Performance Degradation Monitoring and Self‐Healing Control for Industrial Control Systems via Reinforcement Learning Aided Optimal Feedback Compensation
Authors:
- 4 June 2025
- journal article
- Published by Wiley in International Journal of Adaptive Control and Signal Processing
- Vol. 39 (9) , 1923-1936
Abstract
The control performance of the automation system significantly influences the reliability of industrial processes and product quality. This article focuses on developing an integrated architecture for monitoring control performance, and recovering from degradation in industrial control systems under abnormal operating conditions. Initially, an online performance evaluation matrix is identified, which demonstrates variations of control performance in dynamic processes. It is produced by parameterizing the performance value function using the recursive Bellman equation, and it provides more full‐dimensional data than standard scalar indicators. On this basis, a performance degradation detection method is proposed by measuring the deviation between the performance evaluation matrix identified in normal and abnormal conditions. Furthermore, a redundancy‐based self‐healing control approach using dynamic feedback compensation allows the closed‐loop system to recover from performance degradation without changing the predesigned controller. The control gain of the proposed self‐healing controller is obtained by model‐free reinforcement learning, avoiding the requirement for an accurate representation of complex industrial systems. Finally, the effectiveness of the proposed approach is verified by a benchmark study on the three‐tank system.Keywords
Funding Information
- National Natural Science Foundation of China (62373012)
- Fundamental Research Funds for the Central Universities (FRF‐EYIT‐23‐06)
This publication has 40 references indexed in Scilit:
- Fault diagnosis and self-healing for smart manufacturing: a reviewJournal of Intelligent Manufacturing, 2023
- A generalized proportional‐integral observer for fault detection: An approximate input disturbance decoupling approachInternational Journal of Adaptive Control and Signal Processing, 2023
- Performance based attack detection and security analysis for cyber‐physical systemsInternational Journal of Robust and Nonlinear Control, 2022
- Observer‐based single‐network incremental adaptive dynamic programming for fault‐tolerant control of nonlinear systems with actuator faultsInternational Journal of Adaptive Control and Signal Processing, 2022
- Control performance‐based fault detection and fault‐tolerant control schemes for a class of nonlinear systemsInternational Journal of Robust and Nonlinear Control, 2019
- A new interval diagnosis method: Application to the spacecraft rendezvous phase of the Mars sample return missionInternational Journal of Adaptive Control and Signal Processing, 2019
- Performance-based fault detection and fault-tolerant control for automatic control systemsAutomatica, 2019
- Self‐healing control architectures and design methodologies for linear parameter varying systemsInternational Journal of Robust and Nonlinear Control, 2015
- Control Performance Management in Industrial Automation2013
- Survey on data-driven industrial process monitoring and diagnosisAnnual Reviews in Control, 2012