An aircraft brake control algorithm with torque compensation based on RBF neural network

The wheel brake system of an aircraft is the key to ensure its safe landing and rejected takeoff. A wheel’s slip state is determined by the brake torque and ground adhesion torque, both of which have a large degree of uncertainty. It is this nature that brings upon the challenge of obtaining high deceleration rate for aircraft brake control. To overcome the disturbances caused by the above uncertainties, a braking control law is designed, which consists of two parts: runway surface recognition and wheel’s slip state tracking. In runway surface recognition, the identification rules balancing safety and braking efficiency are defined, and the actual identification process is realized through recursive least square method with forgetting factors. In slip state tracking, the LuGre model with parameter adaptation and a brake torque compensation method based on RBF neural network are proposed, and their convergence are proven. The effectiveness of our control law is verified through simulation and ground experiment. Especially in the experiments on the ground inertial test bench, compared to the improved pressure-biased-modulation (PBM) anti-skid algorithm, fewer wheel slips occur, and the average deceleration rate is increased by 5.78%, which makes it a control strategy with potential for engineering applications.