Intelligent fuzzy controller design for antilock braking systems

Article type: Research Article

Authors: Le, Tien-Loc^{a; b; *}

Affiliations: [a] Department of Electrical Engineering, Yuan Ze University, Chung-Li, Taoyuan, Taiwan, R.O.C. | [b] Department of Electrical Electronic and Mechanical Engineering, Lac Hong University, Bien Hoa, Vietnam

Correspondence: [*] Corresponding author. Tien-Loc Le. E-mail: tienloc@saturn.yzu.edu.tw.

Abstract:  This paper aims to design a self-evolving function-link type-2 fuzzy neural network for application in controlling antilock braking systems. In this control scheme, the self-evolving algorithm is applied to autonomously construct the control network without an initial rule-base. The function-link is designed to give the interval type-2 fuzzy neural network has more freedom in adjusting the parameters. Based on the steepest descent gradient method and the Lyapunov theory, the adaptive laws for the proposed system are derived, and the control system stability is guaranteed. Further, to rapidly achieve the desired control performance, an online particle swarm optimization algorithm is used to optimize the learning rates for the parameter adaptive laws. The performance of the control system is assessed via multiple simulation results of the antilock braking system response under various road conditions.

Keywords: Type-2 fuzzy logic system, particle swarm optimization, self-evolving learning algorithm, antilock braking systems

DOI: 10.3233/JIFS-181014

Journal: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 4, pp. 3303-3315, 2019