Article(id=1154037277324989229, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154037268550509325, articleNumber=null, orderNo=null, doi=10.13234/j.issn.2095-2805.2024.4.251, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1640793600000, receivedDateStr=2021-12-30, revisedDate=1646236800000, revisedDateStr=2022-03-03, acceptedDate=1648051200000, acceptedDateStr=2022-03-24, onlineDate=1753073527889, onlineDateStr=2025-07-21, pubDate=1722268800000, pubDateStr=2024-07-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753073527889, onlineIssueDateStr=2025-07-21, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753073527889, creator=13701087609, updateTime=1753073527889, updator=13701087609, issue=Issue{id=1154037268550509325, tenantId=1146029695717560320, journalId=1146031654075715584, year='2024', volume='22', issue='4', pageStart='1', pageEnd='338', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753073525798, creator=13701087609, updateTime=1753780979931, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1157004546338804561, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154037268550509325, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1157004546338804562, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154037268550509325, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=251, endPage=259, ext={EN=ArticleExt(id=1154037277912191793, articleId=1154037277324989229, tenantId=1146029695717560320, journalId=1146031654075715584, language=EN, title=Remaining Useful Life Prediction of Simulation Substation Batteries Based on VMD and Bat-KELM, columnId=1152281491788100462, journalTitle=Journal of Power Supply, columnName=Battery and Energy Storage, runingTitle=null, highlight=null, articleAbstract=

Simulation substation batteries often work under discontinuous operation conditions, which will result in capacity regeneration of batteries during their performance degradation. The degradation of batteries shows nonstationary and random characteristics, leading to a low prediction accuracy for the remaining useful life(RUL). Aimed at the problem of RUL prediction of batteries with capacity regeneration, a prediction method is proposed based on variational mode decomposition(VMD) and bat optimized kernel extreme learning machine(Bat-KELM). First, VMD is employed to decompose the battery state-of-health(SOH) time series into overall degradation components and capacity regeneration components. Then, Bat-KELM is used to construct prediction models of each component, so that the prediction accuracy of component trend is improved. At last, the prediction results of all components are blended together to yield the accurate battery SOH prediction results as well as the RUL results. The proposed method is applied to the analysis of battery degradation instance data, and results show its superiority in terms of prediction accuracy compared with the KELM and VMD-KELM models.

, 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=Gang REN, Ning JI, Xiaoli HU, Shiqian LI, Jiehua ZHANG, Yi WU), CN=ArticleExt(id=1154037326406734740, articleId=1154037277324989229, tenantId=1146029695717560320, journalId=1146031654075715584, language=CN, title=基于VMD和Bat-KELM的仿真变电站蓄电池剩余寿命预测, columnId=1149830274575463188, journalTitle=电源学报, columnName=电池与储能, runingTitle=null, highlight=null, articleAbstract=

仿真变电站蓄电池的工作模式呈现间歇非连续性,导致电池性能在退化过程中存在容量再生现象,退化规律具有非平稳性和随机性,增大了蓄电池精确剩余寿命RUL(remaining useful life)的难度。针对存在容量再生现象的蓄电池剩余寿命预测问题,提出了变分模态分解 VMD(variational mode decomposition)和蝙蝠(Bat)优化核极限学习机 KELM(kernel extreme learning machine)组合的预测方法。基于 VMD 将蓄电池健康状态SOH(state of health)时间序列分解为整体退化分量和容量再生分量;利用 Bat优化 KELM构建各分量预测模型,以提高分量趋势预测精度;通过各分量独立预测结果的叠加,得到精确的蓄电池健康状态及剩余寿命预测值。将该方法应用于蓄电池退化数据实例分析中,结果表明该方法相较于KELM模型及VMD-KELM模型,预测精度更高,验证了该方法的优越性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=IYmaAJ3gMc3H1KZp4NlFvg==, magXml=8ZDSUXgP034OVP3SzqJfjw==, pdfUrl=null, pdf=4ywbpRupSkBI2hj9yj9GTg==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=TH8gL2cOlm0CC9x/C3hNfg==, mapNumber=null, authorCompany=null, fund=null, authors=

任罡(1983-),男,硕士,高级工程师。研究方向:电网稳定运行及调控、智能检测与控制。E-mail:cbs20151216@163.com。

季宁(1985-),女,本科,高级讲师。研究方向:电网调控运行与电力系统仿真、智能检测与控制。E-mail: gitanjali1985@163.com。

胡晓丽(1980-),女,硕士,高级讲师。研究方向:电力系统安全监测。E-mail: foxhuxiaoli@163.com。

李世倩(1971-),男,本科,高级讲师。研究方向:电网调控仿真和继电保护仿真。Email: lsq561@sina.com。

张洁华(1989-),女,硕士,中级讲师。研究方向:电力系统储能系统规划与配置技术。E-mail: 88264833@qq.com。

吴祎(1990-),女,中国电源学会会员,通信作者,博士,讲师。研究方向:蓄电池健康监测技术。E-mail: yiw@njupt.edu.cn。

, authorsList=任罡, 季宁, 胡晓丽, 李世倩, 张洁华, 吴祎)}, authors=[Author(id=1154048210181018331, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cbs20151216@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154048210273293021, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048210181018331, language=EN, stringName=Gang REN, firstName=Gang, middleName=null, lastName=REN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154048212202672862, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048210181018331, language=CN, stringName=任罡, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网江苏省电力有限公司 技能培训中心 苏州 215004, bio={"img":"q34TbC2UfWL44LGg/VqVdA==","content":"

任罡(1983-),男,硕士,高级工程师。研究方向:电网稳定运行及调控、智能检测与控制。E-mail:cbs20151216@163.com。

"}, bioImg=q34TbC2UfWL44LGg/VqVdA==, bioContent=

任罡(1983-),男,硕士,高级工程师。研究方向:电网稳定运行及调控、智能检测与控制。E-mail:cbs20151216@163.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154048209031779025, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=1, ext=[AuthorCompanyExt(id=1154048209035973330, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China), AuthorCompanyExt(id=1154048210025829075, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网江苏省电力有限公司 技能培训中心 苏州 215004)])]), Author(id=1154048212320113379, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=gitanjali1985@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154048212387222247, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048212320113379, language=EN, stringName=Ning JI, firstName=Ning, middleName=null, lastName=JI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154048212466914028, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048212320113379, language=CN, stringName=季宁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网江苏省电力有限公司 技能培训中心 苏州 215004, bio={"content":"

季宁(1985-),女,本科,高级讲师。研究方向:电网调控运行与电力系统仿真、智能检测与控制。E-mail: gitanjali1985@163.com。

"}, bioImg=null, bioContent=

季宁(1985-),女,本科,高级讲师。研究方向:电网调控运行与电力系统仿真、智能检测与控制。E-mail: gitanjali1985@163.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154048209031779025, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=1, ext=[AuthorCompanyExt(id=1154048209035973330, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China), AuthorCompanyExt(id=1154048210025829075, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网江苏省电力有限公司 技能培训中心 苏州 215004)])]), Author(id=1154048212538217201, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=foxhuxiaoli@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154048215864300317, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048212538217201, language=EN, stringName=Xiaoli HU, firstName=Xiaoli, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154048215923020577, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048212538217201, language=CN, stringName=胡晓丽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网江苏省电力有限公司 技能培训中心 苏州 215004, bio={"content":"

胡晓丽(1980-),女,硕士,高级讲师。研究方向:电力系统安全监测。E-mail: foxhuxiaoli@163.com。

"}, bioImg=null, bioContent=

胡晓丽(1980-),女,硕士,高级讲师。研究方向:电力系统安全监测。E-mail: foxhuxiaoli@163.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154048209031779025, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=1, ext=[AuthorCompanyExt(id=1154048209035973330, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China), AuthorCompanyExt(id=1154048210025829075, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网江苏省电力有限公司 技能培训中心 苏州 215004)])]), Author(id=1154048216011100965, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lsq561@sina.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154048216099181355, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048216011100965, language=EN, stringName=Shiqian LI, firstName=Shiqian, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154048216162095917, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048216011100965, language=CN, stringName=李世倩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网江苏省电力有限公司 技能培训中心 苏州 215004, bio={"content":"

李世倩(1971-),男,本科,高级讲师。研究方向:电网调控仿真和继电保护仿真。Email: lsq561@sina.com。

"}, bioImg=null, bioContent=

李世倩(1971-),男,本科,高级讲师。研究方向:电网调控仿真和继电保护仿真。Email: lsq561@sina.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154048209031779025, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=1, ext=[AuthorCompanyExt(id=1154048209035973330, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China), AuthorCompanyExt(id=1154048210025829075, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网江苏省电力有限公司 技能培训中心 苏州 215004)])]), Author(id=1154048216233399089, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=88264833@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154048216715744058, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048216233399089, language=EN, stringName=Jiehua ZHANG, firstName=Jiehua, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154048216770270011, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048216233399089, language=CN, stringName=张洁华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网江苏省电力有限公司 技能培训中心 苏州 215004, bio={"content":"

