Regulatory Controller Tuning Using Positive-Change Policy Updates

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing regulatory controllers are often poorly tuned, leading to inefficient operation, wasted energy, and excessive wear on control system components. Manual tuning is tedious, error-prone, and time-consuming, especially in systems with multiple controllers.

Innovation Solution

An automated method for tuning regulatory controllers, which updates controller policies iteratively based on performance levels. The updated policies are optimized to have the highest likelihood of producing a positive change in performance rather than maximizing the largest positive magnitude of change.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual tuning of regulatory controllers is performed, then tuning accuracy can be improved, but time consumption and operational complexity increase significantly

Engineering Contradiction:
Improvetuning accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-tuning by automatically adjusting controller parameters based on observed process behavior and performance feedback. The regulatory controller monitors its own performance metrics and autonomously modifies tuning parameters without requiring manual intervention, thereby achieving high tuning accuracy while eliminating time-consuming manual operations.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system implements continuous feedback loops where performance data from the controlled process is fed back to the tuning mechanism. This feedback drives iterative adjustments of controller parameters, enabling the system to learn from past performance and converge toward optimal tuning settings automatically, resolving the contradiction between accuracy and time consumption.

Inventive Principle:
Principle #23Feedback

2Productivity

If aggressive tuning adjustments are made to maximize performance improvement, then productivity can be improved, but system stability and reliability deteriorate

Engineering Contradiction:
Improveperformance improvementVSAvoidsystem stability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system applies partial adjustments to controller parameters rather than extreme changes. By making conservative, incremental modifications to tuning parameters based on performance feedback, the system achieves steady performance improvement while maintaining system stability and avoiding disruptive changes that would compromise reliability.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The tuning mechanism dynamically adapts its adjustment strategy based on current system conditions and performance trends. The system modulates the aggressiveness of parameter changes in real-time, applying larger adjustments when stability margins are high and smaller adjustments when the system is near stability limits, thereby balancing productivity improvement with reliability maintenance.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4024143B1Method and apparatus for tuning a regulatory controller
Publication Date: 2025.04.02 HONEYWELL INTERNATIONAL INC
  • EP4024143B1 patent drawingFigure 1
  • EP4024143B1 patent drawingFigure 2
  • EP4024143B1 patent drawingFigure 3

AI summary

During each of a plurality of iterations, a policy of a controller is updated and at least part of a process is controlled using the updated policy. The updated policy is associated with a performance level of the controller. For each iteration, the updated policy is determined using the associations generated during one or more previous iterations between the policies and the corresponding performance levels of the controller in controlling the at least part of the process, such that the updated policy is optimized to have a highest likelihood of producing a positive change in the performance level of the controller in controlling the at least part of the process rather than optimized to have a highest likelihood of producing a largest positive magnitude of change in the performance level of the controller in controlling the at least part of the process relative to the previous iteration.