information and detailed information by hierarchically configuring text and icon information on the user interface. For example, only the type and occurrence time of an abnormality can be displayed on the basic screen, and detailed information including the cause and expected impact can be provided through additional interaction. This specific information provision method can provide the user with a clear understanding of the abnormality and support quick and efficient problem solving.

Additionally, the step provided through the user interface may include a step (S343) of visualizing the expected impact due to the abnormal symptom in the form of graphics or a dashboard through real-time simulation results.

According to an embodiment, the computing device (100) may analyze the expected impact due to the abnormal sign, visualize it as a real-time simulation result, and provide it through a user interface. For example, the computing device (100) may perform a heat diffusion simulation to predict the impact that an overheating problem occurring in a specific facility may have on surrounding facilities or processes. The simulation result may graphically display the expected temperature change around the facility, or provide the impact, such as a decrease in the operating efficiency of the facility, in the form of a dashboard.

Specifically, the computing device (100) generates graphic elements for visually representing the impact of an abnormality based on simulation data. For example, areas where an overheating problem is likely to spread can be displayed by distinguishing colors on the integrated digital twin model, and high-risk areas can be displayed in red and medium-risk areas in orange to provide an immediate visual warning to the user. In addition, a dashboard-type interface can provide the expected impact of an abnormality through numerical data and graphs to support the user to quantitatively understand the impact.

The computing device (100) can update the simulation results of the expected impact in real time. For example, if the overheating problem of a specific facility is reduced by the operation of the cooling system, the simulation results and graphical display can be adjusted immediately to reflect the latest status to the user. In addition, the interconnectivity between facilities can be analyzed to evaluate the impact of the expected impact on the process flow, and the possibility of the operation of the connected facilities can be predicted and displayed as a warning message on the dashboard.

Additionally, the computing device (100) can provide user-definable simulation scenarios on the user interface. For example, it can support the user to adjust the operating conditions of the facility or set up a virtual scenario to simulate the expected impact under the conditions. This provides the user with a tool to review response strategies for abnormal signs in advance, and can improve the stability and efficiency of facility operation.

A method for monitoring and controlling air conditioning equipment according to one embodiment of the present invention may include a step (S350) of executing a predefined response protocol based on the type and influence of an abnormal symptom.

According to a specific embodiment, referring to FIG. 18, the step of executing the predefined response protocol may include a step (S351) of setting a priority according to the location, type, and severity of the abnormal sign.

In an embodiment, the step of setting priorities based on the location and type and severity of the abnormality may include the steps of identifying the location of the equipment or space where the abnormality occurred, evaluating the equipment importance and operational priority of the identified location, analyzing the type of the abnormality and the impact of the abnormality on equipment performance, and comparing the severity of the abnormality with a predefined threshold value to classify it as an emergency, warning, or normal state.

According to an embodiment, the step of setting the priority according to the location, type, and severity of the occurrence of the abnormality may include a step of analyzing the interaction and operating status between the facilities when multiple abnormalities occur in adjacent facilities or within the same section, and generating individual control commands so that the abnormality of each facility can be independently processed without affecting the mutual operation, a step of transmitting an immediate execution command to immediately execute a response command for facilities or spaces with a high occurrence frequency of abnormalities, and a step of adjusting the priority of abnormalities with a low occurrence frequency to generate a delayed execution command.

To explain in more detail, the computing device (100) can analyze the equipment status data and environmental data collected in real time to identify the location of the equipment or space where an abnormality symptom has occurred. For example, the location of the occurrence of an abnormality symptom can be accurately identified based on the change in the status of the equipment, such as temperature, pressure, and vibration, and the location within the process section or facility space connected to the physical location of the equipment can be mapped and highlighted on the integrated digital twin model.

The computing device (100) can refer to predefined facility grade information to evaluate the importance and operation priority of the identified facility. For example, if a specific facility plays a key role in the process, the facility is given a high importance and is given priority for processing. In addition, the operation priority can be adjusted by analyzing the impact of the operation stoppage of the facility where an abnormality has occurred on the adjacent facility or process.

