ML Recommendation Engine for Industrial Control Logic Configuration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Industrial automation environments face challenges in extracting enterprise-level 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 hampers the integration of important connections and logic in control programs.

Innovation Solution

Implementing a machine learning-based recommendation engine within industrial programming environments to suggest components, connections, and configurations for control logic, leveraging historical operational data to provide auto-completions and contextual information, thereby assisting programmers and data scientists in improving control logic and data analytics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If control programmers manually edit control programs to incorporate operational data, then control logic accuracy can be improved, but the time and complexity required for programming increases significantly

Engineering Contradiction:

Improvecontrol logic accuracyVSAvoidprogramming time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system enables self-service by allowing control programmers to access and utilize operational data, statistics, and insights directly within the programming environment without requiring external data science expertise. The programming environment automatically provides relevant operational information, enabling programmers to independently improve control logic accuracy while maintaining efficient programming workflows.

Inventive Principle:

Principle #25Self-service

2Manufacturing precision

If control programmers are provided with access to runtime data and operational information, then control logic quality can be improved, but the complexity of the programming environment increases

Engineering Contradiction:

Improvecontrol logic qualityVSAvoidprogramming environment complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The programming environment acts as an intermediary between operational data sources and control programmers. It automatically retrieves, processes, and presents relevant operational data, statistics, and insights in a programmer-friendly format, eliminating the need for programmers to directly manage complex data sources while still providing access to high-quality operational information for improved control logic.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of information

If data scientists perform data mining and predictive modeling on operational data, then enterprise-level insights can be extracted, but the difficulty of understanding control logic and industrial automation environments increases

Engineering Contradiction:

Improveenterprise-level insightsVSAvoidcontrol logic understanding

Core Design Contradiction:

Loss of informationVSDifficulty of detecting and measuring

Solution Approach 1:

The programming environment serves as an intermediary that translates complex operational data and data science results into contextually relevant information for control logic development. It automatically connects operational data to control logic elements, providing data scientists and programmers with a shared understanding of the industrial automation environment without requiring deep expertise in either domain.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Manufacturing precision

If programmers manually connect and configure every important variable, tag, or device in industrial processes, then completeness of control logic can be improved, but the time and effort required increases dramatically

Engineering Contradiction:

Improvecompleteness of control logicVSAvoidprogramming productivity

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The system performs preliminary action by automatically identifying, organizing, and presenting relevant variables, tags, and devices before the programmer begins control logic development. The programming environment pre-processes operational data to highlight important connections and configurations, enabling programmers to quickly complete comprehensive control logic without manually investigating every variable and device in the industrial process.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentEP4155849A1Model asset library and recommendation engine for industrial automation environments

Publication Date: 2023.03.29 ROCKWELL AUTOMATION TECH INC

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 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.