Neural network based aircraft control

This paper presents a technique of landing control, roll control, pitch control and altitude hold control of an airplane using neural networks. Firstly the neural network is trained from available flight data and then that trained neural network controls the landing, roll, pitch and altitude hold of the airplane. The neural network control has been implemented in MATLAB and the data for training have been taken from Flight Gear Simulator. The neural network control has been simulated for commercial airplane i.e. Cessna 172 using the Flight Gear Simulator. The trained neural network control detects variations from the Flight Gear Simulator and supplies back the corrective signals to aileron, elevator, throttle, and rudder. The flight performance has been shown in the Flight Gear Simulator. The objective is to improve the performance of conventional landing, roll, pitch and altitude hold controllers. Simulated results show that control for different flight phases is successful and the neural network controllers provide the robustness to system parameter variation.