Automatic extraction of assets data from engineering data sources for generating an HMI
Systems and methods for controlling industrial process automation and control systems can automatically, through the use of machine learning (ML) models and algorithms, extract plant assets from engineering diagrams and other plant engineering data sources. The systems and methods can establish asset relationships to create a plant asset registry and build an asset hierarchy from the plant assets. The systems and methods can generate an ontological knowledge base from the plant asset hierarchy, and provide an HMI for controlling the industrial process based on the plant asset hierarchy and the ontological knowledge base.
1. A control system for an industrial plant, comprising:
one or more processors; and
a storage unit communicatively coupled to the one or more processors and storing processor-executable instructions thereon that, when executed by the one or more processors, cause the control system to:
perform a process that inputs data from a plurality of engineering data sources for the industrial plant;
perform a process that extracts one or more assets of the industrial plant from the data;
perform a process that creates an HMI (human-machine interface) asset model from the assets, the HMI asset model arranging the assets in a hierarchical structure;
perform a process that generates an HMI display from the HMI asset model, the HMI display displaying symbols that represent the one or more assets of the industrial plant and lines that represent processes, connections, and data links between the assets; and
perform a process that displays the HMI display to a user and allows the user to navigate vertically and horizontally along the display, wherein the HMI display dynamically changes which assets are displayed based on a change in position of the user on the HMI display, wherein
asset relationships are established from the one or more assets of the industrial plant to create a plant asset registry and build an asset hierarchy,
an ontological knowledge base is generated from the plant asset hierarchy, and
the process to create the HMI asset model is for an HMI for controlling an industrial process, wherein the model is created from the one or more assets of the industrial plant, the plant asset hierarchy, and the ontological knowledge base.
2. The control system of claim 1 , wherein the processor-executable instructions further cause the control system to perform a process that identifies all alarms currently raised for the industrial plant and assets corresponding to the alarms and displays the alarms on the HMI display.
3. The control system of claim 1 , wherein the processor-executable instructions further cause the control system to perform a process that displays the HMI display at a plant level, the plant level displaying all currently raised alarms identified for the industrial plant and assets corresponding to the alarms.
4. The control system of claim 1 , wherein the processor-executable instructions further cause the control system to perform a process that determines and displays on the HMI display assets that are potential root causes for an alarm upon the user selecting an asset corresponding to one of the alarms.
5. The control system of claim 4 , wherein the control system determines the assets that are potential root causes by finding all assets that are connected to one another that also have an alarm.
6. The control system of claim 5 , wherein the processor-executable instructions further cause the control system to perform a process that allows a user to manually correct a root cause of an alarm on the HMI display, and provides the root cause from the user as feedback to the control system.
7. The control system of claim 1 , wherein the processor-executable instructions further cause the control system to perform a process that automatically zooms in or zooms out on the assets displayed on the HMI display based on a change in a position of the user on the HMI screen.
8. The control system of claim 1 , wherein the processor-executable instructions further cause the control system to perform a process that displays assets in the HMI display as a two-dimensional view, wherein the HMI display allows a user to navigate vertically and horizontally within the two-dimensional view.
9. The control system of claim 1 , wherein the processor-executable instructions further cause the control system to perform a process that dynamically changes the assets displayed on the HMI display based on an alarm occurring on an asset.
10. The control system of claim 1 , wherein the processor-executable instructions further cause the control system to perform a process that displays assets on the HMI display at runtime based on one of: static weight assigned to an asset based on a position of the asset in an asset hierarchy, and dynamic weight assigned to the asset based on an alarm being raised at the asset.
11. A method for controlling for an industrial plant, comprising:
inputting data from a plurality of engineering data sources for the industrial plant;
extracting one or more assets of the industrial plant from the data;
establishing asset relationships to create a plant asset registry and building an asset hierarchy from the assets;
generating an ontological knowledge base from the asset hierarchy;
creating an HMI (human-machine interface) asset model for an HMI controlling an industrial process from the assets, the asset hierarchy, and the ontological knowledge base, the HMI asset model arranging the assets in a hierarchical structure;
generating an HMI display from the HMI asset model, the HMI display displaying symbols that represent the one or more assets of the industrial plant and lines that represent processes, connections, and data links between the assets; and
displaying the HMI display to a user and allowing the user to navigate vertically and horizontally along the display, wherein the HMI display dynamically changes which assets are displayed based on a change in position of the user on the HMI display.
12. The method of claim 11 , further comprising identifying all alarms currently raised for the industrial plant and assets corresponding to the alarms and displays the alarms on the HMI display.
13. The method of claim 11 , further comprising displaying the HMI display at a plant level, the plant level displaying all currently raised alarms identified for the industrial plant and assets corresponding to the alarms.
14. The method of claim 11 , further comprising determining and displaying on the HMI display assets that are potential root causes for an alarm upon the user selecting an asset corresponding to one of the alarms.
15. The method of claim 14 , wherein determining the assets that are potential root causes includes finding all assets that are connected to one another that also have an alarm.
16. The method of claim 11 , further comprising allowing a user to manually correct a root cause of an alarm on the HMI display, and providing the root cause from the user as feedback to a control system.
17. The method of claim 11 , further comprising automatically zooming in or zooming out on the assets displayed on the HMI display based on a change in a position of the user on the HMI screen.
18. The method of claim 11 , further comprising displaying assets in the HMI display as a two-dimensional view, and allowing a user to navigate vertically and horizontally within the two-dimensional view.
19. The method of claim 11 , further comprising dynamically changing the assets displayed on the HMI display based on an alarm occurring on an asset.
20. The method of claim 11 , further comprising displaying assets on the HMI display at runtime based on one of: static weight assigned to an asset based on a position of the asset in an asset hierarchy, and dynamic weight assigned to the asset based on an alarm being raised at the asset.
21. The control system of claim 1 , wherein the process that extracts one or more assets of the industrial plant from the data extracts the one or more assets of the industrial plant from the data using machine learning to identify the one or more assets.
22. The method of claim 11 , wherein the extracting one or more assets of the industrial plant from the data includes extracting the one or more assets of the industrial plant from the data using machine learning to identify the one or more assets.