NO20180628A1 - Digital twin and decision support for low or unmanned facilities - Google Patents
Digital twin and decision support for low or unmanned facilitiesInfo
- Publication number
- NO20180628A1 NO20180628A1 NO20180628A NO20180628A NO20180628A1 NO 20180628 A1 NO20180628 A1 NO 20180628A1 NO 20180628 A NO20180628 A NO 20180628A NO 20180628 A NO20180628 A NO 20180628A NO 20180628 A1 NO20180628 A1 NO 20180628A1
- Authority
- NO
- Norway
- Prior art keywords
- data
- installation
- systems
- equipment
- physical
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Automation & Control Theory (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Coin-Freed Apparatuses For Hiring Articles (AREA)
- Preparation Of Compounds By Using Micro-Organisms (AREA)
Description
Digital twin and decision support for low or unmanned facilities
Introduction
The present invention concerns data processing systems, and more specifically a method and system for monitoring and optimizing the design and operations of physical systems by representing the systems by digital twins producing continuously updated actual and modelled data about the operational behaviour of the physical systems.
Background and prior art
The occurrence of failures in different types of components, equipment and systems comprised in an installation can be costly and even catastrophic. Early detection and elimination of potential operational problems during the design phase as well as continues surveillance and regular maintenance during the operational phase are therefore vital for running installations and systems without facing problems.
One way of foreseeing or predicting a problem or a need for maintenance is to simulate the behaviour of the physical system using a digital twin.
A digital twin is a digital duplicate of a real physical system, facility or equipment. When running on a computer it will behave like the physical system it is duplicating. In this way, the digital representation of a physical system can be used for various purposes, such as for instance early simulation of the system’s operational behaviour or maintenance friendliness or real-time surveillance.
By combining digital twins with expected performance data and real-time data collected from the equipment and systems that are simulated, potential failures can be predicted and prevented.
In a design phase, potential failures may be detected by comparing expected performance data with simulated and historical data.
In an operational phase, analysing the behaviour of equipment and systems i s possible by means of advanced sensors, data collection systems, data storage/transfer capabilities and data analytic tools developed for such purpose.
US 2016/0247129 A1 describes digital twins for energy efficient asset maintenance. It is described that a digital twin can form the basis for simulations which help develop predictive maintenance procedures based on how individual machines operate under real-world conditions.
US 20170091791 A1 describes a digital power plant and a digital twin model of th is comprising visualization a software tool where critical events are visualized for an operator.
Even though prior art systems comprise tools for predicting and visualizing critical events or equipment for an operator, designers or operators will not be able to fix a problem if a possible solution is not known.
There is a need for a method and system visualizing and suggesting how a detected problem should be solved.
The present invention comprises a method and system for visualizing potential performance problems, critical events, equipment and suggestion of solutions to avoid and fix problems.
Kongsberg Digital has developed a digital platform named kognifai<TM>. It is a complex ecosystem interconnecting networks of organizations, applications, and assets. It supports collaboration and knowledge-sharing between all organizations that are part of it, enabling them to interact at a new level to provide new reach and business value. The digital platform acts as a single digital platform for all data produced by different physical systems across the technology spectrum.
This digital ecosystem is as a key player in the present invention for retrieving and processing data from different installations. Digital twins of different installations are connected to this ecosystem as well as user interfaces for presenting updated information for an operator. In this way a few designers can simulate and optimize the behaviour of an entire system and one or a few operators can monitor and control operations of different types at installations located at remote sites. The number of designers and operators needed can thus be reduced or eliminated. The solution is well suited for both optimizing design and operating low- and unmanned installations.
According to the invention, a designer or operator is presented with a visualization of a possible problem at an installation, as well as suitable tools for investigating the specific problem for finding a solution. This is a guided investigation and one is given access to information and tools required to analyse events and fixing possible problems needing maintenance, such as for instance faulty component, equipment, leakage or offset due to wear and tear, etc.
A problem may for instance be stuck or offset equipment operation in a processing plant. In a design phase, a designer or operator will then get access to a software tool (App) that will guide him to set the correct diagnostic for fixing the problem. Type of App enabled will depend on type of problem. In the case of bottlenecks in the process, the designer will get access to software tools related to this for investigating the problem and improving the design of the plant. Bottlenecks are factors contributing to a suboptimal operation, e.g. not optimal design, unfit pipe dimensions and/or valve type etc. It may also be that a better set point should be set for a controller.