Thereafter, the computing device (100) analyzes the type of abnormality sign and evaluates the impact on the equipment performance. For example, if the efficiency of the equipment decreases or safety risks increase due to overheating, the overheating sign may be given an urgent priority. On the other hand, relatively minor abnormalities (e.g., minor vibration) are processed with a low priority. The severity of the abnormality sign is classified by comparing the data detected in real time with a predefined threshold value. An emergency state requires an immediate response, and a warning state requires a response within a certain period of time, but immediate action may not be necessary.

When multiple abnormal signs occur in adjacent facilities or within the same section, the computing device (100) analyzes the interaction and operating status between the facilities. For example, when an overheating warning occurs simultaneously in two facilities in the same process line, the computing device (100) generates a command to redistribute the operating load of the two facilities or adjust the output of the cooling device so that the abnormal signs can be handled independently.

In addition, immediate execution orders can be sent to facilities with a high frequency of occurrence of abnormal signs to respond preferentially, and delayed execution orders can be generated by adjusting the priority of facilities with a low frequency of occurrence. For example, facilities with a high frequency of occurrence can be given priority for measures such as shutdown or replacement of parts, and facilities with relatively less frequent occurrences can be handled later unless they have an urgent impact.

In this way, the computing device (100) comprehensively evaluates the location, type, and severity of the abnormality, optimizes the equipment status according to a predefined response protocol, and generates control commands to maintain the stability of the process and equipment. These steps can be visualized in real time through a user interface or executed in an automated manner.

Additionally, in the embodiment, the step of executing the predefined response protocol may include a step (S35) of generating a control command for each of the process equipment and the air conditioning equipment according to priority.

More specifically, the computing device (100) can generate individual control commands for each of the process equipment and the air conditioning equipment based on the priority information of the abnormality symptoms. The priorities are set by comprehensively considering the importance of the equipment, the type and severity of the abnormality symptoms, and the interaction between the equipment. For example, an overheating warning generated in a core component of the process equipment can be given a high priority, and an immediate cooling command can be generated. On the other hand, a minor vibration generated in the air conditioning equipment can be given a low priority, and a delay command can be generated.

When generating a control command for a process facility, the computing device (100) may analyze the current operating status and abnormality symptom data of the facility to generate a command for adjusting the output level, operating time, or operating mode of the facility. For example, when the pressure of a specific facility exceeds a threshold value, the computing device (100) may generate a command to reduce the operating speed of the facility or distribute the load to other facilities. In addition, for facilities with excessive vibration, a command may be transmitted to automatically stop operation and generate an inspection notification.

In generating control commands for air conditioning equipment, commands for airflow speed, temperature setting, or humidity control can be generated by considering environmental data provided by the equipment. For example, if the temperature of a specific area exceeds a predefined standard, the computing device (100) can transmit a command to activate a cooling device in the area or adjust the airflow direction to lower the temperature.

In the process of generating control commands, the computing device (100) can be designed to generate conflict-free commands by considering the interaction between the equipment. For example, if an abnormality occurs simultaneously in two equipment connected to the same process line, the computing device (100) can optimize the control signal by adjusting the operating conditions of the two equipment so that the response action of one equipment does not have a negative impact on the other equipment.

The generated control commands are transmitted to each of the process equipment and air conditioning equipment, and the computing device (100) can monitor in real time whether the equipment is operating normally according to the commands, and can generate and transmit additional commands when necessary. This process is intended to maintain the stability of the process and environment, and to minimize the impact of abnormal signs on the equipment and the entire process.

Additionally, in the embodiment, the step of executing the predefined response protocol may include a step (S353) of transmitting the generated control command to each of the process equipment and the air conditioning equipment to adjust the equipment status or modify the environmental conditions.

