A hybrid method for online cycle life prediction of lithium-ion batteries

Fu Kwun Wang*, Zemenu Endalamaw Amogne, Cheng Tseng, Jia Hong Chou

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

14 Scopus citations

Abstract

Many industrial applications use lithium-ion batteries, but lack of maintenance, harsh use environments, and poor charging operations accelerate their degradation. Therefore, online remaining useful lifetime (RUL) prediction is a hot research topic. The RUL estimation analysis of a battery can be based on the normalized capacity as the state of health of its cycle life. We propose a hybrid method based on a bidirectional long short-term memory model with an attention mechanism (BiLSTM-AM) model and a support vector regression (SVR) model for online cycle life prediction. Once the sensor collects temperature readings, it uses SVR to update the initial data online to obtain a multistep advance prediction of the temperature and then uses BiLSTM-AM to predict cycle life. The proposed model is verified using 12 lithium-ion phosphate/graphite cells, and the results show that the average RUL estimation error is 3.72%.

Original languageEnglish
Pages (from-to)9080-9096
Number of pages17
JournalInternational Journal of Energy Research
Volume46
Issue number7
DOIs
StatePublished - 10 06 2022
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2022 John Wiley & Sons Ltd.

Keywords

  • bidirectional long short-term memory with attention mechanism
  • lithium-ion battery
  • online cycle life prediction
  • support vector regression

Fingerprint

Dive into the research topics of 'A hybrid method for online cycle life prediction of lithium-ion batteries'. Together they form a unique fingerprint.

Cite this