Article(id=1153695644687524322, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153695641046864317, articleNumber=null, orderNo=null, doi=10.13234/j.issn.2095-2805.2024.5.278, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1625068800000, receivedDateStr=2021-07-01, revisedDate=1631116800000, revisedDateStr=2021-09-09, acceptedDate=1631721600000, acceptedDateStr=2021-09-16, onlineDate=1752992076321, onlineDateStr=2025-07-20, pubDate=1727625600000, pubDateStr=2024-09-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752992076321, onlineIssueDateStr=2025-07-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752992076321, creator=13701087609, updateTime=1752992076321, updator=13701087609, issue=Issue{id=1153695641046864317, tenantId=1146029695717560320, journalId=1146031654075715584, year='2024', volume='22', issue='5', pageStart='1', pageEnd='330', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752992075453, creator=13701087609, updateTime=1753780969288, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1157004501661078352, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153695641046864317, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1157004501661078353, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153695641046864317, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=278, endPage=285, ext={EN=ArticleExt(id=1153695645073400293, articleId=1153695644687524322, tenantId=1146029695717560320, journalId=1146031654075715584, language=EN, title=Estimation of Lithium-ion Battery SOH Based on SSA-BPNN, columnId=1152281491788100462, journalTitle=Journal of Power Supply, columnName=Battery and Energy Storage, runingTitle=null, highlight=null, articleAbstract=

Since lithium-ion batteries have been widely applied in energy storage systems and electric vehicles, the accurate estimation of their state-of-health(SOH) is a necessary condition for ensuring the reliable and safe operation of the system. SOH is analyzed from the perspective of capacity, with seven health indicators which are extracted from the constant current-constant voltage charging voltage and temperature curves as input. Based on the data-driven method, a sparrow search algorithm-back propagation neural network(SSA-BPNN) SOH estimation method for lithium-ion batteries is proposed, and data enhancement is applied to further improve the model's robustness. Finally, this method is verified on the NASA Randomized Battery Usage Dataset. Compared with the traditional BP neural network without data enhancement, the SOH estimation accuracy of the proposed method is significantly improved. The maximum absolute error and root mean square error of SOH estimation on the test set are less than 3% and 1.32%, respectively. Experimental results show that this method has advantages of small error, fast convergence, global search capability and adaptation to different characteristics of battery aging.

, correspAuthors=null, 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=Kaifei ZHANG, Jinlong ZHANG, Manping LÜ), CN=ArticleExt(id=1153695680683041383, articleId=1153695644687524322, tenantId=1146029695717560320, journalId=1146031654075715584, language=CN, title=基于 SSA-BPNN的锂离子电池SOH估算, columnId=1149830274575463188, journalTitle=电源学报, columnName=电池与储能, runingTitle=null, highlight=null, articleAbstract=

锂离子电池已被广泛应用于储能系统与电动汽车中,精确地估算锂离子电池健康状态SOH(state-of-health)是保证系统安全可靠运行的必要条件。从容量的角度分析 SOH,在恒流-恒压 CC-CV(constant current-constant voltage)充电电压和温度曲线中提取了7个健康特征HI(health indicator)作为输入,基于数据驱动法提出了麻雀搜索算法-反向传播神经网络 SSA-BPNN(sparrow search algorithm-back propagation neural network)的锂离子电池 SOH 估算方法,并应用数据增强进一步提高模型的鲁棒性,最终在 NASA 锂离子电池随机使用数据集上进行验证。通过与未采取数据增强的传统BP神经网络相比,获得 SOH 估算精度有明显提升,测试集 SOH 估算的最大绝对误差和均方根误差分别小于3%和1.32%,实验结果表明该方法兼顾误差小,收敛快,全局搜索能力且能够适应电池老化差异特性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=veQqe3bWnI1V51ixeixjXw==, magXml=SkkJAWvzqRqMmDrSWez7BA==, pdfUrl=null, pdf=33KuH0R+NhGrk9ZXgcCuKA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=3o4dsmn6o8srHy7nWqaWhg==, mapNumber=null, authorCompany=null, fund=null, authors=

张凯飞(1995-),男,硕士研究生。研究方向:锂离子电池健康状态估算。E-mail: zkaif@stumail.ysu.edu.cn。

张金龙(1983-),男,通信作者,博士,副教授。研究方向:蓄电池储能技术研究。E-mail:maxlong83@163.com。

吕满平(1996-),男,硕士研究生。研究方向:同步电动机电机参数辨识。E-mail: lvmanpin1996@stumail.ysu.edu.cn。

, authorsList=张凯飞, 张金龙, 吕满平)}, authors=[Author(id=1154032916804919400, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zkaif@stumail.ysu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154032916863639660, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, authorId=1154032916804919400, language=EN, stringName=Kaifei ZHANG, firstName=Kaifei, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, School of Electrical Engineering Yanshan University Qinhuangdao 066004 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154032916918165614, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, authorId=1154032916804919400, language=CN, stringName=张凯飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004, bio={"img":"jK53ImsT8V9kAjcfM/6Gww==","content":"

张凯飞(1995-),男,硕士研究生。研究方向:锂离子电池健康状态估算。E-mail: zkaif@stumail.ysu.edu.cn。

"}, bioImg=jK53ImsT8V9kAjcfM/6Gww==, bioContent=

张凯飞(1995-),男,硕士研究生。研究方向:锂离子电池健康状态估算。E-mail: zkaif@stumail.ysu.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154032916742004835, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, xref=null, ext=[AuthorCompanyExt(id=1154032916746199140, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, companyId=1154032916742004835, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, School of Electrical Engineering Yanshan University Qinhuangdao 066004 China), AuthorCompanyExt(id=1154032916754587749, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, companyId=1154032916742004835, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004)])]), Author(id=1154032916976885874, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=maxlong83@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154032917035606132, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, authorId=1154032916976885874, language=EN, stringName=Jinlong ZHANG, firstName=Jinlong, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, School of Electrical Engineering Yanshan University Qinhuangdao 066004 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154032917085937782, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, authorId=1154032916976885874, language=CN, stringName=张金龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004, bio={"content":"

张金龙(1983-),男,通信作者,博士,副教授。研究方向:蓄电池储能技术研究。E-mail:maxlong83@163.com。

"}, bioImg=null, bioContent=

张金龙(1983-),男,通信作者,博士,副教授。研究方向:蓄电池储能技术研究。E-mail:maxlong83@163.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154032916742004835, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, xref=null, ext=[AuthorCompanyExt(id=1154032916746199140, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, companyId=1154032916742004835, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, School of Electrical Engineering Yanshan University Qinhuangdao 066004 China), AuthorCompanyExt(id=1154032916754587749, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, companyId=1154032916742004835, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004)])]), Author(id=1154032917127880826, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lvmanpin1996@stumail.ysu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154032917186601086, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, authorId=1154032917127880826, language=EN, stringName=Manping LÜ, firstName=Manping, middleName=null, lastName=LÜ, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, School of Electrical Engineering Yanshan University Qinhuangdao 066004 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154032917245321345, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, authorId=1154032917127880826, language=CN, stringName=吕满平, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004, bio={"content":"

