Self-Enhancing Knowledge Model for Industrial Automation Ontologies

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The creation and maintenance of ontologies in industrial automation engineering domains require significant human effort, making them costly and unscalable, especially when extending to new domains.

Innovation Solution

A method is developed to automatically augment a knowledge model by obtaining instance data from industrial automation systems, processing it using data analytics algorithms, and deriving knowledge to enhance the ontology, allowing for self-enhancement and self-assessment of the knowledge model.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If human experts manually create and maintain ontologies, then the knowledge model achieves high accuracy and reliability, but the process becomes costly and unscalable

Engineering Contradiction:

Improveknowledge model accuracyVSAvoidontology creation speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system enables self-service by allowing the knowledge model to automatically augment itself through data analytics algorithms. The ontology can self-enhance by processing instance data and deriving new knowledge without continuous human intervention, thereby maintaining reliability while improving productivity and scalability.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback mechanisms where the knowledge model continuously processes instance data from industrial automation systems, derives new knowledge, and updates the ontology accordingly. This closed-loop feedback enables the ontology to evolve and improve automatically while maintaining high accuracy through iterative refinement.

Inventive Principle:

Principle #23Feedback

2Reliability

If human experts manually extend ontologies to new domains, then the knowledge model maintains high quality, but the process becomes costly and unscalable

Engineering Contradiction:

Improveontology qualityVSAvoidontology extension complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system replaces the mechanical process of manual ontology extension with automated data analytics algorithms. These algorithms process instance data to automatically derive and integrate new domain knowledge, substituting human expert labor with computational processes that reduce complexity and enable scalable extension to new domains while maintaining quality.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated data analytics algorithms are used to augment the knowledge model, then scalability and cost-effectiveness improve, but the need for explainable and transparent knowledge derivation increases

Engineering Contradiction:

Improveontology augmentation speedVSAvoidknowledge derivation transparency

Core Design Contradiction:

ProductivityVSDifficulty of detecting and measuring

Solution Approach 1:

The system introduces an intermediary layer between automated data analytics and the knowledge model that ensures transparency and explainability. This intermediary component tracks and documents how instance data is processed into derived knowledge, making the automation process interpretable while maintaining high productivity in ontology augmentation.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20240020548A1Self-Enhancing Knowledge Model

Publication Date: 2024.01.18 ABB (SCHWEIZ) AG

AI summary

A method of automatically augmenting a knowledge model representing one or more automation engineering domains. The method comprises: obtaining instance data relating to at least one component of an industrial automation system, wherein the component represents an instance of at least one entity in the knowledge model; processing the instance data using one or more data analytics algorithms to derive knowledge to be added to the knowledge model; and augmenting the knowledge model to represent the derived knowledge. Corresponding systems are also provided.