Scholarlink

First, this paper proposes a data repair method based on Generative Adversarial Networks (GANs) to address poor data quality in vehicle-cloud collaborative environments. Then, this paper predict heavy-duty trucks’ battery swapping probability with a Dynamic Bayesian Network (DBN) model, containing six critical features extracted from daily battery-swapping operations in QiYuan Green Power Co., Ltd. Finally, an empirical analysis is conducted using a dataset of 90 battery-swapping stations and 1,660 heavy-duty trucks over 6 days. The result shows that the model achieves an average accuracy of approximately 80% for predicting battery-swapping within 2 h, with 6 stations exceeding 90% accuracy.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Short-Term Battery Swapping Prediction of Heavy-Duty Trucks Based on Generative Adversarial Networks and Dynamic Bayesian Networks

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Bo Ma,
  • Fei Gao,
  • Liuqin Cai,
  • Yan Li,
  • Lifang Liu,
  • Peng Guo

摘要

First, this paper proposes a data repair method based on Generative Adversarial Networks (GANs) to address poor data quality in vehicle-cloud collaborative environments. Then, this paper predict heavy-duty trucks’ battery swapping probability with a Dynamic Bayesian Network (DBN) model, containing six critical features extracted from daily battery-swapping operations in QiYuan Green Power Co., Ltd. Finally, an empirical analysis is conducted using a dataset of 90 battery-swapping stations and 1,660 heavy-duty trucks over 6 days. The result shows that the model achieves an average accuracy of approximately 80% for predicting battery-swapping within 2 h, with 6 stations exceeding 90% accuracy.