KR20250083044A - Real object data diagnosing apparatus and method according to simulation object configuration - Google Patents

Abstract

The present invention relates to a real object data diagnosis device according to a simulation object configuration, comprising: a processor; and a memory storing a command executed by the processor, wherein the processor extracts a real object mapped to a virtual object when executing a simulation, and compares a predicted value of a prediction model previously generated for the real object with a measured value of the real object input in a real environment to diagnose data of the real object.

Description

{Real object data diagnosing apparatus and method according to simulation object configuration}

The present invention relates to a device and method for diagnosing real object data according to a configuration of a simulation object.

A digital twin creates a twin of a real-world object on a computer, and simulates situations that may occur in the real world on a computer to obtain accurate information about the characteristics of the real-world asset.

Digital twins are gaining attention because they can improve efficiency across a wide range of industries, including production and services, by providing information on the various statuses, productivity, and operating scenarios of real assets.

Digital twins can perform simulations using real objects that are the subject of simulation among real objects in the real environment, and apply the simulation results to the field. Digital twins repeat the above process to minimize errors between the field and simulation.

In this case, in a simulation environment, virtual objects perform simulations using data mapped from real objects.

The virtual objects used in the simulation assume that the real objects mapped to them will operate normally. However, the equipment of the real objects may malfunction. Even if the equipment of the real objects malfunctions, the data of the real objects are transferred to the virtual objects as is, which makes it difficult for simulations using virtual objects to produce the intended results.

The background technology of the present invention is disclosed in Korean Patent Publication No. 10-2023-0090859 (June 22, 2023).

The purpose of the present invention is to provide a device and method for diagnosing real object data according to a simulation object configuration, which diagnoses data of a real object to be mapped and provides it to a simulation, thereby enabling an accurate simulation to be executed.

According to some embodiments of the present invention, a real object data diagnosis device according to a configuration of a simulation object comprises: a processor; and a memory storing a command executed by the processor, wherein the processor extracts a real object mapped to a virtual object when a simulation is executed, and compares a predicted value of a prediction model previously generated for the real object with a measured value of the real object input in a real environment to diagnose data of the real object.

A device and method for diagnosing real object data according to a simulation object configuration according to one aspect of the present invention diagnoses data of a real object to be mapped and provides it to a simulation, thereby enabling an accurate simulation to be performed.

According to another aspect of the present invention, a real object data diagnosis device and method according to a simulation object configuration can achieve optimization of simulation application between a real environment and a virtual environment in a short period of time, so that temporal and economical effects can be obtained in applications using this as a domain.

FIG. 1 is a conceptual diagram of the operation of a real object data diagnosis device according to a simulation object configuration according to an embodiment of the present invention.
FIG. 2 is a block diagram of a real object data diagnosis device according to a simulation object configuration according to an embodiment of the present invention.
Figure 3 is a conceptual diagram of a prediction model according to one embodiment of the present invention.
FIG. 4 is a flowchart of a method for diagnosing real object data according to a simulation object configuration according to an embodiment of the present invention.
FIG. 5 is a flowchart illustrating a process for constructing a prediction model according to an embodiment of the present invention.
FIG. 6 is a flowchart illustrating a process for correcting data errors according to one embodiment of the present invention.

Hereinafter, an embodiment of a real object data diagnosis device and method according to a configuration of a simulation object according to an embodiment of the present invention will be described. In this process, the thickness of lines and the size of components illustrated in the drawings may be exaggerated for clarity and convenience of explanation. In addition, the terms described below are terms defined in consideration of functions in the present invention, and these may vary depending on the intention or custom of the user or operator. Therefore, the definitions of these terms should be made based on the contents throughout this specification.

The present invention can be implemented in various different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, whenever a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise stated.

The implementations described herein may be implemented, for example, as a method or process, an apparatus, a software program, a data stream or a signal. Even if discussed only in the context of a single form of implementation (e.g., discussed only as a method), the implementation of the features discussed may also be implemented in other forms (e.g., as an apparatus or a program). The apparatus may be implemented as suitable hardware, software, firmware, and the like. The method may be implemented in a device such as a processor, which generally refers to a processing device including, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device.

FIG. 1 is a conceptual diagram of the operation of a real object data diagnosis device according to a configuration of a simulation object according to an embodiment of the present invention, FIG. 2 is a block diagram of a real object data diagnosis device according to a configuration of a simulation object according to an embodiment of the present invention, and FIG. 3 is a conceptual diagram of a prediction model according to an embodiment of the present invention.

