Robust predictive control of wheel slip in antilock braking systems based on radial basis function neural network

Anti-Lock Braking System (ABS) is a well-known technology for vehicle safety enhancement during hard braking. The wheel slip control has been a challenging problem due to a complex behavior of the tire and strong nonlinearity in a braking process. Furthermore, the system is subjected to unknown uncertainties that would arise from changing the vehicle parameters and un-model dynamics. Thus, it is required to design a nonlinear robust control law for ABS to overcome these problems. In this paper, a novel robust prediction-based controller for ABS is proposed that guarantees the stability against uncertainties. An optimal control law is firstly designed for ABS using nonlinear predictive method. Then, the unknown uncertainties are adaptively approximated utilizing a radial basis function neural network (RBFNN). The Lyapunov approach is employed to develop an update control law to determine the network weights. Finally, some simulations are conducted to examine the performance of the proposed control system for tracking the reference wheel slip in the presence of uncertainties in different maneuvers. Also, the performance of the proposed controller is compared with the conventional sliding mode controller (SMC) through simulation results. (C) 2018 Elsevier B.V. All rights reserved.