Battery state of health estimation under fast charging via deep transfer learning.

Journal: iScience
Published Date:

Abstract

Accurate state of health (SOH) estimation is essential for effective lithium-ion battery management, particularly under fast-charging conditions with a constrained voltage window. This study proposes a hybrid deep neural network (DNN) learning model to improve SOH prediction. With approximately 22,000 parameters, the model effectively estimates battery capacity by combining local feature extraction (convolutional neural networks [CNNs]) and global dependency analysis (self-attention). The model was validated on 222 lithium iron phosphate (LFP) batteries, encompassing 146,074 cycles, with limited data availability in a state of charge (SOC) range of 80%-97%. Trained on fast-charging protocols (3.6C-8C charge, 4C discharge), it demonstrates high predictive accuracy, achieving a mean absolute percentage error (MAPE) of 3.89 mAh, a root-mean-square error (RMSE) of 4.79 mAh, and a coefficient of determination (R) of 0.97. By integrating local and global analysis, this approach significantly enhances battery aging detection under fast-charging conditions, demonstrating strong potential for battery health management systems.

Authors

  • Jingyuan Zhao
    Institute of Transportation Studies, University of California, Davis, Davis, CA 95616, USA.
  • Di Li
    Department of Urology, General Hospital of the Air Force, PLA, No. 30 Fucheng Road Haidian District, Beijing, 100142 China.
  • Yuqi Li
    Department of Urology, Affiliated Hospital of Southwest Medical University, Luzhou, Sichuan 646000, China; Public Center of Experimental Technology, Southwest Medical University, Luzhou, Sichuan 646000, China.
  • Dapai Shi
    Hubei Longzhong Laboratory, Hubei University of Arts and Science, Xiangyang 441000, China.
  • Jinrui Nan
    Shenzhen Automotive Research Institute, Beijing Institute of Technology, Shenzhen 518000, China.
  • Andrew F Burke
    Institute of Transportation Studies, University of California, Davis, Davis, CA 95616, USA.

Keywords

No keywords available for this article.