Optimization of Bang-of-Bang TS-Fuzzy Based via DARLA Technique for ABS System
Subject Areas : B. Computer Systems Organization
Nahid
Ebrahimi Meymand
1
(Electrical Engineering Department, Shahid Bahonar University of Kerman, Kerman ,Iran)
Aliakbar
Gharaveisi
2
(Electrical Engineering Department, Shahid Bahonar University of Kerman, Kerman ,Iran)
Keywords: Anti-lock Braking System (ABS), Discrete Action Reinforcement Learning Automata (DARLA), Fuzzy Controller,
Abstract :
Anti-lock Braking System (ABS) which is a nonlinear and time variant system may not be easily controlled by classic control methods. This is due to the fact that classic linear controllers are just capable of controlling a specific plant in small region of state space. To overcome this problem, a more powerful control technique must be employed for complex nonlinear plants. Fuzzy controllers are potential candidates for the control of such systems, while they have an intrinsic ability to control a complex set of dynamics like ABS in an appropriate wider region in the state space.This paper introduces a new zero order Takagi-Sugeno fuzzy controller. The input membership functions of the proposed controller have been optimized such that the ABS performance enhances over different braking situations. Simulation shows the effectiveness of the proposed controller under various road conditions. The optimization is done by using DARLA, a powerful heuristic technique.