吕满平(1996-),男,硕士研究生。研究方向:同步电动机电机参数辨识。E-mail: lvmanpin1996@stumail.ysu.edu.cn。

"}, bioImg=null, bioContent=

吕满平(1996-),男,硕士研究生。研究方向:同步电动机电机参数辨识。E-mail: lvmanpin1996@stumail.ysu.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154032916742004835, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, xref=null, ext=[AuthorCompanyExt(id=1154032916746199140, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, companyId=1154032916742004835, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, School of Electrical Engineering Yanshan University Qinhuangdao 066004 China), AuthorCompanyExt(id=1154032916754587749, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, companyId=1154032916742004835, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004)])])], keywords=[Keyword(id=1154032917807358090, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, orderNo=1, keyword=Lithium-ion battery), Keyword(id=1154032917874466955, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, orderNo=2, keyword=state-of-health(SOH) estimation), Keyword(id=1154032917920604300, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, orderNo=3, keyword=data-driven), Keyword(id=1154032917966741645, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, orderNo=4, keyword=sparrow search algorithm-back prop-agation neural network (SSA-BPNN)), Keyword(id=1154032918012878990, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, orderNo=5, keyword=data enhancement), Keyword(id=1154032918059016335, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, orderNo=1, keyword=锂离子电池), Keyword(id=1154032918105153680, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, orderNo=2, keyword=健康状态估算), Keyword(id=1154032918168068241, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, orderNo=3, keyword=数据驱动), Keyword(id=1154032918222594194, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, orderNo=4, keyword=SSA-BPNN), Keyword(id=1154032918268731539, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, orderNo=5, keyword=数据增强)], refs=[Reference(id=1154032920739176624, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2019, volume=4, issue=5, pageStart=383, pageEnd=391, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Severson KA, Attia PM, Jin N, journalName=Nuture Energy, refType=null, unstructuredReference=Severson KA, Attia PM, Jin N, et al. Data-driven prediction of battery cycle life before capacity degradation[J]. Nuture Energy, 2019. 4(5): 383-391., articleTitle=Data-driven prediction of battery cycle life before capacity degradation, refAbstract=null), Reference(id=1154032920789508273, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2019, volume=235, issue=null, pageStart=661, pageEnd=672, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Cadini F, Sbarufatti C, Cancelliere F, journalName=Applied Energy, refType=null, unstructuredReference=Cadini F, Sbarufatti C, Cancelliere F, et al. State-of-life prognosis and diagnosis of lithium-ion batteries by data-driven particle filters[J]. Applied Energy, 2019. 235: 661-672., articleTitle=State-of-life prognosis and diagnosis of lithium-ion batteries by data-driven particle filters, refAbstract=null), Reference(id=1154032920844034226, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=李国政, journalName=null, refType=null, unstructuredReference=李国政. 数据驱动的航天器电池性能退化建模方法研究[D]. 长沙: 国防科技大学, 2018., articleTitle=数据驱动的航天器电池性能退化建模方法研究, refAbstract=null), Reference(id=1154032920894365875, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Li Guozheng, journalName=null, refType=null, unstructuredReference=Li Guozheng. Research on modeling method of data-driven spacecraft battery performance degradation[D]. Changsha: National University of Defense Technology, 2018. (in Chinese)., articleTitle=Research on modeling method of data-driven spacecraft battery performance degradation, refAbstract=null), Reference(id=1154032920940503220, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=5, pageStart=7651, pageEnd=7662, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Sun Yening, Zhang Jinlong, Zhang Kaifei, journalName=International Journal of Energy Research, refType=null, unstructuredReference=Sun Yening, Zhang Jinlong, Zhang Kaifei, et al. Battery state of health estimation method based on sparse auto-encoder and backward propagation fading diversity among battery cells[J]. International Journal of Energy Research, 2021. 45(5): 7651-7662., articleTitle=Battery state of health estimation method based on sparse auto-encoder and backward propagation fading diversity among battery cells, refAbstract=null), Reference(id=1154032920990834869, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=1, pageStart=61, pageEnd=67, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=张金龙, 李端凯, 佟微, journalName=燕山大学学报, refType=null, unstructuredReference=张金龙, 李端凯, 佟微, 等. 锂离子电池老化差异特性研究现状[J]. 燕山大学学报, 2019. 43(1): 61-67., articleTitle=锂离子电池老化差异特性研究现状, refAbstract=null), Reference(id=1154032921070526646, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=1, pageStart=61, pageEnd=67, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Zhang Jinlong, Li Duankai, Tong Wei, journalName=Journal of Yanshan University, refType=null, unstructuredReference=Zhang Jinlong, Li Duankai, Tong Wei, et al. Research status of Li-ion battery aging diversities[J]. Journal of Yanshan University, 2019. 43(1): 61-67 (in Chinese)., articleTitle=Research status of Li-ion battery aging diversities, refAbstract=null), Reference(id=1154032921133441207, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2019, volume=412, issue=null, pageStart=442, pageEnd=450, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Guo Peiyao, Cheng Ze, Yang Lei, journalName=Journal of Power Sources, refType=null, unstructuredReference=Guo Peiyao, Cheng Ze, Yang Lei. A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction[J]. Journal of Power Sources, 2019. 412: 442-450., articleTitle=A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction, refAbstract=null), Reference(id=1154032921187967160, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=277, issue=null, pageStart=115504, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Li Yuanyuan, Sheng Haimin, Cheng Yuhua, journalName=Applied Energy, refType=null, unstructuredReference=Li Yuanyuan, Sheng Haimin, Cheng Yuhua, et al. State-of-health estimation of lithium-ion batteries based on semi-supervised transfer component analysis[J]. Applied Energy, 2020. 277: 115504., articleTitle=State-of-health estimation of lithium-ion batteries based on semi-supervised transfer component analysis, refAbstract=null), Reference(id=1154032921246687417, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2017, volume=15, issue=2, pageStart=128, pageEnd=134, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=张金龙, 佟微, 孙叶宁, journalName=电源学报, refType=null, unstructuredReference=张金龙, 佟微, 孙叶宁, 等. 锂离子电池健康状态估算方法综述[J]. 电源学报, 2017. 15(2): 128-134., articleTitle=锂离子电池健康状态估算方法综述, refAbstract=null), Reference(id=1154032921313796282, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2017, volume=15, issue=2, pageStart=128, pageEnd=134, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Zhang Jinlong, Tong Wei, Sun Yening, journalName=Journal of Power Supply, refType=null, unstructuredReference=Zhang Jinlong, Tong Wei, Sun Yening, et al. Summarize of lithium battery status of health estimation method[J]. Journal of Power Supply, 2017. 15(2): 128-134 (in Chinese)., articleTitle=Summarize of lithium battery status of health estimation method, refAbstract=null), Reference(id=1154032921364127931, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=刘月峰, journalName=null, refType=null, unstructuredReference=刘月峰. 