A Novel High-Gain Dual Active Bridge to Semi-Half-Bridge Converter Approach with Advanced Control for Improving Fast Charging Efficiency in Electric Vehicles

Electric Vehicles (EVs) support sustainable transportation by utilizing battery power to reduce emissions and fossil fuel consumption. Fast charging infrastructure enables quick energy transfer but poses challenges like high power demand, grid stability, and thermal safety. This manuscript presents a novel high-gain Dual Active Bridge (DAB)-Semi Half Bridge (SHB) converter with advanced control techniques to enhance fast charging efficiency in electric vehicles by improving voltage conversion, optimizing power flow, and ensuring stable system performance. The proposed method is the Banyan Tree Growth Optimization (BTGO) and Quantum Self-Attention Neural Network (QSANN), named as BTGO-QSANN. BTGO used for optimal scheduling of EV charging and QSANN for precise predictions of EV charging requirements. The primary objective of the proposed method is to enhance fast charging efficiency and voltage gain in electric vehicles by minimizing Total Harmonic Distortion (THD) and improving charging system stability. The proposed method is implemented utilizing MATLAB to evaluate its performance and is compared with existing methods like the Dragonfly Algorithm (DA), Neighborhood Attraction Firefly Algorithm (NFNA), and Deep Q-Network (DQN). Compared to conventional methods, the proposed BTGO-QSANN method enhances convergence speed, minimizes THD, and improves voltage gain stability under dynamic load conditions. The originality of this work lies in the BTGO-QSANN method for DAB-SHB fast charging control enabling superior performance in terms of efficiency, reduced harmonics, and fast transient response. Hence, the proposed method based charging control provides robust and computationally efficient solution for high-performance EV charging applications.