Robust control of wheel slip in anti-lock brake system of automobiles

Abstract

In this paper, performances of two model-free control systems including Fuzzy Logic Control (FLC) and Neural Predictive Control (NPC) on tracking performance of wheel-slip in Anti-lock Braking System (ABS) are compared. As an accurate and control oriented model, a half vehicle model is developed to generate extensive simulation data of the braking system. Brake system identification is preformed through a Perceptron neural networks model of brake system which is trained with offline data by Gradient Descent Back Propagation (GDBP) algorithm. In order to reduce the time cost of the calculations and improving the robustness of closed loop control system, an online Perceptron neural network adaptively generates the optimum control actions. By a comparative simulation analysis it is shown that the NPC system has a better tracking performance, shorter stopping time and distance than the FLC controllers. The robustness of the proposed control systems are evaluated under ±25 % uncertainty. It is shown that the NPC system is more robust against both exogenous disturbances and modeling uncertainties than the FLC system.