An operator monitoring a system in an operational phase will get access to software tools (Apps) for identifying the root cause of the problem and for eliminating it by for instance controlling valves at a processing plant at a remote site.
The present invention enables visualization of different types of installations with different levels of detail. Several remote located installations can be monitored and controlled from one location. An operator will be presented with a visual overview of the different installations, and if there is a problem with one or more of the installations they will be indicated and visualised in the overview showing the installations. The operator can then zoom in on an indicated installation for viewing more details of systems, sub-systems and components comprised in an installation where a problem is detected. If several problems are detected, they will be ranked. Minor problems can then be corrected by the system, either manually or automatically, and only problems requiring follow-up from an operator will be flagged/indicated.
Short description of the invention
The present invention comprises a method for discovering and visualizing potential operational problems of processes running in physical equipment and systems comprised in at least one installation. The method comprises the steps of:
- simulating the physical equipment, systems and processes in a physical model established from installation design basis and data characterizing the physical equipment, systems and processes comprised in the at least one installation;
- establishing a first set of data characterizing the processes running in the physical equipment and systems comprised in the at least one installation, and generating a second set of data from the physical model characterizing the processes running in physical equipment and systems comprised in the at least one installation;
- inputting the first and second set of data to a machine learning model for training the model in operational behaviours and dependencies;
- generating a third set of data in the machine learning model, where the third set of data comprises proposed improvements and optimized solutions derived from the first and second set of data;
- outputting the third set of data to a validation module, and validating and testing the third set of data in the validation module to determine if the proposed improvements and optimized solutions are feasible, and
- visualizing possible problems in equipment and systems of the at least one installation, based on results from the validation module thereby indicating which equipment or systems should be further investigated for optimization and correction purposes.
Further features of the method are defined in the claims.
The invention is also defined by a device with means for performing the method defined in the claims, as well as a computer program product for performing the method when executed on a computer.
Detailed description of the invention
A purpose of the present invention is to enable optimization during a design phase of an installation. Early detection and elimination of potential operational problems during the design phase is vital for running installations and systems without facing problems. Potential failures are detected and visualized by comparing expected performance data with simulated and historical data.
Another purpose is to enable remote monitoring and controlling of installations in an operational phase, without having to use personnel with detailed knowledge of the installations. This is enabled by visualizing possible problems for an operator. The operator can then investigate further by zooming in on indicated problems in a visualization of the installations. The operator may further be given access to suggested software tools for adjusting and optimizing parameters of components and systems, or fixing indicated problems.
The invention will now be described in detail with reference to the figures where:
Fig. 1.1 shows a flowchart of a decision support model according to the invention;
Fig. 1.2 shows a flowchart of a use case example;
Fig. 2 shows an overview of the dataflow to and from physical systems and databases providing different types of data about equipment, systems and processes of at least one installation;
Fig. 3 shows an example of screen dump from the user interface at an operator station visualizing details of a production well;
Fig. 4 show an example of a visualization of a warning of suspect Production Riser;
Fig. 5 shows the state of a gas lift control valve;
Fig. 6 shows an example of automatic browsing and display of faulty equipment;
Fig. 7.1 shows one example of Equipment localization in 3D model and CCTV – automatic position correlation;
Fig. 7.2 shows another example of Equipment localization in 3D model and CCTV– automatic position correlation;
Fig. 8.1 shows an example of visualization of walk to work inspector, and
Fig. 8.2 shows an example of a screen dump walk to work inspector.
The Digital Twin according to the present invention is utilizing a hybrid modelling approach by combining estimated data from a physical model, machine learning model and measured field data.
The physical model is a high fidelity dynamic model produced with sound basis in first principles physics, chemistry and engineering, which is used together with a Machine Learning Model using neural networks, regression methods and statistics.
The Digital twin implemented by the hybrid modelling approach enables equipment and process performance monitoring in real-time by constantly measuring data from a field and constantly comparing and monitoring the data with data from the hybrid model.
The Machine Learning Model is using these data to build knowledge of process behaviour and dependencies, i.e. how different equipment and processes are related to each other. The hybrid modelling approach will not only be based on historical conditions but also enables to predict future states of equipment as well as detecting equipment degradation and suggesting production optimization.
The Digital Twin also integrates information and status from a maintenance planning system.