According to an embodiment, the computing device (100) generates a control command required for the facility or space based on the abnormal symptom analysis result and the priority setting data. For example, if overheating is detected in a specific process facility, a command may be generated to increase the output of the cooling system or adjust the operating speed of the facility. Additionally, in the case of air conditioning facilities, if the temperature of a specific section rises, a command may be generated to adjust the air flow to supply additional cooling air to the section.

The computing device (100) directly transmits the generated control command through a network capable of communicating with the equipment, and checks the response status of the equipment in real time during the command transmission process. For example, when a speed reduction command for the process equipment is transmitted, it can be verified through feedback data whether the equipment successfully received and executed the command.

Thereafter, the computing device (100) continuously monitors the execution result of the transmitted control command to evaluate whether the equipment status is normalized to a predefined target condition. For example, after the cooling command is executed, it is checked through the temperature sensor whether the temperature of the equipment returns to a normal range, and an additional control command can be generated or an existing command can be modified based on the result.

In addition, the computing device (100) may perform a retransmission command or activate a predefined emergency response protocol if there is no response within a certain period of time to ensure the reliability of command execution even in the event of network delay or abnormal response of the equipment. For example, if the cooling system of the equipment is not operating abnormally, a command to switch the entire equipment to a safe mode may be preferentially executed.

In this process, the computing device (100) monitors the status of each process facility and air conditioning facility in real time, and continuously analyzes the operating conditions and environmental data of each facility to generate additional optimization commands or update the learning data of the abnormality detection model. Through this, the stability of the facility can be maintained and operational interruption due to abnormal conditions can be minimized.

In various embodiments, the method for monitoring and controlling air conditioning equipment may further include the step of activating a predefined emergency response protocol to stop equipment operation or provide visual and audio warnings via a user interface if the abnormal condition persists or worsens after the execution of a response command for the abnormality symptom. Such emergency response protocol is designed as a last resort to maintain the safety of the equipment and the stability of the system.

More specifically, the computing device (100) continuously monitors real-time environmental data and equipment status data collected from equipment or spaces where abnormal signs have occurred, and if the abnormal condition exceeds a threshold or shows a worsening trend, it can automatically trigger an emergency response protocol. For example, if the temperature of a specific equipment exceeds a predefined maximum allowable temperature or the vibration level continuously increases and structural damage to the equipment is expected, the computing device (100) can command the equipment to immediately stop operating and switch to a safe mode.

Additionally, the emergency response protocol may include steps for providing visual and audio alerts via the user interface. The computing device (100) displays details of the abnormality (e.g., location, type, severity) in graphical or text form on the user interface, and enables the operator to take action quickly via audio notification. For example, along with an audio alert such as “Overheating condition occurred at facility A - immediate inspection required,” the location of the abnormality may be highlighted on the integrated digital twin model to provide intuitive information to the user.

Additionally, the computing device (100) can create a detailed log of the emergency situation and store it in a database. This log can record the cause of the emergency situation, the response measures, and the results, and can be utilized for future analysis and system improvement. For example, the computing device (100) can analyze the repetitive abnormal state of the facility based on the emergency situation log, or can evaluate the effectiveness of the emergency response protocol and configure an optimized protocol.

Through this, the air conditioning equipment monitoring and control method of the present invention can maintain the safety of the equipment and the stability of the system even in an abnormal symptom situation, provide quick and clear information to the user, and improve the efficiency of the system through continuous data analysis.

According to one embodiment of the present invention, as illustrated in FIG. 19, the method for monitoring and controlling air conditioning equipment may further include a step (S361) of extracting environmental data and equipment status data at the time of occurrence of an abnormality to configure cause analysis data for analyzing the cause of an abnormality, a step (S362) of automatically generating an abnormality report according to a predefined format based on the configured cause analysis data, a step (S363) of storing the cause analysis data and the generated abnormality report in a database, and a step (S364) of performing re-learning on an abnormality detection model based on data stored in the database.

