Knowledge Base for Industrial Control Loop Design Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The design of control applications, human machine interfaces, and cabinet engineering for industrial processes is time-consuming and resource-intensive, requiring significant engineering skill and manual effort to determine if new solutions can reuse existing artifacts, and conventional methods lack scalability and require high-level engineering expertise.
Innovation Solution
A knowledge-driven artificial intelligence engine that automates engineering design by using machine learning to train a knowledge base with control loop data, predicting templates for new designs, and updating the knowledge base through conflict reviews and feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual design methods are used with engineering expertise, then design accuracy and reliability are maintained, but time consumption and resource requirements increase significantly
Solution Approach 1:
The system performs preliminary actions by pre-processing design data, training machine learning models with historical design artifacts, and preparing knowledge bases before actual design tasks. This allows the automated system to quickly generate designs without requiring manual engineering analysis for each new design, thus reducing time consumption while maintaining reliability through pre-validated design patterns.
Solution Approach 2:
The system creates and stores digital copies of historical design artifacts, control loop configurations, and engineering templates in a knowledge base. These copies can be automatically retrieved and adapted for new designs, eliminating the need to recreate designs from scratch and reducing time consumption while maintaining design quality through proven templates.
2Stability of the object's composition
If strictly rules driven approach is applied, then design consistency is improved, but scalability is limited and engineering skill requirements remain high
Solution Approach 1:
The system replaces manual mechanical design processes with an automated machine learning-based system. The machine learning models automatically learn design patterns and rules from historical data, substituting the need for human engineers to manually apply rules. This enables scalability while maintaining consistency through automated decision-making based on learned patterns rather than manual rule application.
Solution Approach 2:
The system transforms design data into standardized parameters and features that can be processed automatically. By converting unstructured design artifacts into structured parameters with defined relationships, the system enables scalable automated processing while maintaining design consistency through parameter-based decision-making rather than ad-hoc rule application.
3Productivity
If existing design artifacts are reused, then productivity and efficiency are improved, but the complexity of identifying applicable artifacts increases
Solution Approach 1:
The system introduces machine learning models as intermediaries between historical design artifacts and new design tasks. These models automatically analyze the characteristics of existing artifacts and match them with appropriate new designs, eliminating the need for manual artifact identification. This reduces the complexity of finding applicable artifacts while improving productivity through automated matching.
Solution Approach 2:
The system transforms unstructured design artifacts into structured data with defined parameters and features. This parameterization enables automated comparison and matching algorithms to efficiently identify applicable artifacts based on parameter similarity rather than manual review, reducing identification complexity while improving productivity through systematic artifact reuse.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of automating engineering design is provided. The method includes receiving a training set including pairings of control loop data for respective control loops identified in digitized design data and templates that were instantiated using the control loop data of the respective control loops and training, using machine learning, a knowledge base, based on the training set. The knowledge base, once trained, is configured to be queried with digitized new control loop data, predict a template to pair with the digitized new control loop data, and the predicted template, and the predicted template is configured to be instantiated with the new control loop data for implementation of a control loop in an engineering system.