张洁华(1989-),女,硕士,中级讲师。研究方向:电力系统储能系统规划与配置技术。E-mail: 88264833@qq.com。

"}, bioImg=null, bioContent=

张洁华(1989-),女,硕士,中级讲师。研究方向:电力系统储能系统规划与配置技术。E-mail: 88264833@qq.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154048209031779025, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=1, ext=[AuthorCompanyExt(id=1154048209035973330, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China), AuthorCompanyExt(id=1154048210025829075, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网江苏省电力有限公司 技能培训中心 苏州 215004)])]), Author(id=1154048216837378878, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yiw@njupt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154048216929653574, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048216837378878, language=EN, stringName=Yi WU, firstName=Yi, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 College of Automation Nanjing University of Posts and Telecommunications Nanjing 210023 China
3 College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing 210023 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154048216988373832, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, authorId=1154048216837378878, language=CN, stringName=吴祎, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 南京邮电大学 自动化学院 南京 210023
3 南京邮电大学 人工智能学院 南京 210023, bio={"content":"

吴祎(1990-),女,中国电源学会会员,通信作者,博士,讲师。研究方向:蓄电池健康监测技术。E-mail: yiw@njupt.edu.cn。

"}, bioImg=null, bioContent=

吴祎(1990-),女,中国电源学会会员,通信作者,博士,讲师。研究方向:蓄电池健康监测技术。E-mail: yiw@njupt.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154048210076160724, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=2, ext=[AuthorCompanyExt(id=1154048210080355029, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048210076160724, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Automation Nanjing University of Posts and Telecommunications Nanjing 210023 China), AuthorCompanyExt(id=1154048210084549334, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048210076160724, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 南京邮电大学 自动化学院 南京 210023)]), AuthorCompany(id=1154048210126492375, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=3, ext=[AuthorCompanyExt(id=1154048210134880984, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048210126492375, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing 210023 China), AuthorCompanyExt(id=1154048210139075289, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048210126492375, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 南京邮电大学 人工智能学院 南京 210023)])])], keywords=[Keyword(id=1154048217672045399, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, orderNo=1, keyword=Simulation substation), Keyword(id=1154048217734959961, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, orderNo=2, keyword=battery), Keyword(id=1154048217793680219, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, orderNo=3, keyword=remaining useful life(RUL) prediction), Keyword(id=1154048217856594781, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, orderNo=4, keyword=variational mode decomposition (VMD)), Keyword(id=1154048217911120735, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, orderNo=5, keyword=kernel extreme learning machine(KELM)), Keyword(id=1154048217974035298, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, orderNo=1, keyword=仿真变电站), Keyword(id=1154048218108253028, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, orderNo=2, keyword=蓄电池), Keyword(id=1154048218175361893, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, orderNo=3, keyword=剩余寿命预测), Keyword(id=1154048218234082152, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, orderNo=4, keyword=变分模态分解), Keyword(id=1154048218326356841, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, orderNo=5, keyword=核极限学习机)], refs=[Reference(id=1154048220972962705, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=刘跃文, journalName=null, refType=null, unstructuredReference=刘跃文. 变电站直流电源系统运维管理研究[D]. 济南: 山东大学, 2020., articleTitle=变电站直流电源系统运维管理研究, refAbstract=null), Reference(id=1154048221086208917, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Liu Yuewen, journalName=null, refType=null, unstructuredReference=Liu Yuewen. Research on operation and maintenance management of substation DC power system[D]. Ji'nan: Shandong University, 2020. (in Chinese)., articleTitle=Research on operation and maintenance management of substation DC power system, refAbstract=null), Reference(id=1154048221170094998, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=174, issue=null, pageStart=109057, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Ge Mingfeng, Liu Yiben, Jiang Xingxing, journalName=Measurement, refType=null, unstructuredReference=Ge Mingfeng, Liu Yiben, Jiang Xingxing, et al. A review on state of health estimations and remaining useful life prognostics of lithium-ion batteries[J]. Measurement, 2021. 174: 109057., articleTitle=A review on state of health estimations and remaining useful life prognostics of lithium-ion batteries, refAbstract=null), Reference(id=1154048221228815255, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2017, volume=120, issue=null, pageStart=975, pageEnd=984, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Lü Chao, Lai Qingzhi, Ge Tengfei, journalName=Energy, refType=null, unstructuredReference= Chao, Lai Qingzhi, Ge Tengfei, et al. A lead-acid battery's remaining useful life prediction by using electrochemical model in the particle filtering framework[J]. Energy, 2017. 120: 975-984., articleTitle=A lead-acid battery's remaining useful life prediction by using electrochemical model in the particle filtering framework, refAbstract=null), Reference(id=1154048221300118424, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=292, issue=null, pageStart=126044, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Hossain Lipu M S, Hannan M A, Karim T F, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=Hossain Lipu M S, Hannan M A, Karim T F, et al. Intelligent algorithms and control strategies for battery management system in electric vehicles: Progress, challenges and future outlook[J]. Journal of Cleaner Production, 2021. 292: 126044., articleTitle=Intelligent algorithms and control strategies for battery management system in electric vehicles: Progress, challenges and future outlook, refAbstract=null), Reference(id=1154048221371421593, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2020, volume=4, issue=2, pageStart=310, pageEnd=346, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=Hu Xiaosong, Xu Le, Lin Xianke, journalName=Joule, refType=null, unstructuredReference=Hu Xiaosong, Xu Le, Lin Xianke, et al. Battery lifetime prognostics[J]. Joule, 2020. 4(2): 310-346., articleTitle=Battery lifetime prognostics, refAbstract=null), Reference(id=1154048221442724762, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=17, issue=5, pageStart=3478, pageEnd=3487, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Ren Lei, Dong Jiabao, Wang Xiaokang, journalName=IEEE transactions on industrial informatics, refType=null, unstructuredReference=Ren Lei, Dong Jiabao, Wang Xiaokang, et al. A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life[J]. IEEE transactions on industrial informatics, 2021. 17(5): 3478-3487., articleTitle=A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life, refAbstract=null), Reference(id=1154048221509833629, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2020, volume=402, issue=null, pageStart=134, pageEnd=147, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=Yu Yong, Hu Changhua, Si Xiaosheng, journalName=Neurocomputing, refType=null, unstructuredReference=Yu Yong, Hu Changhua, Si Xiaosheng, et al. Averaged Bi-LSTM networks for RUL prognostics with non-life-cycle labeled dataset[J]. Neurocomputing, 2020. 402: 134-147., articleTitle=Averaged Bi-LSTM networks for RUL prognostics with non-life-cycle labeled dataset, refAbstract=null), Reference(id=1154048221597914015, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=36, issue=3, pageStart=666, pageEnd=674, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=孙丙香, 任鹏博, 陈育哲, journalName=电工技术学报, refType=null, unstructuredReference=孙丙香, 任鹏博, 陈育哲, 等. 锂离子电池在不同区间下的衰退影响因素分析及任意区间的老化趋势预测[J]. 电工技术学报, 2021. 36(3): 666-674., articleTitle=锂离子电池在不同区间下的衰退影响因素分析及任意区间的老化趋势预测, refAbstract=null), Reference(id=1154048221648245664, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=36, issue=3, pageStart=666, pageEnd=674, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=Sun Bingxiang, Ren Pengbo, Chen Yuzhe, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Sun Bingxiang, Ren Pengbo, Chen Yuzhe, et al. Analysis of influencing factors of degradation under different interval stress and prediction of aging trend in any interval for lithium-ion battery[J]. Transactions of China Electrotechnical Society, 2021. 36(3): 666-674 (in Chinese)., articleTitle=Analysis of influencing factors of degradation under different interval stress and prediction of aging trend in any interval for lithium-ion battery, refAbstract=null), Reference(id=1154048221736326051, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2020, volume=6, issue=2, pageStart=363, pageEnd=374, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=Tang Xiaopeng, Liu Kailong, Wang Xin, journalName=IEEE Transactions on Transportation Electrification, refType=null, unstructuredReference=Tang Xiaopeng, Liu Kailong, Wang Xin, et al. Model migration neural network for predicting battery aging trajectories[J]. IEEE Transactions on Transportation Electrification, 2020. 6(2): 363-374., articleTitle=Model migration neural network for predicting battery aging trajectories, refAbstract=null), Reference(id=1154048221799240613, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2020, volume=18, issue=6, pageStart=207, pageEnd=214, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=刘斌, 毕小熊, 党军朋, journalName=电源学报, refType=null, unstructuredReference=刘斌, 毕小熊, 党军朋, 等. 基于支持向量回归的变电站蓄电池退化趋势预测[J]. 电源学报, 2020. 18(6): 207-214., articleTitle=基于支持向量回归的变电站蓄电池退化趋势预测, refAbstract=null), Reference(id=1154048221870543783, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2020, volume=18, issue=6, pageStart=207, pageEnd=214, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=Liu Bin, Bi Xiaoxiong, Dang Junpeng, journalName=Journal of Power Supply, refType=null, unstructuredReference=Liu Bin, Bi Xiaoxiong, Dang Junpeng, et al. Degradation trend prediction of battery in substation based on support vector regression[J]. Journal of Power Supply, 2020. 18(6): 207-214 (in Chinese)., articleTitle=Degradation trend prediction of battery in substation based on support vector regression, refAbstract=null), Reference(id=1154048221933458345, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2020, volume=476, issue=null, pageStart=228581, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=Ma Yanying, Wu Lifeng, Guan Yong, journalName=Journal of Power Sources, refType=null, unstructuredReference=Ma Yanying, Wu Lifeng, Guan Yong, et al. The capacity estimation and cycle life prediction of lithium-ion batteries using a new broad extreme learning machine approach[J]. Journal of Power Sources, 2020. 476: 228581., articleTitle=The capacity estimation and cycle life prediction of lithium-ion batteries using a new broad extreme learning machine approach, refAbstract=null), Reference(id=1154048222004761514, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2015, volume=149, issue=null, pageStart=253, pageEnd=264, url=null, language=null, rfNumber=[12], rfOrder=14, authorNames=Liu Xinwang, Wang Lei, Huang Guangbin, journalName=Neurocomputing, refType=null, unstructuredReference=Liu Xinwang, Wang Lei, Huang Guangbin, et al. Multiple kernel extreme learning machine[J]. Neurocomputing, 2015. 149: 253-264., articleTitle=Multiple kernel extreme learning machine, refAbstract=null), Reference(id=1154048222084453291, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=208, issue=null, pageStart=107440, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=15, authorNames=Zhang Senju, Kang Rui, Lin Yanhui, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=Zhang Senju, Kang Rui, Lin Yanhui. Remaining useful life prediction for degradation with recovery phenomenon based on uncertain process[J]. Reliability Engineering & System Safety, 2021. 