Title: RBF NN observer based adaptive feedback control for the ABS system under parametric uncertainties and modelling errors
Authors: Ait Abbas Hamou; Rabhi Abdelhamid; Belkheiri Mohammed
Addresses: Laboratory of Materials and Durable Development-LM2D, Akli Mohand Oulhadj University-Bouira, Drissi Yahia Street, 10000, Bouira, Algeria ' Laboratory of Modeling Information and Systems, Jules Verne University-Picardie, 33 Saint Leu Street, 80000, Amiens, France ' Laboratory of Telecommunications Signals and Systems, Amar Telidji University – Laghouat, BP G37 Road of Ghardaia (03000 Laghouat), Algeria
Abstract: An antilock braking (ABS) scheme control is a relatively difficult task due to its uncertain nonlinear dynamics. According to the requirement that the braking process must be fast and robust, we contribute to extending the universal function approximation property of the radial-basis-function (RBF) neural network (NN) to design both: (a) adaptive NN observer to estimate the tracking error dynamics; and (b) intelligent NN output feedback controller (OFC) that will overcome successfully the existing high uncertainties. Notice that the OFC is introduced to linearise the ABS nonlinear system, and the dynamic compensator is involved to stabilise the linearised system. The estimated states are used in the adaptation laws as an error signal. Simulations of the proposed control algorithm based adaptive RBFNN observer are conducted then compared to the Bang-bang controller to demonstrate its practical potential. Furthermore, its efficiency has been successfully confirmed through a robustness test.
Keywords: antilock braking system; parametric variations; unmodelled dynamics; radial basis function neural network; adaptive observer; comparative study; robustness test; tracking error dynamics; intelligent neural network output feedback controller; high uncertainties; dynamic compensator; bang-bang controller.
International Journal of Modelling, Identification and Control, 2020 Vol.35 No.4, pp.316 - 326
Received: 29 Jan 2020
Accepted: 24 Jun 2020
Published online: 29 Apr 2021 *