Article(id=1153375944363467604, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153375932170621317, articleNumber=null, orderNo=null, doi=10.13234/j.issn.2095-2805.2024.6.188, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1636646400000, receivedDateStr=2021-11-12, revisedDate=1642694400000, revisedDateStr=2022-01-21, acceptedDate=1646064000000, acceptedDateStr=2022-03-01, onlineDate=1752915853825, onlineDateStr=2025-07-19, pubDate=1732896000000, pubDateStr=2024-11-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752915853825, onlineIssueDateStr=2025-07-19, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752915853825, creator=13701087609, updateTime=1752915853825, updator=13701087609, issue=Issue{id=1153375932170621317, tenantId=1146029695717560320, journalId=1146031654075715584, year='2024', volume='22', issue='6', pageStart='1', pageEnd='326', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752915850917, creator=13701087609, updateTime=1753780959263, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1157004459600597839, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153375932170621317, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1157004459600597840, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153375932170621317, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=188, endPage=198, ext={EN=ArticleExt(id=1153375945835668314, articleId=1153375944363467604, tenantId=1146029695717560320, journalId=1146031654075715584, language=EN, title=Prediction of Remaining Useful Life of Lithium-ion Battery Based on VMD and ISSA-ELM, columnId=1152281491788100462, journalTitle=Journal of Power Supply, columnName=Battery and Energy Storage, runingTitle=null, highlight=null, articleAbstract=

Accurately predicting the remaining useful life (RUL) of lithium-ion batteries is of significance for improving the safety of working environment and the reliability of equipment. To improve the stability and accuracy of RUL prediction, a battery RUL prediction method based on the combination of denoising technology and hybrid data-driven model is proposed. First, the original data is decomposed by variational mode decomposition, and the noise components are filtered by the analysis of correlation. The residual error is combined with the components which have a strong correlation to complete the sequence reconstruction process. Second, with the combination of Tent chaotic mapping, sine cosine algorithm and Levy flight strategy, the sparrow search algorithm (SSA) is optimized, and the optimal weight threshold of extreme learning machine (ELM) is obtained. Finally, the improved SSA-ELM model is trained by using the smoothed denoised data, and the RUL prediction is completed. The NASA data sets are used to verify the effectiveness of the proposed method. Experimental results show that the average absolute error and root mean square error of the prediction result obtained using this method are controlled within 1.58% and 2.14%, respectively, indicating that this method has a high robustness and a high prediction accuracy. Therefore, the proposed method can be applied to battery RUL prediction.

, 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=Heng DING, Kai HUANG, Haijian TIAN), CN=ArticleExt(id=1153376128094953478, articleId=1153375944363467604, tenantId=1146029695717560320, journalId=1146031654075715584, language=CN, title=基于VMD 和ISSA-ELM 的锂离子电池剩余使用寿命预测, columnId=1149830274575463188, journalTitle=电源学报, columnName=电池与储能, runingTitle=null, highlight=null, articleAbstract=

准确预测锂离子电池的剩余使用寿命RUL(remaining useful life)对提高工作环境安全性和设备可靠性等具有重要意义。为提高RUL 预测的稳定性和精度,提出1种基于去噪技术与混合数据驱动模型相结合的电池RUL 预测方法。首先,利用变分模态分解处理原始数据,采用相关性分析筛选出噪声分量,将残差与相关性较强的分量进行组合完成序列重构过程;其次,结合 Tent 混沌映射、正余弦算法和 Levy 飞行策略优化麻雀搜索算法 SSA(sparrow search algorithm), 通过寻优得到极限学习机ELM(extreme learning machine)的最优权阈值;最后,采用平滑去噪数据训练改进的SSA-ELM模型并完成 RUL预测,采用NASA 数据集验证算法有效性。实验结果表明,所提方法预测结果的平均绝对误差和均方根误差可分别控制在1.58%和2.14%內,具有较高的鲁棒性和预测精度,可应用于电池RUL预测。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=x6tb6atzLlExtSILs+aXbg==, magXml=5gFmL1asKQ7OMr4aTHoYgw==, pdfUrl=null, pdf=cb+jhtN0N2TEHcOHhhwTvw==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=zIXT/OX7+EQL7wFCNI2rbA==, mapNumber=null, authorCompany=null, fund=null, authors=

丁恒(1997-),男,硕士研究生。研究方向:电器可靠性理论及检测技术、储能电池组建模及寿命预测等。E-mail: 1377752790@qq.com。

黄凯(1980-),男,中国电源学会会员,通信作者,博士,副教授。研究方向:电器可靠性理论及检测技术、储能电池组健康状态预测与可靠性评估。E-mail: huangkai@hebut.edu.cn。

田海建(1995-),男,硕士研究生。研究方向:电器可靠性理论及检测技术、储能电池组建模及寿命预测。E-mail: 1843718316@qq.com。

, authorsList=丁恒, 黄凯, 田海建)}, authors=[Author(id=1154032442605294470, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1377752790@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154032442718540681, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, authorId=1154032442605294470, language=EN, stringName=Heng DING, firstName=Heng, middleName=null, lastName=DING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin 300130 China
2 Hebei University of Technology Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Tianjin 300130 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154032442773066635, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, authorId=1154032442605294470, language=CN, stringName=丁恒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130
2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130, bio={"img":"KJWr0gWhiuhRAG8UcqMUgg==","content":"

丁恒(1997-),男,硕士研究生。研究方向:电器可靠性理论及检测技术、储能电池组建模及寿命预测等。E-mail: 1377752790@qq.com。

"}, bioImg=KJWr0gWhiuhRAG8UcqMUgg==, bioContent=

丁恒(1997-),男,硕士研究生。研究方向:电器可靠性理论及检测技术、储能电池组建模及寿命预测等。E-mail: 1377752790@qq.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154032439748973421, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, xref=1, ext=[AuthorCompanyExt(id=1154032439757362030, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032439748973421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin 300130 China), AuthorCompanyExt(id=1154032442412356481, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032439748973421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130)]), AuthorCompany(id=1154032442475271042, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, xref=2, ext=[AuthorCompanyExt(id=1154032442479465347, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032442475271042, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Hebei University of Technology Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Tianjin 300130 China), AuthorCompanyExt(id=1154032442487853956, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032442475271042, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130)])]), Author(id=1154032442848564110, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=huangkai@hebut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154032443414795165, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, authorId=1154032442848564110, language=EN, stringName=Kai HUANG, firstName=Kai, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin 300130 China
2 Hebei University of Technology Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Tianjin 300130 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154032443481904031, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, authorId=1154032442848564110, language=CN, stringName=黄凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130
2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130, bio={"content":"

黄凯(1980-),男,中国电源学会会员,通信作者,博士,副教授。研究方向:电器可靠性理论及检测技术、储能电池组健康状态预测与可靠性评估。E-mail: huangkai@hebut.edu.cn。

"}, bioImg=null, bioContent=

黄凯(1980-),男,中国电源学会会员,通信作者,博士,副教授。研究方向:电器可靠性理论及检测技术、储能电池组健康状态预测与可靠性评估。E-mail: huangkai@hebut.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154032439748973421, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, xref=1, ext=[AuthorCompanyExt(id=1154032439757362030, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032439748973421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin 300130 China), AuthorCompanyExt(id=1154032442412356481, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032439748973421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130)]), AuthorCompany(id=1154032442475271042, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, xref=2, ext=[AuthorCompanyExt(id=1154032442479465347, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032442475271042, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Hebei University of Technology Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Tianjin 300130 China), AuthorCompanyExt(id=1154032442487853956, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032442475271042, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130)])]), Author(id=1154032443549012898, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1843718316@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154032443624510373, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, authorId=1154032443549012898, language=EN, stringName=Haijian TIAN, firstName=Haijian, middleName=null, lastName=TIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin 300130 China
2 Hebei University of Technology Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Tianjin 300130 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154032443679036325, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, authorId=1154032443549012898, language=CN, stringName=田海建, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130
2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130, bio={"content":"

