Wheel-slip estimation for advanced braking controllers in aircraft: Model based vs. black-box approaches

As of today, most aircraft are endowed with Anti-lock Braking Systems that are active during landings and rejected take-off manoeuvres, ensuring the maximum exploitation of road-friction capability. Due to strict certification issues, the braking controller must function using only signals that are local to the landing gear, which is the aircraft sub-system hosting the braking actuators. In the most common scenarios, the only available signals are the wheel speed and the braking pressure. This limited set of information prevents the use of advanced braking control architectures which are now mainstream in the automotive sector, i.e., those based on the regulation of the wheel slip, so that typical aircraft Anti-lock Braking Systems are usually based on the regulation of the wheel deceleration. This paper investigates how a reliable wheel slip estimation can be achieved using wheel speed and braking pressure signals, analysing different wheel slip observers options. In particular, a model-based approach that uses a sliding-mode observer is proposed, together with a black-box approach based on Nonlinear Auto-Regressive models with eXogenous input, with a neural network implementation. Both approaches are tested and compared on experimental data, proving that the obtained estimation performance are adequate for use in closed-loop braking systems.