208: 107440., articleTitle=Remaining useful life prediction for degradation with recovery phenomenon based on uncertain process, refAbstract=null), Reference(id=1154048222130590636, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=2, pageStart=287, pageEnd=296, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=丁承君, 冯玉伯, 王曼娜, journalName=振动与冲击, refType=null, unstructuredReference=丁承君, 冯玉伯, 王曼娜. 基于变分模态分解与深度卷积神经网络的滚动轴承故障诊断[J]. 振动与冲击, 2021. 40(2): 287-296., articleTitle=基于变分模态分解与深度卷积神经网络的滚动轴承故障诊断, refAbstract=null), Reference(id=1154048222218671021, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=2, pageStart=287, pageEnd=296, url=null, language=null, rfNumber=[14], rfOrder=17, authorNames=Ding Chengjun, Feng Yubo, Wang Manna, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=Ding Chengjun, Feng Yubo, Wang Manna. Rolling bearing fault diagnosis using variational mode decom-position and deep convolutional neural network[J]. Journal of Vibration and Shock, 2021. 40(2): 287-296 (in Chinese)., articleTitle=Rolling bearing fault diagnosis using variational mode decom-position and deep convolutional neural network, refAbstract=null), Reference(id=1154048222277391277, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=46, issue=2, pageStart=263, pageEnd=270, url=null, language=null, rfNumber=[15], rfOrder=18, authorNames=周静雷, 颜婷, journalName=声学学报, refType=null, unstructuredReference=周静雷, 颜婷. 应用变分模态分解及能量熵的扬声器异常声分类[J]. 声学学报, 2021. 46(2): 263-270., articleTitle=应用变分模态分解及能量熵的扬声器异常声分类, refAbstract=null), Reference(id=1154048222327722927, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2021, volume=46, issue=2, pageStart=263, pageEnd=270, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=Zhou Jinglei, Yan Ting, journalName=Acta Acustica, refType=null, unstructuredReference=Zhou Jinglei, Yan Ting. Loudspeaker abnormal sound classification using variational mode decomposition and energy entropy[J]. Acta Acustica, 2021. 46(2): 263-270 (in Chinese)., articleTitle=Loudspeaker abnormal sound classification using variational mode decomposition and energy entropy, refAbstract=null), Reference(id=1154048222390637489, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2018, volume=46, issue=4, pageStart=886, pageEnd=894, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=陈志敏, 吴盘龙, 薄煜明, journalName=电子学报, refType=null, unstructuredReference=陈志敏, 吴盘龙, 薄煜明, 等. 基于自控蝙蝠算法智能优化粒子滤波的机动目标跟踪方法[J]. 电子学报, 2018. 46(4): 886-894., articleTitle=基于自控蝙蝠算法智能优化粒子滤波的机动目标跟踪方法, refAbstract=null), Reference(id=1154048222449357747, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2018, volume=46, issue=4, pageStart=886, pageEnd=894, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=Chen Zhimin, Wu Panlong, Bo Yuming, journalName=Acta Electronica Sinica, refType=null, unstructuredReference=Chen Zhimin, Wu Panlong, Bo Yuming, et al. Adaptive control Bat algorithm intelligent optimization particle filter for maneuvering target tracking[J]. Acta Electronica Sinica, 2018. 46(4): 886-894 (in Chinese)., articleTitle=Adaptive control Bat algorithm intelligent optimization particle filter for maneuvering target tracking, refAbstract=null), Reference(id=1154048222516466613, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, doi=null, pmid=null, pmcid=null, year=2008, volume=58, issue=2, pageStart=291, pageEnd=296, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=Saha B, Goebel K, Poll S, journalName=IEEE Transactions on Instrumentation and Measurement, refType=null, unstructuredReference=Saha B, Goebel K, Poll S, et al. Prognostics methods for battery health monitoring using a Bayesian framework[J]. IEEE Transactions on Instrumentation and Measurement, 2008. 58(2): 291-296., articleTitle=Prognostics methods for battery health monitoring using a Bayesian framework, refAbstract=null)], funds=[Fund(id=1154048220750664588, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, awardId=J2021020, language=EN, fundingSource=Science and Technology Project of State Grid Jiangsu Electric Power Co., Ltd.(J2021020), fundOrder=null, country=null), Fund(id=1154048220851327886, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, awardId=J2021020, language=CN, fundingSource=国网江苏省电力有限公司科技项目(J2021020), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1154048209031779025, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=1, ext=[AuthorCompanyExt(id=1154048209035973330, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China), AuthorCompanyExt(id=1154048210025829075, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048209031779025, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网江苏省电力有限公司 技能培训中心 苏州 215004)]), AuthorCompany(id=1154048210076160724, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=2, ext=[AuthorCompanyExt(id=1154048210080355029, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048210076160724, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Automation Nanjing University of Posts and Telecommunications Nanjing 210023 China), AuthorCompanyExt(id=1154048210084549334, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048210076160724, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 南京邮电大学 自动化学院 南京 210023)]), AuthorCompany(id=1154048210126492375, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, xref=3, ext=[AuthorCompanyExt(id=1154048210134880984, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048210126492375, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing 210023 China), AuthorCompanyExt(id=1154048210139075289, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, companyId=1154048210126492375, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 南京邮电大学 人工智能学院 南京 210023)])], figs=[ArticleFig(id=1154048219437847412, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, label=Fig. 1, caption=Battery RUL prediction process based on VMD and Bat-KELM, figureFileSmall=v+3fGvDI75e7o7kWxcSOLQ==, figureFileBig=gbXBCOADiFPbq5pdUwhqdQ==, tableContent=null), ArticleFig(id=1154048219492373365, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, label=图1, caption=基于 VMD 和 Bat-KELM 的蓄电池 RUL 预测流程, figureFileSmall=v+3fGvDI75e7o7kWxcSOLQ==, figureFileBig=gbXBCOADiFPbq5pdUwhqdQ==, tableContent=null), ArticleFig(id=1154048219542705014, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, label=Fig. 2, caption=Curves of battery $\mathrm{{SOH}}$ with number of cycles, figureFileSmall=fHoUfgU8JIn1LSdLonVbmg==, figureFileBig=+NFZn/5Nj/t8L4LWWIWMRQ==, tableContent=null), ArticleFig(id=1154048219597230967, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, label=图2, caption=蓄电池 $\mathrm{{SOH}}$ 随循环周期的变化曲线, figureFileSmall=fHoUfgU8JIn1LSdLonVbmg==, figureFileBig=+NFZn/5Nj/t8L4LWWIWMRQ==, tableContent=null), ArticleFig(id=1154048219651756920, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, label=Fig. 3, caption=Battery SOH decomposition curves based on VMD, figureFileSmall=1O2LxKWdeGIXyDMA5CmKcg==, figureFileBig=9nC4PCiQkgz4DxSYUIfqEg==, tableContent=null), ArticleFig(id=1154048219702088569, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, label=图3, caption=基于 $\mathrm{{VMD}}$ 的蓄电池 $\mathrm{{SOH}}$ 分解曲线, figureFileSmall=1O2LxKWdeGIXyDMA5CmKcg==, figureFileBig=9nC4PCiQkgz4DxSYUIfqEg==, tableContent=null), ArticleFig(id=1154048219773391739, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, label=Fig. 4, caption=Battery SOH prediction curves based on three methods, figureFileSmall=x4jjxCX6O00Q6DibCd0kQw==, figureFileBig=V0IwXB3N6YDOZbyswvAKdA==, tableContent=null), ArticleFig(id=1154048219844694909, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, label=图4, caption=基于 3 种方法的蓄电池 $\mathrm{{SOH}}$ 预测曲线, figureFileSmall=x4jjxCX6O00Q6DibCd0kQw==, figureFileBig=V0IwXB3N6YDOZbyswvAKdA==, tableContent=null), ArticleFig(id=1154048219962135423, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, label=Fig. 5, caption=Battery B5 SOH prediction curves based on three methods at different prediction cycles, figureFileSmall=m0C2ZfAzf9AgoX2GQnlbsA==, figureFileBig=a+wQlD6vdUNjPT89ktOT5w==, tableContent=null), ArticleFig(id=1154048220012467073, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, label=图5, caption=不同预测周期点、基于 3 种方法的 B5 蓄电池 $\mathrm{{SOH}}$ 预测曲线, figureFileSmall=m0C2ZfAzf9AgoX2GQnlbsA==, figureFileBig=a+wQlD6vdUNjPT89ktOT5w==, tableContent=null), ArticleFig(id=1154048220062798723, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, label=Tab. 1, caption=Evaluation indexes for battery prediction performance based on three methods, figureFileSmall=null, figureFileBig=null, tableContent=
电池 预测方法 RMSE MAPE RUL 真实值 RUL 预测值 RUL 预测绝对误差
B5 KELM 0.0927 0.1109 55 31 24
VMD+KELM 0.0783 0.0941 55 32 23
VMD+Bat+KELM 0.0468 0.0553 55 39 16
B6 KELM 0.0694 0.1002 39 13 26
VMD+KELM 0.0462 0.0659 39 25 14
VMD+Bat+KELM 0.0176 0.0250 39 46 7
B7 KELM 0.0688 0.0786 96 48 48
VMD+KELM 0.0353 0.0397 96 66 30
VMD+Bat+KELM 0.0283 0.0317 96 71 25
B18 KELM 0.0477 0.0575 27 13 14
VMD+KELM 0.0387 0.0459 27 15 12
VMD+Bat+KELM 0.0164 0.0203 27 33 6
), ArticleFig(id=1154048220159267719, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, label=表1, caption=基于 3 种方法的蓄电池预测性能评价指标, figureFileSmall=null, figureFileBig=null, tableContent=
电池 预测方法 RMSE MAPE RUL 真实值 RUL 预测值 RUL 预测绝对误差
B5 KELM 0.0927 0.1109 55 31 24
VMD+KELM 0.0783 0.0941 55 32 23
VMD+Bat+KELM 0.0468 0.0553 55 39 16
B6 KELM 0.0694 0.1002 39 13 26
VMD+KELM 0.0462 0.0659 39 25 14
VMD+Bat+KELM 0.0176 0.0250 39 46 7
B7 KELM 0.0688 0.0786 96 48 48
VMD+KELM 0.0353 0.0397 96 66 30
VMD+Bat+KELM 0.0283 0.0317 96 71 25
B18 KELM 0.0477 0.0575 27 13 14
VMD+KELM 0.0387 0.0459 27 15 12
VMD+Bat+KELM 0.0164 0.0203 27 33 6
), ArticleFig(id=1154048220217987976, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=EN, label=Tab. 2, caption=Evaluation indexes for battery B5 prediction performance based on three methods at different prediction cycles, figureFileSmall=null, figureFileBig=null, tableContent=
预测起始 周期 预测方法 RMSE MAPE RUL 真实值 RUL 预测值 RUL 预测 绝对误差
70 KELM 0.0927 0.1109 55 31 24
VMD+KELM 0.0783 0.0941 55 32 23
VMD+Bat+KELM 0.0468 0.0553 55 39 16
80 KELM 0.0731 0.0894 45 25 20
VMD+KELM 0.0582 0.0716 45 27 18
VMD+Bat+KELM 0.0269 0.0347 45 61 16
90 KELM 0.0545 0.0678 35 19 16
VMD+KELM 0.0373 0.0466 35 22 13
VMD+Bat+KELM 0.0147 0.0191 35 40 5
100 KELM 0.0337 0.0424 25 14 11
VMD+KELM 0.0223 0.0278 25 17 8
VMD+Bat+KELM 0.0121 0.0158 25 29 4
), ArticleFig(id=1154048220276708233, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154037277324989229, language=CN, label=表2, caption=不同预测周期点, 基于 3 种方法的 B5 蓄电池预测性能评价指标, figureFileSmall=null, figureFileBig=null, tableContent=
预测起始 周期 预测方法 RMSE MAPE RUL 真实值 RUL 预测值 RUL 预测 绝对误差
70 KELM 0.0927 0.1109 55 31 24
VMD+KELM 0.0783 0.0941 55 32 23
VMD+Bat+KELM 0.0468 0.0553 55 39 16
80 KELM 0.0731 0.0894 45 25 20
VMD+KELM 0.0582 0.0716 45 27 18
VMD+Bat+KELM 0.0269 0.0347 45 61 16
90 KELM 0.0545 0.0678 35 19 16
VMD+KELM 0.0373 0.0466 35 22 13
VMD+Bat+KELM 0.0147 0.0191 35 40 5
100 KELM 0.0337 0.0424 25 14 11
VMD+KELM 0.0223 0.0278 25 17 8
VMD+Bat+KELM 0.0121 0.0158 25 29 4
)], 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.2095-2805.2024.4.251, detailUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/10.13234/j.issn.2095-2805.2024.4.251, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/PDF/10.13234/j.issn.2095-2805.2024.4.251, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/PDF/10.13234/j.issn.2095-2805.2024.4.251, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于VMD和Bat-KELM的仿真变电站蓄电池剩余寿命预测
收藏切换
PDF下载
任罡 1 , 季宁 1 , 胡晓丽 1 , 李世倩 1 , 张洁华 1 , 吴祎 2, 3
电源学报 | 电池与储能 2024,22(4): 251-259
收起
收藏切换
电源学报 | 电池与储能 2024, 22(4): 251-259
基于VMD和Bat-KELM的仿真变电站蓄电池剩余寿命预测
全屏
任罡1 , 季宁1 , 胡晓丽1 , 李世倩1 , 张洁华1 , 吴祎2, 3
作者信息
  • 1 国网江苏省电力有限公司 技能培训中心 苏州 215004
  • 2 南京邮电大学 自动化学院 南京 210023
  • 3 南京邮电大学 人工智能学院 南京 210023
  • 任罡(1983-),男,硕士,高级工程师。研究方向:电网稳定运行及调控、智能检测与控制。E-mail:cbs20151216@163.com。

