Neural-network-identification-based adaptive control of wing rock motions

Abstract

The proposed control system comprises a computation controller and a tracking controller. The computation controller containing a recurrent neural network identifier is the principal controller, and the tracking controller is designed to achieve L-2 tracking performance with a desired attenuation level. To investigate the effectiveness of the proposed control system the design methodology is used to control a wing rock motion, manifested by a limit-cycle oscillation predominantly for an aircraft operating at subsonic speeds and high angles of attack. Simulation results demonstrate that the proposed control system can achieve favourable tracking performance for the wing rock motion.