Neural Sliding mode control of a regenerative braking system for electric vehicles

Abstract

This paper summarizes the work done on the development of a Neural Sliding Mode Controller (NSMC) for a regenerative braking system used in an electric vehicle (EV), which is composed of a Main Energy System (MES) and an Auxiliary Energy System (AES). This last one contains a buck-boost converter and a super-capacitor. The AES aims to recover the energy generated during braking that the MES cannot retrieve and use later during acceleration. A neural identifier trained with the Extended Kalman Filter (EKF) has been used to estimate the buck-boost converter real dynamics and to build up the NSMC, which is implemented to regulate the voltage and current dynamics in the AES. Simulation results, illustrate the effectiveness of the proposed control scheme to track time-varying references of the AES voltage and current dynamics measured at the buck-boost converter and ensure the charging and discharging operation modes of the super-capacitor. In addition, the proposed control scheme enhances the EV storage system efficiency and performance, when the regenerative braking system is employed.