Reconfigurable flight control for UAV with multiple control effectors based on neural network and dynamic inversion

A reconfigurable flight control based on a single hidden layer perception (SHL) neural network (NN) for adaptive compensation of dynamic inversion for the Unmanned Aerial Vehicle (UAV) with multiple control effectors is described. This approach has not to depend on failure identification and isolation. The basic control law is designed by nonlinear dynamic inversion, and SHL neural networks are used to eliminate the inversion error due to parameter uncertainty, disturbance, control effectors´ failure, etc. The simulation results indicate that SHL NN can eliminate the inversion error adaptively and properly, and this reconfigurable flight control method can improve the robustness of the system when the control effectors´ failure occurs.