Design of Electric Vehicle’s Wireless Power Transfer System Based on Deep Learning Combined With Multi-Objective Optimization

Abstract

During the wireless power transmission of an electric vehicle (EV), due to the influence of the compensation circuit’s manufacturing process, the driver’s operating technique, and other factors, the wireless power transfer (WPT) efficiency features strong uncertainty. The article chooses the coil group’s spatial parameters as well as the compensation circuit’s parameters as input variables, and then builds the deep learning network as the framework of uncertainty quantification, so as to obtain the relevant statistical characteristic parameters of WPT efficiency, through comparing with the calculation results of classical Monte Carlo (MC), it can be verified that the uncertainty quantification based on deep learning has almost the same solution accuracy and higher computational efficiency. At the same time, the article adopts tent chaotic mapping and adaptive inertia weight strategy to improve the traditional Aquila Optimization (AO) algorithm, then uses the improved multiobjective AO algorithm to accomplish the optimization of the WPT system’s structure. Through the comparison of improved AO and other optimization algorithms, it can be concluded that the improved AO can search out the optimal design parameter group with faster speed and higher accuracy, which provides effective guidance for the actual optimized design of the EVs WPT system.