Adaptive learning based fault tolerant control for uncertain nonlinear systems

Abstract

This paper introduces a fault tolerant controller design for nonlinear unknown systems with multiple actuators and bounded disturbance. The controller consists of an adaptive learning-based control law and a switching function mechanism. The adaptive control law is implemented by a two-layer neural network and the switching function is designed to automatically search for the correct switching vector to turn off the unknown faulty actuator if there is any. The stability of the system output under the occurrence of actuator failure is proved through standard Lyapunov approach, while the other signals are guaranteed to be bounded. The theoretical result is substantiated by a simulation example with a continuous stirred tank reactor.