电源学报

基于GRU-BP的锂电池部分充电数据SOH估计

PDF下载

钟耿钦 , 王学梅中国电源学会会员 , 康龙云中国电源学会会员

电源学报 | 新能源发电与储能 2026,24(5): 139-148

收起

电源学报 |新能源发电与储能 2026 , 24 (5) : 139 -148

基于GRU-BP的锂电池部分充电数据SOH估计

全屏

[Author(id=1322531749964403119, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=202121016536@mail.scut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322531750039900593, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, authorId=1322531749964403119, language=EN, stringName=Gengqin ZHONG, firstName=Gengqin, middleName=null, lastName=ZHONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Electric Power Engineering, South China University of Technology, Guangzhou 510000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322531750132175282, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, authorId=1322531749964403119, language=CN, stringName=钟耿钦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华南理工大学电力学院，广州　510000, bio={"content":"

钟耿钦（1998—　），男，硕士研究生。研究方向：锂电池健康状态估计。E-mail：202121016536@mail.scut.edu.cn。

"}, bioImg=null, bioContent=

钟耿钦（1998—　），男，硕士研究生。研究方向：锂电池健康状态估计。E-mail：202121016536@mail.scut.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322531749867934123, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, xref=null, ext=[AuthorCompanyExt(id=1322531749876322732, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, companyId=1322531749867934123, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Electric Power Engineering, South China University of Technology, Guangzhou 510000, China), AuthorCompanyExt(id=1322531749884711341, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, companyId=1322531749867934123, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华南理工大学电力学院，广州　510000)])]), Author(id=1322531750195089844, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=epxmwang@scut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322531750278975926, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, authorId=1322531750195089844, language=EN, stringName=Xuemei WANG, firstName=Xuemei, middleName=null, lastName=WANG, prefix=null, suffix=Member, CPSS, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Electric Power Engineering, South China University of Technology, Guangzhou 510000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322531750341890487, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, authorId=1322531750195089844, language=CN, stringName=王学梅中国电源学会会员, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华南理工大学电力学院，广州　510000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322531749867934123, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, xref=null, ext=[AuthorCompanyExt(id=1322531749876322732, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, companyId=1322531749867934123, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Electric Power Engineering, South China University of Technology, Guangzhou 510000, China), AuthorCompanyExt(id=1322531749884711341, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, companyId=1322531749867934123, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=华南理工大学电力学院，广州　510000)])]), Author(id=1322531750434165177, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lykang@scut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322531750513856955, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, authorId=1322531750434165177, language=EN, stringName=Longyun KANG, firstName=Longyun, middleName=null, lastName=KANG, prefix=null, suffix=Member, CPSS, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Electric Power Engineering, South China University of Technology, Guangzhou 510000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322531750589354428, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322531748840329638, authorId=1322531750434165177, language=CN, stringName=康龙云中国电源学会会员, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=华南理工大学电力学院，广州　510000, bio={"content":"

康龙云（1961—　），男，中国电源学会会员，博士，教授。研究方向：电池储能技术和网逆变技术。E-mail：lykang@scut.edu.cn。

"}, bioImg=null, bioContent=

康龙云（1961—　），男，中国电源学会会员，博士，教授。研究方向：电池储能技术和网逆变技术。E-mail：lykang@scut.edu.cn。

钟耿钦, 王学梅中国电源学会会员, 康龙云中国电源学会会员

作者信息

华南理工大学电力学院，广州　510000

通讯作者:

王学梅（1972—　），女，中国电源学会会员，通信作者，博士，教授。研究方向：电力电子非线性行为与控制。E-mail：epxmwang@scut.edu.cn。

作者简介:

钟耿钦（1998—　），男，硕士研究生。研究方向：锂电池健康状态估计。E-mail：202121016536@mail.scut.edu.cn。

康龙云（1961—　），男，中国电源学会会员，博士，教授。研究方向：电池储能技术和网逆变技术。E-mail：lykang@scut.edu.cn。

SOH Estimation of Partial Charging Data for Lithium Batteries Based on GRU-BP

Gengqin ZHONG, Xuemei WANG Member, CPSS, Longyun KANG Member, CPSS

Affiliations

School of Electric Power Engineering, South China University of Technology, Guangzhou 510000, China

