Neural network path-tracking and real-time multi-task flight simulation for the automatic transition of tilt-rotor aircraft

The purpose of this research is to accomplish the neural network path-tracking and real-time multi-task flight simulation for the automatic transition of tilt-rotor aircraft. For the highly instability of the system during the period of the dynamic transition maneuver, it is necessary to design a neural network control system to stabilize the unstable aircraft and accomplish the desired path tracking for the VTOL (Vertical Take-Off and Landing) transition flight. First, we simulate and validate the aerodynamic force and control law with Matlab. Secondly, the VTOL flight control system is designed and simulated with the back-propagation neural network path-tracking methodology and the tracking performance has been validated from the flight dynamic behavior. Finally, we set up a real-time multi-task flight simulation system to simulate and validate the system dynamic behavior of the tilt-rotor aircraft.