田海建(1995-),男,硕士研究生。研究方向:电器可靠性理论及检测技术、储能电池组建模及寿命预测。E-mail: 1843718316@qq.com。

"}, bioImg=null, bioContent=

田海建(1995-),男,硕士研究生。研究方向:电器可靠性理论及检测技术、储能电池组建模及寿命预测。E-mail: 1843718316@qq.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154032439748973421, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, xref=1, ext=[AuthorCompanyExt(id=1154032439757362030, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032439748973421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin 300130 China), AuthorCompanyExt(id=1154032442412356481, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032439748973421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130)]), AuthorCompany(id=1154032442475271042, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, xref=2, ext=[AuthorCompanyExt(id=1154032442479465347, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032442475271042, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Hebei University of Technology Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Tianjin 300130 China), AuthorCompanyExt(id=1154032442487853956, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032442475271042, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130)])])], keywords=[Keyword(id=1154032445037990855, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, orderNo=1, keyword=Lithium-ion battery), Keyword(id=1154032445084128201, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, orderNo=2, keyword=remaining useful life (RUL) prediction), Keyword(id=1154032445138654155, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, orderNo=3, keyword=variational mode decomposition), Keyword(id=1154032445193180109, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, orderNo=4, keyword=sparrow search algorithm (SSA)), Keyword(id=1154032445251900367, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, orderNo=5, keyword=extreme learning machine (ELM)), Keyword(id=1154032445306426321, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, orderNo=1, keyword=锂离子电池), Keyword(id=1154032445356757970, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, orderNo=2, keyword=剩余使用寿命预测), Keyword(id=1154032445415478228, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, orderNo=3, keyword=变分模态分解), Keyword(id=1154032445470004182, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, orderNo=4, keyword=麻雀搜索算法), Keyword(id=1154032445583250393, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, orderNo=5, keyword=极限学习机)], refs=[Reference(id=1154032449391677456, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=18, issue=3, pageStart=175, pageEnd=183, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=姚芳, 张楠, 黄凯, journalName=电源学报, refType=null, unstructuredReference=姚芳, 张楠, 黄凯. 锂离子电池状态估算与寿命预测综述[J]. 电源学报, 2020. 18(3): 175-183., articleTitle=锂离子电池状态估算与寿命预测综述, refAbstract=null), Reference(id=1154032449437814801, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=18, issue=3, pageStart=175, pageEnd=183, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Yao Fang, Zhang Nan, Huang Kai, journalName=Journal of Power Supply, refType=null, unstructuredReference=Yao Fang, Zhang Nan, Huang Kai. Review of state estimation and life prediction for lithiumion batteries[J]. Journal of Power Supply, 2020. 18(3): 175-183 (in Chinese)., articleTitle=Review of state estimation and life prediction for lithiumion batteries, refAbstract=null), Reference(id=1154032449475563538, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=33, issue=5, pageStart=1517, pageEnd=1531, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Zhang Kai, Zhao Peng, Sun Canfei, journalName=Chinese Journal of Aeronautics, refType=null, unstructuredReference=Zhang Kai, Zhao Peng, Sun Canfei, et al. Remaining useful life prediction of aircraft lithium-ion batteries based on F-distribution particle filter and kernel smoothing algorithm[J]. Chinese Journal of Aeronautics, 2020. 33(5): 1517-1531., articleTitle=Remaining useful life prediction of aircraft lithium-ion batteries based on F-distribution particle filter and kernel smoothing algorithm, refAbstract=null), Reference(id=1154032449534283795, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=5, pageStart=182, pageEnd=190, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=张若可, 郭永芳, 余湘媛, journalName=电源学报, refType=null, unstructuredReference=张若可, 郭永芳, 余湘媛, 等. 基于数据驱动的锂离子电池 RUL 预测综述[J]. 电源学报, 2023. 21(5): 182-190., articleTitle=基于数据驱动的锂离子电池 RUL 预测综述, refAbstract=null), Reference(id=1154032449584615444, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=5, pageStart=182, pageEnd=190, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Zhang Ruoke, Guo Yongfang, Yu Xiangyuan, journalName=Journal of Power Supply, refType=null, unstructuredReference=Zhang Ruoke, Guo Yongfang, Yu Xiangyuan, et al. Review of data-driven RUL prediction for Lithium-ion batteries[J]. Journal of Power Supply, 2023. 21(5): 182-190 (in Chinese)., articleTitle=Review of data-driven RUL prediction for Lithium-ion batteries, refAbstract=null), Reference(id=1154032449626558485, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=4, pageStart=1445, pageEnd=1457, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=王瀛洲, 倪裕隆, 郑宇清, journalName=中国电机工程学报, refType=null, unstructuredReference=王瀛洲, 倪裕隆, 郑宇清, 等. 基于ALO-SVR 的锂离子电池剩余使用寿命预测[J]. 中国电机工程学报, 2021. 41(4): 1445-1457., articleTitle=基于ALO-SVR 的锂离子电池剩余使用寿命预测, refAbstract=null), Reference(id=1154032449697861654, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=4, pageStart=1445, pageEnd=1457, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Wang Yingzhou, Ni Yulong, Zheng Yuqing, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=Wang Yingzhou, Ni Yulong, Zheng Yuqing, et al. Remaining useful life prediction of lithium-ion batteries based on support vector regression optimized and ant lion optimizations[J]. Proceedings of the CSEE, 2021. 41(4): 1445-1457 (in Chinese)., articleTitle=Remaining useful life prediction of lithium-ion batteries based on support vector regression optimized and ant lion optimizations, refAbstract=null), Reference(id=1154032449752387607, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=2, pageStart=138, pageEnd=145, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=徐波, 雷敏, 王钋, journalName=电源学报, refType=null, unstructuredReference=徐波, 雷敏, 王钋. 基于TRNN和FA-PF融合的锂离子电池 RUL 预测[J]. 电源学报, 2023. 21(2): 138-145., articleTitle=基于TRNN和FA-PF融合的锂离子电池 RUL 预测, refAbstract=null), Reference(id=1154032449798524952, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=2, pageStart=138, pageEnd=145, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Xu Bo, Lei Min, Wang Po, journalName=Journal of Power Supply, refType=null, unstructuredReference=Xu Bo, Lei Min, Wang Po. RUL prediction of lithium-ion battery based on fusion of TRNN and FA-PF[J]. Journal of Power Supply, 2023. 21(2): 138-145 (in Chinese)., articleTitle=RUL prediction of lithium-ion battery based on fusion of TRNN and FA-PF, refAbstract=null), Reference(id=1154032449865633817, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=450, issue=null, pageStart=227700, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=Qiu Xianghui, Wu Weixiong, Wang Shuangfeng, journalName=Journal of Power Sources, refType=null, unstructuredReference=Qiu Xianghui, Wu Weixiong, Wang Shuangfeng. Remaining useful life prediction of lithium-ion battery based on improved cuckoo search particle filter and a novel state of charge estimation method[J]. Journal of Power Sources, 2020. 450: 227700., articleTitle=Remaining useful life prediction of lithium-ion battery based on improved cuckoo search particle filter and a novel state of charge estimation method, refAbstract=null), Reference(id=1154032449911771162, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=2, pageStart=154, pageEnd=162, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=杨战社, 王云浩, 孔晨再, journalName=电源学报, refType=null, unstructuredReference=杨战社, 王云浩, 孔晨再. 基于GWO-SVR的锂电池剩余使用寿命预测[J]. 电源学报, 2023. 21(2): 154-162., articleTitle=基于GWO-SVR的锂电池剩余使用寿命预测, refAbstract=null), Reference(id=1154032449962102811, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=2, pageStart=154, pageEnd=162, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Yang Zhanshe, Wang Yunhao, Kong Chenzai, journalName=Journal of Power Supply, refType=null, unstructuredReference=Yang Zhanshe, Wang Yunhao, Kong Chenzai. Prediction of remaining useful life of lithium-ion batteries based on GWO-SVR method[J]. Journal of Power Supply, 2023. 21(2): 154-162 (in Chinese)., articleTitle=Prediction of remaining useful life of lithium-ion batteries based on GWO-SVR method, refAbstract=null), Reference(id=1154032450016628764, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=6, pageStart=1285, pageEnd=1292, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=刘月峰, 赵光权, 彭喜元, journalName=电子学报, refType=null, unstructuredReference=刘月峰, 赵光权, 彭喜元. 多核相关向量机优化模型的锂电池剩余寿命预测方法[J]. 电子学报, 2019. 47(6): 1285-1292., articleTitle=多核相关向量机优化模型的锂电池剩余寿命预测方法, refAbstract=null), Reference(id=1154032450079543325, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=6, pageStart=1285, pageEnd=1292, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Liu Yuefeng, Zhao Guangquan, Peng Xiyuan, journalName=Acta Electronica Sinica, refType=null, unstructuredReference=Liu Yuefeng, Zhao Guangquan, Peng Xiyuan. A lithium-ion battery remaining using life prediction method based on multi-kernel relevance vector machine optimized model[J]. Acta Electronica Sinica, 2019. 