Knowledge Graph Consistency Validation for Engineered Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Configuring and reconfiguring engineered systems, such as industrial automation solutions, is laborious and prone to errors due to complex interplay of components and frequent changes in requirements or design practices, making it difficult to ensure consistency and compatibility.
Innovation Solution
A method and system using a knowledge graph and reinforcement learning agents to evaluate consistency by extracting paths and classifying components, providing interpretable explanations for compatibility issues, and facilitating automated data-driven validation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual configuration and validation of engineered systems is performed, then domain-specific knowledge and expertise can be applied, but the process becomes laborious and time-consuming
Solution Approach 1:
The patent replaces manual mechanical configuration processes with an automated computer-implemented system. The evaluation system automatically validates component selections and configurations by comparing them against stored reference configurations and consistency criteria, eliminating the need for manual domain expertise while maintaining validation accuracy.
Solution Approach 2:
The patent creates digital copies of validated system configurations and stores them in a database. These reference configurations are then reused to validate new configurations, allowing the system to leverage past expertise without requiring manual review of each new configuration, thereby reducing time while maintaining reliability.
2Reliability
If comprehensive validation of all components is performed, then system consistency and compatibility are ensured, but the complexity of the evaluation process increases
Solution Approach 1:
The patent divides the complex validation task into separate modular components: an evaluation module that assesses individual components against consistency criteria, a database module that stores reference configurations, and a reporting module that generates validation results. Each module handles specific aspects of validation independently, making the overall system more manageable despite comprehensive coverage.
Solution Approach 2:
The patent implements targeted validation that focuses on evaluating only the specific components and configurations that are actually present in the engineered system, rather than performing exhaustive validation of all possible components. This partial action approach maintains system consistency while avoiding unnecessary complexity from evaluating irrelevant elements.
3Productivity
If automated evaluation systems are implemented, then manual effort is reduced and productivity increases, but the system requires sophisticated algorithms and data structures
Solution Approach 1:
The patent pre-processes and stores reference configurations, consistency criteria, and component specifications in a structured database before validation is needed. This preliminary action allows the automated evaluation system to quickly retrieve and compare configurations during validation, increasing productivity without requiring complex real-time processing algorithms.
Solution Approach 2:
The patent introduces a knowledge graph as an intermediary data structure that represents system configurations, component relationships, and consistency rules in a standardized format. This knowledge graph serves as a mediator between the raw configuration data and the evaluation logic, simplifying the overall system architecture while enabling automated validation.
Data Source
AI summary
A graph database stores a knowledge graph, with nodes of the knowledge graph corresponding to components of an engineered system and edges of the knowledge graph specifying connections between the components. A reasoning module is equipped with a first agent and a second agent. The agents have been trained with opposing goals and extract paths from the knowledge graph beginning with a node that corresponds to a first component of the engineered system. A prediction module uses a classifier to classify the extracted paths in order to produce a classification result, which indicates consistency, and in particular compatibility, of the first component in relation to the engineered system. This information is provided to an engineer, supporting him in validating the engineered system, for example an industrial automation solution. The method and system provide an automated data-driven algorithm that leverages a large collection of historical examples for consistency checking of components.