| アイテムタイプ |
共通アイテムタイプ(1) |
| 公開日 |
2025-06-30 |
| タイトル |
|
|
タイトル |
Multi-scale analysis of voltage curves for accurate and adaptable lifecycle prediction of lithium-ion batteries |
|
言語 |
en |
| 著者 |
Jiang, Hongmin
Zhai, Qiangxiang
Long, Nengbing
Kang, Qiaoling
Meng, Xianhe
Zhou, Mingjiong
Yan, Lijing
馬, 廷麗
|
| 著作権関連情報 |
|
|
権利情報 |
Copyright (c) 2024 Published by Elsevier B.V. |
|
言語 |
en |
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Health status prediction of lithium-ion batteries is critical for the stable operation of electrical equipment. The data-driven approach can fit the degradation laws based on the historical cyclic data and identify potential problems in time. However, existing prediction methods mainly focus on acquiring various cyclic degradation features, and excessive battery-related data types increase the complexity and indeterminacy, posing a challenge for efficient and accurate prediction during practical application scenarios. Herein, this study only uses cyclic voltages and proposes a novel multi-scale cyclic voltage data preprocessing technique, involving the selection of highly correlated feature parameters with battery life in both the time and frequency domains, and constructing graphical samples with dynamic node connectivity properties. The proposed multi-scale graph convolutional network model adeptly captures and amalgamates the evolving features among graphical samples with efficacy. The one-step prediction experiments demonstrate the capability to predict subsequent capacity degradation solely based on the voltages of any consecutive 20 cycles, with a root mean square error of 0.173 %, exhibiting adaptable capability across different battery datasets. Compared to existing methods that transform data into images for health status prediction, this study highlights the significance of a multi-scale approach to voltage analysis in cyclic data, leveraging advanced feature engineering and modeling techniques, not only to enhance the accuracy and adaptability of battery lifecycle predictions but also to offer a robust framework for overcoming prevailing challenges in monitoring accuracy and cost-effectiveness. |
|
言語 |
en |
| 書誌情報 |
en : Journal of Power Sources
巻 627,
p. 235768,
発行日 2024-11-14
|
| 出版社 |
|
|
出版者 |
Elsevier |
|
言語 |
en |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Lithium-ion batteries |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
State of health |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Multiscale |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Health indicator |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Graph convolutional network |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
| 出版タイプ |
|
|
出版タイプ |
AM |
|
出版タイプResource |
http://purl.org/coar/version/c_ab4af688f83e57aa |
| DOI |
|
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1016/j.jpowsour.2024.235768 |
| NCID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA00705373 |
| ISSN |
|
|
収録物識別子タイプ |
PISSN |
|
収録物識別子 |
0378-7753 |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
1873-2755 |
| 研究者情報 |
|
|
URL |
https://hyokadb02.jimu.kyutech.ac.jp/html/100000666_ja.html |
| 論文ID（連携） |
|
|
値 |
10451767 |
| 連携ID |
|
|
値 |
14516 |
10451767.pdf (1 MB)
