Hybrid Controller Oversight for Changing Control Conditions

Solution Overview

Problem

Existing controllers, including hybrid controllers that combine dynamic components and system-modeling elements, may perform sub-optimally when the system under control and its environment differ significantly from the conditions used to develop the controller.

Innovation Solution

A governing controller is introduced to monitor and adjust the operation of the hybrid controller, allowing for dynamic updates of constraints and parameters based on real-time performance metrics, thereby improving control outcomes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a hybrid controller combining dynamic components and system-modeling elements is used, then control performance under training conditions is improved, but performance deteriorates when system conditions differ from training conditions

Engineering Contradiction:

Improvecontrol performanceVSAvoidadaptability to changing conditions

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements a governing controller that dynamically adjusts the hybrid controller's operational parameters (such as learning rates, model selection, or active components) based on real-time system conditions. This allows the controller to adapt its behavior when operating conditions diverge from training conditions, resolving the contradiction between optimized training performance and adaptability to changing conditions.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The governing controller continuously monitors system performance and environmental conditions, using this feedback to dynamically modify the hybrid controller's parameters. This feedback mechanism enables the system to maintain optimal performance across varying conditions by adjusting the learned model's behavior based on current operational context, thereby improving adaptability while preserving control reliability.

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If the learned system model is updated frequently to adapt to changing conditions, then adaptability is improved, but computational resources and time are increased

Engineering Contradiction:

Improveadaptability to changing conditionsVSAvoidupdate time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The governing controller implements periodic or event-triggered updates to the learned system model rather than continuous updates. It monitors system conditions and only initiates model updates when specific thresholds are met or at predetermined intervals, reducing unnecessary computational overhead while maintaining adaptability to significant condition changes.

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

Instead of fully retraining the learned model frequently, the governing controller adjusts specific parameters of the existing model (such as learning rates, regularization parameters, or active subset of features) based on current conditions. This partial parameter adjustment approach maintains adaptability while significantly reducing the computational time and resources required compared to complete model retraining.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If the learned system model is updated frequently to adapt to changing conditions, then adaptability is improved, but computational resources are increased

Engineering Contradiction:

Improveadaptability to changing conditionsVSAvoidcomputational resources

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The governing controller implements periodic or event-triggered updates to the learned system model rather than continuous updates. It monitors system conditions and only initiates model updates when specific thresholds are met or at predetermined intervals, reducing unnecessary computational overhead while maintaining adaptability to significant condition changes.

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

Instead of fully retraining the learned model frequently, the governing controller adjusts specific parameters of the existing model (such as learning rates, regularization parameters, or active subset of features) based on current conditions. This partial parameter adjustment approach maintains adaptability while significantly reducing the computational time and resources required compared to complete model retraining.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250181037A1Combined Learned and Dynamic Control System

Publication Date: 2025.06.05 UNIVERSITY OF CHICAGO

AI summary

Example embodiments allow for networks of hybrid controllers that can be computed efficiently and that can adapt to changes in the system(s) under control. Such a network includes at least one hybrid controller that includes a dynamic sub-controller and a learned system sub-controller. Information about the ongoing performance of the system under control is provided to both the hybrid controller and to an over-controller, which provides one or more control inputs to the hybrid controller in order to modify the ongoing operation of the hybrid controller. These inputs can include the set-point of the hybrid controller, one or more parameters of the dynamic controller, and an update rate or other parameter of the learned system controller. The over-controller can control multiple hybrid controllers (e.g., controlling respective sub-systems of an overall system) and can, itself, be a hybrid controller.