Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells

Jiwei Wang; Yunhong Che; Zhongwei Deng; Kaile Peng; Guoqing Guan; Abuliti Abudula

doi:10.1109/ICIBA52610.2021.9688313

Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells

Jiwei Wang, Yunhong Che, Zhongwei Deng, Kaile Peng, Guoqing Guan, Abuliti Abudula^*

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

Lifetime prognostics of lithium-ion batteries plays an important role in improving safety and reducing operation and maintenance costs in the field of energy storage. To rapidly evaluate the lifetime of newly developed battery packs, a method for estimating the future health state of the battery pack using the aging data of the battery cell's full life cycle and the early data of the battery pack is proposed. First, the battery cycle aging characteristics are analyzed from different perspectives. The health indicators (HIs) related to battery aging are extracted from the partial discharge process, and three HIs closely related to battery capacity aging are selected through the Pearson coefficient analysis method. Then, the HIs degradation model of the battery cell based on exponential fitting is corrected by the HIs in the early cycle of the battery pack to predict the HIs degradation curve of each cell in the battery pack in the future cycle. Finally, based on the Gaussian Process Regression (GPR) model, the battery pack's lifetime is predicted using the early 10% cycle data of the battery pack and the predicted HIs of the battery in remaining life cycle. The experimental results show that the mean absolute error (MAE) and root mean squared error (RMSE) of the proposed method are 0.49% and 0.71%, respectively, which verify its advantages of high accuracy and reliability.

Original language	English
Title of host publication	Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021
Editors	Bing Xu, Kefen Mou
Number of pages	5
Publisher	IEEE
Publication date	2021
Pages	961-965
Article number	9688313
ISBN (Print)	978-1-6654-2878-1
ISBN (Electronic)	978-1-6654-2877-4
DOIs	https://doi.org/10.1109/ICIBA52610.2021.9688313
Publication status	Published - 2021
Event	2nd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021 - Chongqing, China Duration: 17 Dec 2021 → 19 Dec 2021

Conference

Conference	2nd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021
Country/Territory	China
City	Chongqing
Period	17/12/2021 → 19/12/2021
Sponsor	Chengdu Union Institute of Science and Technology, Chongqing Geeks Education Technology Co., Ltd, Global Union Academy of Science and Technology, Chongqing Institute of Technology, Global Union Academy of Science and Technology, IEEE Beijing Section

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Energy Storage
Gaussian Process Regression
Health Indicator
Lithium-ion Battery
State of Health

Access to Document

10.1109/ICIBA52610.2021.9688313

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Wang, J., Che, Y., Deng, Z., Peng, K., Guan, G., & Abudula, A. (2021). Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells. In B. Xu, & K. Mou (Eds.), Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021 (pp. 961-965). Article 9688313 IEEE. https://doi.org/10.1109/ICIBA52610.2021.9688313

Wang, Jiwei ; Che, Yunhong ; Deng, Zhongwei et al. / Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells. Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021. editor / Bing Xu ; Kefen Mou. IEEE, 2021. pp. 961-965

@inproceedings{8b55fe27198145f5a172fc3a966b5025,

title = "Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells",

abstract = "Lifetime prognostics of lithium-ion batteries plays an important role in improving safety and reducing operation and maintenance costs in the field of energy storage. To rapidly evaluate the lifetime of newly developed battery packs, a method for estimating the future health state of the battery pack using the aging data of the battery cell's full life cycle and the early data of the battery pack is proposed. First, the battery cycle aging characteristics are analyzed from different perspectives. The health indicators (HIs) related to battery aging are extracted from the partial discharge process, and three HIs closely related to battery capacity aging are selected through the Pearson coefficient analysis method. Then, the HIs degradation model of the battery cell based on exponential fitting is corrected by the HIs in the early cycle of the battery pack to predict the HIs degradation curve of each cell in the battery pack in the future cycle. Finally, based on the Gaussian Process Regression (GPR) model, the battery pack's lifetime is predicted using the early 10% cycle data of the battery pack and the predicted HIs of the battery in remaining life cycle. The experimental results show that the mean absolute error (MAE) and root mean squared error (RMSE) of the proposed method are 0.49% and 0.71%, respectively, which verify its advantages of high accuracy and reliability. ",

keywords = "Energy Storage, Gaussian Process Regression, Health Indicator, Lithium-ion Battery, State of Health",

author = "Jiwei Wang and Yunhong Che and Zhongwei Deng and Kaile Peng and Guoqing Guan and Abuliti Abudula",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2nd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021 ; Conference date: 17-12-2021 Through 19-12-2021",

