Article(id=1149837645427209036, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154040955071095059, articleNumber=null, orderNo=null, doi=10.13234/j.issn.2095-2805.2024.1.1, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1704211200000, receivedDateStr=2024-01-03, revisedDate=1706457600000, revisedDateStr=2024-01-29, acceptedDate=1706457600000, acceptedDateStr=2024-01-29, onlineDate=1752072257619, onlineDateStr=2025-07-09, pubDate=1706544000000, pubDateStr=2024-01-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752072257619, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752072257619, creator=13701087609, updateTime=1752072257619, updator=13701087609, issue=Issue{id=1154040955071095059, tenantId=1146029695717560320, journalId=1146031654075715584, year='2024', volume='22', issue='1', pageStart='1', pageEnd='235', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753074404733, creator=13701087609, updateTime=1753781011721, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1157004679654760494, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154040955071095059, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1157004679654760495, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154040955071095059, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1, endPage=10, ext={EN=ArticleExt(id=1149837645813085006, articleId=1149837645427209036, tenantId=1146029695717560320, journalId=1146031654075715584, language=EN, title=Data-driven State of Health Estimation for Sodium-ion Batteries, columnId=1154038487448806144, journalTitle=Journal of Power Supply, columnName=Invited Manuscript, runingTitle=null, highlight=null, articleAbstract=

The state of health (SOH) estimation for sodium-ion batteries is crucial for their safe and efficient applications, which is also a key to large-scale energy storage implementations. However, sodium-ion batteries exhibit usage-induced degradation with unclear mechanisms and are sensitive to operating conditions and environmental factors, posing a challenge to the accurate SOH estimation. In this paper, a data-driven SOH estimation method for sodium-ion batteries is proposed. The charging data is correlated with capacity degradation, and variance filtering, grey relational analysis and recursive feature elimination are integrated for feature selection. In addition, four machine learning methods including multiple linear regression, support vector machine, Gaussian process regression and error back propagation neural network are applied to formulate the corresponding estimation methods. Test results reveal that the root mean square errors for the four methods are all less than 1.6%, with Gaussian process regression showing an error rate below 0.8%, indicating a precise SOH estimation for sodium-ion batteries.

, correspAuthors=Rui XIONG, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Nan LU, Yue SUN, Peng PENG, Rui XIONG, Fengchun SUN), CN=ArticleExt(id=1149837653681599328, articleId=1149837645427209036, tenantId=1146029695717560320, journalId=1146031654075715584, language=CN, title=数据驱动的钠离子电池健康状态评估方法研究, columnId=1153695646428160491, journalTitle=电源学报, columnName=特邀专栏, runingTitle=null, highlight=null, articleAbstract=

钠离子电池健康状态估计是其安全高效应用的基础,也是钠电池规模化储能应用的关键。然而,钠离子电池即用即衰,衰退机理不明晰,老化过程受工况和场景影响,准确的健康状态估计极其困难。为此,提出了数据驱动的钠离子电池健康状态估计方法,探究了钠离子电池的充电数据与容量衰退的映射关系,提出了结合方差筛选、灰色关联分析和递归特征消除的特征选择方法,应用多元线性回归、支持向量机、高斯过程回归和误差反向传播神经网络4类机器学习方法估计钠离子电池的健康状态。验证结果表明,4类方法的健康状态估计均方根误差小于1.6%,其中高斯过程回归的误差小于0.8%,实现了钠离子电池健康状态精准估计。

, correspAuthors=熊瑞, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=PbfgEyALnKdfyPv2bmp15A==, magXml=0rb3MPd97Hn4C7mgC1+UJg==, pdfUrl=null, pdf=WytEBW3zpDOTzQGxkJWo+w==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=VFiFSnQpJJUFt/ewNp4GpA==, mapNumber=null, authorCompany=null, fund=null, authors=

陆楠(2001-),女,硕士研究生。研究方向:电池老化评估与健康管理。E-mail: In1100101101@163.com。

孙越(1998-),女,博士研究生。研究方向:电池老化评估与健康管理。E-mail: 13581196698@163.com。

彭鹏(1988-),男,博士研究生。研究方向:电池储能管理。E-mail: 13926169785@139.com。

熊瑞(1985-),男,中国电源学会会员,通信作者,博士,教授。研究方向:电池管理与控制。E-mail:rxiong@bit.edu.cn。

孙逢春(1958-),男,博士,教授,中国工程院院士。研究方向:电动车辆与电传动。E-mail:sunfch@bit.edu.cn。

, authorsList=陆楠, 孙越, 彭鹏, 熊瑞, 孙逢春)}, authors=[Author(id=1154041017532670652, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=In1100101101@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154041017591390910, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041017532670652, language=EN, stringName=Nan LU, firstName=Nan, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154041017624945343, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041017532670652, language=CN, stringName=陆楠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北京理工大学 机械和车辆学院 北京 100081, bio={"img":"dca0oOeNRNZXrytDAfhHew==","content":"

陆楠(2001-),女,硕士研究生。研究方向:电池老化评估与健康管理。E-mail: In1100101101@163.com。

"}, bioImg=dca0oOeNRNZXrytDAfhHew==, bioContent=

陆楠(2001-),女,硕士研究生。研究方向:电池老化评估与健康管理。E-mail: In1100101101@163.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154041017381675701, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, xref=1, ext=[AuthorCompanyExt(id=1154041017390064310, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China), AuthorCompanyExt(id=1154041017394258615, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京理工大学 机械和车辆学院 北京 100081)])]), Author(id=1154041017683665601, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=13581196698@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154041017759163075, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041017683665601, language=EN, stringName=Yue SUN, firstName=Yue, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154041017805300420, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041017683665601, language=CN, stringName=孙越, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北京理工大学 机械和车辆学院 北京 100081, bio={"content":"

孙越(1998-),女,博士研究生。研究方向:电池老化评估与健康管理。E-mail: 13581196698@163.com。

"}, bioImg=null, bioContent=

孙越(1998-),女,博士研究生。研究方向:电池老化评估与健康管理。E-mail: 13581196698@163.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154041017381675701, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, xref=1, ext=[AuthorCompanyExt(id=1154041017390064310, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China), AuthorCompanyExt(id=1154041017394258615, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京理工大学 机械和车辆学院 北京 100081)])]), Author(id=1154041017864020678, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=13926169785@139.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154041018681909964, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041017864020678, language=EN, stringName=Peng PENG, firstName=Peng, middleName=null, lastName=PENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China
2 CSG PGC Energy Storage Research Institute Guangzhou 510630 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154041018740630224, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041017864020678, language=CN, stringName=彭鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 北京理工大学 机械和车辆学院 北京 100081
2 南方电网调峰调频发电有限公司 储能科研院 广州 510630, bio={"content":"

彭鹏(1988-),男,博士研究生。研究方向:电池储能管理。E-mail: 13926169785@139.com。

"}, bioImg=null, bioContent=

彭鹏(1988-),男,博士研究生。研究方向:电池储能管理。E-mail: 13926169785@139.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154041017381675701, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, xref=1, ext=[AuthorCompanyExt(id=1154041017390064310, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China), AuthorCompanyExt(id=1154041017394258615, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京理工大学 机械和车辆学院 北京 100081)]), AuthorCompany(id=1154041017465561784, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, xref=2, ext=[AuthorCompanyExt(id=1154041017469756089, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017465561784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 CSG PGC Energy Storage Research Institute Guangzhou 510630 China), AuthorCompanyExt(id=1154041017473950394, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017465561784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 南方电网调峰调频发电有限公司 储能科研院 广州 510630)])]), Author(id=1154041018803544785, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=rxiong@bit.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154041018883236567, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041018803544785, language=EN, stringName=Rui XIONG, firstName=Rui, middleName=null, lastName=XIONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154041018958734042, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041018803544785, language=CN, stringName=熊瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北京理工大学 机械和车辆学院 北京 100081, bio={"content":"

熊瑞(1985-),男,中国电源学会会员,通信作者,博士,教授。研究方向:电池管理与控制。E-mail:rxiong@bit.edu.cn。

"}, bioImg=null, bioContent=

熊瑞(1985-),男,中国电源学会会员,通信作者,博士,教授。研究方向:电池管理与控制。E-mail:rxiong@bit.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154041017381675701, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, xref=1, ext=[AuthorCompanyExt(id=1154041017390064310, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China), AuthorCompanyExt(id=1154041017394258615, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京理工大学 机械和车辆学院 北京 100081)])]), Author(id=1154041019021648603, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sunfch@bit.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154041019088757471, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041019021648603, language=EN, stringName=Fengchun SUN, firstName=Fengchun, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154041019239752417, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, authorId=1154041019021648603, language=CN, stringName=孙逢春, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北京理工大学 机械和车辆学院 北京 100081, bio={"content":"

