Industrial Control Program Tags for ML-Based Variable Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Industrial automation environments face challenges in effectively integrating machine learning models to assist in generating control programs, making it difficult to target specific variables and optimize industrial processes due to the large number of available tags and the inefficiency in surfacing potentially useful tags.

Innovation Solution

Implementing a system and methods for integrating machine learning models into industrial automation environments, the implementation of a system and methods for integrating machine learning models into industrial automation environments, the system comprises a design application and methods for integrating machine learning models into industrial automation environments, the system comprises a design application and a processing application that selects a program tag that represents a target variable in an industrial process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If machine learning models are integrated into industrial automation environments, then the ability to optimize target variables improves, but the complexity of the programming system increases

Engineering Contradiction:
Improveoptimization capabilityVSAvoidprogramming system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces a design application as an intermediary layer between the machine learning processing application and the control program. This design application serves as a mediator that translates complex machine learning outputs into usable control program elements, thereby enabling optimization capabilities while shielding users from the underlying complexity of the machine learning system.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If the number of available program tags increases, then the coverage of industrial variables improves, but the difficulty of targeting specific variables worsens

Engineering Contradiction:
Improvevariable coverageVSAvoidtag selection difficulty
Core Design Contradiction:
Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The processing application utilizes machine learning algorithms to analyze historical data and provide feedback about which program tags are most relevant to optimizing a given target variable. This feedback mechanism automatically identifies and surfaces the most useful tags from the large available set, eliminating the need for manual searching and making tag selection intuitive despite the large number of available options.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs self-service by automatically analyzing the industrial process data and independently identifying relevant program tags without requiring manual intervention. The machine learning model autonomously determines which tags should be used for optimization based on data patterns, thereby resolving the difficulty of selecting specific variables from a large set.

Inventive Principle:
Principle #25Self-service

3Loss of information

If machine learning algorithms are used to analyze industrial data, then the insight generation capability improves, but the integration difficulty with existing programming systems worsens

Engineering Contradiction:
Improveinsight extractionVSAvoidintegration complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The design application serves multiple functions: it generates control programs, interfaces with machine learning models, and manages program tags. By creating a universal platform that handles both traditional control programming and machine learning integration, the system reduces overall integration complexity while maintaining advanced insight generation capabilities.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4246252B1Insight driven programming tags in an industrial automation environment
Publication Date: 2025.12.17 ROCKWELL AUTOMATION TECH INC
  • EP4246252B1 patent drawingFigure 1
  • EP4246252B1 patent drawingFigure 2
  • EP4246252B1 patent drawingFigure 3

AI summary

Various embodiments of the present technology generally relate to industrial automation environments. More specifically, embodiments include systems and methods to optimize a target variable in an industrial automation environment. In some examples, a design application generates a control program configured and selects a program tag that represents a target variable in an industrial process. A processing application identifies a set of available program tags that represent independent variables in the industrial process and determines correlations between ones of the independent variables and the target variable. The processing application selects available program tags that represent independent variables correlated with the target variable and generates a recommendation that indicates the selected available program tags. The design application modifies the control program using the selected available program tags to optimize the target variable. The design application transfers the control program for implementation by the programmable logic controller.