    季宁(1985-),女,本科,高级讲师。研究方向:电网调控运行与电力系统仿真、智能检测与控制。E-mail: gitanjali1985@163.com。

    胡晓丽(1980-),女,硕士,高级讲师。研究方向:电力系统安全监测。E-mail: foxhuxiaoli@163.com。

    李世倩(1971-),男,本科,高级讲师。研究方向:电网调控仿真和继电保护仿真。Email: lsq561@sina.com。

    张洁华(1989-),女,硕士,中级讲师。研究方向:电力系统储能系统规划与配置技术。E-mail: 88264833@qq.com。

    吴祎(1990-),女,中国电源学会会员,通信作者,博士,讲师。研究方向:蓄电池健康监测技术。E-mail: yiw@njupt.edu.cn。

Remaining Useful Life Prediction of Simulation Substation Batteries Based on VMD and Bat-KELM
Gang REN1 , Ning JI1 , Xiaoli HU1 , Shiqian LI1 , Jiehua ZHANG1 , Yi WU2, 3
Affiliations
  • 1 Technician Training Center State Grid Jiangsu Electric Power Co., Ltd Suzhou 215004 China
  • 2 College of Automation Nanjing University of Posts and Telecommunications Nanjing 210023 China
  • 3 College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing 210023 China
出版时间: 2024-07-30 doi: 10.13234/j.issn.2095-2805.2024.4.251
文章导航
收藏切换

仿真变电站蓄电池的工作模式呈现间歇非连续性,导致电池性能在退化过程中存在容量再生现象,退化规律具有非平稳性和随机性,增大了蓄电池精确剩余寿命RUL(remaining useful life)的难度。针对存在容量再生现象的蓄电池剩余寿命预测问题,提出了变分模态分解 VMD(variational mode decomposition)和蝙蝠(Bat)优化核极限学习机 KELM(kernel extreme learning machine)组合的预测方法。基于 VMD 将蓄电池健康状态SOH(state of health)时间序列分解为整体退化分量和容量再生分量;利用 Bat优化 KELM构建各分量预测模型,以提高分量趋势预测精度;通过各分量独立预测结果的叠加,得到精确的蓄电池健康状态及剩余寿命预测值。将该方法应用于蓄电池退化数据实例分析中,结果表明该方法相较于KELM模型及VMD-KELM模型,预测精度更高,验证了该方法的优越性。

仿真变电站  /  蓄电池  /  剩余寿命预测  /  变分模态分解  /  核极限学习机

Simulation substation batteries often work under discontinuous operation conditions, which will result in capacity regeneration of batteries during their performance degradation. The degradation of batteries shows nonstationary and random characteristics, leading to a low prediction accuracy for the remaining useful life(RUL). Aimed at the problem of RUL prediction of batteries with capacity regeneration, a prediction method is proposed based on variational mode decomposition(VMD) and bat optimized kernel extreme learning machine(Bat-KELM). First, VMD is employed to decompose the battery state-of-health(SOH) time series into overall degradation components and capacity regeneration components. Then, Bat-KELM is used to construct prediction models of each component, so that the prediction accuracy of component trend is improved. At last, the prediction results of all components are blended together to yield the accurate battery SOH prediction results as well as the RUL results. The proposed method is applied to the analysis of battery degradation instance data, and results show its superiority in terms of prediction accuracy compared with the KELM and VMD-KELM models.

