Robust Evolving Neuro-Fuzzy Control of a Novel Tilt-rotor Vertical Takeoff and Landing Aircraft

摘要

This paper presents the design of a robust evolving neuro-fuzzy output feedback control of a novel tilt-rotor vertical takeoff and landing (VTOL) aircraft. Detailed six degrees of freedom nonlinear model of the VTOL is presented. The asymmetry in the longitudinal centre of gravity position and the motor-propellers with diverse thrust and torque characteristics poses unique challenges for the control. The evolving neuro-fuzzy controller described here is called Parsimonious Autonomous Controller (PAC). PAC is based on model free design and is robust against system uncertainties and input disturbances. The effectiveness of the proposed controller is demonstrated through high fidelity numerical simulations for attitude and altitude control of the VTOL.