基于数据驱动的锂离子电池剩余寿命融合预测方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2020., articleTitle=基于数据驱动的锂离子电池剩余寿命融合预测方法研究, refAbstract=null), Reference(id=1154032921414459580, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=Liu Yuefeng, journalName=null, refType=null, unstructuredReference=Liu Yuefeng. Research on data-driven fusion prediction method of Lithum-ion battery remaining useful life[D]. Harbin: Harbin Institute of Technology, 2020. (in Chinese)., articleTitle=Research on data-driven fusion prediction method of Lithum-ion battery remaining useful life, refAbstract=null), Reference(id=1154032921468985533, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2009, volume=86, issue=9, pageStart=1506, pageEnd=1511, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=Ng K S, Moo CS, Chen Yiping, journalName=Applied Energy, refType=null, unstructuredReference=Ng K S, Moo CS, Chen Yiping, et al. Enhanced coulomb counting method for estimating state-of-charge and state-of-health of lithium-ion batteries[J]. Applied Energy, 2009. 86(9): 1506-1511., articleTitle=Enhanced coulomb counting method for estimating state-of-charge and state-of-health of lithium-ion batteries, refAbstract=null), Reference(id=1154032921544483006, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=11, issue=1, pageStart=2419, pageEnd=2430, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=Zhang Yunwei, Tang Qiaochu, Zhang Yao, journalName=Nature Communications, refType=null, unstructuredReference=Zhang Yunwei, Tang Qiaochu, Zhang Yao, et al. Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning[J]. Nature Communications, 2020. 11(1): 2419-2430., articleTitle=Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning, refAbstract=null), Reference(id=1154032921599008959, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2019, volume=1, issue=C, pageStart=100005, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=Han Xuebing, Lu Languang, Zheng Yuejiu, journalName=eTransportation, refType=null, unstructuredReference=Han Xuebing, Lu Languang, Zheng Yuejiu, et al. A review on the key issues of the lithiumion battery degradation among the whole life cycle[J]. eTransportation, 2019. 1(C): 100005., articleTitle=A review on the key issues of the lithiumion battery degradation among the whole life cycle, refAbstract=null), Reference(id=1154032921653534912, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2018, volume=16, issue=1, pageStart=145, pageEnd=150, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=刘璇, 王立欣, 吕超, journalName=电源学报, refType=null, unstructuredReference=刘璇, 王立欣, 吕超, 等. 锂离子电池建模与参数识别[J]. 电源学报, 2018. 16(1): 145-150., articleTitle=锂离子电池建模与参数识别, refAbstract=null), Reference(id=1154032921699672257, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2018, volume=16, issue=1, pageStart=145, pageEnd=150, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=Liu Xuan, Wang Lixin, Lü Chao. et al, journalName=Journal of Power Supply, refType=null, unstructuredReference=Liu Xuan, Wang Lixin, Chao. et al. Modeling and parameter identification for lithium-ion battery[J]. Journal of Power Supply, 2018. 16(1): 145-150 (in Chinese)., articleTitle=Modeling and parameter identification for lithium-ion battery, refAbstract=null), Reference(id=1154032921750003906, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2018, volume=162, issue=null, pageStart=98, pageEnd=107, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=Wang Wenxu, Tang Ruichun, Li Cheng, journalName=Ocean Engineering, refType=null, unstructuredReference=Wang Wenxu, Tang Ruichun, Li Cheng, et al. A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights[J]. Ocean Engineering, 2018. 162: 98-107., articleTitle=A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights, refAbstract=null), Reference(id=1154032921800335555, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=35, pageEnd=40, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=null, journalName=2015 7th International Conference on Information Technology and Electrical Engineering. Chiang Mai, Thailand, refType=null, unstructuredReference=A comparative study of optimization methods for improving artificial neural network performance[C]// 2015 7th International Conference on Information Technology and Electrical Engineering. Chiang Mai, Thailand, 2015: 35-40., articleTitle=A comparative study of optimization methods for improving artificial neural network performance, refAbstract=null), Reference(id=1154032921863250116, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=868375.1, pageEnd=868375.12, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=Nawi N M, Khan A, Rehman M Z, journalName=Mathematical Problems in Engineering, refType=null, unstructuredReference=Nawi N M, Khan A, Rehman M Z, et al. Weight optimization in recurrent neural networks with hybrid meta-heuristic cuckoo search techniques for data classification[J]. Mathematical Problems in Engineering, 2015: 868375.1-868375.12., articleTitle=Weight optimization in recurrent neural networks with hybrid meta-heuristic cuckoo search techniques for data classification, refAbstract=null), Reference(id=1154032921913581765, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=1, pageStart=22, pageEnd=34, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=Xue Jiankai, Shen Bo, journalName=Systems Science & Control Engineering, refType=null, unstructuredReference=Xue Jiankai, Shen Bo. A novel swarm intelligence optimization approach: Sparrow search algorithm[J]. Systems Science & Control Engineering, 2020. 8(1): 22-34., articleTitle=A novel swarm intelligence optimization approach: Sparrow search algorithm, refAbstract=null), Reference(id=1154032921959719110, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=22, authorNames=邱锡鹏, journalName=null, refType=null, unstructuredReference=邱锡鹏. 神经网络与深度学习[M]. 北京: 机械工业出版社, 2020., articleTitle=神经网络与深度学习, refAbstract=null), Reference(id=1154032922005856455, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=Qiu Xipeng, journalName=null, refType=null, unstructuredReference=Qiu Xipeng. Neural Networks and Deep Learning[M]. Beijing: China Machine Press, 2020. (in Chinese)., articleTitle=Neural Networks and Deep Learning, refAbstract=null), Reference(id=1154032922056188104, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=29, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=null, journalName=2014 Conference of the Prognostics & Health Management Society. Fort Worth, TX, USA, refType=null, unstructuredReference=Adaptation of an electro-chemistry-based li-ion battery model to account for deterioration observed under randomized use[C]// 2014 Conference of the Prognostics & Health Management Society. Fort Worth, TX, USA, 2014: 29., articleTitle=Adaptation of an electro-chemistry-based li-ion battery model to account for deterioration observed under randomized use, refAbstract=null), Reference(id=1154032922114908361, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=19, pageStart=4106, pageEnd=4119, url=null, language=null, rfNumber=[20], rfOrder=25, authorNames=李超然, 肖飞, 樊亚翔, journalName=电工技术学报, refType=null, unstructuredReference=李超然, 肖飞, 樊亚翔, 等. 基于卷积神经网络的离子电池 SOH 估算[J]. 电工技术学报, 2020. 35(19): 4106-4119., articleTitle=基于卷积神经网络的离子电池 SOH 估算, refAbstract=null), Reference(id=1154032922161045706, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=19, pageStart=4106, pageEnd=4119, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=Li Chaoran, Xiao Fei, Fan Yaxiang, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Li Chaoran, Xiao Fei, Fan Yaxiang, et al. An approach to lithium-ion battery SOH estimation based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2020. 