47(6): 1285-1292 (in Chinese)., articleTitle=A lithium-ion battery remaining using life prediction method based on multi-kernel relevance vector machine optimized model, refAbstract=null), Reference(id=1154032450138263582, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2019, volume=21, issue=null, pageStart=510, pageEnd=518, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=Li Xiaoyu, Zhang Lei, Wang Zhenpo, journalName=Journal of Energy Storage, refType=null, unstructuredReference=Li Xiaoyu, Zhang Lei, Wang Zhenpo, et al. Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks[J]. Journal of Energy Storage, 2019. 21: 510-518., articleTitle=Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks, refAbstract=null), Reference(id=1154032450201178143, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=5, issue=null, pageStart=100078, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=Yang Hao, Wang Penglei, An Yabin, journalName=eTransportation, refType=null, unstructuredReference=Yang Hao, Wang Penglei, An Yabin, et al. Remaining useful life prediction based on denoising technique and deep neural network for lithium-ion capacitors[J]. eTransportation, 2020. 5: 100078., articleTitle=Remaining useful life prediction based on denoising technique and deep neural network for lithium-ion capacitors, refAbstract=null), Reference(id=1154032450251509793, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2021, volume=214, issue=null, pageStart=107675, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Xu Xiaodong, Tang Shengjin, Yu Chuanqiang, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=Xu Xiaodong, Tang Shengjin, Yu Chuanqiang, et al. Remaining useful life prediction of lithium-ion batteries based on Wiener process under time-varying temperature condition[J]. Reliability Engineering & System Safety, 2021. 214: 107675., articleTitle=Remaining useful life prediction of lithium-ion batteries based on Wiener process under time-varying temperature condition, refAbstract=null), Reference(id=1154032450327007267, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=467, issue=null, pageStart=228358, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Li Xiaoyu, Yuan Changgui, Wang Zhenpo, journalName=Journal of Power Sources, refType=null, unstructuredReference=Li Xiaoyu, Yuan Changgui, Wang Zhenpo. Multi-time-scale framework for prognostic health condition of lithium battery using modified Gaussian process regression and nonlinear regression[J]. Journal of Power Sources, 2020. 467: 228358., articleTitle=Multi-time-scale framework for prognostic health condition of lithium battery using modified Gaussian process regression and nonlinear regression, refAbstract=null), Reference(id=1154032450373144613, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=14, pageStart=3126, pageEnd=3136, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=张婷婷, 于明, 李宾, journalName=电工技术学报, refType=null, unstructuredReference=张婷婷, 于明, 李宾, 等. 基于 Wavelet 降噪和支持向量机的锂离子电池容量预测研究[J]. 电工技术学报, 2020. 35(14): 3126-3136., articleTitle=基于 Wavelet 降噪和支持向量机的锂离子电池容量预测研究, refAbstract=null), Reference(id=1154032450444447783, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=14, pageStart=3126, pageEnd=3136, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=Zhang Tingting, Yu Ming, Li Bin, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Zhang Tingting, Yu Ming, Li Bin, et al. Capacity prediction of lithium-ion batteries based on Wavelet noise reduction and support vector machine[J]. Transactions of China Electrotechnical Society, 2020. 35(14): 3126-3136 (in Chinese)., articleTitle=Capacity prediction of lithium-ion batteries based on Wavelet noise reduction and support vector machine, refAbstract=null), Reference(id=1154032450511556649, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=476, issue=null, pageStart=228581, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=20, 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=1154032450570276907, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=6, pageStart=735, pageEnd=742, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=陈则王, 李福胜, 林娅, journalName=计量学报, refType=null, unstructuredReference=陈则王, 李福胜, 林娅, 等. 基于 GA-ELM 的锂离子电池 RUL 间接预测方法[J]. 计量学报, 2020. 41(6): 735-742., articleTitle=基于 GA-ELM 的锂离子电池 RUL 间接预测方法, refAbstract=null), Reference(id=1154032450633191469, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=6, pageStart=735, pageEnd=742, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=Chen Zewang, Li Fusheng, Lin Ya, journalName=Acta Metrologica Sinica, refType=null, unstructuredReference=Chen Zewang, Li Fusheng, Lin Ya, et al. Indirect prediction method of RUL for lithium-ion battery based on GA-ELM[J]. Acta Metrologica Sinica, 2020. 41(6): 735-742 (in Chinese)., articleTitle=Indirect prediction method of RUL for lithium-ion battery based on GA-ELM, refAbstract=null), Reference(id=1154032450683523119, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=1, pageStart=22, pageEnd=34, url=null, language=null, rfNumber=[16], rfOrder=23, 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=1154032450733854769, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=22, pageStart=1, pageEnd=12, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=李雅丽, 王淑琴, 陈倩茹, journalName=计算机工程与应用, refType=null, unstructuredReference=李雅丽, 王淑琴, 陈倩茹, 等. 若干新型群智能优化算法的对比研究[J]. 计算机工程与应用, 2020. 56(22): 1-12., articleTitle=若干新型群智能优化算法的对比研究, refAbstract=null), Reference(id=1154032450779992114, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=22, pageStart=1, pageEnd=12, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=Li Yali, Wang Shuqin, Chen Qianru, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=Li Yali, Wang Shuqin, Chen Qianru, et al. Comparative study of several new swarm intelligence optimization algorithms[J]. Computer Engineering and Applications, 2020. 56(22): 1-12 (in Chinese)., articleTitle=Comparative study of several new swarm intelligence optimization algorithms, refAbstract=null), Reference(id=1154032450851295284, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2021, volume=46, issue=14, pageStart=9541, pageEnd=9552, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=Zhu Yanlong, Yousefi N, journalName=International Journal of Hydrogen Energy, refType=null, unstructuredReference=Zhu Yanlong, Yousefi N. Optimal parameter identification of PEMFC stacks using adaptive sparrow search algorithm[J]. International Journal of Hydrogen Energy, 2021. 46(14): 9541-9552., articleTitle=Optimal parameter identification of PEMFC stacks using adaptive sparrow search algorithm, refAbstract=null), Reference(id=1154032450910015542, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=null, pageStart=102094, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=Liu Bo, Rodriguez D, journalName=Journal of Building Engineering, refType=null, unstructuredReference=Liu Bo, Rodriguez D. Renewable energy systems optimization by a new multi-objective optimization technique: A residential building[J]. Journal of Building Engineering, 2021. 35: 102094., articleTitle=Renewable energy systems optimization by a new multi-objective optimization technique: A residential building, refAbstract=null), Reference(id=1154032450993901624, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2021, volume=244, issue=null, pageStart=167516, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=Zhou Shenghang, Xie Hao, Zhang Chuncheng, journalName=Optik, refType=null, unstructuredReference=Zhou Shenghang, Xie Hao, Zhang Chuncheng, et al. Wavefront-shaping focusing based on a modified sparrow search algorithm[J]. Optik, 2021. 244: 167516., articleTitle=Wavefront-shaping focusing based on a modified sparrow search algorithm, refAbstract=null), Reference(id=1154032451052621882, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2019, volume=86, issue=null, pageStart=249, pageEnd=265, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=Xu Bo, Zhou Fengxing, Li Huipeng, journalName=ISA Transactions, refType=null, unstructuredReference=Xu Bo, Zhou Fengxing, Li Huipeng, et al. Early fault feature extraction of bearings based on Teager energy operator and optimal VMD[J]. ISA Transactions, 2019. 86: 249-265., articleTitle=Early fault feature extraction of bearings based on Teager energy operator and optimal VMD, refAbstract=null), Reference(id=1154032451115536446, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2019, volume=53, issue=10, pageStart=1852, pageEnd=1864, url=null, language=null, rfNumber=[22], rfOrder=30, authorNames=胡天中, 余建波, journalName=浙江大学学报(工学版), refType=null, unstructuredReference=胡天中, 余建波. 基于多尺度分解和深度学习的锂电池寿命预测[J]. 浙江大学学报(工学版), 2019. 53(10): 1852-1864., articleTitle=基于多尺度分解和深度学习的锂电池寿命预测, refAbstract=null), Reference(id=1154032451174256704, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2019, volume=53, issue=10, pageStart=1852, pageEnd=1864, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=Hu Tianzhong, Yu Jianbo, journalName=Journal of Zhejiang University (Engineering Science), refType=null, unstructuredReference=Hu Tianzhong, Yu Jianbo. Life prediction of lithium-ion batteries based on multiscale decomposition and deep learning[J]. Journal of Zhejiang University (Engineering Science), 2019. 53(10): 1852-1864 (in Chinese)., articleTitle=Life prediction of lithium-ion batteries based on multiscale decomposition and deep learning, refAbstract=null), Reference(id=1154032451216199747, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, doi=null, pmid=null, pmcid=null, year=2019, volume=44, issue=23, pageStart=12270, pageEnd=12276, url=null, language=null, rfNumber=[23], rfOrder=32, authorNames=Li Wenhua, Jiao Zhipeng, Du Le, journalName=International Journal of Hydrogen Energy, refType=null, unstructuredReference=Li Wenhua, Jiao Zhipeng, Du Le, et al. An indirect RUL prognosis for lithium-ion battery under vibration stress using Elman neural network[J]. International Journal of Hydrogen Energy, 2019. 