year = "2021",

doi = "10.1109/ICIBA52610.2021.9688313",

language = "English",

isbn = "978-1-6654-2878-1",

pages = "961--965",

editor = "Bing Xu and Kefen Mou",

booktitle = "Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021",

publisher = "IEEE",

address = "United States",

}

Wang, J, Che, Y, Deng, Z, Peng, K, Guan, G & Abudula, A 2021, Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells. in B Xu & K Mou (eds), Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021., 9688313, IEEE, pp. 961-965, 2nd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021, Chongqing, China, 17/12/2021. https://doi.org/10.1109/ICIBA52610.2021.9688313

Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells. / Wang, Jiwei; Che, Yunhong; Deng, Zhongwei et al.
Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021. ed. / Bing Xu; Kefen Mou. IEEE, 2021. p. 961-965 9688313.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells

AU - Wang, Jiwei

AU - Che, Yunhong

AU - Deng, Zhongwei

AU - Peng, Kaile

AU - Guan, Guoqing

AU - Abudula, Abuliti

PY - 2021

Y1 - 2021

N2 - Lifetime prognostics of lithium-ion batteries plays an important role in improving safety and reducing operation and maintenance costs in the field of energy storage. To rapidly evaluate the lifetime of newly developed battery packs, a method for estimating the future health state of the battery pack using the aging data of the battery cell's full life cycle and the early data of the battery pack is proposed. First, the battery cycle aging characteristics are analyzed from different perspectives. The health indicators (HIs) related to battery aging are extracted from the partial discharge process, and three HIs closely related to battery capacity aging are selected through the Pearson coefficient analysis method. Then, the HIs degradation model of the battery cell based on exponential fitting is corrected by the HIs in the early cycle of the battery pack to predict the HIs degradation curve of each cell in the battery pack in the future cycle. Finally, based on the Gaussian Process Regression (GPR) model, the battery pack's lifetime is predicted using the early 10% cycle data of the battery pack and the predicted HIs of the battery in remaining life cycle. The experimental results show that the mean absolute error (MAE) and root mean squared error (RMSE) of the proposed method are 0.49% and 0.71%, respectively, which verify its advantages of high accuracy and reliability.

AB - Lifetime prognostics of lithium-ion batteries plays an important role in improving safety and reducing operation and maintenance costs in the field of energy storage. To rapidly evaluate the lifetime of newly developed battery packs, a method for estimating the future health state of the battery pack using the aging data of the battery cell's full life cycle and the early data of the battery pack is proposed. First, the battery cycle aging characteristics are analyzed from different perspectives. The health indicators (HIs) related to battery aging are extracted from the partial discharge process, and three HIs closely related to battery capacity aging are selected through the Pearson coefficient analysis method. Then, the HIs degradation model of the battery cell based on exponential fitting is corrected by the HIs in the early cycle of the battery pack to predict the HIs degradation curve of each cell in the battery pack in the future cycle. Finally, based on the Gaussian Process Regression (GPR) model, the battery pack's lifetime is predicted using the early 10% cycle data of the battery pack and the predicted HIs of the battery in remaining life cycle. The experimental results show that the mean absolute error (MAE) and root mean squared error (RMSE) of the proposed method are 0.49% and 0.71%, respectively, which verify its advantages of high accuracy and reliability.

KW - Energy Storage

KW - Gaussian Process Regression

KW - Health Indicator

KW - Lithium-ion Battery

KW - State of Health

UR - http://www.scopus.com/inward/record.url?scp=85126882591&partnerID=8YFLogxK

U2 - 10.1109/ICIBA52610.2021.9688313

DO - 10.1109/ICIBA52610.2021.9688313

M3 - Article in proceeding

AN - SCOPUS:85126882591

SN - 978-1-6654-2878-1

SP - 961

EP - 965

BT - Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021

A2 - Xu, Bing

A2 - Mou, Kefen

PB - IEEE

T2 - 2nd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021

Y2 - 17 December 2021 through 19 December 2021

ER -

Wang J, Che Y, Deng Z, Peng K, Guan G, Abudula A. Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells. In Xu B, Mou K, editors, Proceedings of 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2021. IEEE. 2021. p. 961-965. 9688313 doi: 10.1109/ICIBA52610.2021.9688313

Lifetime prognostics of lithium-ion battery pack based on its early cycling data and complete degradation information of battery cells

Abstract

Conference

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this