Intent-based automation engineering method

Patent metadata

Field	Value
Publication number	US-12222709-B2
Application number	US-202117462017-A
Country	US
Kind code	B2
Filing date	Aug 31, 2021
Priority date	Mar 8, 2019
Publication date	Feb 11, 2025
Grant date	Feb 11, 2025

Abstract

An intent-based automation engineering method for automation of a production process includes: receiving an intent model, correlating to process intent, including production process functions, constraints on measurable properties on the production process functions, and/or production process function sequences required for the production process, as a received intent model; receiving a process model, correlating to process knowledge including a production process behavior, as a received process model; determining a machine-readable production model linking the received intent model to the received process model as a provided production model; and determining a control strategy for controlling the production process dependent on the provided production model as a determined control strategy.

First claim

What is claimed is:

1. An intent-based automation engineering method for automation of a production process, comprising:
receiving an intent model, correlating to process intent, comprising production process functions, constraints on measurable properties on the production process functions, and/or production process function sequences required for the production process, wherein the intent model comprises automation engineering data, which are recorded using an intent-language that formulates a quantifiable expectation on the behavior of one or more components of the production process;
receiving a process model, correlating to process knowledge comprising a production process behavior, wherein the process model comprises statements on a consequence of the production process behavior, wherein the process model is determined by abstracting the process knowledge, wherein the abstracting comprises converting individual machine-readable expert statements on process knowledge into the process model, and wherein the process knowledge is extracted from existing specifications using pattern recognition algorithms, natural language processing and/or AI-based classification;
determining a machine-readable production model linking the received intent model to the received process model, wherein the production model comprises data associated with maintaining and monitoring a state of the production process and represented at a lower degree of complexity than a degree of complexity of the received process model;
determining a control strategy for controlling the production process dependent on the provided production model; and
adjusting at least one production process step based on the control strategy.

2. The method of claim 1 , further comprising:
determining the machine-readable production model by extending the process model dependent on the intent model.

3. The method of claim 1 , wherein the data associated with maintaining and monitoring a state of the production process further comprises data for maintaining and monitoring a steady state, data for maintaining and monitoring a particular state, data for maximizing stability of a control of the production process, and/or data for understanding dynamic aspects of the production process.

4. The method of claim 1 , wherein the process knowledge is additionally provided by a process expert.

5. The method of claim 1 , wherein the production model is determined dependent on an automatic completion of statements, an automatic suggestion for typical process intent, an automatic suggestion for process-specific process intent, an automatic suggestion for refining and/or adding process intent to resolve unclarified and/or a consistency check.

6. The method of claim 1 , wherein the intent model, the process model, and/or the production model uses a dictionary of predetermined terms.

7. The method of claim 1 , further comprising:
determining the control strategy by extending an existing control strategy.

8. The method of claim 1 , wherein the statements on a consequence of the production process behavior further comprises quantitative dependencies in reactions and/or an impact of process connectivity on process stability.

9. The method of claim 1 , further comprising:
validating and/or verifying the production model.

10. The method of claim 1 , further comprising:
generating an alarm if operating the production process violates the production model, the alarm indicating a violated process intent and/or a violated process knowledge and serving as an indicator of a root cause for the violation.

11. The method of claim 10 , further comprising:
automatically generating a configuration for generating the alarm, the alarm comprising the root-cause and/or a suggested responding action determined by tracing measured or simulated alarm triggers dependent on the process model and/or an alarm hiding strategy determined by correlating alarms originating in a same root-cause and prioritizing the alarms according to criticality or impact on production KPIs.

12. The method of claim 1 , further comprising:
determining an inverted process model and/or an inverted production model dependent on the process model and/or the production model, configured for determining operation setpoints.

13. The method of claim 1 , further comprising:
operating the production process based on the determined control strategy.

14. A non-transitory computer-readable medium having processor-executable instructions stored thereon, wherein the processor-executable instructions, when executed by one or more controllers, facilitate the performance of the method of claim 1 .

15. The method of claim 1 , wherein the existing specifications comprise existing process design documents.

16. The method of claim 15 , wherein the process knowledge is additionally provided by the process expert.

17. The method of claim 8 , wherein the process model further comprises quantitative dependencies in reactions and/or the impact of process connectivity on process stability comprises loops in material flow and sharing of material with other processes.

18. The method of claim 9 , further comprising:
validating and/or verifying the production model by virtual testing.

19. The method of claim 10 , further comprising:
determining a suggested responding action based on the alarm.

Assignees

• Abb Schweiz Ag

Inventors

• Schulz Dirk
• Jetley Raoul

Classifications

• G05B2219/42155

  Model · CPC title

• G05B2219/31368

  MAP manufacturing automation protocol · CPC title

• G05B19/41885 Primary

  characterised by modeling, simulation of the manufacturing system · CPC title