Intelligent Adaptive Electric Vehicle Motion Control for Dynamic Wireless Charging
Abstract
Dynamic wireless charging (DWC) is an emerging technology designed to enable electric vehicles (EVs) to be wirelessly charged while in motion. It is gaining significant momentum as it can potentially address the limited range problem for EVs. However, due to the significant power loss caused by wireless power transfer, improving the charging efficiency remains as a major challenge. This paper presents the first Long Short-Term Memory (LSTM)-based EV motion control system for DWC with an aim to maximize the charging efficiency. The dynamics of the electromagnetic field generated from the transmitter coils of a DWC system are effectively captured using a machine-learning approach based on the multi-layer LSTM. The multi-layer LSTM model is used to predict the location where the electromagnetic strength is expected to be maximal and to control the lateral position of EV accordingly to optimize the charging efficiency. Extensive simulations were conducted to demonstrate that our LSTM-based EV motion control system achieves by up to 174% higher charging efficiency compared with existing vehicle motion control systems focused on keeping an EV in the center of the lane.
Publication Title
IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Recommended Citation
Das, L., Dasgupta, D., & Won, M. (2023). Intelligent Adaptive Electric Vehicle Motion Control for Dynamic Wireless Charging. IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2734-2741. https://doi.org/10.1109/ITSC57777.2023.10422064