孙逢春(1958-),男,博士,教授,中国工程院院士。研究方向:电动车辆与电传动。E-mail:sunfch@bit.edu.cn。

"}, bioImg=null, bioContent=

孙逢春(1958-),男,博士,教授,中国工程院院士。研究方向:电动车辆与电传动。E-mail:sunfch@bit.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154041017381675701, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, xref=1, ext=[AuthorCompanyExt(id=1154041017390064310, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China), AuthorCompanyExt(id=1154041017394258615, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京理工大学 机械和车辆学院 北京 100081)])])], keywords=[Keyword(id=1154041020028281575, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, orderNo=1, keyword=Sodium-ion battery), Keyword(id=1154041020087001832, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, orderNo=2, keyword=state of health(SOH)), Keyword(id=1154041020149916393, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, orderNo=3, keyword=data driven), Keyword(id=1154041020212830954, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, orderNo=4, keyword=aging feature), Keyword(id=1154041020271551211, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, orderNo=5, keyword=machine learning), Keyword(id=1154041020347048684, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, orderNo=1, keyword=钠离子电池), Keyword(id=1154041020435129069, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, orderNo=2, keyword=健康状态), Keyword(id=1154041020519015152, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, orderNo=3, keyword=数据驱动), Keyword(id=1154041020594512625, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, orderNo=4, keyword=老化特征), Keyword(id=1154041020674204401, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, orderNo=5, keyword=机器学习)], refs=[Reference(id=1154041024021259037, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2018, volume=8, issue=14, pageStart=1702403, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Xu Guiliang, Amine R, Abouimrane A, journalName=Advanced Energy Materials, refType=null, unstructuredReference=Xu Guiliang, Amine R, Abouimrane A, et al. Challenges in developing electrodes, electrolytes, and diagnostics tools to understand and advance sodium-ion batteries[J]. Advanced Energy Materials, 2018. 8(14): 1702403., articleTitle=Challenges in developing electrodes, electrolytes, and diagnostics tools to understand and advance sodium-ion batteries, refAbstract=null), Reference(id=1154041024121922336, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2019, volume=7, issue=16, pageStart=9406, pageEnd=9431, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Li Fang, Wei Zengxi, Manthiram A, journalName=Journal of Materials Chemistry A, refType=null, unstructuredReference=Li Fang, Wei Zengxi, Manthiram A, et al. Sodium-based batteries: From critical materials to battery systems[J]. Journal of Materials Chemistry A, 2019. 7(16): 9406-9431., articleTitle=Sodium-based batteries: From critical materials to battery systems, refAbstract=null), Reference(id=1154041024226779937, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2020, volume=9, issue=2, pageStart=515, pageEnd=522, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=容晓晖, 陆雅翔, 戚兴国, journalName=储能科学与技术, refType=null, unstructuredReference=容晓晖, 陆雅翔, 戚兴国, 等. 钠离子电池:从基础研究到工程化探索[J]. 储能科学与技术, 2020. 9(2): 515-522., articleTitle=钠离子电池:从基础研究到工程化探索, refAbstract=null), Reference(id=1154041024281305890, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2020, volume=9, issue=2, pageStart=515, pageEnd=522, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Rong Xiaohui, Lu Yaxiang, Qi Xingguo, journalName=Energy Storage Science and Technology, refType=null, unstructuredReference=Rong Xiaohui, Lu Yaxiang, Qi Xingguo, et al. Na-ion batteries: From fundamental research to engineering exploration[J]. Energy Storage Science and Technology, 2020. 9(2): 515-522 (in Chinese)., articleTitle=Na-ion batteries: From fundamental research to engineering exploration, refAbstract=null), Reference(id=1154041024344220452, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=熊瑞, journalName=2版, refType=null, unstructuredReference=熊瑞. 动力电池管理系统核心算法[M]. 2版, 北京: 机械工业出版社, 2021., articleTitle=动力电池管理系统核心算法, refAbstract=null), Reference(id=1154041024407135014, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Xiong Rui, journalName=2nd Edition, refType=null, unstructuredReference=Xiong Rui. Core Algorithm of Battery Management System for EVs[M]. 2nd Edition, Beijing: China Machine Press, 2021. (in Chinese)., articleTitle=Core Algorithm of Battery Management System for EVs, refAbstract=null), Reference(id=1154041024465855272, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2018, volume=205, issue=null, pageStart=115, pageEnd=133, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Lipu MS H, Hannan M A, Hussain A, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=Lipu MS H, Hannan M A, Hussain A, et al. A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations[J]. Journal of Cleaner Production, 2018. 205: 115-133., articleTitle=A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations, refAbstract=null), Reference(id=1154041024541352746, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2020, volume=131, issue=null, pageStart=110015, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Wang Yujie, Tian Jiaqiang, Sun Zhendong, journalName=Renewable and Sustainable Energy Reviews, refType=null, unstructuredReference=Wang Yujie, Tian Jiaqiang, Sun Zhendong, et al. A comprehensive review of battery modeling and state estimation approaches for advanced battery management systems[J]. Renewable and Sustainable Energy Reviews, 2020. 131: 110015., articleTitle=A comprehensive review of battery modeling and state estimation approaches for advanced battery management systems, refAbstract=null), Reference(id=1154041024654598956, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=null, pageStart=41741, pageEnd=41769, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Ramezani S B, Cummins L, Killen B, journalName=IEEE Access, refType=null, unstructuredReference=Ramezani S B, Cummins L, Killen B, et al. Scalability, explainability and performance of data-driven algorithms in predicting the remaining useful life: A comprehensive review[J]. IEEE Access, 2023. 11: 41741-41769., articleTitle=Scalability, explainability and performance of data-driven algorithms in predicting the remaining useful life: A comprehensive review, refAbstract=null), Reference(id=1154041024730096431, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2021, volume=10, issue=4, pageStart=1407, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=Feng Yifeng, Shen Jiani, Che Haiying, journalName=Energy Storage Science and Technology, refType=null, unstructuredReference=Feng Yifeng, Shen Jiani, Che Haiying, et al. State of health prediction for sodium-ion batteries[J]. Energy Storage Science and Technology, 2021. 10(4): 1407., articleTitle=State of health prediction for sodium-ion batteries, refAbstract=null), Reference(id=1154041024822371121, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2020, volume=10, issue=44, pageStart=2002055, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=Goikolea E, Palomares V, Wang Shijian, journalName=Advanced Energy Materials, refType=null, unstructuredReference=Goikolea E, Palomares V, Wang Shijian, et al. Na-ion batteries-Approaching old and new challenges[J]. Advanced Energy Materials, 2020. 10(44): 2002055., articleTitle=Na-ion batteries-Approaching old and new challenges, refAbstract=null), Reference(id=1154041024906257204, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2021, volume=11, issue=47, pageStart=2102489.1, pageEnd=2102489.17, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=Tian Zhihong, Zhang Yu, Zhu Jixin, journalName=Advanced Energy Materials, refType=null, unstructuredReference=Tian Zhihong, Zhang Yu, Zhu Jixin, et al. A reanalysis of the diverse sodium species in carbon anodes for sodium ion batteries: A thermodynamic view[J]. Advanced Energy Materials, 2021. 11(47): 2102489.1-2102489.17., articleTitle=A reanalysis of the diverse sodium species in carbon anodes for sodium ion batteries: A thermodynamic view, refAbstract=null), Reference(id=1154041024977560375, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2023, volume=184, issue=null, pageStart=113576, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=Li Chuan, Zhang Huahua, Ding Ping, journalName=Renewable and Sustainable Energy Reviews, refType=null, unstructuredReference=Li Chuan, Zhang Huahua, Ding Ping, et al. Deep feature extraction in lifetime prognostics of lithium-ion batteries: Advances, challenges and perspectives[J]. Renewable and Sustainable Energy Reviews, 2023. 184: 113576., articleTitle=Deep feature extraction in lifetime prognostics of lithium-ion batteries: Advances, challenges and perspectives, refAbstract=null), Reference(id=1154041025048863546, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2022, volume=261, issue=null, pageStart=125151, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=Wei Meng, Balaya Palani, Ye Min, journalName=Energy, refType=null, unstructuredReference=Wei Meng, Balaya Palani, Ye Min, et al. Remaining useful life prediction for 18650 sodium-ion batteries based on incremental capacity analysis[J]. Energy, 2022. 261: 125151., articleTitle=Remaining useful life prediction for 18650 sodium-ion batteries based on incremental capacity analysis, refAbstract=null), Reference(id=1154041025115972412, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2020, volume=204, issue=null, pageStart=117957, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=Shu Xing, Li Guang, Shen Jiangwei, journalName=Energy, refType=null, unstructuredReference=Shu Xing, Li Guang, Shen Jiangwei, et al. A uniform estimation framework for state of health of lithium-ion batteries considering feature extraction and parameters optimization[J]. Energy, 2020. 204: 117957., articleTitle=A uniform estimation framework for state of health of lithium-ion batteries considering feature extraction and parameters optimization, refAbstract=null), Reference(id=1154041025199858494, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2023, volume=57, issue=null, pageStart=460, pageEnd=470, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=Xiong Rui, Sun Yue, Wang Chenxu, journalName=Energy Storage Materials, refType=null, unstructuredReference=Xiong Rui, Sun Yue, Wang Chenxu, et al. A data-driven method for extracting aging features to accurately predict the battery health[J]. Energy Storage Materials, 2023. 