Machine Learning Optimization for Sustainable Multi-Process Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing life cycle assessment (LCA) tools are inadequate for optimizing parameters in a system of multiple processes, lacking the ability to predict and optimize sustainability metrics across interconnected processes.

Innovation Solution

A computer-implemented method using machine learning (ML) to optimize inputs and outputs of multiple processes within a complex system, incorporating a trained ML model to predict sustainability constraints and process constraints, and output recommendations for optimal operation while minimizing waste and risk of failure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional LCA tools are used to study existing processes, then environmental sustainability can be quantified, but the tools cannot optimize parameters for future states of multiple processes

Engineering Contradiction:
Improvesustainability quantificationVSAvoidoptimization capability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent replaces conventional deterministic LCA calculation methods with machine learning models that can predict sustainability outcomes and enable optimization. The ML models learn from historical LCA data and process parameters to generate optimized process configurations that meet sustainability constraints, transforming the reactive LCA approach into a proactive optimization system.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Object-generated harmful factors

If waste metrics are minimized for sustainability constraints, then environmental performance improves, but the complexity of optimizing multiple interconnected processes increases

Engineering Contradiction:
Improvewaste metricsVSAvoidsystem optimization complexity
Core Design Contradiction:
Object-generated harmful factorsVSDevice complexity

Solution Approach 1:

The patent segments the complex multi-process optimization problem into individual process optimizations, where each process is optimized separately using ML models while considering its specific waste metrics and sustainability constraints. This segmentation allows the system to handle complexity by breaking down the overall optimization into manageable process-level sub-problems that can be solved independently and then integrated.

Inventive Principle:
Principle #1Segmentation

3Loss of substance

If process parameters are optimized for sustainability, then waste is reduced, but the risk of failure to operate processes reliably increases without proper constraints

Engineering Contradiction:
Improvewaste reductionVSAvoidoperational reliability
Core Design Contradiction:
Loss of substanceVSReliability

Solution Approach 1:

The patent applies preliminary anti-action by incorporating process constraints and risk assessments into the optimization framework before determining optimal parameters. The ML models are trained to recognize feasible operating regions that balance waste reduction with reliability requirements, and the system predicts potential failures or constraint violations in advance, allowing corrective actions to be taken before actual operational problems occur.

Inventive Principle:
Principle #9Preliminary anti-action

Data Source

PatentEP4632638A1Machine learning optimization of multiple processes in view of predicted sustainability
Publication Date: 2025.10.15 SCHNEIDER ELECTRIC USA INC
  • EP4632638A1 patent drawingFigure 1
  • EP4632638A1 patent drawingFigure 2
  • EP4632638A1 patent drawingFigure 3

AI summary

A method is provided that includes processing, using a trained machine learning model, a set of inputs and a set of outputs associated with actual, simulated, or twinned performance of multiple processes of a complex system on one or more physical machines to generate objective functions for the respective multiple processes, optimizing the set of inputs and the set of outputs of the multiple processes for meeting sustainability constraints for the complex system in view of waste metrics associated with the set of outputs and further for meeting process constraints for the respective multiple processes, and outputting a recommendation for actually operating the multiple processes on the one or more physical machines based on the optimized set of inputs and set of outputs for avoiding a risk of failure to operate the multiple processes while meeting the sustainability constraints for the complex system and the process constraints for the respective, multiple processes.