Skip to main content

Research Repository

Advanced Search

Remaining useful life prediction and state of health diagnosis of lithium-ion batteries with multiscale health features based on optimized CatBoost algorithm.

Zhou, Yifei; Wang, Shunli; Xie, Yanxing; Zeng, Jiawei; Fernandez, Carlos

Authors

Yifei Zhou

Shunli Wang

Yanxing Xie

Jiawei Zeng



Abstract

Due to the large-scale application of electric vehicles, the remaining service life prediction and health status diagnosis of lithium-ion batteries as their power core is particularly important, and the essence of RUL prediction and SOH diagnosis is the prediction of remaining capacity. Through the aging experiment of cycle charging and discharging of lithium-ion batteries, the health features of experimental data are extracted for the prediction of remaining capacity. In this paper, a deep feature extraction method based on Bilinear CNN combined with CatBoost algorithm based on fractional order method optimization particle swarm optimization, and ant colony optimization algorithm is proposed for battery remaining capacity prediction. Seven groups of health features extracted from ten groups of battery data were used to input them into the optimized CatBoost algorithm for regression prediction. The results show that the proposed model achieves accurate SOH and RUL prediction, the three evaluation indicators MAE, RMSE, and MAPE of SOH are all within 1.7 % and the error rate of RUL is not higher than 1.5 %, and the test of multiple batteries also proves its strong robustness.

Citation

ZHOU, Y., WANG, S., XIE, Y., ZENG, J. and FERNANDEZ, C. 2024. Remaining useful life prediction and state of health diagnosis of lithium-ion batteries with multiscale health features based on optimized CatBoost algorithm. Energy [online], 300, article number 131575. Available from: https://doi.org/10.1016/j.energy.2024.131575

Journal Article Type Article
Acceptance Date May 5, 2024
Online Publication Date May 6, 2024
Publication Date Aug 1, 2024
Deposit Date May 10, 2024
Publicly Available Date May 7, 2025
Journal Energy
Print ISSN 0360-5442
Electronic ISSN 1873-6785
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 300
Article Number 131575
DOI https://doi.org/10.1016/j.energy.2024.131575
Keywords Lithium-ion battery; Remaining useful life; State of health; CatBoost; IFO-PSO-ACO
Public URL https://rgu-repository.worktribe.com/output/2333300