A Self-Improved Optimization-Based Artificial Neural Network Model for WPT System for Electric Vehicle Charging

Engineering notes

Key topics: autonomous driving. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

Recently, research and development actions have been ongoing to overwhelm the issues with Electric Vehicle (EV) battery systems and long-distance driving limits. EV charging stations can be configured as wired and wireless, and their availability is growing. The EV parking spaces are designated for wired power transmissions where the batteries may be charged. The potential of electric sparks or other hazards makes wired charging of EVs unacceptable. Advancements in Wireless Power Transfer (WPT) in EVs demonstrate the capacity to transfer considerable power across short and mid-range distances. The main objective of this study is to predict the efficiency of the EV wireless charging technique. The accuracy of the WPT model in EV charging is increased in this research using the Self-improved Aquila Optimization Algorithm (SI-AOA) based Artificial Neural Network (ANN) model. The SI-AOA method is an enhanced version of the Aquila Optimization Algorithm (AOA), which is used to determine the weights of the ANN classifier most effectively. This strategy is suggested since it is efficient and time-saving. MATLAB/Simulink is used to model the suggested work, and simulation results are presented. In order to ensure the effectiveness of the envisaged approach, the results produced by the suggested model are compared to the results acquired by conventional methods in terms of error metrics.

Links and sources

• Official / arXiv page

Comments