44(23): 12270-12276., articleTitle=An indirect RUL prognosis for lithium-ion battery under vibration stress using Elman neural network, refAbstract=null)], funds=[Fund(id=1154032449194545166, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, awardId=E2019202328, language=EN, fundingSource=Natural Science Foundation of Hebei Province under the grant E2019202328(E2019202328), fundOrder=null, country=null), Fund(id=1154032449244876815, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, awardId=E2019202328, language=CN, fundingSource=河北省自然科学基金资助项目(E2019202328), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1154032439748973421, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, xref=1, ext=[AuthorCompanyExt(id=1154032439757362030, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032439748973421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin 300130 China), AuthorCompanyExt(id=1154032442412356481, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032439748973421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130)]), AuthorCompany(id=1154032442475271042, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, xref=2, ext=[AuthorCompanyExt(id=1154032442479465347, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032442475271042, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Hebei University of Technology Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Tianjin 300130 China), AuthorCompanyExt(id=1154032442487853956, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, companyId=1154032442475271042, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130)])], figs=[ArticleFig(id=1154032447869146109, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Fig. 1, caption=VMD decomposition result of B5 battery, figureFileSmall=C8ORwMy+FA3lqk/a2UDKiw==, figureFileBig=gBQooyvdRddaUmaL8KRI3w==, tableContent=null), ArticleFig(id=1154032447923672062, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=图1, caption=B5 号电池 VMD 分解结果, figureFileSmall=C8ORwMy+FA3lqk/a2UDKiw==, figureFileBig=gBQooyvdRddaUmaL8KRI3w==, tableContent=null), ArticleFig(id=1154032447978198015, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Fig. 2, caption=Comparison of effect before and after capacity curve reconstruction, figureFileSmall=yX8Jeqhv0NRyx1ORbBziAA==, figureFileBig=9prDLdM7ZPohcna/UbB8yQ==, tableContent=null), ArticleFig(id=1154032448049501184, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=图2, caption=容量曲线重构前、后效果对比, figureFileSmall=yX8Jeqhv0NRyx1ORbBziAA==, figureFileBig=9prDLdM7ZPohcna/UbB8yQ==, tableContent=null), ArticleFig(id=1154032448120803328, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Fig. 3, caption=Convergence curves for three benchmark functions, figureFileSmall=xa+WandilnbckECuktCr0g==, figureFileBig=rJxg4iSjUJljV3ICExblpw==, tableContent=null), ArticleFig(id=1154032448225660929, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=图3, caption=3个基准函数的收敛曲线, figureFileSmall=xa+WandilnbckECuktCr0g==, figureFileBig=rJxg4iSjUJljV3ICExblpw==, tableContent=null), ArticleFig(id=1154032448284381186, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Fig. 4, caption=Flow chart of lithium-ion battery RUL prediction based on VMD-ISSA-ELM method, figureFileSmall=pJ4q+A5XLdCEJsag3V6Kjg==, figureFileBig=7fC19svooIbtnFb2e9z9LQ==, tableContent=null), ArticleFig(id=1154032448351490051, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=图4, caption=基于 VMD-ISSA-ELM 方法的锂离子电池 RUL 预测流程, figureFileSmall=pJ4q+A5XLdCEJsag3V6Kjg==, figureFileBig=7fC19svooIbtnFb2e9z9LQ==, tableContent=null), ArticleFig(id=1154032448410210308, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Fig. 5, caption=Prediction results of battery RUL based on NASA data sets, figureFileSmall=2v6jCpoieI84sJjL+UAIhA==, figureFileBig=7Qx7Q45P6Rpufyjhd8YK4Q==, tableContent=null), ArticleFig(id=1154032448473124869, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=图5, caption=基于 NASA 数据集的电池 RUL 预测结果, figureFileSmall=2v6jCpoieI84sJjL+UAIhA==, figureFileBig=7Qx7Q45P6Rpufyjhd8YK4Q==, tableContent=null), ArticleFig(id=1154032448540233734, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Fig. 6, caption=Comparison of prediction result among three methods, figureFileSmall=HbJS5nfV5QhN1aO6AIyk2g==, figureFileBig=yxE7p25OZKdumbCfxaE3ng==, tableContent=null), ArticleFig(id=1154032448590565383, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=图6, caption=3种方法预测结果对比, figureFileSmall=HbJS5nfV5QhN1aO6AIyk2g==, figureFileBig=yxE7p25OZKdumbCfxaE3ng==, tableContent=null), ArticleFig(id=1154032448636702728, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Tab. 1, caption=Correlation coefficients between IMF components and capacity for B5 battery, figureFileSmall=null, figureFileBig=null, tableContent=
模态分量 相关系数
IMF1 0.1110
IMF2 0.0457
IMF3 0.0330
IMF4 0.0262
IMF5 0.0214
), ArticleFig(id=1154032448695422985, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=表1, caption=B5 号电池中 IMF 分量与容量间的相关系数, figureFileSmall=null, figureFileBig=null, tableContent=
模态分量 相关系数
IMF1 0.1110
IMF2 0.0457
IMF3 0.0330
IMF4 0.0262
IMF5 0.0214
), ArticleFig(id=1154032448758337546, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Tab. 2, caption=Test results, figureFileSmall=null, figureFileBig=null, tableContent=
测试 函数 算法 最优值 最差值 平均值 标准差
${F}_{1}$ PSO 0 ${1.15}\times {10}^{-{19}}$ ${3.98}\times {10}^{-{21}}$ ${2.09}\times {10}^{-{20}}$
SSA 0 ${5.26}\times {10}^{-{34}}$ ${1.75}\times {10}^{-{35}}$ ${9.61}\times {10}^{-{35}}$
ISSA 0 ${6.04}\times {10}^{-{60}}$ ${6.22}\times {10}^{-{61}}$ ${1.42}\times {10}^{-{60}}$
${F}_{2}$ PSO ${3.39}\times {10}^{-5}$ ${1.73}\times {10}^{-3}$ ${5.77}\times {10}^{-4}$ ${3.16}\times {10}^{-4}$
SSA 0 ${1.11}\times {10}^{-{11}}$ ${3.72}\times {10}^{-{13}}$ ${2.03}\times {10}^{-{12}}$
ISSA 0 0 0 0
${F}_{3}$ PSO 0.74 1.33 1.01 0.14
SSA 0 ${8.89}\times {10}^{-{16}}$ ${2.96}\times {10}^{-{17}}$ ${1.62}\times {10}^{-{16}}$
ISSA 0 0 0 0
), ArticleFig(id=1154032448825446411, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=表2, caption=测试结果, figureFileSmall=null, figureFileBig=null, tableContent=
测试 函数 算法 最优值 最差值 平均值 标准差
${F}_{1}$ PSO 0 ${1.15}\times {10}^{-{19}}$ ${3.98}\times {10}^{-{21}}$ ${2.09}\times {10}^{-{20}}$
SSA 0 ${5.26}\times {10}^{-{34}}$ ${1.75}\times {10}^{-{35}}$ ${9.61}\times {10}^{-{35}}$
ISSA 0 ${6.04}\times {10}^{-{60}}$ ${6.22}\times {10}^{-{61}}$ ${1.42}\times {10}^{-{60}}$
${F}_{2}$ PSO ${3.39}\times {10}^{-5}$ ${1.73}\times {10}^{-3}$ ${5.77}\times {10}^{-4}$ ${3.16}\times {10}^{-4}$
SSA 0 ${1.11}\times {10}^{-{11}}$ ${3.72}\times {10}^{-{13}}$ ${2.03}\times {10}^{-{12}}$
ISSA 0 0 0 0
${F}_{3}$ PSO 0.74 1.33 1.01 0.14
SSA 0 ${8.89}\times {10}^{-{16}}$ ${2.96}\times {10}^{-{17}}$ ${1.62}\times {10}^{-{16}}$
ISSA 0 0 0 0
), ArticleFig(id=1154032448900943884, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=EN, label=Tab. 3, caption=Comparison of RUL prediction effect among three methods based on NASA data sets, figureFileSmall=null, figureFileBig=null, tableContent=
电池 预测方法 起点 1 预测结果 起点 2 预测结果
真实 RUL/次 预测 RUL/次 AE/% MAE/% RMSE/% 真实 RUL/次 预测 RUL/次 AE/% MAE/% RMSE/%
B5 PSO-ELM 45 - - 10.19 13.55 31 6 2.97 3.33
SSA-ELM 54 9 2.88 3.65 25 17 8 2.70 3.07
VMD-ISSA- ELM 45 0 1.34 1.71 25 0 0.62 0.85
B6 PSO-ELM 29 36 7 6.45 7.69 14 5 4.78 5.99
SSA-ELM 33 4 4.42 5.68 9 13 4 3.14 3.55
VMD-ISSA- ELM 31 2 1.50 2.11 11 2 1.40 1.68
B7 PSO-ELM 63 - - 3.16 4.17 - - 4.07 4.35
SSA-ELM 55 8 2.59 2.95 43 38 5 1.53 1.78
VMD-ISSA- ELM 67 4 0.78 1.21 47 4 0.83 1.07
B18 PSO-ELM 32 20 12 8.07 9.65 14 8 5.27 6.24
SSA-ELM 27 5 3.01 4.01 22 37 15 2.01 2.43
VMD-ISSA- ELM 32 0 1.34 1.98 23 1 1.58 2.14
), ArticleFig(id=1154032448980635661, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375944363467604, language=CN, label=表3, caption=3种方法在 NASA 数据集下的 RUL 预测效果对比, figureFileSmall=null, figureFileBig=null, tableContent=
电池 预测方法 起点 1 预测结果 起点 2 预测结果
真实 RUL/次 预测 RUL/次 AE/% MAE/% RMSE/% 真实 RUL/次 预测 RUL/次 AE/% MAE/% RMSE/%
B5 PSO-ELM 45 - - 10.19 13.55 31 6 2.97 3.33
SSA-ELM 54 9 2.88 3.65 25 17 8 2.70 3.07
VMD-ISSA- ELM 45 0 1.34 1.71 25 0 0.62 0.85
B6 PSO-ELM 29 36 7 6.45 7.69 14 5 4.78 5.99
SSA-ELM 33 4 4.42 5.68 9 13 4 3.14 3.55
VMD-ISSA- ELM 31 2 1.50 2.11 11 2 1.40 1.68
B7 PSO-ELM 63 - - 3.16 4.17 - - 4.07 4.35
SSA-ELM 55 8 2.59 2.95 43 38 5 1.53 1.78
VMD-ISSA- ELM 67 4 0.78 1.21 47 4 0.83 1.07
B18 PSO-ELM 32 20 12 8.07 9.65 14 8 5.27 6.24
SSA-ELM 27 5 3.01 4.01 22 37 15 2.01 2.43
VMD-ISSA- ELM 32 0 1.34 1.98 23 1 1.58 2.14
)], 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.2095-2805.2024.6.188, detailUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/10.13234/j.issn.2095-2805.2024.6.188, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/PDF/10.13234/j.issn.2095-2805.2024.6.188, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/PDF/10.13234/j.issn.2095-2805.2024.6.188, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于VMD 和ISSA-ELM 的锂离子电池剩余使用寿命预测
收藏切换
PDF下载
丁恒 1, 2 , 黄凯 1, 2 , 田海建 1, 2
电源学报 | 电池与储能 2024,22(6): 188-198
收起
收藏切换
电源学报 | 电池与储能 2024, 22(6): 188-198
基于VMD 和ISSA-ELM 的锂离子电池剩余使用寿命预测
全屏
丁恒1, 2 , 黄凯1, 2 , 田海建1, 2
作者信息
  • 1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130
  • 2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130
  • 丁恒(1997-),男,硕士研究生。研究方向:电器可靠性理论及检测技术、储能电池组建模及寿命预测等。E-mail: 1377752790@qq.com。