出版时间: 2026-05-30 doi: 10.13234/j.issn.2095-2805.2026.5.139

文章导航

摘要

收起

电池充电时的初始荷电状态SOC（state of charge）往往是随机的，因此在实际应用中难以得到锂电池完整的充电数据，针对这一问题提出一种基于部分充电数据的锂电池健康状态SOH（state of health）估计方法。通过建立的门控循环单元-反向传播GRU-BP（gated recurrent unit-back propagation）模型，可以由部分充电数据得到完整的充电曲线，然后在完整的充电曲线中提取能够有效表征电池老化程度的特征进行SOH预测。该方法能够实现在恒流充电模式下的任意定长电压区间充电数据下电池的SOH估计。通过实验证明，所提出的模型在数据不完备的情况下能够有效预测锂电池SOH，其估计的均方根误差RMSE（root mean square error）均在2%以下。

关键词

锂电池 / 部分数据 / 健康状态估计 / GRU / 神经网络

Abstract

收起

The initial state of charge (SOC) of the battery is frequently random when users charge the batteries. Therefore, it is difficult to obtain complete charging data of lithium batteries in practical applications. To solve this problem, a state of health (SOH) estimation method of lithium battery based on partial charging data is proposed. Through the established GRU-BP (gated recurrent unit-back propagation) model, a complete charging curve can be obtained from partial charging data. Then the SOH can be estimated by the features extracted from the complete charging curve, which can effectively characterize the aging of battery. This method can achieve SOH estimation under any fixed voltage interval charging data in constant current charging mode. The experimental results show that the proposed method can effectively predict the SOH of lithium batteries with incomplete data, and the estimated root mean square error (RMSE) is below 2%.

Key words

Lithium battery / partial data / state of health estimation / GRU / neural network

引用本文

钟耿钦, 王学梅中国电源学会会员, 康龙云中国电源学会会员. 基于GRU-BP的锂电池部分充电数据SOH估计. 电源学报, 2026 , 24 (5) : 139 -148 . DOI: 10.13234/j.issn.2095-2805.2026.5.139

Gengqin ZHONG, Xuemei WANG, Longyun KANG. SOH Estimation of Partial Charging Data for Lithium Batteries Based on GRU-BP[J]. Journal of Power Supply, 2026 , 24 (5) : 139 -148 . DOI: 10.13234/j.issn.2095-2805.2026.5.139

基金

收起

广东省自然科学基金资助项目(2025A1515011914)
东莞市重点领域研发资助项目(20231200300112)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Gismero A, Nørregaard K, Johnsen B, et al. Electric vehicle battery state of health estimation using incremental capacity analysis[J]. Journal of Energy Storage, 2023, 64: 107110.

[2]

成燕, 郑林弘, 刘江. 基于模态分解和时间序列的锂电池健康状态估计[J]. 电源学报, 2025, 23(5): 241-250. Cheng Yan, Zheng Linhong, Liu Jiang. Estimation of state-of-health of lithium-ion batteries based on modal decomposition and time series[J]. Journal of Power Supply, 2025, 23(5): 241-250. (in Chinese)

[3]

王庭华, 鄢博, 吴静云, 等. 基于HPO-LSTM网络的锂电池健康状态估计[J]. 电源学报, 2026, 24(1): 225-232. Wang Tinghua, Yan Bo, Wu Jingyun, et al. State-of-health estimation for lithium-ion battery based on hunterprey optimizer algorithm and long short-term memory neural network[J]. Journal of Power Supply, 2026, 24(1): 225-232. (in Chinese)

[4]

Ma Yan, Shan Ce, Gao Jinwu, et al. Multiple health indicators fusion-based health prognostic for lithium-ion battery using transfer learning and hybrid deep learning method[J]. Reliability Engineering & System Safety, 2023, 229: 108818.

[5]

Cao Mengda, Zhang Tao, Wang Jia, et al. A deep belief network approach to remaining capacity estimation for lithium-ion batteries based on charging process features[J]. Journal of Energy Storage, 2022, 48: 103825.

[6]

Cui Shengmin, Joe I. A dynamic spatial-temporal attention-based GRU model with healthy features for state-of-health estimation of lithium-ion batteries[J]. IEEE Access, 2021, 9: 27374-27388.

