Intelligent Hybrid Control System Design for Antilock Braking Systems Using Self-Organizing Function-Link Fuzzy Cerebellar Model Articulation Controller

Abstract

An antilock braking system (ABS) is designed to maximize wheel traction by preventing the wheels from locking during braking, while also maintaining an adequate ability to steer the vehicle. However, the performance of ABS is often degraded under harsh road conditions. In this paper, a self-organizing function-link fuzzy cerebellar model articulation controller (SOFFC) is proposed and is used as the uncertainty observer of the ABS. The self-organizing approach automatically generates and prunes the fuzzy rules for the SOFFC, without the need for preliminary knowledge. The learning algorithms not only extract the fuzzy rules for the SOFFC, but adjust the parameters of the SOFFC as well. A hybrid control system, composing a computational controller and a hyperbolic tangent compensator (HTC), is then proposed for the ABS. The computational controller, which contains an SOFFC uncertainty observer, forms the principal controller, and the HTC is used to compensate for the estimation uncertainty, in order to achieve ultimately bounded stability in the system. Finally, simulations are performed that demonstrate the effectiveness of the proposed hybrid control system in an ABS under various road conditions.