    黄凯(1980-),男,中国电源学会会员,通信作者,博士,副教授。研究方向:电器可靠性理论及检测技术、储能电池组健康状态预测与可靠性评估。E-mail: huangkai@hebut.edu.cn。

    田海建(1995-),男,硕士研究生。研究方向:电器可靠性理论及检测技术、储能电池组建模及寿命预测。E-mail: 1843718316@qq.com。

Prediction of Remaining Useful Life of Lithium-ion Battery Based on VMD and ISSA-ELM
Heng DING1, 2 , Kai HUANG1, 2 , Haijian TIAN1, 2
Affiliations
  • 1 Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin 300130 China
  • 2 Hebei University of Technology Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province Tianjin 300130 China
出版时间: 2024-11-30 doi: 10.13234/j.issn.2095-2805.2024.6.188
文章导航
收藏切换

准确预测锂离子电池的剩余使用寿命RUL(remaining useful life)对提高工作环境安全性和设备可靠性等具有重要意义。为提高RUL 预测的稳定性和精度,提出1种基于去噪技术与混合数据驱动模型相结合的电池RUL 预测方法。首先,利用变分模态分解处理原始数据,采用相关性分析筛选出噪声分量,将残差与相关性较强的分量进行组合完成序列重构过程;其次,结合 Tent 混沌映射、正余弦算法和 Levy 飞行策略优化麻雀搜索算法 SSA(sparrow search algorithm), 通过寻优得到极限学习机ELM(extreme learning machine)的最优权阈值;最后,采用平滑去噪数据训练改进的SSA-ELM模型并完成 RUL预测,采用NASA 数据集验证算法有效性。实验结果表明,所提方法预测结果的平均绝对误差和均方根误差可分别控制在1.58%和2.14%內,具有较高的鲁棒性和预测精度,可应用于电池RUL预测。

锂离子电池  /  剩余使用寿命预测  /  变分模态分解  /  麻雀搜索算法  /  极限学习机

Accurately predicting the remaining useful life (RUL) of lithium-ion batteries is of significance for improving the safety of working environment and the reliability of equipment. To improve the stability and accuracy of RUL prediction, a battery RUL prediction method based on the combination of denoising technology and hybrid data-driven model is proposed. First, the original data is decomposed by variational mode decomposition, and the noise components are filtered by the analysis of correlation. The residual error is combined with the components which have a strong correlation to complete the sequence reconstruction process. Second, with the combination of Tent chaotic mapping, sine cosine algorithm and Levy flight strategy, the sparrow search algorithm (SSA) is optimized, and the optimal weight threshold of extreme learning machine (ELM) is obtained. Finally, the improved SSA-ELM model is trained by using the smoothed denoised data, and the RUL prediction is completed. The NASA data sets are used to verify the effectiveness of the proposed method. Experimental results show that the average absolute error and root mean square error of the prediction result obtained using this method are controlled within 1.58% and 2.14%, respectively, indicating that this method has a high robustness and a high prediction accuracy. Therefore, the proposed method can be applied to battery RUL prediction.