Figure 1.1 shows a flowchart of a decision support model according to the invention. The flowchart shows the different data, processes and decisions comprised in the method for discovering and visualizing potential operational problems of processes running in physical equipment and systems comprised in at least one installation.
The first step of the method is simulating the physical equipment, systems and processes in a physical model established from installation design basis and data characterizing the physical equipment, systems and processes comprised in the installation.
A Hybrid Model comprises a mix of several different types of data models. In this case it combines a physical model and a machine learning model and utilizes their strengths in order achieve a robust and fast solution with high accuracy.
A prediction model is yet another instance of the physical model for modelling physical processes where the methodology is based on mathematical models predicting a state or output from a system.
The next step of the method is establishing a first set of data characterizing the processes running in the physical equipment and systems comprised in the at least one installation, and generating a second set of data from the physical model characterizing the processes running in the physical equipment and systems comprised in the at least one installation. Said first set of data can be acquired in different ways.
In one embodiment of the invention, the first set of data is established from equipment data, expected performance data and/or historical data characterizing processes running in equipment and systems comprised in the at least one installation. This method is used for detecting and visualizing potential operational problems during a design phase of the at least one installation. In this way layout and design of an installation can be optimized prior to operating the installation.
In another embodiment, the first set of data is established by measured production data acquired from the physical equipment and systems. These data are used to synchronize the physical model in an online prediction mode. This method is generating the second set of data which is used for detecting and visualizing potential operational problems during an operational phase of the at least one installation.
The next step of the method is inputting the first and second set of data to the Machine Learning Model. These data are both used to train the Machine Learning model in operational behaviors and dependencies, and further to propose optimization settings to improve the production. Both measured data and model prediction data are used together with additional prediction data that is not measured or not possible to measure in the field. Optimization algorithms are using these data to find a more optimized operation. Proposed optimization set tings are sent to the validation module as a third set of data.
The validation module is initialized with the current status from the prediction module. The proposed production optimizations from the Machine Learning Model will be tested and validated to see if the proposed settings are feasible.
The third set of data is then assessed and validated. This is necessary since the Machine Learning Model do not necessarily know the physical limitations or boundary conditions of simulated equipment and processes.
Differences between data acquired from the physical processes and the physical model, i.e. differences between the first and second sets of data, indicate possible problems.
In a design phase of an installation, the optimized data will provide decision basis for optimizing a design.
In the operational phase of an installation, the optimized data will provide decision basis for correcting a possible problem.
The last step of the method is visualizing possible problems in equipment and systems of the at least one installation, based on results from the validation module thereby indicating which equipment or systems should be further investigated for optimization and correction purposes.
The visualization can for instance be presented on an interactive screen operated by a user, e.g. operator or engineer. The visualization may initially show an overview of an installation, and the user can then zoom in on any area of interest until an indicated problem is displayed along with information of the problem. Zooming in on an area of an installation can also be done automatically, showing for instance equipment that is not performing as expected.
By inputting said third set of data, suitable software tools are in one embodiment of the invention provided for adjusting and optimizing parameters of components and systems in a design phase. Likewise, software tools for fixing an indicated problem is provided in an operational phase of an installation.
An operator can in one embodiment select an indicated component or system from the visualization of the screen, and then select a suggested software tool for adjusting or correcting a problem. In a design phase this may be that another type of pump is needed, and in an operational phase this may be that a new set point must be set for a controller.
Based on suggestions from the optimization module, different parameters of an installation can be adjusted and optimized.
When the proposed optimization settings are validated; the user can decide to implement the result back to the field/design.
According to an embodiment of the invention, problems can be defined and sorted according to degree of severity. Less severe problems can be fixed automatically, and more severe problems can be presented in said visualization.
In yet another embodiment, the physical model further comprises a modification module, and a training module.
The modification module is used to secure safe and efficient modifications to the existing design and operations. The starting point for the modification module is a copy of the online prediction model which is further updated with planned modifications. The system will then be ready to test out the new design.
The training module is used to train the operational team and validate the operational procedures. This model instance can be copied from any of the other modules depending on the training requirements. As an example, one can train on current running conditions by using the online prediction module, or copy the status from the modification module to prepare the operators on the future modification on the field.
The invention further comprises a device for discovering and visualizing potential operational problems of processes running in physical equipment and systems comprised in at least one installation.