In one embodiment, the computing device (100) configures abnormality cause analysis data based on environmental data and facility status data at the time when the abnormality is detected. In this process, the computing device (100) collects real-time data from a plurality of sensors installed in the process facility and the air conditioning facility, and extracts environmental data such as temperature (e.g., 80°C), humidity (e.g., 65%), and air flow speed (e.g., 5 m/s), and facility status data such as pressure (e.g., 300 kPa), vibration (e.g., 1.2 g), energy consumption (e.g., 150 kW), and operating status (e.g., in operation/standby). Based on this data, a data preprocessing process is performed to supplement missing data or remove outliers in order to clarify the cause of the abnormality occurrence. For example, missing temperature data can be estimated by interpolating data from a previous time point, or abnormal vibration values caused by sensor malfunction can be removed.

Thereafter, the computing device (100) automatically generates an anomaly report according to a predefined format by utilizing the configured cause analysis data. The report may include key information such as the time of occurrence of the anomaly (e.g., 14:32), location (e.g., facility A-2), facility name (e.g., heat exchanger B-1), type of the detected anomaly (e.g., overheating, excessive vibration), cause analysis result (e.g., insufficient cooling flow rate), impact assessment (e.g., reduced facility efficiency and risk of damage), and recommended response action (e.g., inspection of cooling pump and replacement of parts). The generated report is visually provided in graphical form such as a table, chart, or 3D model overlay through a user interface, and may be sent by email or uploaded to a cloud-based management system if necessary.

In one embodiment, the anomaly report and cause analysis data can be stored in a database. The database systematically records the equipment operation history, the frequency of occurrence of anomalies, and the types of detected signs, which can be used as learning data for subsequent analysis and performance improvement of anomaly detection models. For example, identifying anomaly pattern (e.g., periodic overheating) that occurs repeatedly in a specific equipment can be useful for establishing a preemptive maintenance plan for the equipment or suggesting a method for improving equipment performance.

Additionally, the computing device (100) can perform retraining on the anomaly detection model by utilizing the anomaly data stored in the database. In this process, the accuracy and reliability of the model can be improved by combining existing learning data with new anomaly data. For example, by labeling the cause analysis data for the detected anomaly (e.g., a sudden increase in vibration and an increase in energy consumption at a specific time period), the model is trained to detect the anomaly more quickly and accurately in similar situations. Retraining is performed periodically or when new anomaly data is accumulated, and through this, the system can continuously evolve by adapting to the changing facility environment and conditions.

In an additional embodiment, the computing device (100) can apply a facility status prediction and optimization algorithm for preventive measures against abnormal signs. Through this, the possibility of occurrence of abnormal signs can be predicted in advance, and the operation of air conditioning equipment and process equipment can be adjusted in advance to minimize or prevent occurrence of abnormal signs.

Specifically, the computing device (100) predicts the future status of the facility based on the facility status data collected in real time. To this end, a time series prediction model is utilized to analyze changes in the main parameters (e.g., temperature, pressure, vibration, etc.) of the facility, and the possibility of exceeding the threshold is evaluated based on this. For example, if the pressure of a specific facility is currently gradually increasing from 350 kPa and is predicted to exceed the threshold of 400 kPa within 2 hours, the computing device (100) can determine this as a possibility of occurrence of an abnormality sign.

In addition, the computing device (100) analyzes the interaction between the process equipment and the air conditioning equipment to evaluate the impact that a change in the status of a specific equipment will have on other equipment. For example, if a temperature increase in the process equipment may lead to an increase in the load of the cooling system, the computing device (100) can adjust the operating status of the cooling system in advance to distribute the load.

The computing device (100) can determine preventive measures based on such equipment condition prediction data and generate commands to adjust the operating conditions of process equipment and air conditioning equipment. For example, when the vibration of a specific equipment approaches a threshold, the computing device (100) can execute a command to temporarily lower the operating speed of the equipment or distribute the load to adjacent equipment. In addition, the operating history and prediction data of the equipment can be analyzed to suggest replacement timing for specific parts or provide notifications to plan maintenance schedules in advance.

