Composite neural learning-based adaptive actuator failure compensation control for full-state constrained autonomous surface vehicle

Abstract

This article studies composite neural learning-based adaptive failure compensation control issues for the autonomous surface vehicle with full-state constraints. Initially, the control strategy solve the problems of computational complexity and state constraints and eliminate the negative effect of filter error on tracking performance by integrating with the command-filtered backstepping technique and barrier Lyapunov functions. Then, a composite neural learning framework is established, where the effect caused by approximation error on tracking accuracy can be efficiently reduced by constructing the serial-parallel estimation model to obtain the estimations of the system states. Furthermore, an adaptive resilient trajectory tracking controller is designed, which can ensure that all the signals of the closed-loop system are semi-globally uniformly ultimately bounded satisfying the preset constraints even if the expected actuator faults occur suddenly. Finally, the feasibility and superiority of the designed control strategy are clarified by simulation results.