Scholarlink

Battery management systems depend on accurately determining the state of lithium-ion batteries. Lithium-ion battery health is predicted using deep neural networks, which offer prediction tiers according to accuracy. Our deep learning approach uses Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), a kind of recurrent neural network, to assess the condition of lithium-ion batteries. The LSTM model shows 99% accuracy and the suggested approach makes the potential substitute for real-world applications in various sectors that use battery-powered equipment.

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

Deep Neural Network Approach for Lithium-Ion Battery Health State Prediction and Remaining Useful Life Estimation

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Md. Abdul Ahad Rifat,
  • Niaz Ahmed,
  • Md. Bayzid Hassan,
  • Sudipta Podder,
  • Md. Shaharear Kabir Rabby,
  • K. M. Safin Kamal,
  • Ahmed Wasif Reza

摘要

Battery management systems depend on accurately determining the state of lithium-ion batteries. Lithium-ion battery health is predicted using deep neural networks, which offer prediction tiers according to accuracy. Our deep learning approach uses Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), a kind of recurrent neural network, to assess the condition of lithium-ion batteries. The LSTM model shows 99% accuracy and the suggested approach makes the potential substitute for real-world applications in various sectors that use battery-powered equipment.