Machine Learning Assets in Industrial Control Code for Real-Time Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation environments face challenges in leveraging operational data for real-time insights due to the complexity and time required for manual editing of control programs, and integrating machine learning algorithms is difficult without specialized knowledge.
Innovation Solution
Implementing pre-packaged machine learning models within industrial control code, allowing programmers to 'drag and drop' models with pre-set parameters, and integrating them into control programs like traditional assets, with visual indicators and feedback components for control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning algorithms are manually integrated into industrial control programs, then process optimization and productivity are improved, but device complexity and difficulty of implementation increase significantly
Solution Approach 1:
The patent introduces a machine learning asset as an intermediary component that bridges the gap between operational data and control decisions. This asset acts as a mediator that processes complex machine learning algorithms internally while presenting a simplified interface to the control program, thereby improving productivity without proportionally increasing control program complexity
Solution Approach 2:
The system implements feedback mechanisms where the machine learning asset continuously receives operational data from the industrial process, processes it through trained models, and returns optimized control decisions. This closed-loop feedback enables automatic adaptation and optimization without requiring manual intervention in the control program structure
2Loss of information
If control programs are manually edited to leverage operational data, then real-time insights are improved, but loss of time and productivity decrease due to the time-consuming nature of manual editing
Solution Approach 1:
The machine learning asset enables the control system to serve itself by automatically processing operational data and generating control decisions without requiring manual editing. The asset autonomously trains on historical data, identifies patterns, and applies learned insights in real-time, eliminating the time-consuming manual editing process while maintaining real-time operational awareness
Solution Approach 2:
The system performs preliminary actions by pre-training machine learning models on historical operational data before deployment. This advance preparation allows the asset to immediately leverage learned patterns when deployed in real-time operations, eliminating the need for time-consuming manual analysis and editing during operational phases
3Adaptability or versatility
If machine learning models are integrated into industrial automation objects, then adaptability and ease of operation are improved, but device complexity increases
Solution Approach 1:
The machine learning asset is designed as a universal component that can be integrated into various industrial automation contexts and control programs. It provides multi-functional capabilities including data processing, pattern recognition, prediction, and control optimization, allowing a single asset type to serve multiple purposes across different applications without requiring custom integration for each use case
Data Source
AI summary
Various embodiments of the present technology generally relate to solutions for integrating machine learning models into industrial automation environments. More specifically, embodiments of the present technology include systems and methods for implementing machine learning models within industrial control code to improve performance, increase productivity, and add capability to existing control programs. In an embodiment, a system comprises an interface component configured to display a graphical representation of a machine learning asset in an industrial automation environment, wherein the graphical representation includes a visual indicator representative of an output from the machine learning asset. The interface component is further configured to adjust the visual indicator based on the output from the machine learning asset. In addition, a process control component is configured to control an industrial process in the industrial automation environment based at least in part on the output from the machine learning asset.