35(19): 4106-4119 (in Chinese)., articleTitle=An approach to lithium-ion battery SOH estimation based on convolutional neural network, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1154032916742004835, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, xref=null, ext=[AuthorCompanyExt(id=1154032916746199140, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, companyId=1154032916742004835, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, School of Electrical Engineering Yanshan University Qinhuangdao 066004 China), AuthorCompanyExt(id=1154032916754587749, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, companyId=1154032916742004835, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004)])], figs=[ArticleFig(id=1154032919644463261, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Fig. 1, caption=Structure of BPNN, figureFileSmall=eIALTKiGnQD/4PTuuxwgZQ==, figureFileBig=5Dc0wmpK+M3I9UyPTeyxsQ==, tableContent=null), ArticleFig(id=1154032919698989215, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=图1, caption=BPNN 结构, figureFileSmall=eIALTKiGnQD/4PTuuxwgZQ==, figureFileBig=5Dc0wmpK+M3I9UyPTeyxsQ==, tableContent=null), ArticleFig(id=1154032919745126560, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Fig. 2, caption=Flow chart of SSA-BPNN, figureFileSmall=UUNqOGGfgpR7vankxFy5vg==, figureFileBig=vQ01TbktgKuY0yjRLoVy8A==, tableContent=null), ArticleFig(id=1154032919799652513, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=图2, caption=SSA-BPNN 流程, figureFileSmall=UUNqOGGfgpR7vankxFy5vg==, figureFileBig=vQ01TbktgKuY0yjRLoVy8A==, tableContent=null), ArticleFig(id=1154032919854178466, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Fig. 3, caption=Framework of online SOH estimation based on SSA-BPNN, figureFileSmall=K7gov9+59OSZIH1xRVG+fA==, figureFileBig=SUwnKIxB5WbG3J7ZEzlU4Q==, tableContent=null), ArticleFig(id=1154032919912898723, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=图3, caption=SSA-BPNN 在线 SOH 估算框架, figureFileSmall=K7gov9+59OSZIH1xRVG+fA==, figureFileBig=SUwnKIxB5WbG3J7ZEzlU4Q==, tableContent=null), ArticleFig(id=1154032919963230372, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Fig. 4, caption=Voltage, current and temperature curves during charging, figureFileSmall=BWwI34qGVTcqSmbow213/A==, figureFileBig=3XKr+SbvYUK0I+Wf2SEmMA==, tableContent=null), ArticleFig(id=1154032920013562021, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=图4, caption=充电过程中电压、电流和温度曲线, figureFileSmall=BWwI34qGVTcqSmbow213/A==, figureFileBig=3XKr+SbvYUK0I+Wf2SEmMA==, tableContent=null), ArticleFig(id=1154032920084865190, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Fig. 5, caption=SOH estimation results of test set, figureFileSmall=pJCtUGYDpQASxo1Qn9Q3Lw==, figureFileBig=LApeAtRXClqS5oR3M42jEQ==, tableContent=null), ArticleFig(id=1154032920214888615, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=图5, caption=测试集 $\mathrm{{SOH}}$ 估算结果, figureFileSmall=pJCtUGYDpQASxo1Qn9Q3Lw==, figureFileBig=LApeAtRXClqS5oR3M42jEQ==, tableContent=null), ArticleFig(id=1154032920281997480, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Tab. 1, caption=Aging conditions for NASA Randomized Battery Usage Dataset, figureFileSmall=null, figureFileBig=null, tableContent=
电池编号 充电电流 放电电流 温度/℃
RW1 RW2 RW7 RW8 充电 0.5、1.0、2.0、 2.5 或充满 0.5~4 A 24
RW3 RW4 $2\mathrm{\;A}$ 恒流转恒压至
RW5 RW6 0.01 A
RW9 RW10 RW11 RW12 $\{\pm {4.5}\mathrm{\;A},\pm {3.75}\mathrm{\;A},\pm 3\mathrm{\;A},\pm {2.25}\mathrm{\;A}$,$\pm {1.5}\mathrm{\;A},\pm {0.75}\mathrm{\;A}\}$ 充电为负, 放电为正
RW13 RW14 RW15 RW16 $2\mathrm{\;A}$ 恒流转恒 压至 0.01 A 偏小电流放 电
RW17 RW18 RW19 RW20 偏大电流放 电
RW21 RW22 RW23 RW24 偏小电流放 电 0
RW25 RW26 RW27 RW28 偏大电流放 电
), ArticleFig(id=1154032920332329129, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=表1, caption=NASA 随机使用数据集老化工况, figureFileSmall=null, figureFileBig=null, tableContent=
电池编号 充电电流 放电电流 温度/℃
RW1 RW2 RW7 RW8 充电 0.5、1.0、2.0、 2.5 或充满 0.5~4 A 24
RW3 RW4 $2\mathrm{\;A}$ 恒流转恒压至
RW5 RW6 0.01 A
RW9 RW10 RW11 RW12 $\{\pm {4.5}\mathrm{\;A},\pm {3.75}\mathrm{\;A},\pm 3\mathrm{\;A},\pm {2.25}\mathrm{\;A}$,$\pm {1.5}\mathrm{\;A},\pm {0.75}\mathrm{\;A}\}$ 充电为负, 放电为正
RW13 RW14 RW15 RW16 $2\mathrm{\;A}$ 恒流转恒 压至 0.01 A 偏小电流放 电
RW17 RW18 RW19 RW20 偏大电流放 电
RW21 RW22 RW23 RW24 偏小电流放 电 0
RW25 RW26 RW27 RW28 偏大电流放 电
), ArticleFig(id=1154032920378466474, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Tab. 2, caption=Random discharge probability under aging conditions, figureFileSmall=null, figureFileBig=null, tableContent=
电流/A 放电概率
偏小电流/% 偏大电流/%
0.5 7.2 2.0
1.0 4.8 2.4
1.5 19.3 3.6
2.0 21.6 6.0
2.5 14.6 9.2
3.0 10.0 11.8
3.5 6.5 17.2
4.0 4.0 23.4
4.5 1.5 19.4
5.0 0.5 5.0
), ArticleFig(id=1154032920441381035, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=表2, caption=老化工况随机放电概率, figureFileSmall=null, figureFileBig=null, tableContent=
电流/A 放电概率
偏小电流/% 偏大电流/%
0.5 7.2 2.0
1.0 4.8 2.4
1.5 19.3 3.6
2.0 21.6 6.0
2.5 14.6 9.2
3.0 10.0 11.8
3.5 6.5 17.2
4.0 4.0 23.4
4.5 1.5 19.4
5.0 0.5 5.0
), ArticleFig(id=1154032920483324076, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Tab. 3, caption=Errors of SOH estimation results of test set, figureFileSmall=null, figureFileBig=null, tableContent=
电池编号 是否优化 ${\varepsilon }_{\text{MAE }}/\%$ ${\varepsilon }_{\text{RMSE }}/\%$ ${\varepsilon }_{\mathrm{{MAX}}}/\%$
RW5 0.83 1.08 2.41
1.03 1.31 2.25
RW7 1.10 1.32 2.61
2.35 2.48 3.79
RW10 0.86 0.97 1.76
0.93 1.20 2.59
RW13 0.94 1.12 2.11
1.48 2.00 4.76
RW17 0.62 0.76 1.52
1.42 1.75 3.11
RW21 0.93 1.14 1.88
1.56 2.12 5.00
RW27 1.06 1.29 2.20
1.07 1.41 2.65
), ArticleFig(id=1154032920546238637, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=表3, caption=测试集 SOH 估算结果误差, figureFileSmall=null, figureFileBig=null, tableContent=
电池编号 是否优化 ${\varepsilon }_{\text{MAE }}/\%$ ${\varepsilon }_{\text{RMSE }}/\%$ ${\varepsilon }_{\mathrm{{MAX}}}/\%$
RW5 0.83 1.08 2.41
1.03 1.31 2.25
RW7 1.10 1.32 2.61
2.35 2.48 3.79
RW10 0.86 0.97 1.76
0.93 1.20 2.59
RW13 0.94 1.12 2.11
1.48 2.00 4.76
RW17 0.62 0.76 1.52
1.42 1.75 3.11
RW21 0.93 1.14 1.88
1.56 2.12 5.00
RW27 1.06 1.29 2.20
1.07 1.41 2.65
), ArticleFig(id=1154032920596570286, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=EN, label=Tab. 4, caption=Comparison of SOH estimation results of whole test set among different estimation strategies, figureFileSmall=null, figureFileBig=null, tableContent=
估算类型 ${\varepsilon }_{\text{RMSE }}/\%$ ${\varepsilon }_{\text{MAE }}/\%$
BPNN 未数据增强 2.81 1.65
数据增强 1.82 1.43
SSA-BPNN 未数据增强 2.00 1.42
数据增强 1.13 0.90
), ArticleFig(id=1154032920634319023, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153695644687524322, language=CN, label=表4, caption=不同估算策略的整体测试集 $\mathrm{{SOH}}$ 估算结果对比, figureFileSmall=null, figureFileBig=null, tableContent=
估算类型 ${\varepsilon }_{\text{RMSE }}/\%$ ${\varepsilon }_{\text{MAE }}/\%$
BPNN 未数据增强 2.81 1.65
数据增强 1.82 1.43
SSA-BPNN 未数据增强 2.00 1.42
数据增强 1.13 0.90
)], 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.2095-2805.2024.5.278, detailUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/10.13234/j.issn.2095-2805.2024.5.278, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/PDF/10.13234/j.issn.2095-2805.2024.5.278, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/PDF/10.13234/j.issn.2095-2805.2024.5.278, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于 SSA-BPNN的锂离子电池SOH估算
收藏切换
PDF下载
张凯飞 , 张金龙 , 吕满平
电源学报 | 电池与储能 2024,22(5): 278-285
收起
收藏切换
电源学报 | 电池与储能 2024, 22(5): 278-285
基于 SSA-BPNN的锂离子电池SOH估算
全屏
张凯飞 , 张金龙 , 吕满平
作者信息
  • 燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004
  • 张凯飞(1995-),男,硕士研究生。研究方向:锂离子电池健康状态估算。E-mail: zkaif@stumail.ysu.edu.cn。