Simulation substation  /  battery  /  remaining useful life(RUL) prediction  /  variational mode decomposition (VMD)  /  kernel extreme learning machine(KELM)
任罡, 季宁, 胡晓丽, 李世倩, 张洁华, 吴祎. 基于VMD和Bat-KELM的仿真变电站蓄电池剩余寿命预测. 电源学报, 2024 , 22 (4) : 251 -259 . DOI: 10.13234/j.issn.2095-2805.2024.4.251
Gang REN, Ning JI, Xiaoli HU, Shiqian LI, Jiehua ZHANG, Yi WU. Remaining Useful Life Prediction of Simulation Substation Batteries Based on VMD and Bat-KELM[J]. Journal of Power Supply, 2024 , 22 (4) : 251 -259 . DOI: 10.13234/j.issn.2095-2805.2024.4.251
变电站作为电网的枢纽,担负着不同地区的供电任务, 变电运维人员的培训至关重要。虚实结合的仿真变电站采用真实变电站一次、二次设备本体建设, 在不带电的安全操作场景下, 基于数字物理混合仿真系统构建电力负荷潮流数据, 驱动真实一次设备复杂物理现象运行模拟,仿真一次设备带电工况下的正常和异常故障时温度变化、声光电效果及渗油漏油等物理现象, 从而为培训人员提供物理上近似的变电站作业环境。直流电源系统是仿真变电站的重要组成部分, 其为一次设备物理现象的演示及二次辅控设备等提供电源。而蓄电池作为直流电源系统的关键部件, 运行状态直接决定电源系统的可靠性和安全性。锂离子蓄电池具有污染少、质量小、能量密度高等优势, 因此被用于仿真变电站直流电源系统中。然而, 锂离子蓄电池在工作过程中不可避免出现性能退化及失效问题, 引发仿真变电站供电波动甚至造成安全事故[1]。开展蓄电池健康状态$\mathrm{{SOH}}$ (state-of-health)评估及剩余寿命 RUL(remaining useful life) 预测研究, 可为蓄电池视情维修和科学管理提供决策依据, 对于保障仿真变电站安全运行具有重要意义。
蓄电池 RUL 为电池失效(电池容量或 SOH 下降至某一阈值)前剩余的充、放电周期数, 常见的蓄电池 RUL 预测方法可分为基于模型的预测方法和基于数据的预测方法[2] 这 2 大类。基于模型的预测方法利用先验或专家知识, 通过构建失效或经验退化模型来预测电池剩余寿命[3],其预测精度依赖于模型精度, 且由于电池工作机理复杂性和工况不确定性, 精确数学模型通常难以建立且不具有普适性; 而现有的关于蓄电池 RUL 预测的研究较多地集中于基于数据的预测方法, 其结合传感监测数据(如电压、电流、容量等)和智能算法跟踪来预测电池退化并估算电池RUL[4-5]。基于数据的蓄电池 RUL 预测方法又分为基于深度学习的方法和基于浅层机器学习的方法。深度学习法主要包括卷积神经网络[6] 、长短期记忆网络[7-8] 等; 常用的浅层机器学习方法包括神经网络[9] 、支持向量机[10] 、 极限学习机 ELM(extreme learning machine)[11] 等。 Liu Xinwang 等[12] 在 ELM 基础上改进得到新型单隐层前向网络, 即核极限学习机 KELM(kernel extreme learning machine), 其采用核函数代替 ELM 中的随机映射, 具有泛化性好、非线性强等优点, 然而其正则化参数和核参数需要预先选取, 表现出一定的不确定性。
仿真变电站蓄电池在培训过程中为变电站设备提供电源, 其工作模式具有间歇性, 导致电池容量在退化过程中存在再生现象[13],即发生局部回升,使得电池退化规律呈现随机性、复杂性和非平稳性, 从而增加了电池剩余寿命准确预测的难度。 针对该类问题, 本文采用分解预测并组合的方法进行蓄电池剩余寿命预测, 即通过对原始退化序列进行预分解处理, 并对分解分量进行预测和重组, 以降低信号复杂性, 更好捕捉不同分量的变化特性, 从而提高预测性能。变分模态分解 VMD(variational mode decomposition)是近年来被广泛关注的信号分解新方法, 其将信号按频率从低到高自适应地分解为若干固有模态分量, 相比传统信号分解技术 (如经验模态分解)具有鲁棒性好、收敛控制合理、 抗模态混叠等优点[14],更适用于处理非线性、非平稳信号。
基于上述分析, 本文提出一种基于 VMD 和蝙蝠算法 Bat 优化 KELM 的蓄电池剩余寿命预测方法 Bat-KELM。首先,利用 VMD 对蓄电池 SOH 原始序列进行信号处理, 分解出整体退化分量和容量再生分量;然后,针对不同分解分量, 基于 Bat 算法优化 KELM 模型参数, 构建符合各分量变化规律的预测模型;最后,组合各分量预测值以获取最终蓄电池健康状态及剩余寿命预测结果。
VMD 分解是一种自适应、非递归的信号分解方法, 采用非递归变分模式将信号自适应分解为多个固有模态分量, 其关键过程包括构造和求解变分问题 2 个部分[15]
构造变分问题,即将原始输入信号$f$ 分解为具有有限带宽的多个模态函数${u}_{n}\left( t\right)$,且最小化所有模态带宽之和。具体步骤包括:
步骤 1 对各模态函数${u}_{n}\left( t\right)$ 进行 Hilbert 变换, 获取单侧频谱:$\left({\delta \left( t\right)+ \mathrm{j}/{\pi t}}\right)\times {u}_{n}\left( t\right)$
步骤 2 通过将各模态混合来估计中心频率${\mathrm{e}}^{-\mathrm{j}{\omega }_{n}t}$,把频谱转移到基频区域:$\left\lbrack {\left({\delta \left( t\right)+ \mathrm{j}/{\pi t}}\right)\times {u}_{n}\left( t\right)}\right\rbrack$ ${\mathrm{e}}^{-\mathrm{j}{\omega }_{n}t}$
步骤 3 对解调信号计算梯度 L2 范数, 获取各分量估计带宽, 此时约束变分模型转换为
$\left\{\begin{array}{l}\mathop{\min }\limits_{\left\{{u}_{n}\right\}}\left\{{\mathop{\sum }\limits_{n}{\begin{Vmatrix}{\partial }_{t}\left\lbrack \left(\delta \left( t\right)+ \mathrm{j}/\pi t\right)\times {u}_{n}\left( t\right)\right\rbrack {\mathrm{e}}^{-\mathrm{j}{\omega }_{n}t}\end{Vmatrix}}^{2}}\right\}\\\text{ s.t.}\mathop{\sum }\limits_{n}{u}_{n}= f \end{array}\right.$
式中,$\delta \left( t\right)$ 为 Dirac 分布函数。
基于二次惩罚函数项${C}^{\prime }$ 和拉格朗日乘子$\gamma \left( t\right)$, 将式(1)变为无约束变分问题,即
$ L\left({\left\{{u}_{n}\right\},\left\{{\omega }_{n}\right\},\gamma }\right)= \\{C}^{\prime }\mathop{\sum }\limits_{n}{\begin{Vmatrix}{\partial }_{t}\left\lbrack \left(\delta \left( t\right)+ \mathrm{j}/\pi t\right){u}_{n}\left( t\right)\right\rbrack {\mathrm{e}}^{-\mathrm{j}{\omega }_{n}t}\end{Vmatrix}}^{2}+ \\{\begin{Vmatrix}f\left( t\right)- \mathop{\sum }\limits_{n}{u}_{n}\left( t\right)\end{Vmatrix}}_{2}^{2}+ \left\langle {\lambda \left( t\right), f\left( t\right)- \mathop{\sum }\limits_{n}{u}_{n}\left( t\right)}\right\rangle $
对式(2)通过交替方向乘子进行求解,更新${u}_{n}^{k + 1}\text{、}{\omega }_{n}^{k + 1}\text{、}{\lambda }^{k + 1}(k$ 为迭代次数),以寻找增广拉格朗日函数的鞍点。获取模态序列并结束迭代需满足
$\mathop{\sum }\limits_{n}{\begin{Vmatrix}{\widetilde{u}}_{n}^{k + 1}- {\widetilde{u}}_{n}^{k}\end{Vmatrix}}_{2}^{2}/{\begin{Vmatrix}{\widetilde{u}}_{n}^{k}\end{Vmatrix}}_{2}^{2}< e $
式中:${\widetilde{u}}_{n}^{k + 1}$${u}_{n}^{k + 1}$ 的傅里叶变换;$e$ 为设定的判别精度。否则继续更新上述参数。
KELM 是在 ELM 中采用核函数替换随机映射所得到的学习机算法。在 KELM 算法实现中, 其模型参数需预先设定, 若选取不恰当则会影响模型性能。为避免人工设置导致的参数不确定性和随机性, 本文采用 Bat 算法优化模型参数来提高模型的训练精度和预测精度。
给定$J$ 组训练样本$\left({{\mathbf{x}}_{j},{\mathbf{t}}_{j}}\right)\in {R}^{n}* {R}^{m}$,即${\mathbf{x}}_{j}= \left\lbrack {{x}_{j1},\cdots }\right.$,${\left.{x}_{jn}\right\rbrack }^{\mathrm{T}},{t}_{j}= {\left\lbrack {t}_{j1},\cdots,{t}_{jm}\right\rbrack }^{\mathrm{T}}$,则隐含层节点为$L$ 的单隐层前向网络的输出为
$ y\left({\mathbf{x}}_{j}\right)= \mathop{\sum }\limits_{{i = 1}}^{L}{\mathbf{\beta }}_{i}\mathbf{G}\left({{\mathbf{x}}_{j},{\mathbf{w}}_{i},{\mathbf{b}}_{i}}\right)= {\mathbf{o}}_{j}\;\left({j = 1,2,3,\cdots, J}\right)$
式中,${\mathbf{\beta }}_{i}$ 为第$i$ 个隐含层节点到输出层之间的权值。