[7]

高洋. 三元材料锂离子电池老化诊断、评估与建模方法[D]. 北京: 北京交通大学, 2019. Gao Yang. Aging diagnosis, evaluation and modeling of lithium ion batteries with Li(NiMnCo)O₂ cathode[D]. Beijing: Beijing Jiaotong University, 2019. (in Chinese)

[8]

Li Yi, Abdel-Monem M, Gopalakrishnan R, et al. A quick on-line state of health estimation method for Li-ion battery with incremental capacity curves processed by Gaussian filter[J]. Journal of Power Sources, 2018, 373: 40-53.

[9]

Li Lianfeng, Li Yang, Cui Weiwei, et al. A novel health indicator for online health estimation of lithium-ion batteries using partial incremental capacity and dynamic voltage warping[J]. Journal of Power Sources, 2022, 545: 231961.

[10]

Smart J, Schey S. Battery electric vehicle driving and charging behavior observed early in the EV project[J]. SAE International Journal of Alternative Powertrains, 2012, 1(1): 27-33.

[11]

Yao Jiachi, Han Te. Data-driven lithium-ion batteries capacity estimation based on deep transfer learning using partial segment of charging/discharging data[J]. Energy, 2023, 271: 127033.

[12]

Zhang Meng, Kang Guoqing, Wu Lifeng, et al. A method for capacity prediction of lithium-ion batteries under small sample conditions[J]. Energy, 2022, 238: 122094.

[13]

Lin Hongye, Kang Longyun, Xie Di, et al. Online state-of-health estimation of lithium-ion battery based on incremental capacity curve and BP neural network[J]. Batteries, 2022, 8(4): 29.

[14]

Tian Aina, Yang Chen, Gao Yang, et al. A state of health estimation method of lithium-ion batteries based on DT-IC-V health features extracted from partial charging segment[J]. International Journal of Green Energy, 2023, 20(9): 997-1011.

[15]

Guo Wenchao, Yang Lin, Deng Zhongwei, et al. Rapid online health estimation for lithium-ion batteries based on partial constant-voltage charging segment[J]. Energy, 2023, 281: 128320.

[16]

Meng Huixing, Geng Mengyao, Han Te. Long short-term memory network with Bayesian optimization for health prognostics of lithium-ion batteries based on partial incremental capacity analysis[J]. Reliability Engineering & System Safety, 2023, 236: 109288.

[17]

Wang Qiao, Ye Min, Wei Meng, et al. Random health indicator and shallow neural network based robust capacity estimation for lithium-ion batteries with different fast charging protocols[J]. Energy, 2023, 271: 127029.

[18]

Zhang Chenghui, Kang Yongzhe, Duan Bin, et al. An adaptive battery capacity estimation method suitable for random charging voltage range in electric vehicles[J]. IEEE Transactions on Industrial Electronics, 2022, 69(9): 9121-9132.

[19]

Howey D, Birkl C. Oxford battery degradation dataset 1[EB/OL]. (2017-06-13) [2023-10-08]. https://ora.ox.ac.uk/objects/uuid:03ba4b01-cfed-46d3-9b1a-7d4a7bdf6fac.

[20]

安德鲁·格拉斯纳. 深度学习: 从基础到实践[M]. 罗家佳, 译. 北京: 人民邮电出版社, 2022. Andrew G. Deep Learning: From Basics to Practice[M]. Translated by Luo Jiaze. Beijing: Posts & Telecom Press, 2022. (in Chinese)

[21]

Yang Kaiyi, Zhang Lisheng, Zhang Zhengjie, et al. Battery state of health estimate strategies: From data analysis to end-cloud collaborative framework[J]. Batteries, 2023, 9(7): 351.

2026年第24卷第5期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2026.5.139

接收时间：2023-11-22
首发时间：2026-10-29
出版时间：2026-05-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2023-11-22
修回日期：2024-02-16
录用日期：2024-03-05

基金

广东省自然科学基金资助项目(2025A1515011914)

东莞市重点领域研发资助项目(20231200300112)

作者信息

华南理工大学电力学院，广州　510000

通讯作者:

王学梅（1972—　），女，中国电源学会会员，通信作者，博士，教授。研究方向：电力电子非线性行为与控制。E-mail：epxmwang@scut.edu.cn。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2026.5.139

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT