COVID-based controller: Enhancing automotive safety with a neuroadaptive beta-function optimization for anti-lock braking systems

Abstract

Controlling wheel slip during braking in vehicle tires is a challenging task due to the complex behavior and highly nonlinear dynamics involved. Uncertainties arising from parameter variations and un-modeled dynamics further complicate the control process, along with actuator saturation. This article introduces a novel approach for controlling vehicle antilock braking systems (VABSs) using a robust adaptive (RA) beta basis function (BBF) neural network (NN) framework. The BBF-NN is capable of approximating complex functions and is employed as both an online approximator for unknown nonlinear functions and an actuator saturation compensator. This framework addresses the challenges posed by undefined models, nonlinearity, and uncertainties associated with VABS. The BBF-NN is trained online and its stability is verified using the Lyapunov theory. The performance of the BBF-NN is greatly influenced by its parameter tuning. To address this, the Coronavirus disease optimization algorithm (COVIDOA) is employed to determine the constant parameters of the RA-BBF-NN. The optimization results demonstrate that COVIDOA outperforms other optimization algorithms. The hybrid RA-BBF-NN framework, optimized by COVIDOA, exhibits superior performance compared to alternative methods, as confirmed by the results.