Scholarlink

In this present age, Electric Vehicles are highly dependent on Lithium-ion batteries as they have a vital role in the storage of energy. For maximum efficiency and long-term durability Battery Management Systems (BMS) are important. In the context of Battery Management System RUL has a significant role in maintaining the safe, reliable, and effective operation of the batteries. The three Machine learning techniques used for the predicting the Remaining Useful Life of the batteries are Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) And Random Forest (RF). This paper discusses different ML techniques, generation of synthetic data, comparison of different parameters in ML techniques and prediction of RUL.

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

Leveraging Synthetic Data and LSTM Networks for Reliable RUl Estimation of EV battery

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • S. Tresa Sangeetha,
  • Ayush Tiwari,
  • C. R. Amrutha Varshini,
  • Yeddula Poojitha,
  • K. Deepa

摘要

In this present age, Electric Vehicles are highly dependent on Lithium-ion batteries as they have a vital role in the storage of energy. For maximum efficiency and long-term durability Battery Management Systems (BMS) are important. In the context of Battery Management System RUL has a significant role in maintaining the safe, reliable, and effective operation of the batteries. The three Machine learning techniques used for the predicting the Remaining Useful Life of the batteries are Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) And Random Forest (RF). This paper discusses different ML techniques, generation of synthetic data, comparison of different parameters in ML techniques and prediction of RUL.