57: 460-470., articleTitle=A data-driven method for extracting aging features to accurately predict the battery health, refAbstract=null), Reference(id=1154041025287938880, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2023, volume=282, issue=null, pageStart=128794, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=Zuo Hongyan, Liang Jingwei, Zhang Bin, journalName=Energy, refType=null, unstructuredReference=Zuo Hongyan, Liang Jingwei, Zhang Bin, et al. Intelligent estimation on state of health of lithium-ion power batteries based on failure feature extraction[J]. Energy, 2023. 282: 128794., articleTitle=Intelligent estimation on state of health of lithium-ion power batteries based on failure feature extraction, refAbstract=null), Reference(id=1154041025405379396, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2018, volume=150, issue=null, pageStart=759, pageEnd=769, url=null, language=null, rfNumber=[16], rfOrder=17, authorNames=Zheng Linfeng, Zhu Jianguo, Lu DDC, journalName=Energy, refType=null, unstructuredReference=Zheng Linfeng, Zhu Jianguo, Lu DDC, et al. Incremental capacity analysis and differential voltage analysis based state of charge and capacity estimation for lithium-ion batteries[J]. Energy, 2018. 150: 759-769., articleTitle=Incremental capacity analysis and differential voltage analysis based state of charge and capacity estimation for lithium-ion batteries, refAbstract=null), Reference(id=1154041025506042693, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2020, volume=448, issue=null, pageStart=227575, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=18, authorNames=Zhu Jiangong, Dewi D M S, Knapp M, journalName=Journal of Power Sources, refType=null, unstructuredReference=Zhu Jiangong, Dewi D M S, Knapp M, et al. Investigation of lithium-ion battery degradation mechanisms by combining differential voltage analysis and alternating current impedance[J]. Journal of Power Sources, 2020. 448: 227575., articleTitle=Investigation of lithium-ion battery degradation mechanisms by combining differential voltage analysis and alternating current impedance, refAbstract=null), Reference(id=1154041025568957254, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2020, volume=190, issue=null, pageStart=116467, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=19, authorNames=Li Xiaoyu, Yuan Changgui, Li Xiaohui, journalName=Energy, refType=null, unstructuredReference=Li Xiaoyu, Yuan Changgui, Li Xiaohui, et al. State of health estimation for Li-ion battery using incremental capacity analysis and Gaussian process regression[J]. Energy, 2020. 190: 116467., articleTitle=State of health estimation for Li-ion battery using incremental capacity analysis and Gaussian process regression, refAbstract=null), Reference(id=1154041025652843336, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=20, authorNames=周志华, journalName=1版, refType=null, unstructuredReference=周志华. 机器学习[M]. 1版, 北京: 清华大学出版社, 2016., articleTitle=机器学习, refAbstract=null), Reference(id=1154041025715757898, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=21, authorNames=Zhou Zhihua, journalName=1st Edition, refType=null, unstructuredReference=Zhou Zhihua. Maching Learning[M]. 1st Edition, Beijing: Tsinghua University Publishing House Co., Ltd, 2016. (in Chinese)., articleTitle=Maching Learning, refAbstract=null), Reference(id=1154041025803838282, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2015, volume=282, issue=null, pageStart=146, pageEnd=157, url=null, language=null, rfNumber=[20], rfOrder=22, authorNames=Sun Bingxiang, Jiang Jiuchun, Zheng Fangdan, journalName=Journal of Power Sources, refType=null, unstructuredReference=Sun Bingxiang, Jiang Jiuchun, Zheng Fangdan, et al. Practical state of health estimation of power batteries based on Delphi method and grey relational grade analysis[J]. Journal of Power Sources, 2015. 282: 146-157., articleTitle=Practical state of health estimation of power batteries based on Delphi method and grey relational grade analysis, refAbstract=null), Reference(id=1154041025870947148, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2020, volume=59, issue=null, pageStart=101903, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=23, authorNames=Richhariya B, Tanveer M, Rashid A H, journalName=Biomedical Signal Processing and Control, refType=null, unstructuredReference=Richhariya B, Tanveer M, Rashid A H. Diagnosis of Alzheimer's disease using universum support vector machine based recursive feature elimination (USVM-RFE)[J]. Biomedical Signal Processing and Control, 2020. 59: 101903., articleTitle=Diagnosis of Alzheimer's disease using universum support vector machine based recursive feature elimination (USVM-RFE), refAbstract=null), Reference(id=1154041025933861710, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2022, volume=14, issue=19, pageStart=11865, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=24, authorNames=Zhao Jiahui, Zhu Yong, Zhang Bin, journalName=Sustainability, refType=null, unstructuredReference=Zhao Jiahui, Zhu Yong, Zhang Bin, et al. Method of predicting SOH and RUL of Lithium-ion battery based on the combination of LSTM and GPR[J]. Sustainability, 2022. 14(19): 11865., articleTitle=Method of predicting SOH and RUL of Lithium-ion battery based on the combination of LSTM and GPR, refAbstract=null), Reference(id=1154041026005164880, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=1986, volume=323, issue=6088, pageStart=533, pageEnd=536, url=null, language=null, rfNumber=[23], rfOrder=25, authorNames=Rumelhart D E, Hinton G E, Williams R J, journalName=Nature, refType=null, unstructuredReference=Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986. 323(6088): 533-536., articleTitle=Learning representations by back-propagating errors, refAbstract=null), Reference(id=1154041026089050960, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2000, volume=null, issue=null, pageStart=1647, pageEnd=1649, url=null, language=null, rfNumber=[24], rfOrder=26, authorNames=null, journalName=WCC 2000 -ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000: col 3, refType=null, unstructuredReference=The improvements of BP neural network learning algorithm[C]// WCC 2000 -ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000: col 3, 2000: 1647-1649., articleTitle=The improvements of BP neural network learning algorithm, refAbstract=null), Reference(id=1154041026151965522, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2019, volume=7, issue=8, pageStart=3691, pageEnd=3696, url=null, language=null, rfNumber=[25], rfOrder=27, authorNames=Wang Jianbiao, Luo Ningjing, Wu Junxiu, journalName=Journal of Materials Chemistry A, refType=null, unstructuredReference=Wang Jianbiao, Luo Ningjing, Wu Junxiu, et al. Hierarchical spheres constructed by ultrathin VS2 nanosheets for sodium-ion batteries[J]. Journal of Materials Chemistry A, 2019. 7(8): 3691-3696., articleTitle=Hierarchical spheres constructed by ultrathin VS2 nanosheets for sodium-ion batteries, refAbstract=null), Reference(id=1154041026206491476, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2021, volume=5, issue=6, pageStart=1521, pageEnd=1534, url=null, language=null, rfNumber=[26], rfOrder=28, authorNames=Tian Jinpeng, Xiong Rui, Shen Weixiang, journalName=Joule, refType=null, unstructuredReference=Tian Jinpeng, Xiong Rui, Shen Weixiang, et al. Deep neural network battery charging curve prediction using 30 points collected in 10 min[J]. Joule, 2021. 5(6): 1521-1534., articleTitle=Deep neural network battery charging curve prediction using 30 points collected in 10 min, refAbstract=null), Reference(id=1154041026269406038, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, doi=null, pmid=null, pmcid=null, year=2023, volume=556, issue=null, pageStart=232466, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=29, authorNames=Jiang Yiyue, Chen Yuan, Yang Fangfang, journalName=Journal of Power Sources, refType=null, unstructuredReference=Jiang Yiyue, Chen Yuan, Yang Fangfang, et al. State of health estimation of lithium-ion battery with automatic feature extraction and self-attention learning mechanism[J]. Journal of Power Sources, 2023. 556: 232466., articleTitle=State of health estimation of lithium-ion battery with automatic feature extraction and self-attention learning mechanism, refAbstract=null)], funds=[Fund(id=1154041023786378011, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, awardId=STKJXM20210104, language=EN, fundingSource=Key Project of CSG(STKJXM20210104), fundOrder=null, country=null), Fund(id=1154041023840903964, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, awardId=STKJXM20210104, language=CN, fundingSource=南方电网公司重点科技项目(STKJXM20210104), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1154041017381675701, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, xref=1, ext=[AuthorCompanyExt(id=1154041017390064310, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China), AuthorCompanyExt(id=1154041017394258615, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017381675701, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京理工大学 机械和车辆学院 北京 100081)]), AuthorCompany(id=1154041017465561784, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, xref=2, ext=[AuthorCompanyExt(id=1154041017469756089, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017465561784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 CSG PGC Energy Storage Research Institute Guangzhou 510630 China), AuthorCompanyExt(id=1154041017473950394, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, companyId=1154041017465561784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 南方电网调峰调频发电有限公司 储能科研院 广州 510630)])], figs=[ArticleFig(id=1154041022570029825, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Fig. 1, caption=Framework of SOH estimation, figureFileSmall=8L3sHrXPxc59c1Eoabh81w==, figureFileBig=9ff8tNaJ1gUY4by+VkR4OA==, tableContent=null), ArticleFig(id=1154041022628750084, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=图1, caption=SOH 