Transition flight control using adaptive neutral network dynamic inversion for Canard Rotor/Wing UAV

The problem of designing transition flight controller via improved adaptive neural network dynamic inversion for Canard Rotor/Wing (CRW) UAV is studied. The transition control strategy from rotary-wing mode to fixed-wing mode is derived according to the flight characteristic analysis. The controller is composed of trajectory outer-loop and attitude inner-loop. The dynamic inversion method is used to design these loops. In addition, the angular rate error equations with proportional-integral desired dynamics are used to design the adaptive update law for compensating the system model error. The main advantage of this approach is its ability of the fast adaptation that leads to good steady and transient performance as well as simple design process. The longitudinal nonlinear dynamic simulations show that this approach improves the stability and transient response of attitude angle and achieves the transition flight control of the CRW UAV successfully.