Hybrid RNN-GA Controller for ALS in Wind Shear Condition

Abstract

The automatic landing system of an aircraft is enabled only under limited conditions. If severe wind shear is encountered, the pilot must handle the aircraft based on the limits of the automatic landing system. The purpose of this study is to investigate the use of a recurrent neural network (RNN) controller with a genetic algorithm (GA) in aircraft automatic landing control and to make automatic landing systems more intelligent. Current flight control law is adopted in the intelligent design. Tracking performance and adaptive capability are demonstrated through software simulation. The proposed intelligent controller can act as an experienced pilot and guide the aircraft to a safe landing in severe wind shear environment.