Hybrid Controller Tuning for Changing Operating Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack effective methods to optimize the performance of complex, hierarchical, or distributed control systems under dynamic conditions, particularly when the operating environment deviates from the conditions used for training, leading to suboptimal behavior and challenges in adjusting constraints and performance goals in real-time.
Innovation Solution
The implementation of a hybrid controller that combines dynamic components and learned system models, along with a governing controller to monitor and adjust the hybrid controller's parameters, such as constraints, dynamic system parameters, and learning rates, to ensure optimal performance and adapt to changing conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a hybrid controller combining dynamic components and learned system models is used, then control performance under normal conditions is improved, but the controller exhibits suboptimal behavior when the system or environment differs significantly from training conditions
Solution Approach 1:
The patent implements a governing controller that dynamically adjusts the hybrid controller's parameters (constraints, dynamic system parameters, learning rates) based on real-time performance monitoring. This allows the controller to adapt its behavior when operating conditions change, resolving the contradiction between maintaining reliable control performance and adapting to new conditions.
Solution Approach 2:
The governing controller continuously monitors the hybrid controller's performance and uses this feedback to adjust parameters and generate control inputs. This closed-loop feedback mechanism enables the system to detect when performance degrades due to changing conditions and automatically correct for it, maintaining both reliability and adaptability.
2Adaptability or versatility
If the learned system model is updated frequently to adapt to new conditions, then adaptability is improved, but computational resources and time are consumed
Solution Approach 1:
The governing controller adjusts the learning rate parameter periodically or based on performance thresholds rather than continuously updating the learned system model. This periodic update strategy maintains adaptability while reducing computational overhead and time loss compared to continuous updates.
Solution Approach 2:
The governing controller modifies parameters of the hybrid controller (including learning rates, constraints, and dynamic parameters) rather than completely retraining the learned system model. These parameter adjustments enable adaptation to new conditions with minimal computational resources and time, avoiding the expensive process of full model retraining.
3Productivity
If the governing controller continuously monitors and adjusts parameters, then performance optimization is improved, but device complexity increases
Solution Approach 1:
The control system is segmented into two distinct components: a hybrid controller for primary control functions and a governing controller for parameter adjustment. This segmentation allows each component to specialize in specific tasks, improving overall performance optimization while maintaining manageable complexity through clear functional separation.
Solution Approach 2:
The governing controller serves multiple functions: monitoring performance, detecting degradation, adjusting parameters, and generating control inputs. This multi-functionality consolidates what could be multiple separate systems into a single component, improving performance optimization without proportionally increasing device complexity.
Data Source
Figure 1A
Figure 1B
Figure 2
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.