Knowledge-Based Model Verification for Industrial Automation Intent

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing manual approaches to creating engineering intention representations using ontology editors in intent-based engineering of modular process plants are error-prone, leading to issues during design, commissioning, and operation due to missing, ambiguous, or inconsistent information.

Innovation Solution

A support system that assists in defining a model for industrial automation systems by obtaining user-provided definitions, verifying their correctness or completeness against a knowledge base, and providing prompts for correcting or completing the information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual approaches are used to create engineering intention representations using ontology editors, then flexibility and user control are maintained, but error-proneness increases leading to missing, ambiguous, or inconsistent information

Engineering Contradiction:
Improveaccuracy of engineering intention representationsVSAvoidcomplexity of verification system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system implements automated feedback mechanisms by verifying user-provided model definitions against a knowledge base and returning prompts for correction. This feedback loop continuously improves the accuracy of engineering intention representations by identifying and highlighting errors, inconsistencies, or incomplete information in real-time during the modeling process.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary verification system that mediates between the user's manual input and the final engineering model. This intermediary layer automatically checks definitions against a knowledge base, acting as a bridge that guides users toward accurate representations without completely replacing manual input, thus maintaining flexibility while improving reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If automated verification is continuously performed, then model accuracy is improved, but processing time and system resource usage increase

Engineering Contradiction:
Improvecorrectness of model definitionsVSAvoidtime for model verification
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The verification system operates periodically rather than continuously, checking model definitions at strategic intervals or triggered by specific user actions. This periodic verification approach maintains model accuracy while minimizing processing time and resource consumption by avoiding constant validation of every input change.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system performs preliminary verification checks on user input before it is fully processed and integrated into the model. By validating information early in the input process, the system prevents errors from propagating through the model, reducing the need for extensive rework and saving overall processing time.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4502737A1Engineering and operations support systems and methods
Publication Date: 2025.02.05 ABB (SCHWEIZ) AG
  • EP4502737A1 patent drawingFigure 1
  • EP4502737A1 patent drawingFigure 2
  • EP4502737A1 patent drawingFigure 3

AI summary

There is provided a support system for defining a model representing at least part of an industrial automation system. The support system is configured to: obtain a user-provided definition of at least part of the model; process the user-provided definition to verify correctness or completeness of the at least part of the model with reference to at least one knowledge base; and in response to determining that the user-provided definition comprises incorrect or incomplete information, provide system output, wherein the system output comprises a prompt to the user to provide correct or complete information for inclusion in the definition of the at least part of the model.