Design of Neurofuzzy Self Tuning PID Controller for Antilock Braking Systems

Abstract

In this paper, a Neurofuzzy self tuning PID controller for wheel slip ratio control has been designed based on a quarter vehicle model. The proposed control structure consists of a Neurofuzzy controller and conventional PID controller, which has self tuning capabilities. The parameters of the PID controller (Kp, Kd and Ki) can be self-tuned on-line with the output of the system under control. Variations in the values of weight, the friction coefficient of the road, road inclination and other nonlinear dynamic parameters may highly affect the performance of the Antilock Braking Systems (ABS). The conventional PID controller with fixed parameters cannot overcome these effects; therefore, the PID controller with adaptable parameters has been used. The paper develops a self tuning PID control scheme with application to ABS via combinations of fuzzy logic systems and neural networks. The performance of the Neurofuzzy self tuning PID controller based ABS is demonstrated by simulation for different road conditions: Snowy road, Wet asphalt, Dry asphalt; and transitions between such conditions, e.g. when emergency braking occurs and the road switches from snowy to wet. Robustness against road conditions is examined via numerically test results of the ABS controlled by proposed scheme are compared with the results of the ABS controlled by optimal PID controller. Simulation results show good performance of the proposed controller.