A Neural Network Approach to a Modified Quadratic Boost Multiport Resonant Converter for Electric Vehicle Chargers

TL;DR

This paper presents a neural network approach to optimize a modified quadratic boost multiport resonant converter, achieving high voltage gain and efficiency improvements for electric vehicle chargers.

Contribution

It introduces a novel converter topology combined with a neural network-based control strategy for enhanced performance in EV charging applications.

Findings

Achieves approximately three times voltage gain at nominal duty ratio

Reduces voltage and current stress on switches

Maximum efficiency reaches 96.7%

Abstract

This topology can achieve a high step-up gain by utilizing a switched capacitor and switched inductor-based VMC network arrangement.Furthermore, the proposed topology can achieve an output gain of approximately three times at a nominal duty ratio with reduced voltage and current stress across the switch, and enhance the maximum efficiency to 96.7