Finite-Time Fractional-Order Neural Adaptive Fault-Tolerant Control of High-Speed UAV with Redundant Second-Order Actuators

To address the safety control problem of high-speed unmanned aerial vehicle (UAV) with redundant actuators, this paper investigates the finite-time fault-tolerant control scheme of high-speed UAV under actuator faults. In the proposed scheme, tracking errors are transformed by a proportional-integral-derivative (PID) filter. Then, a composite learning algorithm with neural network and finite-time disturbance observer is used to estimate the transform errors and external disturbances. Considering the second-order actuator dynamics, the virtual control variable and the fault-tolerant control law are designed by using the fractional-order (FO) sliding mode control (SMC) strategy. The adaptive neural network is used to estimate the unknown term induced by model uncertainties. Furthermore, by using the Lyapunov stability analysis, it is shown that UAV can track the desired attitudes and the tracking errors are finite-time convergent. Finally, simulation results are presented to show the effectiveness of the proposed control scheme.