若网络输出零误差且等于样本输出,即$\mathop{\sum }\limits_{{j = 1}}^{J}\begin{Vmatrix}{{\mathbf{o}}_{j}- {\mathbf{t}}_{j}}\end{Vmatrix}= 0$,则存在${\mathbf{\beta }}_{i}\text{、}{\mathbf{w}}_{i}\text{、}{\mathbf{b}}_{i}$,使
$\mathop{\sum }\limits_{{i = 1}}^{L}{\mathbf{\beta }}_{i}\mathbf{G}\left({{\mathbf{x}}_{j},{\mathbf{w}}_{i},{\mathbf{b}}_{i}}\right)= {\mathbf{t}}_{j}\;\left({j = 1,2,3,\cdots, J}\right)$
改写为矩阵形式
$\mathbf{{HB}}= \mathbf{T}$
式中:$\mathbf{H}$ 为隐含层节点输出,$\mathbf{H}= \left\lbrack \begin{matrix}\mathbf{h}\left({\mathbf{x}}_{1}\right)\\\vdots \\\mathbf{h}\left({\mathbf{x}}_{J}\right)\end{matrix}\right\rbrack =$
${\left\lbrack \begin{matrix}\mathbf{G}\left({{\mathbf{x}}_{1},{\mathbf{w}}_{1},{\mathbf{b}}_{1}}\right)\cdots \mathbf{G}\left({{\mathbf{x}}_{1},{\mathbf{w}}_{L},{\mathbf{b}}_{L}}\right)\\\vdots \\\mathbf{G}\left({{\mathbf{x}}_{J},{\mathbf{w}}_{1},{\mathbf{b}}_{1}}\right)\cdots \mathbf{G}\left({{\mathbf{x}}_{J},{\mathbf{w}}_{L},{\mathbf{b}}_{L}}\right)\end{matrix}\right\rbrack }_{J \times L};\mathbf{B}$ 为输出权值,
$\mathbf{B}= {\left\lbrack \begin{matrix}{\mathbf{\beta }}_{1}^{\mathrm{T}}\\\vdots \\{\mathbf{\beta }}_{L}^{\mathrm{T}}\end{matrix}\right\rbrack }_{L \times m};\mathbf{T}$ 为模型输出,$\mathbf{T}= {\left\lbrack \begin{matrix}{\mathbf{t}}_{1}^{\mathrm{T}}\\\vdots \\{\mathbf{t}}_{J}^{\mathrm{T}}\end{matrix}\right\rbrack }_{J \times m}$
与传统神经网络采用梯度下降法训练网络权值的方式不同, ELM 采用求线性方程组最小二乘解的方式获取输出权值矩阵, 即
$\begin{Vmatrix}{\mathbf{H}\left({{\mathbf{w}}_{1},\cdots,{\mathbf{w}}_{L},{\mathbf{b}}_{1},\cdots,{\mathbf{b}}_{L}}\right)\widehat{\mathbf{B}}- \mathbf{T}}\end{Vmatrix}= $
$\mathop{\min }\limits_{{\beta }_{i}}\parallel \mathbf{H}\left({{\mathbf{w}}_{1},\cdots,{\mathbf{w}}_{L},{\mathbf{b}}_{1},\cdots,{\mathbf{b}}_{L}}\right)\mathbf{B}- \mathbf{T}\parallel $
为提高网络稳定性和泛化能力, 基于 Tikhonov 正则化和岭回归思想,给定正则化参数$\eta$,则$\mathbf{B}$ 的最小二乘解为
$\widehat{\mathbf{B}}= {\mathbf{H}}^{\mathrm{T}}{\left(\mathbf{H}{\mathbf{H}}^{\mathrm{T}}+ \eta \mathbf{I}\right)}^{-1}\mathbf{T}$
考虑特征映射函数$h\left( x\right)$ 未知,在 ELM 中引入核函数,定义核矩阵为${\Omega }_{\mathrm{{ELM}}}= {\mathbf{{HH}}}^{\mathrm{T}}$,其元素为${\Omega }_{\mathrm{{ELM}}}$ $\left({i, j}\right)= h\left({x}_{i}\right)\cdot h\left({x}_{j}\right)= K\left({{x}_{i},{x}_{j}}\right)$,利用式 (8) 得到网络输出
$ y\left( x\right)= h\left( x\right)\widehat{\mathbf{B}}= h\left( x\right){\mathbf{H}}^{\mathrm{T}}{\left(\eta \mathbf{I}+ \mathbf{H}{\mathbf{H}}^{\mathrm{T}}\right)}^{-1}\mathbf{T}= \\{\left\lbrack \begin{matrix} K\left({x,{x}_{1}}\right)\\\vdots \\ K\left({x,{x}_{N}}\right)\end{matrix}\right\rbrack }^{\mathrm{T}}{\left(\eta \mathbf{I}+ {\Omega }_{\mathrm{{ELM}}}\right)}^{-1}\mathbf{T}$
常用的核函数$K\left({{x}_{i},{x}_{j}}\right)$ 有径向基核函数、多项式核函数及线性核函数等。考虑径向基核函数具有强大的非线性处理能力, 适合对蓄电池复杂时变退化规律进行建模, 本文采用径向基核函数
$ K\left({{x}_{i},{x}_{j}}\right)= \exp \left({-\frac{{\begin{Vmatrix}{x}_{i}- {x}_{j}\end{Vmatrix}}^{2}}{{\gamma }^{2}}}\right)$
式中,$\gamma$ 为核参数。
Bat 算法模拟蝙蝠捕食行为自适应搜索寻优, 相比经典群智能优化算法(如粒子群优化),具有更好的收敛速度和收敛精度[16]。因此,采用 Bat 算法对模型正则化参数$\eta$ 及核参数$\gamma$ 进行优化。
在采用 Bat 算法优化 KELM 模型参数$\theta =\{\eta,\gamma \}$ 时, 设计适应度函数为
$\text{ Minimize :}I\left(\theta \right)= \sqrt{\frac{1}{M}\mathop{\sum }\limits_{{i = 1}}^{M}{\left({z}_{i}- {z}_{i}^{\prime }\right)}^{2}}$
式中:${z}_{i}$$\mathrm{{KELM}}$ 模型期望输出;${z}_{i}$ ’为$\mathrm{{KELM}}$ 模型预测输出。
具体寻优实现步骤如下:
步骤 1 种群初始化。通过均匀分布随机采样$N$ 个粒子$\left\{{{\theta }_{i}\left( 0\right), i = 1,2,\cdots, N}\right\}$ 作为初始粒子群,对每个粒子随机分配搜索脉冲频率${f}_{i}= \left\lbrack {{f}_{\min },{f}_{\max }}\right\rbrack$、脉冲频度${r}_{i}\left( 0\right)$ 和音强${A}_{i}\left( 0\right)$
步骤 2 模拟蝙蝠全局搜索行为, 更新粒子脉冲频率、速度及位置
$\left\{\begin{array}{l}{f}_{i}= {f}_{\min }+ \left({{f}_{\max }- {f}_{\min }}\right){\beta }^{\prime }\\{v}_{i}\left( n\right)= {v}_{i}\left({n - 1}\right)+ \left\lbrack {{\theta }_{i}\left({n - 1}\right)- {\theta }_{\text{best }}}\right\rbrack {f}_{i}\\{\theta }_{i}\left( n\right)= {\theta }_{i}\left({n - 1}\right)+ {v}_{i}\left( n\right)\end{array}\right.$
式中:${\beta }^{\prime }$$\left\lbrack {0,1}\right\rbrack$ 随机数;${v}_{i}\left( n\right)$$n$ 次迭代时第$i$ 个粒子速度;${\theta }_{i}\left( n\right)$$n$ 次迭代时第$i$ 个粒子位置;${\theta }_{\text{best }}$ 为粒子群全局最优位置。
步骤 3 模拟蝙蝠局部搜索行为, 从均匀分布$\left\lbrack {0,1}\right\rbrack$ 生成随机数${\operatorname{rand}}_{1}$,若${\operatorname{rand}}_{1}< {r}_{i}$,则接受通过式 (12)更新的粒子位置;若${\operatorname{rand}}_{1}> {r}_{i}$,则计算新位置
${\theta }_{i}\left( n\right)= {\theta }_{\text{best }}+ \varepsilon {A}^{\prime }$
式中:$\varepsilon$$\left\lbrack {0,1}\right\rbrack$ 随机数;${A}^{\prime }$ 为所有粒子的平均音强。
步骤 4 从均匀分布$\left\lbrack {0,1}\right\rbrack$ 生成随机数${\operatorname{rand}}_{2}$,若${\operatorname{rand}}_{2}< {A}_{i}\left({n - 1}\right)$$I\left\lbrack {{\theta }_{i}\left( n\right)}\right\rbrack < I\left({\theta }_{\text{best }}\right)$,则粒子位置为${\theta }_{i}\left( n\right)$, 并调整粒子局部搜索能力,更新脉冲音强${A}_{i}\left( n\right)$ 和脉冲频度${r}_{i}\left( n\right)$
$\left\{\begin{array}{l}{A}_{i}\left( n\right)= \delta {A}_{i}\left({n - 1}\right)\\{r}_{i}\left( n\right)= {r}_{i}\left( 0\right)\left\lbrack {1 -\exp \left({-{\xi n}}\right)}\right\rbrack \end{array}\right.$
