ML Control Scheme Switching for Real-Time Industrial Asset Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Industrial manufacturing environments face challenges in extracting enterprise-level insights from vast amounts of data generated quickly, particularly in real-time operational analytics. Additionally, adjusting control programs in industrial automation environments is difficult due to the complexity and the need for specialized knowledge in data science and process control.

Innovation Solution

The integration of machine learning models into industrial automation environments, allowing these models to be implemented within industrial control code. This system includes a processor and memory that execute executable components, such as storage and control components, which manage and optimize industrial processes using machine learning models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If machine learning models are integrated into industrial control systems to optimize parameters in real-time, then productivity and performance are improved, but device complexity increases

Engineering Contradiction:

Improvereal-time process optimizationVSAvoidcontrol system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces a model management component as an intermediary that handles the complexity of machine learning model deployment and switching. This component manages multiple model control schemes and automatically switches between them based on operational conditions, thereby improving productivity without requiring the end user to directly manage the complex ML infrastructure.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The control system incorporates automated model selection and switching capabilities that enable the system to self-optimize without continuous human intervention. The model management component automatically monitors performance metrics and switches between different model control schemes to maintain optimal operation, reducing the need for manual complexity management.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If multiple model control schemes are maintained for optimizing different parameters, then adaptability is improved, but device complexity increases

Engineering Contradiction:

Improveparameter optimization flexibilityVSAvoidmodel management complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the control system into multiple independent model control schemes, each optimized for specific parameters (e.g., energy efficiency, production rate, product quality). The model management component selectively activates appropriate segments based on current operational priorities, enabling adaptability without requiring all models to run simultaneously, thus managing complexity through modular organization.

Inventive Principle:

Principle #1Segmentation

3Manufacturing precision

If manual editing of control programs is performed to adjust for operational data insights, then manufacturing precision is improved, but loss of time increases

Engineering Contradiction:

Improveprocess control accuracyVSAvoidprogram editing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system pre-trains multiple machine learning models with different optimization objectives before deployment. These models are prepared in advance and stored as ready-to-use control schemes. When operational conditions change, the system can immediately switch to a pre-prepared model rather than requiring time-consuming manual program editing, thus maintaining manufacturing precision while reducing time loss.

Inventive Principle:

Principle #10Preliminary action

4Productivity

If computational power is increased to process operational data in real-time, then productivity is improved, but use of energy increases

Engineering Contradiction:

Improvereal-time data processing speedVSAvoidcomputational energy consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts computational resource allocation by switching between different model control schemes based on current operational priorities. When energy efficiency is prioritized, models optimized for lower computational intensity are activated. When maximum productivity is required, the system can switch to models that utilize higher computational power, creating a dynamic balance between energy consumption and productivity.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS12242233B2Machine learning models for asset optimization within industrial automation environments

Publication Date: 2025.03.04 ROCKWELL AUTOMATION TECH INC

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: a storage component configured to maintain a set of model control schemes for controlling an industrial process, a control component configured to control the industrial process with a control program running a model control scheme, wherein the model control scheme is configured to optimize a first parameter of the industrial process, and a model management component configured to change the model control scheme to optimize a second parameter of the industrial process that is distinct from the first parameter.