    张金龙(1983-),男,通信作者,博士,副教授。研究方向:蓄电池储能技术研究。E-mail:maxlong83@163.com。

    吕满平(1996-),男,硕士研究生。研究方向:同步电动机电机参数辨识。E-mail: lvmanpin1996@stumail.ysu.edu.cn。

Estimation of Lithium-ion Battery SOH Based on SSA-BPNN
Kaifei ZHANG , Jinlong ZHANG , Manping LÜ
Affiliations
  • Key Lab of Power Electronics for Energy Conservation and Motor Drive of Hebei Province, School of Electrical Engineering Yanshan University Qinhuangdao 066004 China
出版时间: 2024-09-30 doi: 10.13234/j.issn.2095-2805.2024.5.278
文章导航
收藏切换

锂离子电池已被广泛应用于储能系统与电动汽车中,精确地估算锂离子电池健康状态SOH(state-of-health)是保证系统安全可靠运行的必要条件。从容量的角度分析 SOH,在恒流-恒压 CC-CV(constant current-constant voltage)充电电压和温度曲线中提取了7个健康特征HI(health indicator)作为输入,基于数据驱动法提出了麻雀搜索算法-反向传播神经网络 SSA-BPNN(sparrow search algorithm-back propagation neural network)的锂离子电池 SOH 估算方法,并应用数据增强进一步提高模型的鲁棒性,最终在 NASA 锂离子电池随机使用数据集上进行验证。通过与未采取数据增强的传统BP神经网络相比,获得 SOH 估算精度有明显提升,测试集 SOH 估算的最大绝对误差和均方根误差分别小于3%和1.32%,实验结果表明该方法兼顾误差小,收敛快,全局搜索能力且能够适应电池老化差异特性。

锂离子电池  /  健康状态估算  /  数据驱动  /  SSA-BPNN  /  数据增强

Since lithium-ion batteries have been widely applied in energy storage systems and electric vehicles, the accurate estimation of their state-of-health(SOH) is a necessary condition for ensuring the reliable and safe operation of the system. SOH is analyzed from the perspective of capacity, with seven health indicators which are extracted from the constant current-constant voltage charging voltage and temperature curves as input. Based on the data-driven method, a sparrow search algorithm-back propagation neural network(SSA-BPNN) SOH estimation method for lithium-ion batteries is proposed, and data enhancement is applied to further improve the model's robustness. Finally, this method is verified on the NASA Randomized Battery Usage Dataset. Compared with the traditional BP neural network without data enhancement, the SOH estimation accuracy of the proposed method is significantly improved. The maximum absolute error and root mean square error of SOH estimation on the test set are less than 3% and 1.32%, respectively. Experimental results show that this method has advantages of small error, fast convergence, global search capability and adaptation to different characteristics of battery aging.