Referring to FIGS. 1 to 3, a real object data diagnosis device according to a simulation object configuration according to an embodiment of the present invention can diagnose data of a real object (30), for example, a measured value, when mapping a real object (30) of a real environment (10) and a virtual object (40) that is an information provider of a simulation in a digital twin environment.

A virtual object (40) can be mapped to a real object (30) in a real environment (10) to collect data from a real site.

That is, the real object data diagnosis device according to the simulation object configuration extracts a virtual object (40), generates a prediction model for each real object (30) mapped to the virtual object (40), and compares the predicted value obtained by executing the prediction model with the actual measured value obtained for the real object (30) to determine a data error of the real object (30), for example, an error in the actual measured value. The data of the real object (30) is not limited to the predicted value described above.

The prediction model is described later.

In this case, the prediction model can be created through relationship analysis between the real object (30) and other equipment (140). Other equipment (140) will be described later.

Referring to FIG. 2, a real object data diagnosis device according to a simulation object configuration according to an embodiment of the present invention may include a memory (110), a data storage (120), and a processor (130).

The memory (110) can store various data used by the processor (130). The data can store commands for performing operations or steps according to an embodiment of the present invention. That is, the memory (110) can store commands for detecting abnormal situations of real objects (30) that are targets when real objects (30) of a real environment (10) are mapped to virtual objects (40) of a simulation and providing them to the simulation.

The memory (110) may include at least one storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory, a RAM (Random Access Memory), a SRAM (Static Random Access Memory), a ROM (Read-Only Memory), a PROM (Programmable Read-Only Memory), an EPROM (Erasable Programmable Read-Only Memory), and an EEPROM (Electrically Erasable Programmable Read-Only Memory).

The data storage (120) can store data or prediction models required for the processor (130) to detect anomalies in data of a real object (30), i.e., actual measured values, and provide them to the simulation.

The data storage (120) can store mapping information between a virtual object (40) and a real object (30).

In a simulation environment, a virtual object (40) can be mapped to a real object (30).

Mapping information may be information defining a mapping relationship between a mapped virtual object (40) and a real object (30).

Mapping information can be used to extract real objects (30) mapped to virtual objects (40) when running a simulation in a virtual environment (20).

For example, if a digital twin is applied to a livestock farm, the mapping information may include livestock farm information, livestock shed information, pigsty information, latitude, longitude, sensor type, and sensor ID.

The data storage (120) can store a prediction model. In this case, the data storage (120) can be a prediction model pool for storing the prediction model.

A prediction model can be created for each real object (30) and a prediction value can be extracted.

A prediction model can be created based on the relationship between a real object (30) and other equipment (140).

Other equipment (140) may be another real object (30) that has a relationship with the real object (30) that is the target of prediction model creation, for example, transmits and receives information or links with the real object (30) that is the target of prediction model creation, among the remaining real objects (30).

The predictive model can be updated as needed, and the data store (120) can continuously store the updated predictive model.

The data storage (120) may store data collected in a real environment (10) to create a prediction model and data obtained by preprocessing the data.

The data storage (120) can store measured values and predicted values.

The actual value may be a value obtained from a real object (30) based on the operation of the real object (30).

The actual value can be a result value that represents a measurement value or an operation result, and the type of the actual value is not particularly limited.

The actual value can be obtained in various ways depending on the type or operation characteristics of the actual object (30). For example, the actual value can be obtained from the actual object (30) that performed the corresponding operation, but can also be obtained from another actual object (30) other than the actual object (30) that performed the corresponding operation.

The predicted value can be a value obtained from a prediction model based on the execution of the prediction model.

A predicted value can be a measured value or an outcome value that represents a predicted result, and the type of the predicted value is not particularly limited.

The predicted value can be obtained in various ways depending on the type of prediction model, operation characteristics, etc. For example, the predicted value can be obtained from the prediction model that performed the corresponding operation, but it can also be obtained from a prediction model other than the prediction model that performed the corresponding operation.

The data storage (120) can store diagnostic result information.

The diagnosis result information may be information on the result of the processor (130) diagnosing the actual measured value of the real object (30).

The diagnosis result information may include information about the real object (30), information about the prediction model, information indicating whether the real object (30) is abnormal, and information about the error between the actual value and the predicted value. The diagnosis result information is not particularly limited.

Diagnostic result information can be generated for each real object (30) to be diagnosed.

The processor (130) may be connected to the memory (110) and may execute instructions stored in the memory (110). The processor (130) may execute instructions stored in the memory (110) to control at least one other component (e.g., hardware or software component) connected to the processor (130) and perform various data processing or operations.