The device comprises different modules and means enabling the method described above. This includes simulation means for simulating the physical equipment, systems and processes in a physical model established from installation design basis and data characterizing the equipment, systems and processes comprised in the at least one installation.
The device further comprised input means for inputting a first set of data characterizing the processes running in the physical equipment and systems comprised in the at least one installation, and generating means for generating a second set of data from the physical model characterizing the processes running in the physical equipment and systems comprised in the at least one installation.
The device further comprises a machine learning model with input means for receiving the first and second set of data and means for training the model in operational behaviours and dependencies, and generation means for generating and outputting a third set of data comprising proposed improvements and optimized solutions derived from the first and second set of data, and a validation module with validation means for validating and testing the third set of data received from the machine learning model via input means, and means for determining if the proposed improvements and optimized solutions are feasible.
The device further comprises means for generating visualization data of possible problems in equipment and systems of the at least one installation based on result s from the validation module thereby indicating which equipment or systems should be further investigated for optimization and correction purposes.
As understood from the description above, the device may be a computer with input- and output means as well as memory means. The computer further comprises a computer program for performing the method above, and where the program has access to a database with data defining physical equipment and systems comprised in at least one installation.
The invention is also defined by a computer program product that when run on a computer executes the method described above for discovering and visualizing potential operational problems of processes running in physical equipment and systems comprised in at least one installation.
Figure 1.2 shows a flowchart illustrating a use case example where modification and training modes of the physical model are included. When modifying a design basis for an installation, the design changes are tested in a modification mode of the physical simulator. The test results generate a fourth set of data which is tested and either approved or rejected by the designer. If approved, the modification will be implemented in the design basis.
When in training mode, the physical model enables training of personnel operating an installation. Figure 1.2 illustrates how operational teams can use the physical model for training purposes. This is performed in a training mode of the physical model. The operational procedures are validated in this mode where flaws are removed and corrections are fed back to the design basis which implements the new procedures in the Field.
Figure 2 shows an example of the digital twin according to the invention. Different physical systems are connected to the kognifai<TM>platform. The platform acts as a single source for all data produced by different physical systems across the technology spectrum, providing data about equipment, systems and processes to the tools (Apps) operators use to visualize and improve the design basis and detect and solve operational problems, and well as providing access to models and services for rapid development of new tools (Apps) through open APIs.
The invention can visualize both 2D and 3D design data enriched with all sets of data mentioned above for giving the user additional insight knowledge of the status. Multiple instances of the digital twin can be started in parallel, all gathering data from the same data source hosted in the cloud, e.g. kognifai<TM>. This enables multidisciplinary collaboration workflows which again increase the common understanding across disciplines, as exemplified in Figure 2.
In the following, some examples of implementing and using the invention are presented as use cases, with reference to figures 3 to 8, for explaining and illustrating the practical use of the invention, an example based on a failing gas lift control valve will be explained.
Decision support and increasing production
One of the production wells in an installation has been closed for some days due to reduced production capacity at a field centre. The capacity is now back to normal and the well can start producing again.
The control room operator opens the well from the operator station, ref. Figure 3, to initiate the startup and monitor the change in production. The following procedure is performed:
1) Open the Gas Lift Valve.
2) Open the Production Wing Valve and the Production Choke Valve.
3) The well is now opened and the operator will see the flowrate on the multiphase flow computer.
4) The operator will soon see that something is wrong, i.e. the well is open, but no production is measured.
5) This situation needs further investigation, which is challenging due to lack of people in the field. The operator uses the Digital Twin and the method according to the invention as a decision support guidance tool to do the diagnostics.
6) Warnings generated by “Smart Agents” (Performance Monitoring System) in the Digital Twin indicates that the Production Riser and the Gas Lift Valve has an issue, ref. Figure 4.
7) The operator opens an “Inspector” view for the Riser that indicates and visualizes insufficient gas lift flow to lift the liquid column up to the platform.
8) The next step for the operator is to investigate why the gas lift flowrate is that low by following the active warning on the gas lift valve and open the Inspector view, ref. Figure 5. This confirms deviation between operator command (Target = 50%) from the Control System, and the estimated position from the online prediction model (Estimated = 1%)
9) Based on the warnings and previous history for this valve (12 Notifications registered in maintenance system, see top row in the valve inspector), the operational team hand over the case to the maintenance team for further investigation.