估计框架, figureFileSmall=8L3sHrXPxc59c1Eoabh81w==, figureFileBig=9ff8tNaJ1gUY4by+VkR4OA==, tableContent=null), ArticleFig(id=1154041022708441863, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Fig. 2, caption=Flow chart of feature selection and $\mathrm{{SOH}}$ estimation method, figureFileSmall=oThjHpB2p5p+LIn988G+3g==, figureFileBig=u+bR3r5DU6rLrNCMknu9Hg==, tableContent=null), ArticleFig(id=1154041022762967817, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=图2, caption=方法原理流程, figureFileSmall=oThjHpB2p5p+LIn988G+3g==, figureFileBig=u+bR3r5DU6rLrNCMknu9Hg==, tableContent=null), ArticleFig(id=1154041022809105163, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Fig. 3, caption=Platform of accelerated life experiment for sodium-ion battery, figureFileSmall=RqVi3BsqjDcaF47hc3ohLg==, figureFileBig=NtYTdrD0H9BQYKSzRWAj0w==, tableContent=null), ArticleFig(id=1154041022872019726, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=图3, caption=钠离子电池加速寿命实验平台, figureFileSmall=RqVi3BsqjDcaF47hc3ohLg==, figureFileBig=NtYTdrD0H9BQYKSzRWAj0w==, tableContent=null), ArticleFig(id=1154041022926545679, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Fig. 4, caption=Degradation curves of sodium-ion batteries, figureFileSmall=mYsuYB8S53TCdwhFBKspXg==, figureFileBig=R0Sr8uU5dJTQriGv4DEveg==, tableContent=null), ArticleFig(id=1154041022993654544, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=图4, caption=钠离子电池退化曲线, figureFileSmall=mYsuYB8S53TCdwhFBKspXg==, figureFileBig=R0Sr8uU5dJTQriGv4DEveg==, tableContent=null), ArticleFig(id=1154041023039791889, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Fig. 5, caption=Curves of battery degradation features, figureFileSmall=AtCXfntYv+2zRYzm7PHWzg==, figureFileBig=pJ3xnPUkF6Gn/ssESOMPEA==, tableContent=null), ArticleFig(id=1154041023094317842, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=图5, caption=电池衰退特征曲线, figureFileSmall=AtCXfntYv+2zRYzm7PHWzg==, figureFileBig=pJ3xnPUkF6Gn/ssESOMPEA==, tableContent=null), ArticleFig(id=1154041023140455187, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Fig. 6, caption=SOH estimation results and the corresponding errors, figureFileSmall=FbQ1nJYUiYN0Tmmrjf1c2Q==, figureFileBig=2JM9NXcTeIiHlxjpmqZgUw==, tableContent=null), ArticleFig(id=1154041023207564052, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=图6, caption=SOH 估计结果与误差, figureFileSmall=FbQ1nJYUiYN0Tmmrjf1c2Q==, figureFileBig=2JM9NXcTeIiHlxjpmqZgUw==, tableContent=null), ArticleFig(id=1154041023262090005, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Tab. 1, caption=Specific parameters of battery used in experiment, figureFileSmall=null, figureFileBig=null, tableContent=
参数 数值
标称容量/Ah 2.5
电压范围/V 1.50~3.95
最大充放电倍率/C 1
内阻/mΩ 约 55
), ArticleFig(id=1154041023320810262, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=表1, caption=实验电池具体参数, figureFileSmall=null, figureFileBig=null, tableContent=
参数 数值
标称容量/Ah 2.5
电压范围/V 1.50~3.95
最大充放电倍率/C 1
内阻/mΩ 约 55
), ArticleFig(id=1154041023379530519, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Tab. 2, caption=Results of voltage interval division and feature selection, figureFileSmall=null, figureFileBig=null, tableContent=
划分方法 划分结果 提取特征参数
等宽分组法 (电压/V) EW1:3.20~3.35
EW2: 3.35~3.50
EW3: 3.50~3.65 区间电压均值
EW4: 3.65~3.80 $\left({V}_{\text{mean }}\right)$
EW5: 3.80~3.95 区间电压标准差
EW6: 3.20~3.45 $\left({V}_{\text{std }}\right)$
EW7:3.45~3.70 区间充入容量$\left({V}_{0}\right)$
EW8:3.70~3.95
EW9:3.20~3.95
EW10:3.20~3.50 区间充入容量
EW11:3.20~3.60
EW12:3.20~3.70
EW13:3.30~3.60
EW14: 3.30~3.70
等充入电量分组法 EQ1: 33%~67%
EQ2:67%~100%
EQ3: 33%~100%
区间电压均值
区间电压标准差
区间电压最小值
区间电压最大值
IC 曲线 全电压区间 FR IC 峰值高度 (HP)
IC 峰位置 (PP)
IC 峰面积 (AP)
IC 峰峰半宽 (HWP)
IC 峰左斜率 (LSP)
IC 峰右斜率(RSP)
), ArticleFig(id=1154041023438250776, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=表2, caption=电压区间划分与特征提取结果, figureFileSmall=null, figureFileBig=null, tableContent=
划分方法 划分结果 提取特征参数
等宽分组法 (电压/V) EW1:3.20~3.35
EW2: 3.35~3.50
EW3: 3.50~3.65 区间电压均值
EW4: 3.65~3.80 $\left({V}_{\text{mean }}\right)$
EW5: 3.80~3.95 区间电压标准差
EW6: 3.20~3.45 $\left({V}_{\text{std }}\right)$
EW7:3.45~3.70 区间充入容量$\left({V}_{0}\right)$
EW8:3.70~3.95
EW9:3.20~3.95
EW10:3.20~3.50 区间充入容量
EW11:3.20~3.60
EW12:3.20~3.70
EW13:3.30~3.60
EW14: 3.30~3.70
等充入电量分组法 EQ1: 33%~67%
EQ2:67%~100%
EQ3: 33%~100%
区间电压均值
区间电压标准差
区间电压最小值
区间电压最大值
IC 曲线 全电压区间 FR IC 峰值高度 (HP)
IC 峰位置 (PP)
IC 峰面积 (AP)
IC 峰峰半宽 (HWP)
IC 峰左斜率 (LSP)
IC 峰右斜率(RSP)
), ArticleFig(id=1154041023543108377, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=EN, label=Tab. 3, caption=Results of performance indicators for SOH estimation, figureFileSmall=null, figureFileBig=null, tableContent=
SOH 估计方法 RMSE/% ${R}^{2}/\%$
多元线性回归 1.2 98.8
SVM 1.5 98.2
GPR 0.8 99.5
BP 神经网络 1.4 98.6
), ArticleFig(id=1154041023643771674, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1149837645427209036, language=CN, label=表3, caption=SOH 估计性能指标结果, figureFileSmall=null, figureFileBig=null, tableContent=
SOH 估计方法 RMSE/% ${R}^{2}/\%$
多元线性回归 1.2 98.8
SVM 1.5 98.2
GPR 0.8 99.5
BP 神经网络 1.4 98.6
)], attaches=null, journal=Journal(id=1046111678587809797, delFlag=0, nameCn=电源学报, nameEn=Journal of Power Supply, nameHistory1=null, nameHistory2=null, issn=2095-2805, eissn=, cn=12-1420/TM, coden=null, periodic=bio-monthly, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=Mx+A2dn+ULnPHuEAI1LruQ==, journalPrice=null, startedYear=null, abbrevIsoEn=J Power Supp, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1759802942253, createdBy=null, updatedBy=18614031015, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=Mx+A2dn+ULnPHuEAI1LruQ==, picEn=yHt2vwjzkDgqh+JDCfJKoQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1162453073839375337, language=CN, name=电源学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.jops.cn/EN/home, createdTime=1755080010137, updatedTime=1755080010137, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.jops.cn/CN/column/column7.shtml, submissionAuthorUrl=https://mc03.manuscriptcentral.com/jops, submissionEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionReviewUrl=https://mc03.manuscriptcentral.com/jops, submissionCeEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionAeEditorUrl=https://mc03.manuscriptcentral.com/jops, option={"copyright":""}), JournalExt(id=1162453073902289898, language=EN, name=Journal of Power Supply, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.jops.cn/CN/home, createdTime=1755080010152, updatedTime=1755080010152, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.jops.cn/EN/column/column7.shtml, submissionAuthorUrl=https://mc03.manuscriptcentral.com/jops, submissionEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionReviewUrl=https://mc03.manuscriptcentral.com/jops, submissionCeEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionAeEditorUrl=https://mc03.manuscriptcentral.com/jops, option={"copyright":""})], databaseList=null, tenantJournalId=1146031654075715584, websiteList=[Website(id=1146832214672683008, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031654075715584, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/dyxb/EN, language=EN, createTime=1751355707101, createBy=18614031015, updateTime=1753435268747, updateBy=18614031015, name=电源学报-英文站点, tplId=1146101810881728533, title=电源学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155559379819679852, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=articleTextType, value=kx, createTime=1753436425404, updateTime=1753436425404, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379798708329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=banner, value=null, createTime=1753436425399, updateTime=1753436425399, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379781931112, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=efYTu4aDDzS8GgTA1MjEKw==, createTime=1753436425396, updateTime=1753436425396, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379811291243, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753436425402, updateTime=1753436425402, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379802902634, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753436425400, updateTime=1753436425400, creator=18614031015, updator=18614031015)]), Website(id=1148243202240405915, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031654075715584, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/dyxb/CN, language=CN, createTime=1751692112741, createBy=18614031015, updateTime=1753435242839, updateBy=18614031015, name=电源学报-中文站点, tplId=1146099689490845704, title=电源学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618015060553758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=articleTextType, value=kx, createTime=1751781475081, updateTime=1751781475081, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015035387931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=banner, value=null, createTime=1751781475075, updateTime=1751781475075, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015022805018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=efYTu4aDDzS8GgTA1MjEKw==, createTime=1751781475072, updateTime=1751781475072, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015052165149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781475079, updateTime=1751781475079, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015043776540, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781475077, updateTime=1751781475077, creator=18614031015, updator=18614031015)])], journalTitle=电源学报, weixinUrl=null, journalUrl=http://www.jops.cn/CN/home, iacademicId=null, status=0, seqNo=null, journalTitleEn=Journal of Power Supply, journalPhotoCn=Mx+A2dn+ULnPHuEAI1LruQ==, journalPhotoEn=yHt2vwjzkDgqh+JDCfJKoQ==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.1.1, detailUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/10.13234/j.issn.2095-2805.2024.1.1, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/PDF/10.13234/j.issn.2095-2805.2024.1.1, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/PDF/10.13234/j.issn.2095-2805.2024.1.1, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
数据驱动的钠离子电池健康状态评估方法研究
收藏切换
PDF下载
陆楠 1 , 孙越 1 , 彭鹏 1, 2 , 熊瑞 1 , 孙逢春 1
电源学报 | 特邀专栏 2024,22(1): 1-10
收起
收藏切换
电源学报 | 特邀专栏 2024, 22(1): 1-10
数据驱动的钠离子电池健康状态评估方法研究
全屏
陆楠1 , 孙越1 , 彭鹏1, 2 , 熊瑞1 , 孙逢春1
作者信息
  • 1 北京理工大学 机械和车辆学院 北京 100081
  • 2 南方电网调峰调频发电有限公司 储能科研院 广州 510630
  • 陆楠(2001-),女,硕士研究生。研究方向:电池老化评估与健康管理。E-mail: In1100101101@163.com。

