Cognitive Engineering Graph for Automation Knowledge Reuse
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The complexity of modern automation systems in manufacturing and assembly, coupled with high productivity and safety demands, makes it difficult for human experts to write automation programs efficiently, and the rotation of staff exacerbates this issue.
Innovation Solution
A cognitive engineering system (CES) utilizing a cognitive engineering graph (CEG) and machine learning to assist engineers by recognizing patterns, suggesting design actions, and providing feedback, thereby automating knowledge representation and validation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If human experts manually write automation programs for complex automation systems, then the systems can be designed and implemented, but the productivity and speed of engineering task completion are insufficient due to the high complexity and criticality of modern automation systems
Solution Approach 1:
The patent replaces manual mechanical engineering work with an automated cognitive system that uses machine learning, natural language processing, and knowledge graphs to generate automation programs. The cognitive engineering system extracts requirements from natural language specifications and automatically synthesizes control logic, substituting human expert manual programming with intelligent automated systems.
Solution Approach 2:
The cognitive engineering system performs self-learning by continuously analyzing completed automation projects and extracting patterns to improve future program generation. The system autonomously builds and updates its knowledge base from historical project data, enabling it to progressively improve its engineering capabilities without additional human training intervention.
2Reliability
If human expert teams are increased to handle the complexity of automation systems, then more expertise is available, but the cost and time requirements increase
Solution Approach 1:
The patent replaces human expert teams with a cognitive system that leverages machine learning models trained on historical project data. This substitution maintains high engineering quality through pattern recognition from past successful projects while dramatically reducing the time required, as the automated system operates continuously without fatigue or rotation of staff.
Solution Approach 2:
The cognitive engineering system performs preliminary analysis of project requirements and automatically generates initial automation program structures before detailed implementation. By pre-processing requirements and identifying standard patterns from historical data, the system reduces the overall engineering timeline while maintaining quality through proven design patterns.
3Adaptability or versatility
If staff rotation occurs in automation engineering teams, then organizational changes happen, but knowledge loss and project continuity issues arise due to the specialized expertise required
Solution Approach 1:
The patent captures and stores expert knowledge in structured formats including knowledge graphs, ontologies, and trained machine learning models. This digital copying of expertise allows the organization to retain institutional knowledge independently of individual staff members, enabling seamless transitions when personnel change without losing critical domain expertise.
Solution Approach 2:
The cognitive engineering system serves multiple functions: it generates automation programs, answers technical queries, provides design recommendations, and continuously learns from new projects. This universal system replaces the need for multiple specialized human experts, maintaining adaptability while preserving knowledge across organizational changes.
4Manufacturing precision
If traditional engineering tools are used for automation programming, then the design process can be completed, but the ability to validate and verify complex systems efficiently is limited
Solution Approach 1:
The cognitive engineering system incorporates continuous feedback loops where generated automation programs are validated against requirements and historical project data. The system analyzes completed projects to identify patterns and improvements, feeding this information back into the generation process to enhance validation accuracy and catch potential issues before deployment.
Solution Approach 2:
The system performs comprehensive validation by analyzing not only the current project requirements but also comparing against patterns from multiple historical projects. This excessive analysis approach ensures high validation accuracy by checking against a broader set of criteria and historical precedents than traditional single-project validation methods.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for representing knowledge in a cognitive engineering system (CES) includes receiving information relating to an automation engineering project from an engineering tool, storing the received information in a cognitive engineering graph (CEG) storing a plurality of previously generated CEGs for previous automation engineering projects, and establishing a communication path between the CEG storing the received information and the plurality of previously generated CEGs. The method may further include applying machine learning to the stored CEG based on the received information and the stored plurality of previously generated CEGs. The machine learning may analyze the CEG to identify at least one pattern that is representative of a given object from the automation engineering project. The CES may automatically add an element to the CEG based on the received information and a query from a user. Further, the user may request a change made by the CES be reversed.