10) All relevant data (both measured and estimated data) around the valve can be collected and stored together with the observation and added as a new Notification for documentation of the incident.
Maintenance Operation
1) A maintenance team decides to replace the valve on the next service and uses the Digital Twin to collect all relevant data to plan the replacement. The Digital Twin integrates information from many sources and provides a compiled picture to enhance the situational awareness and ease multidisciplinary collaboration for fault localization, diagnostic and decision making. This includes providing:
• 3D Visualization Portal
• P&ID
• CCTV
• Real-time data
• Historian data
• Condition Monitoring
• Maintenance history
2) Relevant information about the maintenance task is sent to the Maintenance Planning Team who coordinates various tasks on many assets – and with a good overview of logistics and plan for the roving maintenance teams. The Maintenance Planning Team submits the maintenance task to one of the roving teams.
Maritime operations at an installation
3) A roving maintenance team receives the task and all relevant information – they can now investigate the details and get familiar with the asset and maintenance operation, ref. Figure 6, 7.1 and 7.2.
4) When the team arrive at the asset – they are well prepared – and will be assisted by Expert teams onshore as well as by the Digital Twin on a tablet device.
5) The onshore support team can monitor the docking and walk-2-work operation by opening the Inspector view for the supply vessel, Figure 8.1. The walk-2-work inspector includes critical parameters related to marine gangway operations, ref. Figure 8.2, such as:
• Gangway stroke
• Gangway angel
• Gangway status
• Vessel’s position
• Vessel’s heave, roll, pitch and yaw
• Prediction of operating window (Forecast for Stroke)
When the service and replacement is done, the team conclude the operation and submit the maintenance report before exiting the asset.
As understood from the description above, the invention provides a one-stopsolution for both optimizing design when planning and designing an installation, as well as discovering, visualizing and suggesting how a detected problem should be solved in an operational phase of an installation. The solution is well suited for lowand unmanned installations.
Claims (10)
1. A method for discovering and visualizing potential operational problems of processes running in physical equipment and systems comprised in at least one installation, comprising:
- simulating the physical equipment, systems and processes in a physical model established from installation design basis and data characterizing the physical equipment, systems and processes comprised in the at least one installation;
- establishing a first set of data characterizing the processes running in the physical equipment and systems comprised in the at least one installation, and generating a second set of data from the physical model characterizing the processes running in the physical equipment and systems comprised in the at least one installation;
- inputting the first and second set of data to a machine learning model for training the model in operational behaviours and dependencies;
- generating a third set of data in the machine learning model, where the third set of data comprises proposed improvements and optimized solutions derived from the first and second set of data;
- outputting the third set of data to a validation module, and validating and testing the third set of data in the validation module to determine if the proposed improvements and optimized solutions are feasible, and
- visualizing possible problems in the physical equipment and systems of the at least one installation, based on results from the validation module thereby indicating which equipment or systems should be further investigated for optimization and correction purposes.
2. The method according to claim 1, by discovering and visualizing potential operational problems during a design phase of the at least one installation by establishing the first set of data from expected performance data and data characterizing processes running in equipment and systems comprised in the at least one installation.
3. The method according to claim 1, by discovering and visualizing potential operational problems during an operational phase of the at least one installation by establishing the first set of data from measured production data, and running and synchronizing real physical equipment, systems and processes and the corresponding physical model in real-time.
4. The method according to any of the previous claims, by simulating the physical equipment, systems processes in a prediction module comprised in the physical model, and validating said differences in a validation module in the physical model.
5. The method according to any of the previous claims, by inputting said third set of data to an optimization module, and providing software tools for adjusting and optimizing parameters of equipment and systems, or fixing an indicated problem based on suggestions from the optimization module.
6. The method according to claim 5, where access to software tools for adjusting parameters or correcting a problem is activated by selecting indicated equipment or system from the visualization of possible problems in equipment and systems of the at least one installation.
7. The method according to claim 5, by defining and sorting problems according to degree of severity, and fixing problems automatically if possible.
8. The method according to claim 1, where the physical model further comprises a modification module, and a training module.