In addition, the processor (130) may be configured to perform each function separately at the hardware, software, or logic level. In this case, dedicated hardware may be used to perform each function. To this end, the processor (130) may be implemented as at least one of an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), a PLD (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), a CPU (Central Processing Unit), a microcontroller, and/or a microprocessor, or may include at least one of these.

The processor (130) may be implemented as a central processing unit (CPU) or a system on chip (SoC), and may control a plurality of hardware or software components connected to the processor (130) by driving an operating system or application, and may perform various data processing and operations. The processor (130) may be configured to execute at least one command stored in the memory (110) and store the execution result data in the memory (110).

The processor (130) can collect data from real objects (30) in a real environment (10) and preprocess the collected data to create a prediction model for each real object (30).

The processor (130) can extract a real object (30) mapped to a virtual object (40) when executing a simulation. At this time, the processor (130) can obtain a measured value of the extracted real object (30) and execute a prediction model of the corresponding real object (30) to obtain a predicted value.

The processor (130) can diagnose the data of the real object (30) based on the similarity by comparing the actual measured value of the real object (30) with the predicted value of the prediction model.

If it is determined that an error has occurred in the data of the real object (30) as a result of the diagnosis, the processor (130) can correct the actual value of the real object (30) and replace the actual value with a predicted value. In this way, the processor (130) can improve the accuracy of the simulation by inputting the predicted value that replaces the actual value into the simulation.

To explain more specifically, a digital twin can perform a simulation using virtual objects (40) that are simulation targets in a virtual environment (20) among real objects (30) in a real environment (10) and apply the simulation results to the field.

When a real object (30) constituting a real environment (10) is simulated in a virtual environment (20), the real object (30) can be mapped to a virtual object (40) that becomes an information provider of the simulation.

Accordingly, the processor (130) can map a real object (30) and a virtual object (40).

The processor (130) can generate a prediction model for each real object (30) to diagnose data of the real object (30).

First, the processor (130) can collect data of real objects (30) in a real environment (10).

The processor (130) can preprocess data collected in a real environment (10) to be suitable for generating a prediction model and accumulate the preprocessed data in a data storage (120).

The processor (130) can analyze the relationship between a real object (30) for which a prediction model is to be created using accumulated data and other real objects (30) related to the real object (30).

A prediction model can be created based on the relationship between a real object (30) and other equipment (140).

Other equipment (140) may be another real object (30) that transmits and receives information or is linked with the real object (30) that is the target of prediction model creation, among the remaining real objects (30) excluding the real object (30) that is the target of prediction model creation.

The relationship between the real object (30) that is the target of prediction model creation and other equipment (140) can be understood as the real object (30) that is the target of prediction model creation and other equipment (140) being electrically or mechanically connected to transmit and receive data or link with each other.

The processor (130) can analyze the relationships between other real objects (30) related to the real object (30) and learn based on the relationship analysis to create a prediction model. The processor (130) can store the created prediction model in a prediction model pool.

Referring to FIG. 3, a real object A can have a relationship with other equipment B, C, a real object B can have a relationship with other equipment A, D, a real object C can have a relationship with other equipment A, B, D, E, a real object D can have a relationship with other equipment B, C, and a real object E can have a relationship with other equipment A, B, C, D.

The processor (130) can update the prediction model as needed and store the updated prediction model in the data storage (120).

The predictive model can provide information for a virtual object (40) when running a simulation, or generate a predictive value to diagnose data of a real object (30).

The processor (130) can obtain the actual measured value of the real object (30) when executing a simulation and obtain a predicted value from the predicted model by executing the predicted model.

The processor (130) can diagnose data of a real object (30) by comparing predicted values with measured values. The processor (130) can extract the similarity between the predicted values and measured values.

The processor (130) can determine that an error has occurred in the actual value of the real object (30) based on whether the similarity between the predicted value and the actual value is greater than or equal to a preset value. If the similarity between the predicted value and the actual value is greater than or equal to the preset value, the processor (130) can determine that the actual object (30) is normal. If the similarity between the predicted value and the actual value is less than the preset value, the processor (130) can determine that an abnormality has occurred in the actual object (30).

The setting value may be a value that serves as a criterion for determining whether an error has occurred in the data of a real object (30). The setting value may be set for each real object (30).

The processor (130) can generate diagnostic result information based on the above diagnostic result and store it in the data storage (120).

If the processor (130) determines that an error has occurred in the data of the real object (30) as a result of diagnosing the data of the real object (30), the processor (130) can correct the actual value. In this case, the processor (130) replaces the actual value with a predicted value and inputs the predicted value into the simulation instead of the actual value, thereby allowing the simulation to be performed normally.

