Wind Disturbances Encountered during Controlled Landings Using Neural Network Approaches

Abstract

Neural network applications to aircraft automatic landing control are presented. The automatic landing system of an airplane is enabled only under limited conditions. If severe wind disturbances are encountered, the pilot must handle the aircraft due to the limits of the automatic landing system. This paper presents four different neural network controllers to improve the performance of conventional automatic landing systems based on a linearized control law. The neural network controllers can act as an experienced pilot and guide the aircraft to a safe landing in severe wind disturbance environments. Simulation results show that the neural network controller can be used to successfully replace the conventional autolander.