    孙越(1998-),女,博士研究生。研究方向:电池老化评估与健康管理。E-mail: 13581196698@163.com。

    彭鹏(1988-),男,博士研究生。研究方向:电池储能管理。E-mail: 13926169785@139.com。

    熊瑞(1985-),男,中国电源学会会员,通信作者,博士,教授。研究方向:电池管理与控制。E-mail:rxiong@bit.edu.cn。

    孙逢春(1958-),男,博士,教授,中国工程院院士。研究方向:电动车辆与电传动。E-mail:sunfch@bit.edu.cn。

Data-driven State of Health Estimation for Sodium-ion Batteries
Nan LU1 , Yue SUN1 , Peng PENG1, 2 , Rui XIONG1 , Fengchun SUN1
Affiliations
  • 1 School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China
  • 2 CSG PGC Energy Storage Research Institute Guangzhou 510630 China
出版时间: 2024-01-30 doi: 10.13234/j.issn.2095-2805.2024.1.1
文章导航
收藏切换

钠离子电池健康状态估计是其安全高效应用的基础,也是钠电池规模化储能应用的关键。然而,钠离子电池即用即衰,衰退机理不明晰,老化过程受工况和场景影响,准确的健康状态估计极其困难。为此,提出了数据驱动的钠离子电池健康状态估计方法,探究了钠离子电池的充电数据与容量衰退的映射关系,提出了结合方差筛选、灰色关联分析和递归特征消除的特征选择方法,应用多元线性回归、支持向量机、高斯过程回归和误差反向传播神经网络4类机器学习方法估计钠离子电池的健康状态。验证结果表明,4类方法的健康状态估计均方根误差小于1.6%,其中高斯过程回归的误差小于0.8%,实现了钠离子电池健康状态精准估计。

钠离子电池  /  健康状态  /  数据驱动  /  老化特征  /  机器学习

The state of health (SOH) estimation for sodium-ion batteries is crucial for their safe and efficient applications, which is also a key to large-scale energy storage implementations. However, sodium-ion batteries exhibit usage-induced degradation with unclear mechanisms and are sensitive to operating conditions and environmental factors, posing a challenge to the accurate SOH estimation. In this paper, a data-driven SOH estimation method for sodium-ion batteries is proposed. The charging data is correlated with capacity degradation, and variance filtering, grey relational analysis and recursive feature elimination are integrated for feature selection. In addition, four machine learning methods including multiple linear regression, support vector machine, Gaussian process regression and error back propagation neural network are applied to formulate the corresponding estimation methods. Test results reveal that the root mean square errors for the four methods are all less than 1.6%, with Gaussian process regression showing an error rate below 0.8%, indicating a precise SOH estimation for sodium-ion batteries.