In addition, the computing device (100) can provide the user with visualized facility status prediction results and preventive measures on an integrated digital twin model. For example, the location of occurrence of expected abnormal signs of a specific facility can be highlighted on a 3D model, and preventive measures for the location (e.g., cooling reinforcement, component replacement) can be described in text or graphics. In addition, the expected load change simulation results can be visually displayed, or the time course of facility status changes can be provided in a chart form to support the user to intuitively understand the need for preventive measures.

This embodiment is not limited to the post-detection and response to abnormal signs, but also contributes to improving the stability and efficiency of process equipment and air conditioning equipment through equipment condition prediction and preventive measures. This can provide the effect of reducing equipment maintenance costs and increasing process stability.

In summary, the present invention provides a method for monitoring and controlling air conditioning equipment, which monitors the status of air conditioning equipment and process equipment in real time, detects abnormal signs, and enables rapid and appropriate responses. A computing device (100) collects environmental data and equipment status data through a plurality of sensors, and analyzes the equipment status using an artificial intelligence-based abnormal sign detection model, thereby detecting the location, type, cause, and influence of abnormal signs. The detected abnormal signs are reflected in real time in an integrated digital twin model, and are visually provided through a user interface to intuitively convey the equipment status to the user.

In addition, the present invention analyzes the severity of abnormal signs and the interaction between facilities to set priorities, and executes predefined response protocols to adjust facility conditions or optimize environmental conditions. In this process, the computing device (100) generates individual control commands for each of the process facilities and air conditioning facilities, and adjusts the operating conditions to maintain the efficiency and stability of the facilities.

Furthermore, the present invention automatically generates abnormal symptom cause analysis and report based on abnormal symptom occurrence data, stores it in a database, and utilizes it for continuous re-learning of an abnormal symptom detection model, thereby improving the reliability and accuracy of the system. Through this series of processes, the present invention enables efficient operation of equipment, early detection and response to abnormal symptoms, energy saving and equipment life extension, and can contribute to strengthening the stability of process and equipment operation.

FIGS. 20 and 21 are exemplary diagrams showing a user interface provided in an air conditioning facility and process facility monitoring system related to one embodiment of the present invention.

Referring to FIGS. 20 and 21, the user interface provides information on equipment status and abnormal symptoms within the facility space in the form of an integrated digital twin model, and can display power consumption, operating status, and abnormal symptom warning information for each equipment in real time. For example, if an abnormal symptom of a specific equipment is detected, the equipment is visually highlighted (e.g., colored red or highlighted), and an information panel where an AI manager analyzes the abnormal condition and suggests recommended actions can be displayed together.

In addition, the user interface can provide integrated data in various forms, such as hourly power usage graphs, energy efficiency dashboards by facility, and circular charts for areas where abnormal signs occur. This allows managers to intuitively identify the location, frequency, and severity of abnormal signs, and, when necessary, can immediately check key information on current power usage and facility status through AI voice notifications.

In addition, in the embodiment, the user can zoom in on a specific area in the space to check the detailed operating status and related information of each facility, and analyze the cause of the problem and quickly decide on an appropriate response based on the data updated in real time. This user interface can greatly improve the efficiency of facility status monitoring and abnormality management.

The components of the present invention may be implemented as a program (or application) to be executed by combining with a computer as hardware and stored on a medium. The components of the present invention may be executed as software programming or software elements, and similarly, the embodiments may be implemented in a programming or scripting language such as C, C++, Java, assembler, etc., including various algorithms implemented as a combination of data structures, processes, routines, or other programming elements. Functional aspects may be implemented as algorithms that are executed on one or more processors.