式中:$\delta$ 为衰减系数;$\xi$ 为增强系数。
步骤 5 基于式(11)计算各粒子目标函数值, 并更新全局最优值${\theta }_{\text{best }}$
${\theta }_{\text{best }}= \min \left\{{I\left\lbrack {{\theta }_{1}\left( n\right)}\right\rbrack, I\left\lbrack {{\theta }_{2}\left( n\right)}\right\rbrack,\cdots, I\left\lbrack {{\theta }_{N}\left( n\right)}\right\rbrack }\right\}$
当算法达到最大迭代次数或精度阈值时, 停止迭代优化。
本文采用 VMD 分解和 Bat-KELM 进行蓄电池剩余寿命预测, 预测流程如图1所示, 主要分为 4 个步骤。
步骤 1 数据输入: 蓄电池容量可有效反映电池退化状态, 本文首先基于不同充、放电周期下蓄电池容量数据$\left\{{{C}_{1},{C}_{2},\cdots,{C}_{h}}\right\}$,计算电池健康状态$\left\{{{\mathrm{{SOH}}}_{1},{\mathrm{{SOH}}}_{2},\cdots,{\mathrm{{SOH}}}_{h}}\right\}$,以获取蓄电池$\mathrm{{SOH}}$ 时间序列原始数据, 即
${\mathrm{{SOH}}}_{i}= \frac{{C}_{i}}{{C}_{1}}\times {100}\%\left({i = 1,2,3,\cdots, h}\right)$
式中:${C}_{1}$ 为第 1 个循环周期的电池放电容量,即实际初始容量;${C}_{i}$ 为第$i$ 个循环周期的电池放电容量。
步骤 2 数据分解: 采用 VMD 将蓄电池$\mathrm{{SOH}}$ 退化数据分解为$n$ 个特征互异的模态分量序列$\left\{{{\mathrm{{IMF}}}_{1}\left( 1\right),{\mathrm{{IMF}}}_{1}\left( 2\right),\cdots,{\mathrm{{IMF}}}_{1}\left( h\right)}\right\},\cdots,\left\{{{\mathrm{{IMF}}}_{n}\left( 1\right),}\right.$ $\left.{{\mathrm{{IMF}}}_{n}\left( 2\right),\cdots,{\mathrm{{IMF}}}_{n}\left( h\right)}\right\}$,主要包含随机扰动分量、 再生分量和整体退化分量。
步骤 3 分量预测: 针对各个分解分量, 建立模型训练集和预测集, 利用 Bat 优化 KELM 模型核参数和正则化参数,即优化粒子$\theta =\{\eta,\gamma \}$,构建各分量预测模型并进行分量时间序列预测, 得到分量预测结果序列为$\left\{{{\mathrm{{IMF}}}_{1}\left({h + 1}\right),{\mathrm{{IMF}}}_{1}\left({h + 2}\right),\cdots }\right.$,$\left.{{\mathrm{{IMF}}}_{1}\left({h + s}\right)}\right\},\cdots,\left\{{{\mathrm{{IMF}}}_{n}\left({h + 1}\right),{\mathrm{{IMF}}}_{n}\left({h + 2}\right),\cdots,{\mathrm{{IMF}}}_{n}}\right.$ $\left({h + s}\right)\}$
步骤 4 结果输出及性能分析: 将各分量预测结果进行叠加,得到$\mathrm{{SOH}}$ 时间序列预测值$\left\{{\mathrm{{SOH}}}_{h + 1}\right.$,$\left.{{\mathrm{{SOH}}}_{h + 2},\cdots,{\mathrm{{SOH}}}_{h + s}}\right\}$,其中${\mathrm{{SOH}}}_{h + p}= \mathop{\sum }\limits_{{j = 1}}^{{j = n}}{\mathrm{{IMF}}}_{j}$ $\left({h + p}\right)\left({p = 1,2,3,\cdots, s}\right)$。通过对比$\mathrm{{SOH}}$ 预测结果与电池失效阈值${Q}_{\text{threshold }}$ 计算电池剩余寿命,同时对预测结果进行性能分析。蓄电池剩余寿命 RUL 计算公式为
$\mathrm{{RUL}}= \left\{\begin{array}{l}{\mathrm{{SOH}}}_{h +\text{ RUL-1 }}> {Q}_{\text{threshold }}\\{\mathrm{{SOH}}}_{h +\text{ RUL }}\leq {Q}_{\text{threshold }}\end{array}\right.$
NASA 研究中心提供的锂离子电池公开退化数据集[17] 为目前分析电池 RUL 预测方法的常用数据集之一, 该数据集采用的研究对象为锂离子蓄电池, 与仿真变电站中常用的蓄电池材料类别相同。此外, 该数据集对电池进行充放电测试时, 测试工况存在偶然间断性, 与仿真变电站蓄电池的间歇工作特性相吻合。因此, 本文以该数据集为实例, 对所提预测方法进行验证及分析。在数据集测试过程中,对蓄电池(B5、B6、B7、B18) 开展了多次循环充、放电操作,以获取不同循环周期下的退化数据。在每个循环周期内, 首先对蓄电池进行标准恒流-恒压充电直至完全充满, 然后使用恒流放电(1C)方式将电池放电。每个电池的放电结束条件有所不同, 但在计算容量真实值时均以放电到${2.7}\mathrm{\;V}$ 的容量为依据。图2为蓄电池$\mathrm{{SOH}}$ 随循环周期的变化曲线,可知,蓄电池容量随循环周期数的增大, 整体表现为下降趋势, 但在部分周期由于电磁干扰、测量误差、再生现象等不可预知行为的影响, 呈现出非单调性下降规律。
对蓄电池$\mathrm{{SOH}}$ 退化数据进行$\mathrm{{VMD}}$ 分解时, 考虑电池退化数据中主要包含整体退化趋势、再生分量及若干随机分量,则设定分解序列数为 4。图3(a)和(b)分别为利用 VMD 对蓄电池 B5 和 B6 进行分解得到的不同分量曲线, 可知: VMD 将原始容量退化数据分解为波动速率不同的 4 个分量, 其中分量 IMF1 的波动频率最小, 很好地反映了电池整体退化趋势; 而分量 IMF2 的波动速率次之, 表示电池的不规律容量再生行为; 其余分量则为波动速率较高的随机分量。由此可知, 利用 VMD 分解原始信号可以有效地将$\mathrm{{SOH}}$ 退化数据中不同尺度波动及趋势项逐级分解出来, 从而降低信号的非平稳性和复杂性, 为后续 RUL 预测提供基础。
为验证本文预测方法的有效性, 分别采用 KELM、VMD+KELM、VMD+Bat-KELM 这 3 种方法进行$\mathrm{{SOH}}$ 预测,并进行性能对比分析。利用均方根误差 RMSE(root mean square error)和平均绝对百分比误差 MAPE(mean absolute percentage error)来评估$\mathrm{{SOH}}$ 趋势预测结果,采用剩余寿命预测绝对误差 AE(absolute error)评估最终剩余寿命预测准确性。3 种评价指标可分别表示为
$\text{ RMSE }= \sqrt{\frac{1}{N}\mathop{\sum }\limits_{{i = 1}}^{N}{\left({\mathrm{{SOH}}}_{i}- {\mathrm{{SOH}}}_{i}^{\prime }\right)}^{2}}$
$\text{ MAPE }= \frac{1}{N}\mathop{\sum }\limits_{{i = 1}}^{N}\left|\frac{{\mathrm{{SOH}}}_{i}- {\mathrm{{SOH}}}_{i}^{\prime }}{{\mathrm{{SOH}}}_{i}}\right|\times {100}\%$
$\mathrm{{AE}}= \left|{{\mathrm{{RUL}}}_{\text{real }}- {\mathrm{{RUL}}}_{\text{pred }}}\right|$
式中:${\mathrm{{SOH}}}_{i}$ 为真实值;${\mathrm{{SOH}}}_{i}$ ’为预测值;$N$ 为预测点数;${\mathrm{{RUL}}}_{\text{pred }}$ 为剩余寿命预测值;${\mathrm{{RUL}}}_{\text{real }}$ 为剩余寿命真实值。
在式(18)~式(20)中,指标值越小表明预测性能越好。在计算电池 RUL 时, 按标准定义电池失效为实际容量衰减到标称容量$\left({C}_{\text{标称 }}\right)$ 的 70%,则根据式(16)可得电池$\mathrm{{SOH}}$ 失效阈值${Q}_{\text{threshold }}= {0.7}{C}_{\text{标称 }}/{C}_{1}$。 然后根据式(17),结合$\mathrm{{SOH}}$ 真实值和失效阈值计算出剩余寿命真实值,根据$\mathrm{{SOH}}$ 预测值和失效阈值则可对应计算出剩余寿命预测值。
选取蓄电池前 70 个循环周期的 SOH 数据构建训练集,后续$\mathrm{{SOH}}$ 数据作为测试集,以前 10 个循环周期$\mathrm{{SOH}}$ 作为预测模型输入,后一循环周期 SOH 作为模型输出, 分别对 3 种方法进行模型训练及测试。在 KELM 和 VMD+KELM 方法中, 其正则化参数和核参数随机选取; 而对于 VMD+ Bat-KELM 方法, 选取 Bat 优化算法种群数为 50, 进化次数为 10,3 种方法均采取 10 次运行的平均结果进行性能分析。
图4为基于 3 种方法分别对蓄电池 B5 和 B7 进行$\mathrm{{SOH}}$ 预测的曲线,表1为针对 4 个蓄电池进行预测的性能评价指标。由图4表1可知, 针对不同电池, 基于 VMD+Bat-KELM 跟踪 SOH 的变化趋势最接近于真实趋势, 其性能评价指标最小, 其次为 VMD+KELM 方法。以电池 B7 为例, 采用单一 KELM 方法对 RUL 的预测绝对误差为 48 周期, 采用 VMD+KELM 方法的预测绝对误差为 30 周期, 而采用 VMD+Bat-KELM 方法的预测绝对误差为 25 周期, 这表明通过 VMD 分解可有效降低电池退化信号的复杂性和非平稳性, 从而在构建预测模型时更好地捕捉分量特征变化规律, 优于仅采用单一模型进行预测的结构。此外, 相较于 VMD+KELM模型,利用 Bat 优化 KELM 模型参数, 可进一步提升 KELM 模型对非线性退化规律的学习性能,从而提高预测精度。
