Neural network-based adaptive fault tolerant tracking control for unmanned autonomous helicopters with prescribed performance

In this paper, the issue of prescribed performance-based fault tolerant control is investigated for the medium-scale unmanned autonomous helicopter with external disturbance, system uncertainty and actuator fault. The altitude and attitude combination unmanned autonomous helicopter model is established. An error transformation function is proposed to guarantee that the tracking error satisfies the prescribed performance. The parameter adaptation method is adopted to handle the external unknown disturbance and the radial basis function neural networks are employed to approximate the interaction functions including the system uncertainty. The auxiliary system is introduced to weaken the effect of actuator fault, which can effectively avoid the singularity. Based on the backstepping control technology, an adaptive neural fault tolerant control scheme is developed to ensure the boundness of all closed-loop system signals and the specified tracking error performance. Simulation studies on the medium-scale unmanned autonomous helicopter are performed to demonstrate the efficiency of the designed control strategy.