Adaptive Neural Network Finite-Time Fault-Tolerant Control of Fixed-Wing UAV Under State Constraints and Actuator Fault

In this paper, an adaptive neural network finite-time fault-tolerant control scheme is proposed for a fixed-wing UAV under state constraints and actuator fault. To build a state-constraint model, the inertial position dynamics are first formulated to compact model. A Butterworth low-pass filter is introduced to solve the algebraic loop involved by control input. Moreover, the lumped unknown nonlinearities inherent in the UAV system, actuator fault, external disturbances, and approximation errors are respectively identified by utilizing neural network and nonlinear disturbance observer. Furthermore, a barrier Lyapunov function is used to constrain the states of the UAV and verify the finite-time stability of the designed control scheme. Eventually, the effectiveness is demonstrated by simulation results.