Neural networks-based adaptive fault-tolerant control for stochastic nonlinear systems with unknown backlash-like hysteresis and actuator faults

This paper addresses a class of nonstrict-feedback stochastic nonlinear systems. It addresses the impact of backlash-like hysteresis as well as actuator faults simultaneously. Radial basis function neural networks (RBFNNs) are used specifically to approximate unknown nonlinear functions. Furthermore, a backstepping approach is used to design a neural network-based adaptive fault-tolerant controller for the system. The suggested control methodology compensates effectively for the negative impacts of actuator faults and backlash-like hysteresis. Based on the Lyapunov stability theory, the proposed controller ensures that all closed-loop system signals are semi-globally uniformly ultimately bounded (SGUUB) and the system output tracks the reference signal with bounded tracking error. Furthermore, a numerical example and a real-world example of a single-link manipulator demonstrated the effectiveness of the proposed method.