In this embodiment, a real object data diagnosis device according to a simulation object configuration may be provided separately from the simulation system in a digital twin environment and connected via a communication network, but may also be installed within the simulation system.

Hereinafter, a method for diagnosing real object data according to a simulation object configuration according to an embodiment of the present invention will be described with reference to FIGS. 4 to 6.

FIG. 4 is a flowchart of a method for diagnosing real object data according to a simulation object configuration according to an embodiment of the present invention.

Referring to FIG. 4, the processor (130) can collect data of real objects (30) in a real environment (10) and create a prediction model using the collected data (S100).

FIG. 5 is a flowchart illustrating a process for constructing a prediction model according to an embodiment of the present invention.

Referring to FIG. 5, the processor (130) can collect data of real objects (30) in a real environment (10) (S110).

The processor (130) can preprocess data collected in a real environment (10) to be suitable for generating a prediction model (S120).

The processor (130) can accumulate data collected and preprocessed data in a real environment (10) in a data storage (120) (S130).

The processor (130) can analyze the relationship between the real object (30) for which a prediction model is to be created using accumulated data and other real objects (30) related to the real object (30) (S140). The processor (130) can learn based on this relationship analysis (S150) to create a prediction model for each real object (30) and store the created prediction model in the prediction model pool (S160).

With the prediction model stored, the processor (130) can execute a simulation (S200).

The processor (130) can extract a real object (30) mapped to a virtual object (40) when running a simulation.

The processor (130) can obtain a measured value of an extracted real object (30) and execute a prediction model of the real object (30) to obtain a predicted value.

The processor (130) can diagnose data of a real object (30) using the measured value and the predicted value. That is, the processor (130) can diagnose whether an error has occurred in the data of a real object (30) by comparing the measured value and the predicted value (S300).

FIG. 6 is a flowchart illustrating a process for correcting data errors according to one embodiment of the present invention.

Referring to FIG. 6, the processor (130) can obtain a virtual object (40) (S320) while executing an instance of a prediction model (S310).

The processor (130) can extract a real object (30) mapped to an acquired virtual object (40) (S330) and obtain a prediction model of the extracted real object (30) (S340).

In this case, the processor (130) can monitor an instance of the prediction model (S350) and execute the prediction model (S360).

The processor (130) can obtain a measured value from the corresponding real object (30) and obtain a predicted value of the prediction model (S370).

The processor (130) can diagnose data of an actual object (30) by comparing predicted values and measured values (S380).

That is, the processor (130) can extract the similarity between the predicted value and the actual value. The processor (130) can determine whether the similarity between the predicted value and the actual value is greater than a set value.

If the similarity between the predicted value and the actual value is greater than or equal to the set value as a result of the judgment, the processor (130) can determine that the data of the real object (30) is normal. On the other hand, if the similarity between the predicted value and the actual value is less than the set value, the processor (130) can determine that an error has occurred in the data of the real object (30).

If it is determined that an error has occurred in the data of the real object (30) as a result of diagnosing the data of the real object (30), the processor (130) can correct the actual value. For example, the processor (130) replaces the actual value with a predicted value and inputs the predicted value into the simulation, thereby enabling the simulation to be executed with the predicted value (S400). Accordingly, the simulation can be performed normally.

Next, the processor (130) can generate diagnostic result information based on the above diagnostic result and store it in the data storage (120).

According to an embodiment of the present invention, data of a real object that is a mapping target is diagnosed and provided to the simulation according to a simulation object configuration, thereby enabling an accurate simulation to be performed.

In addition, the device and method for diagnosing real object data according to the configuration of a simulation object according to an embodiment of the present invention can achieve optimization of simulation application between a real environment and a virtual environment in a short period of time, so that temporal and economical effects can be obtained in applications using this as a domain.

Although the present invention has been described with reference to the embodiments illustrated in the drawings, these are merely exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible from this. Accordingly, the technical protection scope of the present invention should be defined by the following patent claims.

10: Real environment
20: Virtual Environment
30: Real Object
40: Virtual Object
110: Memory
120: Data storage
130: Processor

Claims (1)

processor; and
A memory for storing instructions executed by the processor,
The above processor is a real object data diagnosis device according to a simulation object configuration, which extracts a real object mapped to a virtual object when a simulation is executed, and diagnoses data of the real object by comparing the predicted value of a prediction model previously generated for the real object with the actual measured value of the real object input in a real environment.

Images