Lithium-ion battery  /  remaining useful life (RUL) prediction  /  variational mode decomposition  /  sparrow search algorithm (SSA)  /  extreme learning machine (ELM)
丁恒, 黄凯, 田海建. 基于VMD 和ISSA-ELM 的锂离子电池剩余使用寿命预测. 电源学报, 2024 , 22 (6) : 188 -198 . DOI: 10.13234/j.issn.2095-2805.2024.6.188
Heng DING, Kai HUANG, Haijian TIAN. Prediction of Remaining Useful Life of Lithium-ion Battery Based on VMD and ISSA-ELM[J]. Journal of Power Supply, 2024 , 22 (6) : 188 -198 . DOI: 10.13234/j.issn.2095-2805.2024.6.188
锂离子电池具有质量轻、能量密度高、自放电率低、使用寿命长等优点, 被广泛应用于航空航天、 电动汽车、军事通信、电子设备等诸多领域。然而, 随着使用时长的增加, 电池会不可避免地老化并出现故障,严重时将导致灾难性事故的发生[1-2]。锂离子电池剩余使用寿命是指当前时刻至失效阈值前的剩余可使用循环数。准确预测电池剩余使用寿命 RUL(remaining useful life)可为电池系统的预防性维护提供决策参考, 有效降低设备维护成本并防止重大危险事故发生[3-4]
通常, RUL 预测方法可以分为 2 类: 基于模型的方法和数据驱动方法。基于模型的方法需要通过电池的先验知识建立可以描述退化过程的数学模型,结合多种滤波算法完成 RUL 预测[5-6]。这种方法精度较高, 但十分依赖所建立的预测模型, 且受环境和电池复杂机制的影响, 建立精确的退化模型有较大困难, 限制了该方法在实际中的应用。
数据驱动方法通过对电池历史数据进行分析来建立相关特征, 采用机器学习算法构建退化过程的前、后期映射关系,最终实现 RUL 预测。文献[7] 通过支持向量回归 SVR(support vector regression) 建立 RUL 预测模型,采用灰狼优化算法 GWO(grey wolf optimizer)对 SVR 重要参数进行优化, 相比于极限学习机 ELM(extreme learning machine), SVR 的核函数选择较为困难; 文献[8]通过果蝇优化算法 FOA(fruit fly optimization algorithm)对多个核函数进行组合, 结合相关向量机 RVM(relevance vector machine)实现 RUL 预测, RVM 计算复杂度较低, 但由于高稀疏性, 预测结果不够稳定; 文献[9]通过经验模态分解EMD(empirical mode decomposition)将容量序列分为高频和低频 2 个部分, 采用 Elman 神经网络和长短期记忆 LSTM(long short-term memory) 神经网络分别进行预测, 但该方法并未筛除原始数据中的噪声分量; 文献[10]通过 CEEMDAN 对数据进行重构, 设计了 1 种结合卷积神经网络 CNN (convolutional neural network)和 LSTM 的 RUL 预测方法, 而作为深度学习, CNN 和 LSTM 更适合处理样本较多的时序预测问题; 文献[11]分析了时变温度条件对电池放电容量和老化规律的影响, 建立了基于维纳过程 WP(Wiener process)的预测模型, 解决了电池在温时变化条件下的 RUL 预测问题, 但维纳过程不适合处理非线性和时间非齐次的数据; 文献[12]通过对容量退化曲线进行深入分析提取出 4 个重要特征, 采用高斯过程回归 GPR (Gaussian process regression)预测电池 RUL, 相比于 ELM, GPR 计算量大且超参数调整过程复杂; 文献[13]利用小波降噪 WD(wavelet denoising)对容量数据进行处理, 通过改进的鸡群优化 CSO (chicken swarm optimization)算法对 SVR 超参数进行寻优, 建立ICSO-SVR预测模型,相比于变分模态分解VMD (variational mode decomposition), 为 WD 选择合适的基函数较繁琐。
ELM是 1 种基于前馈神经网络的机器学习方法, 具有较强的非线性建模能力, 适用于锂离子电池的容量退化评估, 即使样本数很小, 也可以收敛于最优回归。文献[14]开发了 1 种新的 ELM, 通过特征映射生成增强节点重构输入层, 使模型能够快速、 完整地从输入数据中获得有效的特征信息;文献[15]采用等压降放电时间作为退化特征,建立了基于 ELM 的 RUL 预测模型, 并采用遗传算法 GA (genetic algorithm)对 ELM 权阈值进行优化。GA 通过模拟自然界生物种群的进化行为来达到寻优目的, 种群进行选择、交叉、变异操作来结合出新个体, 但种群中有效信息的丢失概率也大大增加。
麻雀搜索算法SSA(sparrow search algorithm)是 1 种新的元启发式算法, 其灵感源于麻雀种群觅食和反捕食行为。由文献[16]可知, 与粒子群优化 PSO(partical swarm optimization)、GWO 等算法相比, SSA 具有更强的优化能力和更快的效率;文献[17] 通过大量实验证明了SSA算法在收敛速度和稳定性方面的优越性。然而, 种群多样性退化和容易陷入局部最优解是 SSA 与大部分智能搜索算法共同存在的问题[18]。为避免局部最优问题的发生,需要对原始算法进行改进来提高其性能。文献[19]采用随机游走策略对麻雀个体的位置进行优化; 文献[20]将自适应超参数和突变算子搜索思想融入 SSA 并提出了改进的麻雀搜索算法 MSSA(modified sparrow search algorithm),在原有基础上提高了全局搜索能力。
基于上述分析, 有些方法在数据预处理方面不够完善, 有些方法本身具有局限性, 因此本文提出 1 种基于 VMD 的数据降噪方法和 ISSA-ELM 的锂离子电池 RUL 预测模型。首先,选取容量作为反应退化趋势的特征, 采用 VMD 对原始数据进行分解, 结合相关性分析 AC(analysis of correlation)去除噪声分量并重构容量序列;然后, 引入 Tent 混沌序列、正余弦算法及 Levy 飞行策略分别对 SSA 的种群初始化、生产者更新及跟随者位置更新这 3 个步骤进行改进并得到改进的麻雀搜索算法 ISSA(improved sparrow search algorithm); 最终, 通过 ISSA 对 ELM 的相关参数进行优化, 旨在完成建模并实现 RUL 预测。
为有效预测电池 RUL, 首先应对电池历史数据进行分析并选出合适的退化特征。与直接测量到的物理参量(电流、电压、温度等)相比,容量可以直接反映电池的退化过程, 因此本文选择容量作为预测特征。采用 VMD 和 AC 对已知容量序列进行分解、筛选、重构来完成降噪处理, 最终选取降噪后的数据完成 RUL 预测模型的构建。
VMD 作为 1 种自适应信号处理方法, 其分解过程可视为约束变分问题的迭代求解过程[21]。通过 VMD 对原始信号进行分解, 可以得到有限个本征模态分量 IMF(intrinsic mode function)和残余分量, 由此产生的约束变分问题为
$\left\{\begin{array}{l}\mathop{\min }\limits_{{\left\{{u}_{k}\right\},\left\{{w}_{k}\right\}}}\left\{{\mathop{\sum }\limits_{{k = 1}}^{K}{\begin{Vmatrix}{\delta }_{t}\left\lbrack {\left(\delta \left( t\right)+ \mathrm{j}/\pi t\right)}^{* }{u}_{k}\left( t\right)\right\rbrack {\mathrm{e}}^{-\mathrm{j}{w}_{k}t}\end{Vmatrix}}_{2}^{2}}\right\}\\\text{ s.t.}\mathop{\sum }\limits_{{k = 1}}^{K}{u}_{k}\left( t\right)= f\left( t\right)\end{array}\right.$
式中:${u}_{k}$ 为分解后的分量;${w}_{k}$ 为中心频率;$K$ 为模态分量个数;${\delta }_{t}$ 为对$t$ 的导数;“*” 代表卷积过程;$f\left( t\right)$ 为原始信号。
引入二阶惩罚因子$\alpha$ 和拉格朗日乘法算子$\lambda \left( x\right)$ 将约束变分问题转化为非约束问题。增广拉格朗日函数可以表示为
$ L\left({\left\{{u}_{k}\right\},\left\{{w}_{k}\right\},\lambda }\right)= \alpha \mathop{\sum }\limits_{{k = 1}}^{K}{\begin{Vmatrix}{\delta }_{t}\left\lbrack \left(\delta \left( t\right)+ \mathrm{j}/\pi t\right)* {u}_{k}\left( t\right)\right\rbrack \end{Vmatrix}}_{2}^{2}+ \\{\begin{Vmatrix}f\left( t\right)- \mathop{\sum }\limits_{{k = 1}}^{K}{u}_{k}\left( t\right)\end{Vmatrix}}_{2}^{2}+ \left\langle {\lambda \left( t\right), f\left( t\right)- \mathop{\sum }\limits_{{k = 1}}^{K}{u}_{k}\left( t\right)}\right\rangle $
式中,$\lambda$ 为拉格朗日乘法算子。
利用交替方向法更新${u}_{k}^{n + 1}$${w}_{k}^{n + 1}$${\lambda }^{n + 1}$,搜索增广拉格朗日表达式的鞍点, 将问题转至傅里叶域内进行简化,对${\widehat{u}}_{k}^{1}\text{、}{w}_{k}^{1}$${\widehat{\lambda }}^{1}$ 进行初始化后, VMD 分解过程如下。
步骤 1 模式函数的更新:${u}_{k}^{n + 1}\left( w\right)\leftarrow \lbrack f\left( w\right)-$ $\left.{\mathop{\sum }\limits_{{i < k}}{\widehat{u}}_{i}^{n + 1}\left( w\right)- \mathop{\sum }\limits_{{i > k}}{\widehat{u}}_{i}^{n}\left( w\right)+ \frac{1}{2}{\widehat{\lambda }}^{n}\left( w\right)}\right\rbrack /\left\lbrack {1 +{2\alpha }{\left( w -{w}_{k}^{n}\right)}^{2}}\right\rbrack。$ 其中,${\widehat{u}}_{i}$${u}_{i}$ 的傅里叶变换形。
步骤 2 中心角频率更新:${w}_{k}^{n + 1}\leftarrow \left({{\int }_{0}^{\infty }w{\left|{\widehat{u}}_{k}^{n + 1}\left( w\right)\right|}^{2}\mathrm{\;d}w}\right)/$ $\left({{\int }_{0}^{\infty }{\left|{\widehat{u}}_{k}^{n + 1}\left( w\right)\right|}^{2}\mathrm{\;d}w}\right)\circ$
