Reconfigurable tolerant control of nonlinear Euler–Lagrange systems under actuator fault: A reinforcement learning-based fixed-time approach

This paper presents a novel fixed-time adaptive Fault Tolerant Control (FTC) framework for MIMO nonlinear Euler-Lagrange systems using sliding mode-based strategy, reinforcement learning (RL) and fixed-time disturbance observer. The primary objective is to enhance system reliability in the presence of actuator faults, uncertainties and disturbances. The proposed RL algorithm incorporates an actor-critic neural network (NN), where the actor NN estimates the uncertainty and the critic NN evaluates the performance cost function. Additionally, a fixed-time adaptive observer is designed to estimate the lumped term of faults and disturbances. To achieve high precision trajectory tracking within a fixed-time interval, a nonsingular fast terminal sliding mode scheme is designed. This scheme ensures fixed-time convergence of the tracking error and facilitates disturbance attenuation and fault mitigation, which are key features of the proposed fixed-time secure control strategy. Furthermore, the closed-loop system's fixed-time stability is analyzed using Lyapunov theory. Experimental results demonstrate the effectiveness of the proposed FTC framework in mitigating the adverse effects of faults, uncertainties and disturbances, thereby enhancing system performance and reliability.