Nonlinear adaptive internal model control using neural networks for tilt rotor aircraft platform

Abstract

An adaptive internal model controller using neural networks is designed for a tilt rotor aircraft platform. The behavior of the research platform, in certain aspects, resembles that of a tilt rotor aircraft. The proposed control architecture can alleviate the requirement of extensive gain scheduling of tilt rotor aircraft and compensate external disturbances, as well as dynamic inversion error. The controller includes an online learning neural network of inverse model and an offline trained neural network of forward model. Lyapunov stability analysis guarantees tracking errors and network parameters are bounded. The performance of the controller is demonstrated using the tilt rotor aircraft platform, with consistent response outcomes throughout experimental performing, including two nacelles tilting flight.