ML Recommendation Engine for Industrial Control Logic Editing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation environments face challenges in extracting enterprise-level insights due to the vast amounts of data generated, with control programmers lacking access to runtime data and statistics, making it difficult to develop effective control programs and data analytics, and data scientists struggling to analyze operational data without insight into control logic or industrial automation environments.
Innovation Solution
Implementing a machine learning-based recommendation engine within industrial programming environments to assist in editing control logic by generating recommendations for adding components, configuring them based on existing logic, and integrating data science tools to provide contextual information, thereby enhancing engineering and data science capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If control programmers manually edit control programs without access to runtime data, then programming can be completed with basic tools, but the programming process becomes extremely time-consuming and important variables are easily overlooked
Solution Approach 1:
The patent introduces an intermediary system (recommendation engine with NLP processing) that bridges control programmers and runtime data. The system automatically processes operational data, identifies relevant variables and relationships, and presents recommendations to programmers, eliminating the need for direct programmer access to raw data while significantly reducing programming time and variable oversight
Solution Approach 2:
The system enables self-service by automatically generating recommendations for control logic improvements, variable connections, and programming suggestions based on runtime data analysis. This automated assistance reduces the manual effort required for programming while ensuring comprehensive variable coverage without increasing programmer workload
2Adaptability or versatility
If data scientists analyze operational data without insight into control logic, then data analysis can be performed independently, but the data scientist cannot effectively mine or process the data without understanding the industrial automation environment
Solution Approach 1:
The patent employs an NLP-based intermediary system that automatically extracts and processes control logic information from programming environments and presents it to data scientists in an accessible format. This intermediary layer enables data scientists to understand control logic and operational relationships without requiring direct expertise in industrial automation control systems, thereby improving adaptability while managing integration complexity
3Reliability
If programmers are provided with enormous amounts of operational data, then better insights can be gained, but the computing power and time required for data science becomes prohibitively large
Solution Approach 1:
The patent extracts only the most relevant information from enormous amounts of operational data using NLP processing and recommendation algorithms. Instead of requiring programmers to process all available data, the system extracts key variables, relationships, and programming recommendations, significantly reducing computing power requirements while maintaining or improving control program quality
Solution Approach 2:
The system applies local quality by providing targeted, context-specific recommendations to programmers based on their current programming needs and the operational data. Rather than presenting all available data uniformly, the system tailors information delivery to specific programming contexts, reducing overall computing requirements while improving local decision-making quality
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 of the present technology 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 recommendation engine configured to, an industrial programming environment, generate a recommendation to add a component to control logic based on an existing portion of the control logic. A notification component is configured to surface the recommendation in the programming environment. A programming component is configured to, in the programming environment, add the component to the control logic. A configuration component is configured to configure the component based at least in part on the existing portion of the control logic.