Control Logic Analysis Wizard for Unused Variable Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation environments face challenges in leveraging operational data for control code programming due to the vast amount of data and limited accessibility to runtime data, leading to difficulties in identifying relevant variables and connections in control logic.
Innovation Solution
Implementing a machine learning-based analysis engine within industrial programming environments to analyze operational data and control logic, identifying unused variables and surfacing notifications for their removal, thereby enhancing programming efficiency and productivity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning-based analysis engine is implemented to analyze operational data and control logic, then identification accuracy of relevant variables is improved, but device complexity increases
Solution Approach 1:
A machine learning-based analysis engine is introduced as an intermediary component between operational data sources and control logic programming tools. This engine automatically analyzes operational data, identifies relevant variables and connections, and provides insights to programmers, thereby improving identification accuracy while managing complexity through automation rather than manual analysis of vast datasets
Solution Approach 2:
The patent replaces manual mechanical analysis methods with machine learning-based automated analysis. Instead of programmers manually examining operational data to identify relevant variables, the system uses trained machine learning models to automatically perform this analysis, substituting human cognitive effort with computational algorithms that can process vast amounts of data efficiently
2Manufacturing precision
If manual editing of control programs is performed to incorporate operational data insights, then control logic accuracy is improved, but productivity deteriorates
Solution Approach 1:
The system performs preliminary analysis of operational data and identification of relevant variables before the control programming process begins. The machine learning engine pre-processes operational data, identifies patterns and relationships, and prepares insights that guide subsequent control logic development, thereby improving accuracy while reducing the time required for manual editing and programming
Solution Approach 2:
The patent implements a feedback mechanism where the machine learning analysis engine continuously monitors operational data and provides real-time or near-real-time insights to the control programming process. This feedback loop allows programmers to incorporate data-driven recommendations into control logic more efficiently, improving accuracy without significant time penalties by having insights available during the programming process rather than requiring extensive post-programming analysis
3Reliability
If control programmers are provided with access to runtime data and statistics, then control logic completeness is improved, but ease of operation deteriorates
Solution Approach 1:
The system extracts only the most relevant variables, patterns, and insights from vast amounts of operational data and presents them to control programmers in a simplified format. Rather than providing access to all raw runtime data and statistics, the machine learning engine filters and extracts only the information that is most useful for control logic development, thereby improving completeness of control logic while maintaining ease of operation by presenting information in an accessible, curated manner
Solution Approach 2:
The patent applies local quality by providing different levels and types of data access to different users based on their needs. Control programmers receive curated, relevant insights tailored to their specific programming tasks, while data scientists and analysts may access more comprehensive datasets. This localized approach ensures that each user group receives the appropriate level of data detail and complexity, improving both completeness and ease of operation for each specific use case
Data Source
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.