Lithium-ion battery  /  state-of-health(SOH) estimation  /  data-driven  /  sparrow search algorithm-back prop-agation neural network (SSA-BPNN)  /  data enhancement
张凯飞, 张金龙, 吕满平. 基于 SSA-BPNN的锂离子电池SOH估算. 电源学报, 2024 , 22 (5) : 278 -285 . DOI: 10.13234/j.issn.2095-2805.2024.5.278
Kaifei ZHANG, Jinlong ZHANG, Manping LÜ. Estimation of Lithium-ion Battery SOH Based on SSA-BPNN[J]. Journal of Power Supply, 2024 , 22 (5) : 278 -285 . DOI: 10.13234/j.issn.2095-2805.2024.5.278
与传统的铅酸电池和镍镉电池相比,锂离子电池由于能量密度高、循环寿命长、自放电率低和无记忆效应等优点, 被广泛应用于电动汽车、混合动力汽车、通信及航空航天等领域[1-3]。然而,锂离子电池复杂的老化过程使其在工程应用中存在问题, 较为明显的是容量衰减差异特性, 即使在相同的工作条件下, 相同类型和规格的电池之间也存在容量衰减差异[4]。通常需要将电池串、并联以满足电动汽车电源系统的能量和功率要求, 而随着时间的推移, 每个电池的性能都会衰减, 并且由于制造工艺和材料的差异, 电池在老化过程中容量衰减的差异会进一步加剧, 这将直接影响电源的整体性能。电池健康状态 SOH(state-of-health)作为电池管理系统 BMS (battery management system) 的基本功能之一, 能够很好地反映电池老化和损坏程度, 但该指标无法直接测量,因此准确地估算锂离子电池$\mathrm{{SOH}}$ 尤其重要[5]$\mathrm{{SOH}}$ 从容量或内阻 2 个不同角度进行定义, 从容量的角度定义$\mathrm{{SOH}}$ 能够更好地反映电池的储能特性,并可以根据估算的$\mathrm{{SOH}}$ 进一步修正电池荷电状态,因此本文从容量的角度分析$\mathrm{{SOH}}$。在老化故障导致整个系统崩溃之前, 更换电池是必要的, 当电池的实际容量下降到其标称值的 70%或 80%时, 由于不能满足车辆的使用, 认为电池已到使用终点,应及时更换新电池[6]
根据文献[7-9], SOH 估算方法可以分为直接测量法、模型法和数据驱动法 3 类。直接测量法基于直接测量的电池容量[10] 或电池内阻[11],并使用不同的方法来分析和估算$\mathrm{{SOH}}$ 值,该方法原理清晰,易于理解, 但需要借助精密的仪器且对电池有损伤, 在应用上具有一定的局限。模型法主要包括电化学模型[12] 和等效电路模型[13],电化学模型物理意义明确, 但电池老化是多因素耦合的共同作用, 该模型过于复杂更适应于电池材料和工艺设计的改进而非$\mathrm{{SOH}}$ 估算中;与电化学模型相比,等效电路模型采用非线性电路元件显著降低了模型复杂度, 然而, 由于对电池内部提出假设, 该模型准确性和鲁棒性受限。数据驱动法无需考虑复杂的化学反应及电池类型, 具有估算精度高和泛化能力强等优点, 受到了研究者的重点关注。数据驱动进行$\mathrm{{SOH}}$ 估算时,需要借助的数据占电池的整个生命周期较长且对数据要求较高, 但随着大数据的到来, 该缺点逐步被克服,因此本文采用数据驱动法对锂离子电池$\mathrm{{SOH}}$ 进行在线估算。数据驱动法进行$\mathrm{{SOH}}$ 估算中,具有代表性的是反向传播网络 BPNN(back propagation neural network) 简称$\mathrm{{BP}}$ 神经网络,理论成熟、 应用广泛, 但该算法存在对初始值敏感, 容易陷入局部最优解,收敛速度慢甚至不收敛的缺点[14]。网络的训练可以看作是 1 个非凸优化问题, 关于神经网络权阈值优化的研究很多, Kajornrit${\mathrm{J}}^{\left\lbrack {15}\right\rbrack }$ 用模拟退火、直接搜索和遗传算法等元启发式算法检验了神经网络的学习性能, 他们将这些启发式算法优化后的 BP 神经网络在公开测试数据库上执行,与其他元启发式算法相比, 遗传算法得到的神经网络性能最好。Nawi N${\mathrm{M}}^{\left({16}\right)}$ 受布谷鸟行为的启发,提出了 1 种布谷鸟搜索算法, 用来训练快速收敛的 Elman 递归网络和反向传播 Elman 递归网络。
基于上述分析, 为能够简便地在线对锂离子电池$\mathrm{{SOH}}$ 进行估算,提出使用麻雀搜索-BP 神经网络 SSA-BPNN (sparrow search algorithm-back propagation neural network) 的估算方法以克服 BP 神经网络的缺点,并应用引入误差的数据增强方法进一步提高模型的鲁棒性。
SSA 源于对麻雀群体觅食行为的研究, 发现者作为种群的开拓者负责带领种群寻找充足的食物源, 加入者跟随发现者觅食并伺机抢夺发现者食物, 当周围出现天敌时, 种群中某些个体会发出警报, 当安全系数低于一定值后, 种群将会整体转移以寻找新的食物源, 该算法是 1 种新型启发式算法,具有寻优能力强和收敛速度快等优点[17]
建立麻雀搜索算法的数学模型为
$ X ={\left({x}_{1}{x}_{2}\cdots {x}_{n}\right)}^{\mathrm{T}}\;{x}_{i}\in {R}^{d}$
式中:$n$ 为种群总数;$d$ 为所需优化数据的维度。
种群适应度可表示为
${F}_{\mathrm{x}}= {\left\lbrack f\left({x}_{1}\right) f\left({x}_{2}\right) f\left({x}_{n}\right)\right\rbrack }^{\mathrm{T}}$
式中,$f\left(\cdot \right)$ 为麻雀单体适应度。单体适应度越高说明该单体获得食物能力越强, 就种群整体而言, 发现者搜索范围更大,适应度相对更高,发现者位置变化矩阵为
${X}_{i, j}^{t + 1}= \left\{\begin{array}{ll}{X}_{i, j}\exp \left({-\frac{i}{{\alpha i}{t}_{\max }}}\right)& {R}_{2}< {ST}\\{X}_{i, j}+ {QL}& {R}_{2}\geq {ST}\end{array}\right.$
式中:${X}_{i, j}$ 为麻雀单体位置;$j$$1 \sim d$ 的正整数;$\alpha$ 为从 0 到 1 的随机数;$i{t}_{\max }$ 为最大迭代次数;$Q$ 为随机数;$\mathbf{L}$$1 \times d$ 维全 1 矩阵;${R}_{2}$ 为预警值;${ST}$ 为安全值。当${R}_{2}< {ST}$ 时表示被捕食的风险较小,可扩大搜索范围,相反,种群中某些个体发现了危险并发出警告,该位置的麻雀将快速转移。
当发现者找到较好的食物时,一些加入者会立即加入发现者位置进行抢夺,若成功,进行式 (3) 的位置变化,若失败,进行的位置变化可表示为
${X}_{i, j}^{t + 1}= \left\{\begin{array}{ll} Q\exp \left(\frac{{X}_{\text{worst }}- {X}_{i, j}^{t}}{{i}^{2}}\right)& i > n/2 \\{X}_{\mathrm{p}}^{t + 1}+ \left|{X}_{i, j}\right|- {X}_{\mathrm{p}}^{t + 1}\mid {\mathbf{A}}^{+ }& i \leq n/2 \end{array}\right.$
式中:${X}_{\text{worst }}$${X}_{\mathrm{p}}$ 分别为当前最有利和最不利的位置;${\mathbf{A}}^{+ }$$\mathbf{A}$ 的广义逆矩阵;$\mathbf{A}$ 为 1 或 -1 的$1 \times d$ 维矩阵。当$i > n/2$ 时,表示加入者未能成功抢夺食物,饥肠辘辘,需转移到全新位置觅食以提高自身适应度。
警戒者位置随机数量占总数量的 20%以内,位置变化为
${X}_{i, j}^{t + 1}= \left\{\begin{array}{ll}{X}_{\text{best }}^{t}+ \beta \left|{{X}_{i, j}^{t}- {X}_{\text{best }}^{t}}\right|& {f}_{i}> {f}_{\mathrm{g}}\\{X}_{i, j}^{t}+ k\frac{{X}_{i, j}^{t}- {X}_{\text{worst }}^{t}}{\left({{f}_{i}- {f}_{\mathrm{w}}}\right)+ \varepsilon }& {f}_{i}= {f}_{\mathrm{g}}\end{array}\right.$
式中:${X}_{\text{best }}$ 为当前最有利位置;$\beta$ 为标准正态随机数,代表步长控制系数;$k$ 为 -1 到 1 的随机数,代表麻雀的方向;${f}_{\mathrm{g}}$ 为当前适应度最大值;${f}_{\mathrm{w}}$${f}_{\mathrm{g}}$ 相反;$\varepsilon$ 为较小的常数以确保分母不为 0。当${f}_{i}> {f}_{j}$ 时,表示麻雀周围存在天敌,有较大的被捕风险; 当${f}_{i}= {f}_{j}$ 时, 表示种群中一些麻雀已意识到危险,需靠近其他麻雀以减少被捕风险。
电池老化十分复杂, 展现了强烈的非线性特性和耦合特性,应用 BPNN 可以实现输入特征到 SOH 的映射。因为单隐藏层存在未能满足估算精度要求且隐藏层过多会造成模型复杂和过拟合等问题,所以本文选取双隐藏层 BPNN 进行分析研究, 建立的 BPNN 模型如图1所示。其中${h}_{ij}$ 为第$i$ 层第$j$ 个神经元。BPNN 理论研究成熟, 本文仅使用单隐藏层神经网络进行简要推导说明,详细推导可查询文献[18]。
设输入层到隐藏层再到输出层的权值和阈值为${w}_{ij}\text{、}{w}_{jk}\text{、}{\theta }_{j}$${\theta }_{k}$。学习样本集合$\mathrm{D}: \left\{{\left({{x}_{1},{y}_{1}}\right),\left({{x}_{2},{y}_{2}}\right)\cdots }\right.$ $\left.\left({{x}_{n},{y}_{n}}\right)\right\}$,输入变量为${x}_{i}\in {R}^{d}$,对应真实输出变量为${y}_{i}\in {R}^{1}$,其中,$d$ 为学习样本维度,$i$ 为学习样本个数, 则
${y}_{j}= {f}_{1}\left({\mathop{\sum }\limits_{{i = 1}}^{n}{w}_{ij}{x}_{i}- {\theta }_{j}}\right)$
${y}_{k}= {f}_{2}\left({\mathop{\sum }\limits_{{j = 1}}^{m}{w}_{jk}{b}_{j}- {\theta }_{k}}\right)$
式中:${y}_{j}$ 为隐藏层神经元$j$ 的输出值;${y}_{k}$ 为网络的实际输出值;$i\text{、}j$$k$ 分别为数值从 1 到输入节点数$n$ 、隐藏层神经元个数$s$ 和输出层神经元数$m$ 的正整数;$f\left(\cdot \right)$ 代表激活。
计算输出层节点的误差${\varepsilon }_{k}$
${\varepsilon }_{k}= \left({{y}_{i}- {y}_{k}}\right){y}_{k}\left({1 -{y}_{k}}\right)$
