Functional Link Neural Network for Wide Load Operation of Bidirectional Onboard Charging System of E-Rickshaw

Abstract

This article investigates the functional link neural network assisted deadbeat predictive current control for an onboard charger (OBC) of an e-rickshaw with multistep charging capability. This control algorithm is presented for wide load operation of OBC since a multistep charging scheme is introduced to reduce the electricity consumption by OBC in the course of the peak load hours. The presented grid-connected OBC topology has two stages interconnected with the dc link capacitor. The first stage is a front-end converter to regulate the voltage at the dc link capacitor. Moreover, it regulates the power quality within the IEEE-519 standard. Furthermore, a dc–dc converter to regulate the charging current is the second stage of the OBC. Keeping this in view, a bidirectional interleaved isolated single ended primary inductor converter (SEPIC) converter topology is utilized. To analyze the performance of the OBC under distinct operating conditions such as grid voltage variations, an experimental prototype of the bidirectional OBC, is developed. Furthermore, the efficacy of the bidirectional operation of the designed system is analyzed through the vehicle to grid operation.