9. Device for discovering and visualizing potential operational problems of processes running in physical equipment and systems comprised in at least one installation, comprising:
- simulation means for simulating the physical equipment, systems and processes in a physical model established from installation design basis and data characterizing the equipment, systems and processes comprised in the at least one installation;
- input means for inputting a first set of data characterizing the processes running in the physical equipment and systems comprised in the at least one installation, and generating means for generating a second set of data from the physical model characterizing the processes running in the physical equipment and systems comprised in the at least one installation;
- a machine learning model with input means for receiving the first and second set of data and means for training the model in operational behaviours and dependencies, and generation means for generating and outputting a third set of data comprising proposed improvements and optimized solutions derived from the first and second set of data;
- a validation module with validation means for validating and testing the third set of data received from the machine learning model via input means, and means for determining if the proposed improvements and optimized solutions are feasible;
- means for generating visualization data of possible problems in equipment and systems of the at least one installation based on resul ts from the validation module thereby.
10. Computer program product that when run on a computer executes the method according to claims 1 to 8 for discovering and visualizing potential operational problems of processes running in physical equipment and systems comprised in at least one installation.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| NO20180628A NO20180628A1 (en) | 2018-05-02 | 2018-05-02 | Digital twin and decision support for low or unmanned facilities |
| PCT/EP2019/061080 WO2019211288A1 (en) | 2018-05-02 | 2019-04-30 | A method and system for discovering and visualizing potential operational problems of processes running in equipment and systems in an installation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| NO20180628A NO20180628A1 (en) | 2018-05-02 | 2018-05-02 | Digital twin and decision support for low or unmanned facilities |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| NO20180628A1 true NO20180628A1 (en) | 2019-11-04 |
Family
ID=66429354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| NO20180628A NO20180628A1 (en) | 2018-05-02 | 2018-05-02 | Digital twin and decision support for low or unmanned facilities |
Country Status (2)
| Country | Link |
|---|---|
| NO (1) | NO20180628A1 (en) |
| WO (1) | WO2019211288A1 (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3822718A1 (en) * | 2019-11-18 | 2021-05-19 | Siemens Aktiengesellschaft | System device and method of integrated model-based management of industrial assets |
| CN111008502B (en) * | 2019-11-25 | 2021-07-13 | 北京航空航天大学 | A digital twin-driven fault prediction method for complex equipment |
| EP3836051A1 (en) * | 2019-12-13 | 2021-06-16 | Basf Se | Industrial plant optimization |
| CN111208759B (en) * | 2019-12-30 | 2021-02-02 | 中国矿业大学(北京) | Digital twin intelligent monitoring system for unmanned fully mechanized coal mining face of mine |
| US11449028B2 (en) | 2020-09-03 | 2022-09-20 | Rockwell Automation Technologies, Inc. | Industrial automation asset and control project analysis |
| US11561517B2 (en) | 2020-09-09 | 2023-01-24 | Rockwell Automation Technologies, Inc. | Industrial development hub vault and design tools |
| US11294360B2 (en) | 2020-09-09 | 2022-04-05 | Rockwell Automation Technologies, Inc. | Industrial automation project code development guidance and analysis |
| US12327210B2 (en) * | 2020-09-11 | 2025-06-10 | Rockwell Automation Technologies, Inc. | Digital engineering on an industrial development hub |
| US11415969B2 (en) | 2020-09-21 | 2022-08-16 | Rockwell Automation Technologies, Inc. | Connectivity to an industrial information hub |
| US11796983B2 (en) | 2020-09-25 | 2023-10-24 | Rockwell Automation Technologies, Inc. | Data modeling and asset management using an industrial information hub |
| CN114019827A (en) * | 2021-10-19 | 2022-02-08 | 中国舰船研究设计中心 | Unmanned ship virtualization platform based on digital twin |
| US20230297098A1 (en) * | 2022-03-15 | 2023-09-21 | CLARITRICS INC. d.b.a BUDDI AI | Analytical system for surface mount technology (smt) and method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070239373A1 (en) * | 2006-03-10 | 2007-10-11 | Edsa Micro Corporation | Systems and methods for automatic real-time capacity assessment for use in real-time power analytics of an electrical power distribution system |
| US20170286572A1 (en) * | 2016-03-31 | 2017-10-05 | General Electric Company | Digital twin of twinned physical system |