计算隐藏层节点误差${\varepsilon }_{j}$
${\varepsilon }_{j}= {y}_{j}\left({1 -{y}_{j}}\right)\mathop{\sum }\limits_{{k = 1}}^{m}{\varepsilon }_{k}{w}_{jk}$
通过网络实际输出定义误差$E$
$ E =\frac{1}{N}\mathop{\sum }\limits_{{k = 1}}^{m}{\left({y}_{i}- {y}_{k}\right)}^{2}$
根据梯度下降法, 网络中每个权值的变化都应与$E$ 的负梯度成正比。权值修正表达式为
${\Delta w}= -\eta \frac{\partial E}{\partial w}$
式中:$\eta$ 为学习率;$w$ 为权值。网络训练就是通过梯度下降法不断调整权、阈值以减小$E$,直到小于设定值或迭代超过设定最大值。
SSA-BPNN 是 SSA 和 BPNN 的结合, 核心思想是将 SSA 启发式全局寻优能力应用于 BPNN 初始权、阈值的优化上,再使用 BPNN 逆向传播进一步反馈优化, 最终达到智能寻优的目的。算法流程如图2所示, 将 SSA-BPNN 应用于锂离子电池在线$\mathrm{{SOH}}$ 估算时主要分为 2 个部分, 如图3所示。
(1)离线训练部分:首先从电池老化数据库中挑选出标称充电曲线, 然后使用安时积分法获得当前电池可用容量,再进一步计算得到真实$\mathrm{{SOH}}$ 值, 即
${C}_{\text{age }}= {\int }_{0}^{{t}_{m}}I\mathrm{\;d}t $
$\mathrm{{SOH}}= \frac{{C}_{\text{age }}}{{C}_{0}}\times {100}\%$
式中:${C}_{\text{age }}$ 为当前可用容量;${t}_{\text{ga }}$ 为进行充电的总时间;$I$ 为充电电流;${C}_{0}$ 为初始容量。
从对应的充电电压、电流和温度曲线中提取出所需的健康特征 HI(health indicator),最后以 HI 为输入,对应$\mathrm{{SOH}}$ 为输出,训练$\mathrm{{SSA}}- \mathrm{{BPNN}}$ 且将训练好的参数保存以便在线估算应用。
(2)在线估算部分:通过 BMS 提取标称充电曲线中模型所需的$\mathrm{{HI}}$,然后将提取的$\mathrm{{HI}}$ 输入到已训练好的 SSA-BPNN 中, 最终通过信息正向传递得到 SOH 估算值。
本文使用美国航空航天局中随机电池使用数据集(NASA Randomized Battery Usage Dataset)[19] 验证所提出的$\mathrm{{SOH}}$ 估算方法的有效性,该数据集由 NASA 的 Ames 卓越预测中心于 2014 年测量提取, 测量平台包括恒温器、传感器、可编程直流电源、数据记录仪和电化学阻抗谱测试仪等。实验使用的电池型号为 LGDAMF11865 钴酸锂电池, 其额定容量为${2.15}\mathrm{{Ah}}$,电压设置的工作范围为${3.2}\sim {4.2}\mathrm{\;V}$。 NASA 随机使用数据集老化工况见表1, 共包含 28 个电池实验数据,分为 7 组,组内 4 个电池老化工况相同,每组老化工况各不相同,工况复杂,更符合电动汽车在实际生活中的使用情况。基本上每 50 个老化工况后进行一次标称充放电、恒功率放电和脉冲放电过程。标称充放电步骤为:首先$2\mathrm{\;A}$ 恒流放电至电压等于${3.2}\mathrm{\;V}$,然后前 3 组不进行静置,剩下 4 组进行静置${1.5}\mathrm{\;h}$,最终采用恒流恒压$\mathrm{{CC}}- \mathrm{{CV}}($ con stant current-constant voltage) 充电至${4.2}\mathrm{\;V}$ 电流小于${0.01}\mathrm{\;A}$。老化工况随机放电概率见表2
上述数据集中大约只有 950 条标称充电曲线可以进行 SOH 估算研究,除去测量存在问题及 SOH 掉到 70%以下的数据样本后,只剩 280 条可供研究。一般情况下, 在数据驱动法中, 数据量越大, 样本多样性越高, 模型鲁棒性越强。文献[20]提供了 1 种数据增强方法, 但引入的误差不符合 BMS 实际的测量。根据上述文献,在原本数据的电压、电流和温度中加入均值为 0 、幅值为样本变化幅值的 0%~2%、功率为 0 的高斯白噪声。进一步根据我国 《GB 38031-2020 电动汽车用动力蓄电池安全要求》 中规定的单体电流测量误差要求小于$\pm 1\%$,单体电压采样误差要求小于$\pm 1\%$,单体温度采样误差要求小于$\pm 2{}^{\circ }\mathrm{C}$,添加电流偏置量$\alpha =\pm {0.008}\mathrm{\;A}$,电压偏置量$\beta =\pm {0.01}\mathrm{\;V}$,温度偏置量$\gamma =\pm 2{}^{\circ }\mathrm{C}$。则有
$ i ={N}_{\mathrm{w}}\left({{i}_{\max }- {i}_{\min }}\right)\pm \alpha $
$ v ={N}_{\mathrm{w}}\left({{v}_{\max }- {v}_{\min }}\right)\pm \beta $
$ T ={N}_{\mathrm{w}}\left({{T}_{\max }- {T}_{\min }}\right)\pm \gamma $
式中,${N}_{\mathrm{w}}$ 为上述高斯白噪声。将数据增强 15 倍,以 RW25 第 1 次标称充电曲线作为范例, 使用数据增强和未采用数据增强的真实值对比如图4所示。
HI 提取通常是基于标称充电和放电曲线, 但是基于这些曲线进行直接建模是不合适的。原因:①数据较多计算量大;②数据冗余拟合效果差; ③BMS 采样时间可能不同且随着电池老化等时间采样数据减少,导致模型输入量不好确定。基于以上原因,本文从标称充电电压和温度曲线中选取了具有代表性的 7 个 HI 作为 SSA-BPNN 的输入并将其分为 3 组, 即
$\left\{\begin{array}{l} S{v}_{\mathrm{{cc}}}= {\int }_{0}^{{t}_{\infty }}{v}_{\mathrm{{cc}}}\mathrm{d}t \\ S{v}_{\mathrm{{ga}}}= {\int }_{0}^{{t}_{\infty }}{v}_{\mathrm{{ga}}}\mathrm{d}t \end{array}\right.$
式中:${v}_{\mathrm{{cc}}}$ 为恒流$\mathrm{{CC}}$ 充电电压曲线;${t}_{\mathrm{{cc}}}$$\mathrm{{CC}}$ 充电时间;$S{v}_{\mathrm{{cc}}}$${v}_{\mathrm{{cc}}}$${t}_{\mathrm{{cc}}}$ 围成的面积;${t}_{\mathrm{{ga}}}$ 为总充电时间;$S{v}_{\mathrm{{ga}}}$ 为总充电电压曲线与${t}_{\mathrm{{ga}}}$ 围成的面积。
$\left\{\begin{array}{ll}{t}_{\mathrm{{cc}}}= {t}_{\min }& i >{i}_{\mathrm{{cc}}}\\{t}_{\mathrm{{ga}}}= {t}_{\max }& \end{array}\right.$
$\left\{\begin{array}{l} S{T}_{\mathrm{{cc}}}= {\int }_{0}^{{t}_{\mathrm{{cc}}}}{T}_{\mathrm{{cc}}}\mathrm{d}t \\ S{T}_{\mathrm{{ga}}}= {\int }_{0}^{{t}_{\mathrm{{cc}}}}{T}_{\mathrm{{ga}}}\mathrm{d}t \\{T}_{\mathrm{{cc}}}= {T}_{\mathrm{{cc}}}.\end{array}\right.$
式中:${T}_{\mathrm{{cc}}}$$\mathrm{{CC}}$ 温度曲线;$S{T}_{\mathrm{{cc}}}$${T}_{\mathrm{{cc}}}$${t}_{\mathrm{{cc}}}$ 围成的面积;${T}_{\mathrm{{ga}}}$ 为温度曲线;$S{T}_{\mathrm{{ga}}}$${T}_{\mathrm{{ga}}}$${t}_{\mathrm{{ga}}}$ 围成的面积;${T}_{\text{peak }}$ 为温度峰值点。
提取上述输入特征后,本文随机选取未进行数据增强的 RW5, RW7, RW10, RW13, RW17, RW21, RW27 作为测试集, 其他数据经过增强为原数据的 15 倍均作为训练集,使用 MATLAB 进行仿真验证。 为消除量纲影响需将输入特征进行归一化,即
${x}_{\mathrm{n}}= \frac{x -{x}_{\min }}{{x}_{\max }- {x}_{\min }}$
式中:${x}_{\mathrm{n}}$ 为归一化后的数据;$x$ 为原始数据;${x}_{\max }$${x}_{\min }$ 分别为原始数据的最大值和最小值。归一化后的结果位于$\left\lbrack {0,1}\right\rbrack$ 之间。设定 SSA-BPNN 中种群规模 pop 等于 150, 最大进化次数 epoch 为 50, 发现者占总种群数的比例是 20%。隐藏层神经元个数为超参数,根据深度学习研究者普遍设置为${2}^{n}$ 且逐层递减, 故本研究选取隐藏层神经元的个数为 16 和 4。 设置寻优目标是最小化训练集均方根误差, 学习率为$1 \times {10}^{-3}$,选择方便且常用的贝叶斯正则化训练算法,该算法基于概率解释定义网络参数且拟合效果较好。
为了能够定量分析实现结果, 采用平均绝对误差${\varepsilon }_{\mathrm{{MAE}}}$ 、均方根误差${\varepsilon }_{\mathrm{{RMSE}}}$ 及最大误差${\varepsilon }_{\mathrm{{MAX}}}$ 作为评估指标,即
${\varepsilon }_{\mathrm{{MAE}}}= \frac{1}{N}\mathop{\sum }\limits_{{i = 1}}^{N}\left|{{Y}_{i}- {\widehat{Y}}_{i}}\right|$
${\varepsilon }_{\mathrm{{RMSE}}}= \sqrt{\frac{1}{N}{\left\lbrack \mathop{\sum }\limits_{{i = 1}}^{N}\left({Y}_{i}- {\widehat{Y}}_{i}\right)\right\rbrack }^{2}}$
${\varepsilon }_{\mathrm{{MAX}}}= \max \left\lbrack {\mathop{\sum }\limits_{{i = 1}}^{N}\left({{Y}_{i}- {\widehat{Y}}_{i}}\right)}\right\rbrack $
式中:${Y}_{i}$ 为第$i$ 个样本经模型输出反归一化后的$\mathrm{{SOH}}$ 估算值;${\widehat{Y}}_{i}$ 为第$i$ 个样本所对应的$\mathrm{{SOH}}$ 实际值;$N$ 为样本数。图5表3展示了 SSA-BPNN 与 BPNN 的 SOH 估算对比。
