Skip to content

Robust reinforcement learning fault diagnosis for complex data-driven nonlinear systems

Jul 2026 · International Journal of Dynamics and Control · Vol 14 · 1 citation · 38 references

TL;DR

Improvements of 13% under normal conditions and 17% in the presence of system noise achieved by the proposed approach, compared to integer-order difference (IOD)-RL are demonstrated.

View source

Similar papers

Aug 2026

Reinforcement learning based fault-tolerant control for rate gyro sensor faults in high-performance aircraft

A study on fault-tolerant control (FTC) design based on RL techniques for a high-performance aircraft to address the faults in angular velocity sensors, and results show that the proposed control system significantly improves the aircraft’s stability and handling under various maneuvers.

Modar Abbas, Seyed Hossein Sadati, Mostafa Khazaee · 0 citations
Open access Aug 2026

Observer-based adaptive neural event-triggered control for nonlinear systems with multiple constraints and multiple faults

For nonlinear constrained systems with sensor and actuator faults (SAFs), a neural network-based adaptive event-triggered controller is proposed. Nonlinearities and SAFs commonly occur in actual engineering plants, which can lead to system instability, and severely degrade control performance. The state observer with a...

Zhenjie Gao, Dong-Juan Li · 0 citations
Conference Aug 2026

Optimal Iterative Learning-Based Fault-Tolerant Control for Vehicle-Manipulator Systems with Actuator Failures

This study investigates a novel neuroadaptive faulttolerant control (FTC) strategy for vehicle-manipulator systems operating under simultaneous actuator faults and uncertain external disturbances. The proposed framework integrates an optimal iterative control policy with extreme learning machine (ELM)-based neural esti...

Yong-Kang Hou, Hong-Tao He, Jun-Hao Xu et al. · 0 citations
Sep 2026

Event-Triggered Self-Learning Parallel Tracking Control for Continuous-Time Nonlinear Systems With Actuator Faults.

This article explores an event-triggered self-learning parallel tracking control strategy for continuous-time nonlinear systems with actuator faults. To mitigate the impact of actuator faults, an enhanced performance index function is developed based on the unknown upper bound of such faults. Furthermore, an augmented...

Wen-Di Chen, Q. Wei, Shan-Shan Jiao et al. · 0 citations
Open access Aug 2026

Validation of Neural Network Controllers for Uncertain Systems Using the Keep‐Close Approach: Robustness Analysis and Safety Verification

The safety verification of neural network (NN) controllers operating in uncertain environments characterized by unmodeled dynamics, nonlinearities, and time delays remains a fundamental challenge in robust control analysis. This article introduces a novel method, termed Keep‐Close , for analyzing the performance...

Abdelhafid Zenati, Nabil Aouf · 0 citations
Sep 2026

Robust data-induced learning control for uncertain nonlinear systems via dual-timescale adaptation.

In addressing the challenge of achieving precise tracking control for uncertain nonlinear systems under complex disturbances, this paper proposes a Robust Data-induced Learning Control (R-DiLC) framework. The R-DiLC introduces a dual-timescale adaptation mechanism that effectively compensates for both iteration-invaria...

Chang-Xin Lu, De-Yuan Meng, Jing-Yao Zhang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.