SOC Estimation of Li-ion Batteries With Learning Rate-Optimized Deep Fully Convolutional Network

Mahammad A. Hannan, Dickson N. T. How, Molla S. Hossain Lipu, Pin Jern Ker, Zhao Yang Dong, Muhamad Manur, Frede Blaabjerg

Research output: Contribution to journalLetterpeer-review

89 Citations (Scopus)
288 Downloads (Pure)

Abstract

In this letter, we train deep learning (DL) models to estimate the state-of-charge (SOC) of lithium-ion (Li-ion) battery directly from voltage, current, and battery temperature values. The deep fully convolutional network model is proposed for its novel architecture with learning rate optimization strategies. The proposed model is capable of estimating SOC at constant and varying ambient temperature on different drive cycles without having to be retrained. The model also outperformed other commonly used DL models such as the LSTM, GRU, and CNN on an open source Li-ion battery dataset. The model achieves 0.85% root mean squared error (RMSE) and 0.7% mean absolute error (MAE) at 25 °C and 2.0% RMSE and 1.55% MAE at varying ambient temperature (-20-25 °C).
Original languageEnglish
Article number9276459
JournalI E E E Transactions on Power Electronics
Volume36
Issue number7
Pages (from-to)7349-7353
Number of pages5
ISSN0885-8993
DOIs
Publication statusPublished - Jul 2021

Keywords

  • CNN
  • convolutional neural network
  • deep learning
  • fully convolutional network (FCN)
  • lithium-ion (Li-ion) battery
  • state-of-charge (SOC)

Fingerprint

Dive into the research topics of 'SOC Estimation of Li-ion Batteries With Learning Rate-Optimized Deep Fully Convolutional Network'. Together they form a unique fingerprint.

Cite this