Capacity Degradation Prediction of Lithium-ion Battery Cycling with Various Protocols

Wenkai Ye; Yilin Xie; Zhenwei Wei; Yalun Li; Hewu Wang; Minggao Ouyang

doi:10.1109/iSPEC58282.2023.10402868

Capacity Degradation Prediction of Lithium-ion Battery Cycling with Various Protocols

Wenkai Ye^*
, Yilin Xie
, Zhenwei Wei
, Yalun Li
, Hewu Wang
, Minggao Ouyang

^*Corresponding author for this work

Tsinghua University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Lithium-ion batteries are important for electrical energy storage and have been widely used in many scenarios like electric vehicles and battery energy storage systems. Capacity degradation prediction is critical for improving both the safety and economics of lithium-ion battery systems. However, the prediction is still challenging, since the battery health condition can not be measured directly while the capacity degradation is slow and non-linear. In this work, a complete set of capacity degradation forecast models is proposed. The capacity self-recovery phenomenon is reconsidered and its relationship to cycling protocols is revealed. Remaining useful life predictor is designed to estimate the rate of degradation and capacity self-recovery phenomenon is applied to build an attention-based model. The proposed method is studied in a real-world dataset consisting of 124 cells cycling with various protocols. In the quantitative comparison, the proposed method exhibits better overall performance over existing ones.

Original language	English
Title of host publication	2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350322699
DOIs	https://doi.org/10.1109/iSPEC58282.2023.10402868
State	Published - 2023
Externally published	Yes
Event	2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023 - Chongqing, China Duration: 28 Nov 2023 → 30 Nov 2023

Publication series

Name	2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023

Conference

Conference	2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023
Country/Territory	China
City	Chongqing
Period	28/11/23 → 30/11/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Attention-based model
capacity self-recovery phenomenon
cycling protocol
lithium-ion battery
rate of degradation (ROD)
state of health (SOH) prediction

Access to Document

10.1109/iSPEC58282.2023.10402868

Cite this

Ye, W., Xie, Y., Wei, Z., Li, Y., Wang, H., & Ouyang, M. (2023). Capacity Degradation Prediction of Lithium-ion Battery Cycling with Various Protocols. In 2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023 (2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/iSPEC58282.2023.10402868

@inproceedings{85d1e50bad0a4a4daef8fb110ec60b6e,

title = "Capacity Degradation Prediction of Lithium-ion Battery Cycling with Various Protocols",

abstract = "Lithium-ion batteries are important for electrical energy storage and have been widely used in many scenarios like electric vehicles and battery energy storage systems. Capacity degradation prediction is critical for improving both the safety and economics of lithium-ion battery systems. However, the prediction is still challenging, since the battery health condition can not be measured directly while the capacity degradation is slow and non-linear. In this work, a complete set of capacity degradation forecast models is proposed. The capacity self-recovery phenomenon is reconsidered and its relationship to cycling protocols is revealed. Remaining useful life predictor is designed to estimate the rate of degradation and capacity self-recovery phenomenon is applied to build an attention-based model. The proposed method is studied in a real-world dataset consisting of 124 cells cycling with various protocols. In the quantitative comparison, the proposed method exhibits better overall performance over existing ones.",

keywords = "Attention-based model, capacity self-recovery phenomenon, cycling protocol, lithium-ion battery, rate of degradation (ROD), state of health (SOH) prediction",

author = "Wenkai Ye and Yilin Xie and Zhenwei Wei and Yalun Li and Hewu Wang and Minggao Ouyang",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023 ; Conference date: 28-11-2023 Through 30-11-2023",

year = "2023",

doi = "10.1109/iSPEC58282.2023.10402868",

language = "英语",

series = "2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023",

address = "美国",

}

Ye, W, Xie, Y, Wei, Z, Li, Y, Wang, H & Ouyang, M 2023, Capacity Degradation Prediction of Lithium-ion Battery Cycling with Various Protocols. in 2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023. 2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023, Chongqing, China, 28/11/23. https://doi.org/10.1109/iSPEC58282.2023.10402868

Capacity Degradation Prediction of Lithium-ion Battery Cycling with Various Protocols. / Ye, Wenkai; Xie, Yilin; Wei, Zhenwei et al.
2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Capacity Degradation Prediction of Lithium-ion Battery Cycling with Various Protocols

AU - Ye, Wenkai

AU - Xie, Yilin

AU - Wei, Zhenwei

AU - Li, Yalun

AU - Wang, Hewu

AU - Ouyang, Minggao

PY - 2023

Y1 - 2023

N2 - Lithium-ion batteries are important for electrical energy storage and have been widely used in many scenarios like electric vehicles and battery energy storage systems. Capacity degradation prediction is critical for improving both the safety and economics of lithium-ion battery systems. However, the prediction is still challenging, since the battery health condition can not be measured directly while the capacity degradation is slow and non-linear. In this work, a complete set of capacity degradation forecast models is proposed. The capacity self-recovery phenomenon is reconsidered and its relationship to cycling protocols is revealed. Remaining useful life predictor is designed to estimate the rate of degradation and capacity self-recovery phenomenon is applied to build an attention-based model. The proposed method is studied in a real-world dataset consisting of 124 cells cycling with various protocols. In the quantitative comparison, the proposed method exhibits better overall performance over existing ones.

AB - Lithium-ion batteries are important for electrical energy storage and have been widely used in many scenarios like electric vehicles and battery energy storage systems. Capacity degradation prediction is critical for improving both the safety and economics of lithium-ion battery systems. However, the prediction is still challenging, since the battery health condition can not be measured directly while the capacity degradation is slow and non-linear. In this work, a complete set of capacity degradation forecast models is proposed. The capacity self-recovery phenomenon is reconsidered and its relationship to cycling protocols is revealed. Remaining useful life predictor is designed to estimate the rate of degradation and capacity self-recovery phenomenon is applied to build an attention-based model. The proposed method is studied in a real-world dataset consisting of 124 cells cycling with various protocols. In the quantitative comparison, the proposed method exhibits better overall performance over existing ones.

KW - Attention-based model

KW - capacity self-recovery phenomenon

KW - cycling protocol

KW - lithium-ion battery

KW - rate of degradation (ROD)

KW - state of health (SOH) prediction

UR - https://www.scopus.com/pages/publications/85185375669

U2 - 10.1109/iSPEC58282.2023.10402868

DO - 10.1109/iSPEC58282.2023.10402868

M3 - 会议稿件

AN - SCOPUS:85185375669

T3 - 2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023

BT - 2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023

Y2 - 28 November 2023 through 30 November 2023

ER -

Capacity Degradation Prediction of Lithium-ion Battery Cycling with Various Protocols

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this