Adaptive Neural Fault-Tolerant Control for Nonlinear System With Multiple Faults and Dead Zone

In this paper, a novel adaptive neural fault-tolerant control scheme is proposed for uncertain large nonlinear systems with sensor, actuator faults and dead zone. Due to the fault of the sensor, the actual state and the fault parameters are coupled, and a fault parameter separation method is designed for decoupling. The radial basis function neural network (RBFNN) is used to approximate the unknown interconnection functions in nonlinear systems, and combining the RBFNN and backstepping technology, an adaptive neural fault-tolerant controller is designed for nonlinear large-scale systems through ordinary Lyapunov function. The stability of the closed-loop system is verified by Lyapunov analysis, and obtained satisfactory tracking performance under the comprehensive influence of sensor, actuator faults and dead zone. Finally, the effectiveness of the proposed adaptive neural fault-tolerant control is illustrated by simulation of large-scale wind farm system.