为进一步验证本文方法的有效性, 从不同循环周期数开始对电池 B5 进行 RUL 预测,图5为从第 70 和 90 周期进行预测的结果曲线,表2给出了分别从第 70、80、90 和 100 周期进行预测的性能评价指标。分析可知, 随着预测周期数的增大和训练样本的增多, 基于 3 种不同方法的 SOH 预测趋势均与真实变化趋势越来越接近, 且预测性能评价指标越小, 说明 3 种预测方法均可有效利用新增训练数据, 提高预测精度。此外, 从同一循环周期开始进行预测时, VMD+Bat-KELM 的预测性能均最优, 其次为 VMD+KELM, 采用 KELM 模型的预测效果最差。如在第 90 时刻点,采用 3 种方法获得的$\mathrm{{SOH}}$ 预测 RMSE 分别为 0.0147、0.0373 和 0.0545, RUL 预测绝对误差分别为 5、13 和 16 周期, 这表明在任一预测时刻,本文方法均能有效提高 RUL 预测性能。
针对间歇工作条件下的仿真变电站蓄电池剩余寿命预测问题, 本文提出了基于 VMD 和 Bat 优化 KELM 的剩余寿命预测方法 Bat-KELM。该方法利用变分模态分解将具有非平稳性和随机性的电池退化量拆分为退化分量、再生分量和随机扰动分量等若干分量, 实现了不同类别分量的有效解耦, 降低了完整退化信号的复杂性和预测难度。其次, 针对不同分量变化规律, 分别利用 Bat 优化 KELM 模型正则化参数和核参数, 构建了分量预测模型, 提高了各分量预测精度, 最终提高了剩余寿命预测整体精度。实例分析表明,采用 VMD 和 Bat-KELM 组合预测框架可准确实现蓄电池剩余寿命预测, 且性能优于 KELM 及 VMD-KELM 方法。
  • 国网江苏省电力有限公司科技项目(J2021020)
参考文献 引证文献
排序方式:
[1]
刘跃文. 变电站直流电源系统运维管理研究[D]. 济南: 山东大学, 2020.
Liu Yuewen. Research on operation and maintenance management of substation DC power system[D]. Ji'nan: Shandong University, 2020. (in Chinese).
[2]
Ge Mingfeng, Liu Yiben, Jiang Xingxing, et al. A review on state of health estimations and remaining useful life prognostics of lithium-ion batteries[J]. Measurement, 2021. 174: 109057.
[3]
Chao, Lai Qingzhi, Ge Tengfei, et al. A lead-acid battery's remaining useful life prediction by using electrochemical model in the particle filtering framework[J]. Energy, 2017. 120: 975-984.
[4]
Hossain Lipu M S, Hannan M A, Karim T F, et al. Intelligent algorithms and control strategies for battery management system in electric vehicles: Progress, challenges and future outlook[J]. Journal of Cleaner Production, 2021. 292: 126044.
[5]
Hu Xiaosong, Xu Le, Lin Xianke, et al. Battery lifetime prognostics[J]. Joule, 2020. 4(2): 310-346.
[6]
Ren Lei, Dong Jiabao, Wang Xiaokang, et al. A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life[J]. IEEE transactions on industrial informatics, 2021. 17(5): 3478-3487.
[7]
Yu Yong, Hu Changhua, Si Xiaosheng, et al. Averaged Bi-LSTM networks for RUL prognostics with non-life-cycle labeled dataset[J]. Neurocomputing, 2020. 402: 134-147.
[8]
孙丙香, 任鹏博, 陈育哲, 等. 锂离子电池在不同区间下的衰退影响因素分析及任意区间的老化趋势预测[J]. 电工技术学报, 2021. 36(3): 666-674.
Sun Bingxiang, Ren Pengbo, Chen Yuzhe, et al. Analysis of influencing factors of degradation under different interval stress and prediction of aging trend in any interval for lithium-ion battery[J]. Transactions of China Electrotechnical Society, 2021. 36(3): 666-674 (in Chinese).
[9]
Tang Xiaopeng, Liu Kailong, Wang Xin, et al. Model migration neural network for predicting battery aging trajectories[J]. IEEE Transactions on Transportation Electrification, 2020. 6(2): 363-374.
[10]
刘斌, 毕小熊, 党军朋, 等. 基于支持向量回归的变电站蓄电池退化趋势预测[J]. 电源学报, 2020. 18(6): 207-214.
Liu Bin, Bi Xiaoxiong, Dang Junpeng, et al. Degradation trend prediction of battery in substation based on support vector regression[J]. Journal of Power Supply, 2020. 18(6): 207-214 (in Chinese).
[11]
Ma Yanying, Wu Lifeng, Guan Yong, et al. The capacity estimation and cycle life prediction of lithium-ion batteries using a new broad extreme learning machine approach[J]. Journal of Power Sources, 2020. 476: 228581.
[12]
Liu Xinwang, Wang Lei, Huang Guangbin, et al. Multiple kernel extreme learning machine[J]. Neurocomputing, 2015. 149: 253-264.
[13]
Zhang Senju, Kang Rui, Lin Yanhui. Remaining useful life prediction for degradation with recovery phenomenon based on uncertain process[J]. Reliability Engineering &amp; System Safety, 2021. 208: 107440.
[14]
丁承君, 冯玉伯, 王曼娜. 基于变分模态分解与深度卷积神经网络的滚动轴承故障诊断[J]. 振动与冲击, 2021. 40(2): 287-296.
Ding Chengjun, Feng Yubo, Wang Manna. Rolling bearing fault diagnosis using variational mode decom-position and deep convolutional neural network[J]. Journal of Vibration and Shock, 2021. 40(2): 287-296 (in Chinese).
[15]
周静雷, 颜婷. 应用变分模态分解及能量熵的扬声器异常声分类[J]. 声学学报, 2021. 46(2): 263-270.
Zhou Jinglei, Yan Ting. Loudspeaker abnormal sound classification using variational mode decomposition and energy entropy[J]. Acta Acustica, 2021. 46(2): 263-270 (in Chinese).
[16]
陈志敏, 吴盘龙, 薄煜明, 等. 基于自控蝙蝠算法智能优化粒子滤波的机动目标跟踪方法[J]. 电子学报, 2018. 46(4): 886-894.
Chen Zhimin, Wu Panlong, Bo Yuming, et al. Adaptive control Bat algorithm intelligent optimization particle filter for maneuvering target tracking[J]. Acta Electronica Sinica, 2018. 46(4): 886-894 (in Chinese).
[17]
Saha B, Goebel K, Poll S, et al. Prognostics methods for battery health monitoring using a Bayesian framework[J]. IEEE Transactions on Instrumentation and Measurement, 2008. 58(2): 291-296.
2024年第22卷第4期
PDF下载
232
79
引用本文
BibTeX
文章信息
doi: 10.13234/j.issn.2095-2805.2024.4.251
  • 接收时间:2021-12-30
  • 首发时间:2025-07-21
  • 出版时间:2024-07-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2021-12-30
  • 修回日期:2022-03-03
  • 录用日期:2022-03-24
基金
Science and Technology Project of State Grid Jiangsu Electric Power Co., Ltd.(J2021020)
国网江苏省电力有限公司科技项目(J2021020)
作者信息
    1 国网江苏省电力有限公司 技能培训中心 苏州 215004
    2 南京邮电大学 自动化学院 南京 210023
    3 南京邮电大学 人工智能学院 南京 210023
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.4.251
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