Those skilled in the art will appreciate that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, various forms of program or design code (referred to herein for convenience as “software”), or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The various embodiments presented herein can be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term "article of manufacture" includes a computer program, a carrier, or a medium that is accessible from any computer-readable device. For example, computer-readable media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Additionally, the various storage media presented herein include one or more devices and/or other machine-readable media for storing information. The term "machine-readable media" includes, but is not limited to, wireless channels and various other media capable of storing, retaining, and/or transmitting instructions(s) and/or data.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of exemplary approaches. It is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present invention based on design priorities. The appended method claims provide elements of various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the invention. Thus, the invention is not intended to be limited to the disclosed embodiments, but is to be construed in the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

A method performed on one or more processors of a computing device,
A step of creating a facility digital twin model corresponding to the facility space and air conditioning equipment based on the design data of the facility space and the configuration data of the air conditioning equipment;
A step of acquiring environmental data within the facility in real time through multiple sensors installed within the above facility space, and updating the facility digital twin model based on the acquired environmental data;
A step of predicting temperature changes and air flow using a simulation analysis algorithm to produce thermal comfort information within the facility space; and
A step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information; comprising:
The above facility digital twin model includes a building model (BIM, Building Information Model) regarding the physical structure and layout of the facility space and an air conditioning facility digital twin model (HVAC Digital Twin Model) regarding the components and operating characteristics of the air conditioning facility.
The above multiple sensors are,
An environmental sensor module provided in each of a plurality of sections within the above facility space to obtain sensing data including information on temperature, humidity and air flow; and
Includes a facility status sensor module that monitors facility data including whether the above air conditioning facility is in operation, the direction of operation, and the output level;
The step of acquiring environmental data within the facility in real time through multiple sensors installed within the above facility space and updating the facility digital twin model based on the acquired environmental data is as follows.
A step of updating the facility digital twin model in real time by reflecting changes in temperature, humidity, and air flow within the air conditioning equipment and facility space based on real-time environmental data acquired from the plurality of sensors;
A step of analyzing the above environmental data and facility data to simulate the operating status and environmental changes of the air conditioning facility, and identifying meaningful events from the simulation results to add them to learning data;
A step of comparing and analyzing the updated environmental data with existing accumulated data to update the operation pattern of the air conditioning equipment and the prediction results for environmental changes; and
A step of determining to visually reflect the operating status and environmental changes of the air conditioning equipment in the facility digital twin model based on the updated learning data and displaying them through a user interface; including;
Method for monitoring and controlling air conditioning equipment.
In the first paragraph,
The step of acquiring environmental data within the facility in real time through multiple sensors installed within the above facility space and updating the facility digital twin model based on the acquired environmental data is as follows.
A step of defining the physical characteristics of the facility space based on the design data of the facility space and the air conditioning equipment configuration data;
A step of generating learning data for simulation by modeling the components and operating characteristics of the above air conditioning equipment; and
A step of generating a facility digital twin model including the building model and the air conditioning equipment digital twin model by utilizing the generated learning data;
Including,
Method for monitoring and controlling air conditioning equipment.
delete delete A method performed on one or more processors of a computing device,
A step of creating a facility digital twin model corresponding to the facility space and air conditioning equipment based on the design data of the facility space and the configuration data of the air conditioning equipment;
A step of acquiring environmental data within the facility in real time through multiple sensors installed within the above facility space, and updating the facility digital twin model based on the acquired environmental data;
A step of predicting temperature changes and air flow using a simulation analysis algorithm to produce thermal comfort information within the facility space; and
A step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information; comprising:
The above facility digital twin model includes a building model regarding the physical structure and layout of the facility space and an air conditioning facility digital twin model regarding the components and operating characteristics of the air conditioning facility.
The step of predicting temperature changes and airflow using a simulation analysis algorithm to produce thermal comfort information within the facility space is as follows.
A step of setting initial conditions for performing air flow and heat transfer simulation based on the physical characteristics of the above facility space and the above air conditioning equipment;