Sodium-ion battery  /  state of health(SOH)  /  data driven  /  aging feature  /  machine learning
陆楠, 孙越, 彭鹏, 熊瑞, 孙逢春. 数据驱动的钠离子电池健康状态评估方法研究. 电源学报, 2024 , 22 (1) : 1 -10 . DOI: 10.13234/j.issn.2095-2805.2024.1.1
Nan LU, Yue SUN, Peng PENG, Rui XIONG, Fengchun SUN. Data-driven State of Health Estimation for Sodium-ion Batteries[J]. Journal of Power Supply, 2024 , 22 (1) : 1 -10 . DOI: 10.13234/j.issn.2095-2805.2024.1.1
锂离子电池被广泛应用于电动化交通、电池储能和便携式电子设备, 然而锂作为一种稀有金属元素, 储量有限, 难以满足锂电池技术带来的日益增长的能源需求[1]。钠盐储备丰富和工作原理相似促使钠离子电池成为大规模储能领域的重要备选技术。相较于锂离子电池, 钠离子电池在资源和安全方面具有明显优势。钠储量丰富,占地壳元素总含量的 2.83%,远高于锂的丰度${\left({0.01}\%\right)}^{\left\lbrack 3\right\rbrack }$。然而,作为复杂电化学系统,钠离子电池工作过程中存在各类副反应, 使其随时间推移和循环工作产生不可避免的性能衰退, 从而使储能设备、电动汽车等用电器的性能大打折扣,甚至危及安全[4]。因此,探究如何精准高效估计钠离子电池健康状态$\mathrm{{SOH}}$ (state of health) 是确保其安全高效应用的基础。
电池健康状态, 描述电池当前性能与初始性能之比,是评估电池老化程度的量化指标[5]。现有$\mathrm{{SOH}}$ 估计方法主要分为三大类:测量分析法、自适应算法和数据驱动法。测量分析法通过对电流、电压和阻抗等参数的分析辨识电池$\mathrm{{SOH}}$;自适应算法基于模型构建状态空间方程, 将容量或内阻视为待估计参数,结合观测器或滤波器实时更新SOH[6]; 数据驱动法则运用机器学习算法挖掘电池老化敏感参数并映射到$\mathrm{{SOH}}$,常用算法包括高斯过程回归 GPR (Gaussian process regression)、神经网络、支持向量机 SVM(support vector machine)等[7]。Feng 等[8] 基于小波分析的 GRP 模型预测钠离子电池$\mathrm{{SOH}}$, 其单步$\mathrm{{SOH}}$ 预测均方根误差为${0.8}\%$,展示了数据驱动法在电池$\mathrm{{SOH}}$ 估计方面的潜力和有效性。
目前, 钠离子电池老化研究处于起步阶段, 鉴于钠离子具有更大半径, 其对电池相变行为和副反应的影响可能更为显著。例如, 合金类负极材料在钠嵌入/脱嵌时产生的巨大体积变化会导致电极粉末化[9],硬碳负极材料会导致电解质分离和较差的离子扩散动力学等严重的副反应[10]。因此,建立准确描述钠离子电池老化过程的机理模型极具挑战性。数据驱动方法无需精确的数学模型或者先验知识[11],为钠离子电池$\mathrm{{SOH}}$ 估计提供解决方案。Wei 等[12] 以 18650 型钠离子电池为研究对象, 通过增量容量分析解释老化机制并提取老化特征预测电池老化。数据驱动方法的性能通常受到输入特征的影响, 老化特征的适用性与可用性有待探究。钠离子电池体系众多,机理研究较少且老化数据可用性有限, 缺少一种通用且有效的钠离子电池特征提取以及评价方法。
综上所述, 本文以电池老化数据分析为出发点, 提取电池老化特征并结合机器学习算法, 提出钠离子电池健康状态估计方法。首先, 从全电压范围和部分电压范围数据中提取特征,结合方差筛选、灰色关联分析 GRA(grey relational analysis) 和递归特征消除 RFE (recursive feature elimination) 等方法筛选高效特征;其次,分别采用多元线性回归、 支持向量机、高斯过程回归以及误差反向传播 BP (back propagation) 神经网络构建$\mathrm{{SOH}}$ 估计模型,并基于${2.5}\mathrm{{Ah}}$ 软包钠离子电池的老化测试数据验证不同模型的性能。
通常按照容量的衰减程度定义电池的健康状态,即$\mathrm{{SOH}}$ 为电池当前容量与初始容量的比值,则有
$\mathrm{{SOH}}= \frac{{Q}_{\text{act }}}{{Q}_{\text{nom }}}\times {100}\%$
式中:${Q}_{\text{act }}$ 为当前老化状态下的实际容量;${Q}_{\text{nom }}$ 为标称容量。
健康状态估计方法的总体架构流程如图1 所示, 主要包括 4 部分。
(1)数据分析:利用实验采集的电池充电数据, 分析获取相关测量或计算参数与容量衰退的映射关系。
(2)特征提取:基于部分充电数据和增量容量曲线提取电压统计值、区间容量、增量容量曲线峰值等参数。
(3)特征选择:结合方差筛选、灰色关联分析和递归特征消除等特征选择算法, 从计算和测量参数中选取最富信息量的特征,用于表征电池的健康状态。
(4)SOH 估计:在选定的老化特征基础上,采用多元线性回归、SVM、GPR 和 BP 神经网络等 4 种主流机器学习方法对电池$\mathrm{{SOH}}$ 进行估计,并在${2.5}\mathrm{{Ah}}$ 软包钠离子电池的老化测试数据下进行算法验证。
重点讨论特征提取、特征选择和 SOH 估计。特征选择和$\mathrm{{SOH}}$ 估计具体算法流程如图2 所示。
老化特征作为数据驱动法的核心要素, 其可靠性和有效性是准确估计$\mathrm{{SOH}}$ 的基础。高质量的衰退特征应易于提取且能有效表征电池老化过程[13]。 电池老化常用评价指标容量和内阻在线测量困难, 因此有必要研究衰退特征的过程性表征。文献[14] 总结了可用于$\mathrm{{SOH}}$ 估计的主要特征,包括基于电压、阻抗、时间、温度、超声波和力等特性参数。实际工作条件下电池放电行为随机不可控, 但充电过程一般遵循固定的充电倍率模式, 充电电流由充电器稳定调节[15],因此可以基于充电电压数据提取老化特征指示电池$\mathrm{{SOH}}$。在充电过程中,电池容量是电压的函数, 即
$ Q\left( V\right)= {\int }_{V\left( t\right)= {V}_{\text{lower }}}^{V\left( t\right)= V}\left|{I\left( t\right)}\right|\mathrm{d}t $
式中,${V}_{\text{lower }}$ 为电池下截止电压。充电过程中某电压区间段的容量可通过电压阶跃$\mathrm{d}V$ 离散为
${\Delta Q}\left({{V}_{1},{V}_{2}}\right)= {\int }_{V\left( t\right)= {V}_{1}}^{V\left( t\right)= {V}_{2}}\left|{I\left( t\right)}\right|\mathrm{d}t = Q\left({V}_{2}\right)- Q\left({V}_{1}\right)$
式中,${V}_{1}$${V}_{2}$ 分别为电压段的起点和终点。
值得注意的是, 电池参数的均值、标准差、最小值和最大值等统计数据均可作为电池老化特征。电池利用过程中, 较容易获得部分电压区间数据, 所以在特征提取过程中, 可以通过等宽分组和等充入电量分组[14] 将电压区间进行划分,再依据分电压区间提取特征。
首先,等宽分组法将已知电压区间$\left\lbrack {{U}_{\mathrm{L}},{U}_{\mathrm{H}}}\right\rbrack$ 均等划分为${n}_{\mathrm{{ew}}}$ 段,${n}_{\mathrm{{ew}}}$ 为分组数,电压段宽度可表示为
$\Delta {U}_{\mathrm{{ew}}}= \frac{{U}_{\mathrm{H}}- {U}_{\mathrm{L}}}{{n}_{\mathrm{{ew}}}}$
其次, 等充入电量分组法通过等分电池充电容量区间划分电压范围,其中充电容量由式 (2) 计算, 积分上、下限是充电过程的下截止电压${V}_{\text{lower }}$ 和上截止电压${V}_{\text{upper }}$,通常使用的电池容量是电池初始容量。可以依据分电压区间提取分段容量和电压统计量作为老化特征。
最后,还可以通过特征曲线提取老化特征,例如 IC 曲线的峰值特征。研究表明, 电池容量衰减与终端电压的变化密切相关[21], IC 曲线可以将电池内部电化学反应引起的电压平台转换成 IC 峰[18], IC 峰与嵌入/脱嵌过程中引起的钠离子电池活性材料的相变有关[12]
电池$\mathrm{{SOH}}$ 估计模型依赖于老化特征与$\mathrm{{SOH}}$ 的映射关系, 但是有效的映射关系有限, 使用过多无关健康因子容易导致过拟合风险,而且显著增加计算成本。本文利用常见的过滤式和包裹式特征选择方法进行特征选择[19]。灰色关联分析是一类常用的过滤式办法,“灰色” 描述已知信息的比例;“白色”和“黑色”分别表示信息量为 0 和${100}{\%}^{\left\lbrack {20}\right\rbrack }$。其基本思想是研究曲线间的几何接近度以评估其关系, 接近度越高表明相关性越强。因此其可以描述电池老化特征变化曲线与容量衰退曲线之间的几何接近度。基于支持向量机的递归特征消除是一类包裹式特征选择方法, 使用 SVM 的权重作为排序标准, 权重向量$w$ 包含数据集各特征的权重[21]。每次迭代, 移除权重向量中的最小值, 即最不重要的特征。在特征集合上重复递归操作直至特征集合为空,即可输出特征的重要性排序。
多元线性回归模型描述因变量与多个自变量之间的线性关系,输入电池$d$ 维老化特征$X =\left\lbrack {x}_{1}\right.$,$\left.{{x}_{2},\cdots,{x}_{d}}\right\rbrack$,输出电池$\mathrm{{SOH}}$$Y$。通过训练辨识偏回归系数${\left\lbrack {\alpha }_{1},{\alpha }_{2},\cdots,{\alpha }_{d}\right\rbrack }^{\mathrm{T}}$ 和待拟合常数$\beta$,可得到钠离子电池 SOH 估计模型。
支持向量机可通过核函数将输入数据映射到更高维的特征空间来处理非线性可分的数据, 因此适用于电池容量衰退的非线性轨迹, 同时 SVM 对于处理钠电小数据样本和高维数据很有优势。其中高斯核函数适用于求解非线性问题且参数较少, 可提高模型精度。SVM 通过选择支持向量来定义超平面和计算边际, 并通过寻找参数优化超平面, 这些参数在最小化分类误差的同时最大化边际, 因此优化模型参数$\omega$$b$ 可显著提升模型泛化能力及精度。
高斯过程回归利用概率方法训练样本数据, 无需特定函数形式构建模型, 适用于高维、小样本、非线性的回归问题[22]。高斯过程回归由均值函数和协方差函数确定, 并利用贝叶斯学习过程根据训练数据和先验分布估计后验分布[18],其目的是建立输入与输出的映射关系, 输出估计结果及其不确定性, GPR 模型精度依赖于其函数和参数选择。