| WO2017192998A1 (en) * | 2016-05-06 | 2017-11-09 | General Electric Company | Controlling aircraft operations and aircraft engine components assignment |
| US20180060759A1 (en) * | 2016-08-31 | 2018-03-01 | Sas Institute Inc. | Automated computer-based model development, deployment, and management |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005054968A1 (en) * | 2003-11-26 | 2005-06-16 | Tokyo Electron Limited | Intelligent system for detection of process status, process fault and preventive maintenance |
| US10762475B2 (en) | 2015-02-25 | 2020-09-01 | Siemens Schweiz Ag | Digital twins for energy efficient asset maintenance |
| US20170091791A1 (en) | 2015-09-25 | 2017-03-30 | General Electric Company | Digital power plant system and method |
| WO2018044507A1 (en) * | 2016-08-29 | 2018-03-08 | Siemens Corporation | Machine learning-aided model-based method for estimating gas turbine component life |
-
2018
- 2018-05-02 NO NO20180628A patent/NO20180628A1/en unknown
-
2019
- 2019-04-30 WO PCT/EP2019/061080 patent/WO2019211288A1/en not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070239373A1 (en) * | 2006-03-10 | 2007-10-11 | Edsa Micro Corporation | Systems and methods for automatic real-time capacity assessment for use in real-time power analytics of an electrical power distribution system |
| US20170286572A1 (en) * | 2016-03-31 | 2017-10-05 | General Electric Company | Digital twin of twinned physical system |
| WO2017192998A1 (en) * | 2016-05-06 | 2017-11-09 | General Electric Company | Controlling aircraft operations and aircraft engine components assignment |
| US20180060759A1 (en) * | 2016-08-31 | 2018-03-01 | Sas Institute Inc. | Automated computer-based model development, deployment, and management |
Non-Patent Citations (1)
| Title |
|---|
| Bura Aman H, Bo Chen, Li YU "Error-Driven Adaptive, Virtual Machine Model-Based Control with High Availability Platform" 11th International Conference on Machine Learning and Applications; 2; 13-17, 2012. IEEE. , Dated: 01.01.0001 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019211288A1 (en) | 2019-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019211288A1 (en) | A method and system for discovering and visualizing potential operational problems of processes running in equipment and systems in an installation | |
| US8688405B2 (en) | Remote monitoring systems and methods | |
| CN107085415B (en) | Rule builder in a process control network | |
| Asadzadeh et al. | An integrated systemic model for optimization of condition-based maintenance with human error | |
| US7062358B2 (en) | System apparatus and method for diagnosing a flow system | |
| RU2557771C1 (en) | Technical control and diagnostics of drone onboard hardware with decision making support and complex of check-and-adjust hardware with intellectual decision making support system to this end | |
| Yang et al. | Online application of a risk management system for risk assessment and monitoring at NPPs | |
| Bartlett et al. | Integrated system fault diagnostics utilising digraph and fault tree-based approaches | |
| WO2019201715A1 (en) | Method for identifying and evaluating common cause failures of system components | |
| CN116910615A (en) | A nuclear power plant fault traceability and auxiliary decision-making system | |
| Ahmed et al. | Improving safety and availability of complex systems using a risk-based failure assessment approach | |
| Rodrigues et al. | Digital twin of subsea assets as a tool for integrity management and risk-based inspection: challenges and perspectives | |
| CN119883892A (en) | Automated test integration system in software development process | |
| Lazarova-Molnar et al. | Reliability modeling and simulation: advancements with data-driven techniques and expert knowledge integration | |
| WO2024226203A9 (en) | System and method for optimal sensor placement | |
| Zaman et al. | Explainable AI for RAMS | |
| Beshears | Diagnostics model enhanced maintenance | |
| EP4625081A1 (en) | Determining the root cause of faults in industrial plants with generative machine learning | |
| Silvestri et al. | Knowledge Integration in Neural Networks for E-Maintenance: Application to an Oil & Gas Plant | |
| Wabnitz et al. | Use of reliability engineering tools to enhance subsea system reliability | |
| Gundaker et al. | Quality technology in product realization systems | |
| Fu et al. | Aeronautics failure: a prognostic methodology based on the physics of failure and statistical approaches for predictive maintenance | |
| Carlucci et al. | Data-centric Maintenance and Operational Knowledge and Its Impact on Classification | |
| Azizyan et al. | The Importance of Studying Markov Processes in the Course of Studying Mathematical Models of a Technical System at the Stages of Diagnostics and Repair | |
| EP4677429A2 (en) | System and method for optimal sensor placement |