Industrial Control Logic Variable Reduction Using Runtime Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation environments face challenges in extracting insights from vast operational data due to the complexity of control code programming, limited access to runtime data, and the difficulty in managing thousands of relevant variables, which hinders efficient control logic programming and data analytics.
Innovation Solution
Implementing a machine learning-based analysis engine that identifies unused variables in control logic by analyzing operational data and control logic, providing notifications for removal and assisting in code completion, integration of data science tools, and surfacing contextual information to enhance engineering and data science capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If control programmers manually edit control programs to incorporate operational data, then control logic can be optimized, but the process becomes extremely time-consuming and difficult
Solution Approach 1:
The system enables self-service by automatically analyzing operational data and control logic to identify unused variables and suggest optimizations, eliminating the need for manual analysis by programmers. The machine learning model autonomously performs the complex analysis that would otherwise require extensive human time and expertise.
Solution Approach 2:
The patent replaces the mechanical process of manual code review and editing with an automated machine learning-based analysis engine. This engine uses natural language processing and machine learning models to automatically identify optimization opportunities, substituting human cognitive effort with computational automation.
2Ease of operation
If control programmers have access to runtime data and statistics, then they can make better programming decisions, but data scientists face challenges in analyzing enormous amounts of operational data without insight into control logic
Solution Approach 1:
The system introduces an intermediary machine learning-based analysis engine that bridges the gap between control programmers and data scientists. This engine automatically analyzes both control logic and operational data, translating between the two domains and providing actionable insights without requiring deep expertise in either field.
Solution Approach 2:
The system extracts and surfaces only the most relevant insights from enormous amounts of operational data, rather than presenting all raw data. The analysis engine identifies and extracts key patterns, unused variables, and optimization opportunities, reducing the complexity of data analysis while maintaining ease of access for programmers.
3Adaptability or versatility
If industrial processes have thousands of relevant variables, then comprehensive control is achieved, but it becomes difficult for programmers to provide connections and logic for every important variable
Solution Approach 1:
The system performs self-service by automatically analyzing control logic and operational data to identify unused variables and suggest optimizations. This eliminates the need for programmers to manually review and connect thousands of variables, while still achieving comprehensive control coverage through automated analysis.
Solution Approach 2:
The system changes the parameter of variable analysis from manual inspection to automated machine learning-based analysis. This transformation allows the system to handle thousands of variables efficiently by changing the methodology from human-cognitive to computational-analysis, maintaining comprehensive coverage while reducing programming complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Various embodiments of the present technology generally relate to solutions for improving industrial automation programming and data science capabilities with machine learning. More specifically, embodiments include systems and methods for implementing machine learning engines within industrial programming and data science environments to improve performance, increase productivity, and add functionality. In an embodiment, a system comprises a machine learning-based analysis engine configured to perform an analysis of operational data from an industrial automation environment. The analysis engine is further configured to perform an analysis of control logic and identify, based on the analysis of the operational data and the analysis of the control logic, a variable that is in the control logic but is not used in the operational data. The system further comprises a notification component configured to surface a notification that the variable is in the control logic but is not used in the operational data.