$\mathrm{{BP}}$ 神经网络是一类典型的前馈网络,其核心思想是信号前向传播和误差反向传播[23]。BP 神经网络包括输入层、隐含层和输出层, 各层之间采用全连接方式。通过梯度下降法, 网络能够调整权重使得实际输出值的平方误差之和最小化, 三层 BP 神经网络能以任意精度逼近任意非线性函数[24]。BP 神经网络的训练循环进行信息正向传播和误差反向传播修正权值, 最终停在预设的误差最小值或训练步骤,得到表征电池$\mathrm{{SOH}}$ 估计模型。修正权值时采用梯度下降法求解无约束最优化方程, 导致学习收敛速度慢且易收敛到局部极小值[24]。首先,学习率影响 BP 神经网络的收敛性,并控制算法迭代的更新步长,学习率小、收敛速度慢,过大则易引起振荡[19]。其次,模型精度依赖于隐含层数和神经元数目,合适的神经元数目能显著优化模型训练时间和学习能力。
本文搭建的电池测试平台如图3 所示, 主要包括 Arbin-BT2000-5V-30A 电池充放电设备、DGBELL 可控温箱、上位机、钠离子电池单体以及电池夹具等。其中, 充放电设备通过夹具与电池连接, 用于对被测电池施加电流激励, 并通过传感器采集被测钠离子电池的电流电压信号;温度箱用于放置电池并为其提供恒定在实验所需温度的工作环境;上位机实现对充放电设备的控制并接收测试数据。本文实验使用额定容量${2.5}\mathrm{{Ah}}$ 的 4 只软包钠离子电池进行测试, 其正极材料为层状氧化物 (镍铁锰酸钠)、 负极材料为硬碳,具体参数如表1 所示。
本次实验分为特性测试和加速寿命测试两部分, 特性测试包含容量标定、开路电压测试。实验环境温度为${25}^{\circ }\mathrm{C}$,按照$1\mathrm{C}$ 倍率恒流充电至上截止电压${3.95}\mathrm{\;V}$ -静置${10}\mathrm{\;{min}}- {0.5}/1\mathrm{C}$ 倍率恒流放电至下截止电压${1.5}\mathrm{\;V}$ -静置${10}\mathrm{\;{min}}$ 循环测试至电池容量衰减到$\mathrm{{SOH}}$ 失效阈值${80}\%$,采样频率为$1\mathrm{\;{Hz}}$。考虑不同放电倍率条件下动力电池性能衰退特性, 不同放电倍率下实验样本各为 2 只电池。测试电池的容量和$\mathrm{{SOH}}$ 趋势如图4 所示,电池的寿命均接近 50 个循环,容量和$\mathrm{{SOH}}$ 随着充放电循环进行呈现退化趋势, 但伴随着无规律的局部波动。
电池的容量衰减与终端电压的变化密切相关[20]。由图5(a)可见,随电池充放电循环进行,相同充电电压对应更小的容量, 因此充电电压相关参数能够表征电池老化;IC 曲线将电池内部电化学反应引起的电压平台转换成 IC 峰[18],同时 IC 峰与插层/去插层过程引起的钠离子电池活性材料的相变有关[25]。Wei 等[12] 研究发现 IC 峰的高度和面积与反应钠离子的量有关,峰的位置和斜率与氧化还原反应密切相关, 因此 IC 曲线峰值特征参数亦映射电池老化;其中峰值面积代表峰值所覆盖的特定电压范围的累计充/放电容量, 表明在电池不同老化条件下, 使电池端电压发生相同变化所需的容量变化不同。图5(b)表明不同分电压区间的累计容量变化同样可以指示电池$\mathrm{{SOH}}$
本文实验所用软包钠离子电池的上截止电压为${3.95}\mathrm{\;V}$,下截止电压为${1.50}\mathrm{\;V}$。实际应用场景中, 充电过程开始于各种状态, 且通常不会以完全充电状态结束,完整的充电曲线难以获取[26]。因此,本文基于充电数据提取的老化特征只覆盖${3.20}\sim {3.95}\mathrm{\;V}$ 电池实际工作常用的电压范围。基于部分电压区间提取的老化特征质量与电压区间宽度有关, 随电压区间宽度减小, 所提取特征的噪声增大, SOH 估计精度较差,故应限制电压区间的最小宽度[14]。电压范围的增大在提高精度的同时需要从更大的电压范围内获取数据, 增大实际应用中的数据获取难度。本文基于不同的宽度划分电压区间进行特征提取, 参考 Xiong 等 [14]的方法, 确定最小电压区间宽度为${0.15}\mathrm{\;V}$,依据论文提出的等宽分组和等充入电量分组法对电压区间进行划分。电压区间划分与特征提取结果如表2 所示, 其中等宽分组法中的 EW10~ EW14 的提出是为了验证是否可以无需计算 IC 曲线直接得到能够指示$\mathrm{{SOH}}$ 的分电压区间的累计容量变化值。
初步提取 50 个钠离子电池备选老化特征, 机器学习模型可通过训练学习建立所提取老化特征与$\mathrm{{SOH}}$ 的映射关系,但特征的质量影响模型的精度, 且数量过多的特征输入会增加计算成本和过拟合的风险[27],因此本节结合方差选择法、灰色关联分析与递归特征消除方法逐层筛选出对电池容量衰减最富信息的老化特征。
首先, 对所提取的 50 个特征做初步方差筛选, 方差过小说明提取的特征不随电池老化而对应改变,滤去方差小于${10}^{-4}$ 的特征; 其次,对初步筛选后的特征进行灰色关联分析, 选择与电池衰退轨迹几何接近度更好的特征,定义阈值为 0.65 ;最后,对关联度大于 0.65 的 15 个特征进行递归特征消除计算。递归特征消除用于训练的基模型选择 SVM, 第 1 次训练选择现有所有特征, 每次迭代按照权重降序排列并去除排在末尾的特征, 直至特征集合为空, 得到特征集合的排序集。本文选择排名前 4 的特征用作钠离子电池$\mathrm{{SOH}}$ 估计模型的输入,依次为: EQ3 容量区间下的电压标准差、EQ2 容量区间下的电压最小值、EQ1 容量区间下的电压最大值和 EW9 电压区间下的充入容量值。
本文采用多元线性回归、SVM、GPR 和 BP 神经网络等 4 种机器学习方法分别构建钠离子电池$\mathrm{{SOH}}$ 估计模型。$\mathrm{{SOH}}$ 估计结果与误差如图6 所示。 在多元线性回归模型中, 通过对训练集数据的拟合得到偏回归系数和常数项。支持向量机和高斯过程回归的核函数分别选择高斯核函数与平方指数核函数,采用基于$k$ 折交叉验证的网格搜索算法优化主要超参数, 以提高模型的泛化能力和防止过拟合。BP 神经网络采用了一层隐含层, 神经元节点数为 3, 学习率设置为 0.1, 迭代次数限制为 100 次。训练集与测试集的比例通常为$7 : 3$$8 : 2$,钠离子电池样本共 4 只电池, 随机选取 3 只电池数据作为训练集, 剩余为测试集。为消除原始数据的不同维度对模型训练的影响, 归一化处理数据。图6 展示了 49 号电池为测试集时 4 种算法的$\mathrm{{SOH}}$ 估计结果,均接近真实值,图6(b)(d)(f)(h) 所示 SOH 估计误差基本在 1%以内,最大误差值小于 3%。
引入模型性能评估指标均方根误差 RMSE、拟合优度${R}^{2}$,用作分析所构建模型的性能,计算方法可表示为
$\left\{\begin{array}{l}\mathrm{{RMSE}}= \sqrt{\left\lbrack {\mathop{\sum }\limits_{{i = 1}}^{n}{\left({y}_{i}- f\left({x}_{i}\right)\right)}^{2}}\right\rbrack /m}\\{R}^{2}= 1 -\mathop{\sum }\limits_{{i = 1}}^{n}{\left({y}_{i}- f\left({x}_{i}\right)\right)}^{2}/\mathop{\sum }\limits_{{i = 1}}^{n}{\left({y}_{i}- {\bar{y}}_{i}\right)}^{2}\end{array}\right.\\ i = 1,2,\cdots, n $
式中:${y}_{i}$ 为真实值;${\bar{y}}_{i}$ 为真实值的平均值;$f\left({x}_{i}\right)$ 为估计值;$n$ 为样本个数。RMSE 表示估计值与真实值之间的偏差, 对数据中的异常点较为敏感, RMSE 越接近 0,模型性能越优秀; 拟合优度${R}^{2}$ 表示因变量的波动能被自变量的波动所描述的程度, 展示了$\mathrm{{SOH}}$ 估计值与真实值之间的相关性,因此可以评估模型准确度。${R}^{2}$ 越接近 1,表示模型精度越高。 4 个$\mathrm{{SOH}}$ 估计模型的性能评价指标如表3 所示。
SOH 估计性能指标表明, 基于所选的 4 个老化特征,多元线性回归、SVM、GPR、BP 神经网络均能实现钠离子电池$\mathrm{{SOH}}$ 的精准估计,其均方根误差依次为 1.2%、1.5%、0.8%和 1.4%。GPR 方法精度最高,图6 $\left(\mathrm{e}\right)$ 和(f)展示 GPR 估计的$\mathrm{{SOH}}$ 曲线接近真实曲线,分布区间窄,估计误差均在 1%以内。其次是多元线性回归模型, 本文钠离子电池的衰退轨迹曲线形状近似线性,多元线性回归模型估计曲线与真实$\mathrm{{SOH}}$ 曲线基本一致。$\mathrm{{BP}}$ 神经网络模型和 SVM 模型在电池寿命后期 SOH 估计值小幅度上飘,估计误差增大。钠离子电池数据具有小样本的特点, BP 神经网络无法得到大量的训练数据而导致更易过拟合。同时, 最终选定的特征均为基于充电电压直接或者间接得到, 实验直接采集的电压数据样本噪声较大以及参数的选择导致模型对噪声较为敏感等原因,导致 SVM 预测模型性能下降。
本文提出一种融合特征选择与机器学习算法的钠离子电池$\mathrm{{SOH}}$ 估计方法。首先,结合方差选择法、灰色关联分析与递归特征消除选择与钠离子电池$\mathrm{{SOH}}$ 最相关的特征; 其次,基于所选特征,分别利用多元线性回归、支持向量机、高斯过程回归、BP 神经网络构建钠离子电池的$\mathrm{{SOH}}$ 估计模型,并利用${2.5}\mathrm{{Ah}}$ 软包钠离子电池加速寿命老化实验数据对 4 个模型进行验证与性能分析。结果表明,对于老化特征选择结果, 4 种机器学习算法均能实现对钠离子电池$\mathrm{{SOH}}$ 的精准估计,$\mathrm{{SOH}}$ 估计均方根误差均小于 2%。其中, GPR 模型精度最高, 置信区间为${95}\%$ 时的$\mathrm{{SOH}}$ 估计均方根误差仅为${0.8}\%$,这为钠离子电池的管理与状态估计提供了有力支撑。
  • 南方电网公司重点科技项目(STKJXM20210104)
参考文献 引证文献
排序方式:
[1]
Xu Guiliang, Amine R, Abouimrane A, et al. Challenges in developing electrodes, electrolytes, and diagnostics tools to understand and advance sodium-ion batteries[J]. Advanced Energy Materials, 2018. 8(14): 1702403.
[2]
Li Fang, Wei Zengxi, Manthiram A, et al. Sodium-based batteries: From critical materials to battery systems[J]. Journal of Materials Chemistry A, 2019. 7(16): 9406-9431.
[3]
容晓晖, 陆雅翔, 戚兴国, 等. 钠离子电池:从基础研究到工程化探索[J]. 储能科学与技术, 2020. 9(2): 515-522.
Rong Xiaohui, Lu Yaxiang, Qi Xingguo, et al. Na-ion batteries: From fundamental research to engineering exploration[J]. Energy Storage Science and Technology, 2020. 9(2): 515-522 (in Chinese).
