Neural-network estimators based fault-tolerant tracking control for AUV via ADP with rudders faults and ocean current disturbance

Abstract

This paper investigates fault-tolerant tracking control problem for autonomous underwater vehicle (AUV) with rudders faults and ocean current disturbance. The adaptive dynamic programming (ADP) method is adopted to transform the fault-tolerant tracking control problem into an optimal control problem. Two neural-network estimators (NNEs) are designed to estimate rudders faults and ocean current disturbance respectively. The estimated rudders faults and the estimated ocean current disturbance are utilized to construct the performance index function. By using policy iteration (PI), critic neural network and action neural network are constructed to solve the Hamilton-Jacobi-Bellman (HJB) equation. The error tracking system of AUV is guaranteed to be uniformly ultimately bounded (UUB) based on the Lyapunov stability theorem. Simulation results are given to verify the effectiveness of the control scheme proposed in this paper.