步骤 3 拉格朗日乘法运算符的更新:${\widehat{\lambda }}^{n + 1}\left( w\right)\leftarrow$ ${\widehat{\lambda }}^{n}\left( w\right)+ \tau \left\lbrack {\widehat{f}\left( w\right)- \mathop{\sum }\limits_{k}\left|{{\widehat{u}}_{k}^{n + 1}\left( w\right)}\right|}\right\rbrack。$
步骤 4 重复步骤 1~步骤 3,满足终止条件$\mathop{\sum }\limits_{k}\left({{\begin{Vmatrix}{\widehat{u}}_{k}^{n + 1}- {\widehat{u}}_{k}^{n}\end{Vmatrix}}^{2}/{\begin{Vmatrix}{\widehat{u}}_{k}^{n}\end{Vmatrix}}^{2}}\right)< \varepsilon$ 后结束迭代过程。其中,${\widehat{u}}_{k}$$\widehat{\lambda }$ 分别为${u}_{k}$$\lambda$ 的傅里叶变换形。
本文电池数据集来自 NASA 预测中心 PCoE (prognostics center of excellence), 选取标号为 B5、 B6、B7、B18 的电池作为研究对象[7]。电池额定容量为${2.00}\mathrm{\;A}\cdot \mathrm{h}$,在室温下进行充、放电过程: 首先以${1.5}\mathrm{\;A}$ 恒定电流进行充电,直到达到${4.2}\mathrm{\;V}$ 截止电压,然后以恒压模式充电,直到充电电流降至${20}\mathrm{{mA}}$;接下来以${2.0}\mathrm{\;A}$ 恒定电流进行放电,直到$\mathrm{B}5\text{、}\mathrm{\;B}6$ 、 B7、B18 电池电压分别降至 2.7、2.5、2.2、2.5 V。 一般来说, 电池容量的失效阈值定义为额定容量的${70}\%\left({\text{即}{1.40}\mathrm{\;A}\cdot \mathrm{h}}\right)$,考虑到$\mathrm{B}7$ 号电池容量并未降至${1.40}\mathrm{\;A}\cdot \mathrm{h}$,因此将其失效阈值设为${1.45}\mathrm{\;A}\cdot \mathrm{h}$
受复杂的物理-化学反应和环境因素影响, 电池退化曲线中存在容量回升现象和噪声。为有效消除波动和噪声,采用 VMD 对容量序列进行分解。 以 B5 号电池为例, 基于 B5 号电池的分解结果如图1所示, 可见: 原序列分解为残差和 5 个 IMF 分量, 其中残差代表了原始容量的主要趋势, IMF 分量反映了退化过程的局部状态。采用$\mathrm{{AC}}$ 计算模态分量与原始容量间的相关系数, 如表1所示。
设定关联阈值来判别 IMF 分量与容量间的相关性, 当分量的相关系数大于关联阈值时, 判定该分量为强相关性, 将其与残差进行组合来完成容量序列的重构。根据文献[22]中阈值设定公式$\mathrm{{CT}}=$ $\max \left({\text{IMF}i}\right)/n$ 计算的结果为 0.0222,表明 IMF1~ IMF4 均满足要求。但由图2分析可知, IMF2~IMF4 的波动频率较高,会对建模产生严重干扰。
为提高判定精度, 将阈值设定公式改进为$\mathrm{{CT}}= \left({\mathop{\sum }\limits_{{i = 1}}^{n}\operatorname{IMF}i}\right)/n$,计算$\mathrm{{CT}}= {0.04746}$,该关联阈值较之前有明显提升,有效提高了筛选精度。参考该阈值对 B5 号电池的模态分量进行自适应筛选, 经过多次组合测试, 判定 IMF1 为强相关性, 与残差进行结合并舍弃其他分量, 完成降噪过程。对所有电池的容量序列进行重构, 电池原始容量退化曲线和重构后的降噪曲线如图2所示, 可见: 重构后的序列具有平滑的递减趋势, 且在去除噪声分量的基础上保留了原始数据的真实特性。
ELM 是 1 种典型的单隐层前馈神经网络, 设训练数据集为$\left({{\mathbf{X}}_{i},{\mathbf{Y}}_{i}}\right)$,其中${\mathbf{X}}_{i}= {\left\lbrack \begin{array}{llll}{x}_{i1}& {x}_{i2}& \cdots &{x}_{in}\end{array}\right\rbrack }^{\mathrm{T}}\in {\mathbf{R}}^{n}$,${\mathbf{Y}}_{i}= {\left\lbrack \begin{array}{llll}{y}_{i1}& {y}_{i2}& \cdots &{y}_{im}\end{array}\right\rbrack }^{\mathrm{T}}\in {\mathbf{R}}^{m}\circ$
$L$ 为隐层节点数,$h\left( x\right)$ 为激活函数, ELM 模型可表示为
$\mathop{\sum }\limits_{{i = 1}}^{L}{\mathbf{\beta }}_{i}h\left({{\mathbf{w}}_{i}\cdot {\mathbf{x}}_{i}+ {b}_{i}}\right)= {\mathbf{o}}_{k}\;k = 1,2,\cdots, N $
式中:${\mathbf{\beta }}_{i}$ 为连接第$i$ 个隐层节点和输出层节点的权重;${\mathbf{w}}_{i}$ 为连接输入层节点和第$i$ 个隐层节点的权重;${b}_{i}$ 为隐层第$i$ 个节点的阈值;${\mathbf{o}}_{k}$ 为网络的输出。${\mathbf{w}}_{i}$${\mathbf{\beta }}_{i}$${\mathbf{o}}_{k}$ 可分别表示为
$\left\{\begin{array}{l}{\mathbf{w}}_{i}= {\left\lbrack \begin{array}{llll}{w}_{i1}& {w}_{i2}& \cdots &{w}_{in}\end{array}\right\rbrack }^{\mathrm{T}}\\{\mathbf{\beta }}_{i}= {\left\lbrack \begin{array}{llll}{\beta }_{i1}& {\beta }_{i2}& \cdots &{\beta }_{im}\end{array}\right\rbrack }^{\mathrm{T}}\\{\mathbf{o}}_{k}= {\left\lbrack \begin{array}{llll}{o}_{k1}& {o}_{k2}& \cdots &{o}_{kn}\end{array}\right\rbrack }^{\mathrm{T}}\end{array}\right.$
设 ELM 输出矩阵为$\mathbf{H}$,模型结果经过一定训练时间后可接近实际输出$\mathop{\sum }\limits_{{k = 1}}^{N}\begin{Vmatrix}{{o}_{k}- {y}_{k}}\end{Vmatrix}= 0$, ELM 模型可等效为$\mathbf{H}\beta = Y,\mathbf{H}$ 可展开为
$\mathbf{H}= {\left\lbrack \begin{matrix} h\left({{\mathbf{w}}_{1}\cdot {\mathbf{x}}_{1}+ {b}_{1}}\right)& \cdots & h\left({{\mathbf{w}}_{L}\cdot {\mathbf{x}}_{1}+ {b}_{L}}\right)\\\vdots && \vdots \\ h\left({{\mathbf{w}}_{1}\cdot {\mathbf{x}}_{N}+ {b}_{1}}\right)& \cdots & h\left({{\mathbf{w}}_{L}\cdot {\mathbf{x}}_{N}+ {b}_{L}}\right)\end{matrix}\right\rbrack }_{N \times L}$
最终输出权重可计算为$\beta ={\mathbf{H}}^{+ }Y$,其中${\mathbf{H}}^{+ }$$\mathbf{H}$ 的逆矩阵。
本文使用平滑降噪后的容量数据进行模型的训练和测试,通过起点$T$ 将电池的整体容量序列划分为训练集(历史数据)和测试集。通过对历史数据的充分学习完成模型训练过程, 建立预测模型为
${\widehat{C}}_{i + 1}= \operatorname{ELM}\left({{C}_{i - l + 1},{C}_{i - l + 2},\cdots,{C}_{i - 1},{C}_{i}}\right)$
式中:${\widehat{C}}_{i + 1}$ 为下一循环的容量预测值;$l$ 为输入数据长度。将测试数据集代入式(6)进行迭代预测, 进而得出起点后每一循环的容量预测值, 从而可以计算出电池的 RUL。
为了确保 ELM 模型具有较高的预测精度和泛化能力, 必须选择合适的输入权值和隐含层阈值, 因此本文采用改进后的 SSA 优化 ELM 的相关参数。
麻雀搜索算法灵感源于麻雀的觅食和警戒行为,第$i$ 只麻雀在空间中的位置可表示为${\mathbf{X}}_{i}= \left\lbrack {x}_{i,1}\right.$,$\left.{{x}_{i,2},\cdots,{x}_{i, d}}\right\rbrack$。其中,$i = 1,2,\cdots, N;d$ 为空间维度;$N$ 为麻雀总数。适应度矩阵为
$\left\{\begin{array}{l}{\mathbf{F}}_{X}= {\left\lbrack \begin{array}{llll}\mathbf{f}\left({x}_{1}\right)& \mathbf{f}\left({x}_{2}\right)& \cdots &\mathbf{f}\left({x}_{N}\right)\end{array}\right\rbrack }^{\mathrm{T}}\\\mathbf{f}\left({x}_{i}\right)= \left\lbrack \begin{array}{llll} f\left({x}_{i,1}\right)& f\left({x}_{i,2}\right)& \cdots & f\left({x}_{i, d}\right)\end{array}\right\rbrack \end{array}\right.$
式中,$f\left({x}_{i}\right)$ 为第$i$ 只麻雀的适应度值。生产者、 跟随者、警戒者位置更新公式可分别表示为
$\begin{cases}{x}_{i, j}^{t + 1}& =\begin{cases}{x}_{i, j}^{t}\exp \left(\frac{-i}{\alpha \cdot \cdot \mathrm{i}\cdot {\mathrm{{ter}}}_{\max }}\right)& {R}_{2}< \mathrm{{ST}}\\{x}_{i, j}^{t}+ Q.& {R}_{2}\geq \mathrm{{ST}}\end{cases}\\{x}_{i, j}^{t + 1}& =\begin{cases} Q\exp \left(\frac{{x}_{\max }^{t}- {x}_{i, j}^{t}}{\alpha {v}^{t}}\right)& i >\frac{N}{2}\\{x}_{i, j}^{t + 1}+ \left|{{x}_{i, j}^{t}- {x}_{i, j}^{t + 1}}\right|\cdot {A}^{+ }.& i \leq \frac{N}{2}\\{x}_{i, j}^{t + 1}+ \left|{{x}_{i, j}^{t}- {x}_{i, j}^{t + 1}}\right|& {f}_{j}> {f}_{b}\\{x}_{i, j}^{t + 1}+ \left|{{x}_{i, j}^{t}- {x}_{i, j}^{t + 1}}\right|& f ={f}_{b}\end{cases}\end{cases}$