[4]
熊瑞. 动力电池管理系统核心算法[M]. 2版, 北京: 机械工业出版社, 2021.
Xiong Rui. Core Algorithm of Battery Management System for EVs[M]. 2nd Edition, Beijing: China Machine Press, 2021. (in Chinese).
[5]
Lipu MS H, Hannan M A, Hussain A, et al. A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations[J]. Journal of Cleaner Production, 2018. 205: 115-133.
[6]
Wang Yujie, Tian Jiaqiang, Sun Zhendong, et al. A comprehensive review of battery modeling and state estimation approaches for advanced battery management systems[J]. Renewable and Sustainable Energy Reviews, 2020. 131: 110015.
[7]
Ramezani S B, Cummins L, Killen B, et al. Scalability, explainability and performance of data-driven algorithms in predicting the remaining useful life: A comprehensive review[J]. IEEE Access, 2023. 11: 41741-41769.
[8]
Feng Yifeng, Shen Jiani, Che Haiying, et al. State of health prediction for sodium-ion batteries[J]. Energy Storage Science and Technology, 2021. 10(4): 1407.
[9]
Goikolea E, Palomares V, Wang Shijian, et al. Na-ion batteries-Approaching old and new challenges[J]. Advanced Energy Materials, 2020. 10(44): 2002055.
[10]
Tian Zhihong, Zhang Yu, Zhu Jixin, et al. A reanalysis of the diverse sodium species in carbon anodes for sodium ion batteries: A thermodynamic view[J]. Advanced Energy Materials, 2021. 11(47): 2102489.1-2102489.17.
[11]
Li Chuan, Zhang Huahua, Ding Ping, et al. Deep feature extraction in lifetime prognostics of lithium-ion batteries: Advances, challenges and perspectives[J]. Renewable and Sustainable Energy Reviews, 2023. 184: 113576.
[12]
Wei Meng, Balaya Palani, Ye Min, et al. Remaining useful life prediction for 18650 sodium-ion batteries based on incremental capacity analysis[J]. Energy, 2022. 261: 125151.
[13]
Shu Xing, Li Guang, Shen Jiangwei, et al. A uniform estimation framework for state of health of lithium-ion batteries considering feature extraction and parameters optimization[J]. Energy, 2020. 204: 117957.
[14]
Xiong Rui, Sun Yue, Wang Chenxu, et al. A data-driven method for extracting aging features to accurately predict the battery health[J]. Energy Storage Materials, 2023. 57: 460-470.
[15]
Zuo Hongyan, Liang Jingwei, Zhang Bin, et al. Intelligent estimation on state of health of lithium-ion power batteries based on failure feature extraction[J]. Energy, 2023. 282: 128794.
[16]
Zheng Linfeng, Zhu Jianguo, Lu DDC, et al. Incremental capacity analysis and differential voltage analysis based state of charge and capacity estimation for lithium-ion batteries[J]. Energy, 2018. 150: 759-769.
[17]
Zhu Jiangong, Dewi D M S, Knapp M, et al. Investigation of lithium-ion battery degradation mechanisms by combining differential voltage analysis and alternating current impedance[J]. Journal of Power Sources, 2020. 448: 227575.
[18]
Li Xiaoyu, Yuan Changgui, Li Xiaohui, et al. State of health estimation for Li-ion battery using incremental capacity analysis and Gaussian process regression[J]. Energy, 2020. 190: 116467.
[19]
周志华. 机器学习[M]. 1版, 北京: 清华大学出版社, 2016.
Zhou Zhihua. Maching Learning[M]. 1st Edition, Beijing: Tsinghua University Publishing House Co., Ltd, 2016. (in Chinese).
[20]
Sun Bingxiang, Jiang Jiuchun, Zheng Fangdan, et al. Practical state of health estimation of power batteries based on Delphi method and grey relational grade analysis[J]. Journal of Power Sources, 2015. 282: 146-157.
[21]
Richhariya B, Tanveer M, Rashid A H. Diagnosis of Alzheimer's disease using universum support vector machine based recursive feature elimination (USVM-RFE)[J]. Biomedical Signal Processing and Control, 2020. 59: 101903.
[22]
Zhao Jiahui, Zhu Yong, Zhang Bin, et al. Method of predicting SOH and RUL of Lithium-ion battery based on the combination of LSTM and GPR[J]. Sustainability, 2022. 14(19): 11865.
[23]
Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986. 323(6088): 533-536.
[24]
The improvements of BP neural network learning algorithm[C]// WCC 2000 -ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000: col 3, 2000: 1647-1649.
[25]
Wang Jianbiao, Luo Ningjing, Wu Junxiu, et al. Hierarchical spheres constructed by ultrathin VS2 nanosheets for sodium-ion batteries[J]. Journal of Materials Chemistry A, 2019. 7(8): 3691-3696.
[26]
Tian Jinpeng, Xiong Rui, Shen Weixiang, et al. Deep neural network battery charging curve prediction using 30 points collected in 10 min[J]. Joule, 2021. 5(6): 1521-1534.
[27]
Jiang Yiyue, Chen Yuan, Yang Fangfang, et al. State of health estimation of lithium-ion battery with automatic feature extraction and self-attention learning mechanism[J]. Journal of Power Sources, 2023. 556: 232466.
2024年第22卷第1期
PDF下载
345
140
引用本文
BibTeX
文章信息
doi: 10.13234/j.issn.2095-2805.2024.1.1
  • 接收时间:2024-01-03
  • 首发时间:2025-07-09
  • 出版时间:2024-01-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-03
  • 修回日期:2024-01-29
  • 录用日期:2024-01-29
基金
Key Project of CSG(STKJXM20210104)
南方电网公司重点科技项目(STKJXM20210104)
作者信息
    1 北京理工大学 机械和车辆学院 北京 100081
    2 南方电网调峰调频发电有限公司 储能科研院 广州 510630
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.1.1
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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