A step of calculating the speed, pressure, and density of air flow by applying the Bernoulli equation and air resistance model based on the above initial conditions;
A step of analyzing the calculated air flow and heat transfer data to derive temperature distribution and air flow characteristics by section; and
A step of calculating thermal comfort information within the facility space based on the derived temperature distribution and air flow characteristics;
Including,
Method for monitoring and controlling air conditioning equipment.
A method performed on one or more processors of a computing device,
A step of creating a facility digital twin model corresponding to the facility space and air conditioning equipment based on the design data of the facility space and the configuration data of the air conditioning equipment;
A step of acquiring environmental data within the facility in real time through multiple sensors installed within the above facility space, and updating the facility digital twin model based on the acquired environmental data;
A step of predicting temperature changes and air flow using a simulation analysis algorithm to produce thermal comfort information within the facility space; and
A step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information; comprising:
The above facility digital twin model includes a building model regarding the physical structure and layout of the facility space and an air conditioning facility digital twin model regarding the components and operating characteristics of the air conditioning facility.
The step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information comprises:
A step of determining whether thermal comfort information corresponding to each of a plurality of sections exists within a predefined reference range;
A step of individually generating a control signal for a section that falls outside the above-mentioned reference range as a result of the judgment; and
A step of transmitting the generated control signal to a corresponding air conditioning facility to adjust the temperature of the section or control the air flow;
Including,
Method for monitoring and controlling air conditioning equipment.
A method performed on one or more processors of a computing device,
A step of creating a facility digital twin model corresponding to the facility space and air conditioning equipment based on the design data of the facility space and the configuration data of the air conditioning equipment;
A step of acquiring environmental data within the facility in real time through multiple sensors installed within the above facility space, and updating the facility digital twin model based on the acquired environmental data;
A step of predicting temperature changes and air flow using a simulation analysis algorithm to produce thermal comfort information within the facility space; and
A step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information; comprising:
The above facility digital twin model includes a building model regarding the physical structure and layout of the facility space and an air conditioning facility digital twin model regarding the components and operating characteristics of the air conditioning facility.
The step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information comprises:
A step of comparing thermal comfort information between multiple sections to derive a deviation of the thermal comfort information, and identifying a section requiring additional control if the deviation exceeds a predefined reference value;
A step of generating a control signal for equalizing thermal comfort between sections based on thermal comfort information of the identified section and sections adjacent to the identified section; and
A step of transmitting the generated control signal to the corresponding air conditioning equipment to adjust the temperature difference between sections within a preset allowable range or to adjust the air flow direction and speed;
Including,
Method for monitoring and controlling air conditioning equipment.
A method performed on one or more processors of a computing device,
A step of creating a facility digital twin model corresponding to the facility space and air conditioning equipment based on the design data of the facility space and the configuration data of the air conditioning equipment;
A step of acquiring environmental data within the facility in real time through multiple sensors installed within the above facility space, and updating the facility digital twin model based on the acquired environmental data;
A step of predicting temperature changes and air flow using a simulation analysis algorithm to produce thermal comfort information within the facility space; and
A step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information; comprising:
The above facility digital twin model includes a building model regarding the physical structure and layout of the facility space and an air conditioning facility digital twin model regarding the components and operating characteristics of the air conditioning facility.
The step of generating a control signal for controlling the air conditioning equipment based on the thermal comfort information comprises:
A step of analyzing the current operating status of air conditioning equipment and thermal comfort information generated in real time;
A step of calculating predicted thermal comfort information based on the above analyzed information when the air conditioning equipment is continuously operated for a specific period of time;
A step of generating a control signal for correcting the operating state of the air conditioning equipment when the predicted thermal comfort information is out of a predefined target range; and
A step of transmitting the generated control signal to a corresponding air conditioning facility to adjust the output level, operating time, or air flow direction of the air conditioning facility;
Including,
Method for monitoring and controlling air conditioning equipment.
Memory that stores one or more instructions; and
A processor comprising: a processor for executing one or more instructions stored in said memory;
A device wherein the processor performs the method of claim 1, claim 5, claim 6, claim 7 or claim 8 by executing one or more of the instructions.
A computer program stored on a computer-readable recording medium, which is combined with a computer as hardware and enables the method of claim 1, claim 5, claim 6, claim 7 or claim 8 to be performed.