表3图5是对应的,表3中的优化是指使用 SSA-BPNN 进行 SOH 估算,未优化指仅使用 BPNN 进行$\mathrm{{SOH}}$ 估算。从表3可以了解到 SSA-BPNN 的$\mathrm{{SOH}}$ 估算精度较高,${\varepsilon }_{\mathrm{{MAE}}}$ 最大为${1.10}\%,{\varepsilon }_{\mathrm{{MAX}}}$ 最大为${2.61}\%,{\varepsilon }_{\text{RMSE }}$ 最大为${1.32}\%$。从图5中可以观察到, 锂离子电池在$\mathrm{{SOH}}$ 较高的前提下, BPNN 估算精度也比较高,甚至有出现精度高于 SSA-BPNN 的情况,但随着循环次数增加到 150 次且$\mathrm{{SOH}}$ 约降为 93%以后, SSA-BPNN 的估算精度明显优于 BPNN, 这符合 SSA-BPNN 的全局寻优特点。在实际的锂离子电池使用中,随着$\mathrm{{SOH}}$ 降低,安全系数会逐步下降, 老化的不一致性对成组的电池包危害也越大, 这也是$\mathrm{{SOH}}$ 值越低对精度要求越苛刻的原因,因此本文提出的 SSA-BPNN 锂离子电池$\mathrm{{SOH}}$ 估算方法更有利于 BMS 实际使用。
训练集数据都是经过数据增强后得到的估算验证, 为研究数据增强和 SSA 对精度的单独影响,表4将测试集作为 1 个整体进行对比分析。从表中可以看出, SSA-BPNN 精度相对更高, 能够适应老化差异特性且经数据增强后精度得到进一步提升。
从容量的角度进行分析, 基于数据驱动提出 SSA-BPNN 的锂离子$\mathrm{{SOH}}$ 估算方法并使用数据增强进一步提高模型鲁棒性, 最终在 NASA 随机使用数据集作出验证。结果表明,该模型搜索能力强,泛化性能好, 能够适应电池老化的差异特性且误差稳定控制在 3%以内。下一步会将该方法投入到 BMS 实际应用中, 进一步验证其优越性。数据驱动理论上不受电池类型限制, 但目前只将本估算方法应用在钴酸锂电池数据中, 之后会重点关注与磷酸铁锂电池等数据建模效果, 进一步开展方法的泛化性能研究。
参考文献 引证文献
排序方式:
[1]
Severson KA, Attia PM, Jin N, et al. Data-driven prediction of battery cycle life before capacity degradation[J]. Nuture Energy, 2019. 4(5): 383-391.
[2]
Cadini F, Sbarufatti C, Cancelliere F, et al. State-of-life prognosis and diagnosis of lithium-ion batteries by data-driven particle filters[J]. Applied Energy, 2019. 235: 661-672.
[3]
李国政. 数据驱动的航天器电池性能退化建模方法研究[D]. 长沙: 国防科技大学, 2018.
Li Guozheng. Research on modeling method of data-driven spacecraft battery performance degradation[D]. Changsha: National University of Defense Technology, 2018. (in Chinese).
[4]
Sun Yening, Zhang Jinlong, Zhang Kaifei, et al. Battery state of health estimation method based on sparse auto-encoder and backward propagation fading diversity among battery cells[J]. International Journal of Energy Research, 2021. 45(5): 7651-7662.
[5]
张金龙, 李端凯, 佟微, 等. 锂离子电池老化差异特性研究现状[J]. 燕山大学学报, 2019. 43(1): 61-67.
Zhang Jinlong, Li Duankai, Tong Wei, et al. Research status of Li-ion battery aging diversities[J]. Journal of Yanshan University, 2019. 43(1): 61-67 (in Chinese).
[6]
Guo Peiyao, Cheng Ze, Yang Lei. A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction[J]. Journal of Power Sources, 2019. 412: 442-450.
[7]
Li Yuanyuan, Sheng Haimin, Cheng Yuhua, et al. State-of-health estimation of lithium-ion batteries based on semi-supervised transfer component analysis[J]. Applied Energy, 2020. 277: 115504.
[8]
张金龙, 佟微, 孙叶宁, 等. 锂离子电池健康状态估算方法综述[J]. 电源学报, 2017. 15(2): 128-134.
Zhang Jinlong, Tong Wei, Sun Yening, et al. Summarize of lithium battery status of health estimation method[J]. Journal of Power Supply, 2017. 15(2): 128-134 (in Chinese).
[9]
刘月峰. 基于数据驱动的锂离子电池剩余寿命融合预测方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.
Liu Yuefeng. Research on data-driven fusion prediction method of Lithum-ion battery remaining useful life[D]. Harbin: Harbin Institute of Technology, 2020. (in Chinese).
[10]
Ng K S, Moo CS, Chen Yiping, et al. Enhanced coulomb counting method for estimating state-of-charge and state-of-health of lithium-ion batteries[J]. Applied Energy, 2009. 86(9): 1506-1511.
[11]
Zhang Yunwei, Tang Qiaochu, Zhang Yao, et al. Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning[J]. Nature Communications, 2020. 11(1): 2419-2430.
[12]
Han Xuebing, Lu Languang, Zheng Yuejiu, et al. A review on the key issues of the lithiumion battery degradation among the whole life cycle[J]. eTransportation, 2019. 1(C): 100005.
[13]
刘璇, 王立欣, 吕超, 等. 锂离子电池建模与参数识别[J]. 电源学报, 2018. 16(1): 145-150.
Liu Xuan, Wang Lixin, Chao. et al. Modeling and parameter identification for lithium-ion battery[J]. Journal of Power Supply, 2018. 16(1): 145-150 (in Chinese).
[14]
Wang Wenxu, Tang Ruichun, Li Cheng, et al. A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights[J]. Ocean Engineering, 2018. 162: 98-107.
[15]
A comparative study of optimization methods for improving artificial neural network performance[C]// 2015 7th International Conference on Information Technology and Electrical Engineering. Chiang Mai, Thailand, 2015: 35-40.
[16]
Nawi N M, Khan A, Rehman M Z, et al. Weight optimization in recurrent neural networks with hybrid meta-heuristic cuckoo search techniques for data classification[J]. Mathematical Problems in Engineering, 2015: 868375.1-868375.12.
[17]
Xue Jiankai, Shen Bo. A novel swarm intelligence optimization approach: Sparrow search algorithm[J]. Systems Science &amp; Control Engineering, 2020. 8(1): 22-34.
[18]
邱锡鹏. 神经网络与深度学习[M]. 北京: 机械工业出版社, 2020.
Qiu Xipeng. Neural Networks and Deep Learning[M]. Beijing: China Machine Press, 2020. (in Chinese).
[19]
Adaptation of an electro-chemistry-based li-ion battery model to account for deterioration observed under randomized use[C]// 2014 Conference of the Prognostics &amp; Health Management Society. Fort Worth, TX, USA, 2014: 29.
[20]
李超然, 肖飞, 樊亚翔, 等. 基于卷积神经网络的离子电池 SOH 估算[J]. 电工技术学报, 2020. 35(19): 4106-4119.
Li Chaoran, Xiao Fei, Fan Yaxiang, et al. An approach to lithium-ion battery SOH estimation based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2020. 35(19): 4106-4119 (in Chinese).
2024年第22卷第5期
PDF下载
312
120
引用本文
BibTeX
文章信息
doi: 10.13234/j.issn.2095-2805.2024.5.278
  • 接收时间:2021-07-01
  • 首发时间:2025-07-20
  • 出版时间:2024-09-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2021-07-01
  • 修回日期:2021-09-09
  • 录用日期:2021-09-16
基金
作者信息
    燕山大学 电气工程学院电力电子节能与传动控制河北省重点实验室 秦皇岛 066004
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.5.278
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