Enhanced Isolated Bidirectional Resonant DC-DC Converter with Artificial Neural Network Control for Electric Vehicle Onboard Chargers

This paper presents a comprehensive study on a bidirectional CLLL (Coupled-Inductor and Capacitor, and Low-Loss) DC-DC converter for the electric vehicle (EV) onboard charger, augmented with the artificial neural network (ANN) optimization approach. The key contribution of this study lies in the integration of an artificial neural network to optimize the converter's performance. The ANN is trained using a dataset generated through simulations and experiments, capturing the intricate relationships between converter parameters and performance metrics. Levenberg-Marquardt algorithm, known for its efficiency in optimizing complex nonlinear systems, is employed for training the neural network. The results imply valuable in-sights into the performance of the converter and offer superiority over existing studies in terms of step response characteristics.