Neural Network-Based Adaptive Feedback Linearization Control of Antilock Braking System

Abstract

Safety systems in road vehicles are categorised into two main types: passive and active systems. The antilock braking system (ABS) is an active safety system in road vehicles, which senses the slip value between the tyre and the road and uses these values to determine the optimum braking force. Due to the high non-linearity of the tyre and road interaction, and uncertainties from vehicle dynamics, standard control methods: like PID, sliding mode control and feedback linearization will not suffice. This paper, therefore proposes a neural network-based feedback linearization control design method. The experimental results reveal that slip regulation using neural network-based control scheme is feasible for different slip values (road conditions) and robust to external disturbances.