式中:$j = 1,2,\cdots, d;t$ 为当前迭代次数; iter${}_{\max }$ 为最大迭代次数;$\alpha \in (0,1\rbrack ;{R}_{2}$ 和 ST 分别为警告值和安全值,其中${R}_{2}\in \left\lbrack {0,1}\right\rbrack,\mathrm{{ST}}\in \left\lbrack {{0.5},1}\right\rbrack ;Q$ 为遵循正态分布的随机数;$\mathbf{L}$ 为元素值全部为 1 的$1 \times d$ 阶矩阵;${x}_{\text{worst }}^{t}$ 为全局最差位置;${x}_{\mathrm{e}}^{t + 1}$ 为生产者在$t + 1$ 代占据的最佳位置;$\mathbf{A}$$1 \times d$ 阶矩阵,每个元素随机分配值 1 或-1,且${\mathbf{A}}^{+ }= {\mathbf{A}}^{\mathrm{T}}{\left(\mathbf{A}{\mathbf{A}}^{\mathrm{T}}\right)}^{-1};{x}_{\text{best }}^{t}$ 为全局最佳位置;$\beta$ 为步长控制参数,服从方差为 1 、 均值为 0 的正态分布;$k$ 为步进控制参数,$k \in \left\lbrack {-1,1}\right\rbrack$;${f}_{\mathrm{b}}$${f}_{\mathrm{w}}$ 分别为全局最佳和最差适应度值;${f}_{i}$ 为第$i$ 只麻雀的适应度值。
虽然 SSA 具有较强的优化性能, 但在处理复杂问题时搜索能力退化, 易陷入局部最优解。因此本文提出 1 种改进的 SSA 算法, 具体措施包括: 基于 Tent 混沌映射 TCM(Tent chaotic mapping)的种群初始化、通过正余弦算法 SCA(sine cosine algorithm)和 Levy 飞行 LF(levy flight)策略优化生产者和跟随者的位置更新公式。
SSA 的随机初始化过程对算法自身的全局搜索能力产生了限制。Tent 混沌映射具有遍历性和规律性, 采用 Tent 混沌映射来生成初始种群可以保证种群的多样性。映射表达式为
${X}_{i + 1}= \left\{\begin{array}{ll}\kappa {X}_{i}& 0 \leq {X}_{i}\leq {0.5}\\\kappa \left({1 -{X}_{i}}\right)& {0.5}< {X}_{i}\leq 1 \end{array}\right.$
式中:${X}_{i}$ 为第$i$ 次迭代时变量的值;$\kappa$ 为映射函数的参数。
在有限的迭代次数下, 生产者的移动范围会逐渐缩小, 使算法全局搜索能力下降。针对此问题, 本文引入正余弦算法对生产者的位置公式进行动态调整, 以平衡全局拓展和局部优化这 2 个过程, 使 SSA 在早期具有更强的全局开发能力, 在后期具有更强的小范围搜索能力。改进后生产者位置更新公式为
${X}_{i, j}^{t + 1}= \left\{\begin{array}{ll}{X}_{i, j}^{t}+ {r}_{1}\sin \left({r}_{2}\right)\left|{{r}_{3}{x}_{\text{best }}^{t}- {X}_{i, j}^{t}}\right|& {R}_{2}< \mathrm{{ST}}\\{X}_{i, j}^{t}+ {r}_{1}\cos \left({r}_{2}\right)\left|{{r}_{3}{x}_{\text{best }}^{t}- {X}_{i, j}^{t}}\right|& {R}_{2}\geq \mathrm{{ST}}\end{array}\right.$
式中:${r}_{1}= \chi -{t\chi }/{\text{iter}}_{\max },\chi = 2;{r}_{2}\in \left({0,{2\pi }}\right);{r}_{3}\in$ $\left\lbrack {0,2}\right\rbrack$
在觅食过程中, 跟随者在生产者的引导下向目标方向移动。如果生产者受困于局部范围, 将导致所有跟随者均被吸引至该区域, 使算法过早收敛。 为克服此困难, 本文引入 Levy 飞行策略对跟随者位置公式进行优化, 该策略的特点是多次小范围移动伴随偶然的长距离迁越。Levy 飞行步长$s$ 和改进后的跟随者位置${x}_{i, j}^{t + 1}$ 可分别表示为
$\left\{\begin{array}{l} s =\mu \left|\right|\beta {\left|\right|}^{1/\beta }0 <\beta \leq 2 \\\mu \sim N\left({0,{\sigma }_{\alpha }^{2}}\right),\nu \sim N\left({0,1}\right)\\{\sigma }_{\mu }= {\left\{\frac{\Gamma \left({1 +\beta }\right)\cdot \sin \left({{\pi \beta }/2}\right)}{\Gamma \left\lbrack {\left({1 +\beta }\right)/2}\right\rbrack \cdot \beta \cdot {2}^{\left({\beta - 1}\right)/2}}\right\}}^{1/\beta }\\\Gamma \left({1 +\beta }\right)= {\int }_{0}^{x}{t}^{\beta }{\mathrm{e}}^{-t}\mathrm{\;d}t \\{x}_{i, j}^{t + 1}= \left\{\begin{array}{ll} Q\exp \left(\frac{x{x}_{\operatorname{tot}}^{\prime }- {x}_{i, j}^{\prime }}{{i}^{2}}\right)& i >\frac{N}{2}\\\frac{x{x}_{i, j}^{t + 1}}{{i}^{2}}+ s{\left\lbrack \frac{x{x}_{i, j}^{\prime \prime }}{{i}^{2}}\right\rbrack }^{1/2}& i <\frac{N}{2}\end{array}\right.\end{array}\right.$
为验证本文算法的正确性和有效性, 选择 3 个基准函数来测试 ISSA 的性能, 并与 PSO 和 SSA 进行比较,测试维度设置为 30。其中函数${F}_{1}$ 极值数为 1, 适用于测试算法的全局搜索能力; 而函数${F}_{2}$${F}_{3}$ 具有多个极值,用来检验算法的局部寻优能力,3 个基准函数${F}_{1}\text{、}{F}_{2}\text{、}{F}_{3}$ 可分别表示为
$\left\{\begin{array}{l}{F}_{1}\left( x\right)= \mathop{\max }\limits_{i}\left\{{\left|{x}_{i}\right|,1 \leq i \leq n}\right\}\\{F}_{2}\left( x\right)= \mathop{\sum }\limits_{{i = 1}}^{n}\left\lbrack {{x}_{i}^{2}- {10}\cos \left({{2\pi }{x}_{i}}\right)+ {10}}\right\rbrack \\{F}_{3}\left( x\right)= \frac{1}{4}\mathop{\sum }\limits_{{i = 1}}^{n}{x}_{i}^{2}- \mathop{\prod }\limits_{{i = 1}}^{n}\cos \left(\frac{{x}_{i}}{\sqrt{i}}\right)+ 1 \end{array}\right.$
3 种优化算法的种群数量$N$ 均设置为 30,最大迭代数$M ={100}$。对于 SSA 和 ISSA,生产者占比 PD 和警戒者占比$\mathrm{{SD}}$ 统一为${20}\%$,安全阈值${R}_{2}= {0.8}$。 对于 PSO,设定参数${C}_{1}= {C}_{2}= {1.5}, w ={0.729}$
选取最优值、最差值、平均值和标准差作为评价指标,通过 3 种优化算法分别对基准函数${F}_{1}\text{、}{F}_{2}$${F}_{3}$ 进行 30 次独立仿真实验,所得测试结果见表2。 由表2可以看出, 对于 3 个基准函数, ISSA 的 4 个评价指标均最低, 其中最优值、最差值和均值这 3 个指标最低反映出 ISSA 的寻优能力较强, 而标准差指标最低反映出 ISSA 鲁棒性更好。由此可得, ISSA 搜索精度高且非常稳定。
为更直观体现 ISSA 算法的收敛性能, 绘制 3 种优化算法的适应度曲线, 如图3所示。可见, 与 PSO、SSA 相比, ISSA 曲线恒处于最下方,表示其寻优能力最好、收敛速度最快。
为验证基于 VMD-ISSA-ELM 预测方法的优越性和鲁棒性,将其与 PSO-ELM 和 SSA-ELM 这 2 种方法进行对比,采用 NASA 电池数据集进行实验。为更全面地展现 VMD-ISSA-ELM 预测方法的适应性, 设定 2 个不同的预测起点$T$ 进行 RUL 预测,其中 B5、B6、 B7 号电池起点 1 和 2 分别为 80、100,而 B18 号电池起点 1 和 2 分别为 65、75。采用 VMD-ISSA-ELM 方法对锂离子电池 RUL 进行预测的流程如图4所示。
选取绝对误差 AE(absolute error)、平均绝对误差 MAE(mean absolute error)和均方根误差 RMSE (root mean square error)作为预测模型的评价准则, 即
$\left\{\begin{array}{l}\mathrm{{AE}}= \left|{\mathrm{{RUL}}- \widehat{\mathrm{{RUL}}}}\right|\\\mathrm{{MAE}}= \frac{1}{n}\mathop{\sum }\limits_{{i = 1}}^{n}\left|{x\left( i\right)- \widehat{x}\left( i\right)}\right|\\\mathrm{{RMSE}}= \sqrt{\frac{1}{n}\mathop{\sum }\limits_{{i = 1}}^{n}{\left\lbrack x\left( i\right)- \widehat{x}\left( i\right)\right\rbrack }^{2}}\end{array}\right.$
式中:$\overset{⏜}{\mathrm{{RUL}}}$ 为 RUL 预测值;$x\left( i\right)$ 为容量真实值;$\widehat{x}\left( i\right)$ 为容量预测值。MAE 和 RMSE 代表预测值与实际值的契合效果。$\mathrm{{AE}}$$\mathrm{{MAE}}$$\mathrm{{RMSE}}$ 的值越小, 表明预测效果越好。
3 种方法基于 NASA 数据集的 RUL 预测曲线如图5所示, 可见: 与 PSO-ELM 和 SSA-ELM 这 2 种方法相比, VMD-ISSA-ELM 方法的容量预测曲线最接近真实退化趋势, 在不同预测条件下 RUL 计算结果误差均最小,这说明基于 VMD-ISSA-ELM 方法的预测精度最高。
3 种方法在 NASA 数据集下的 RUL 预测效果对比如表3所示。预测起点$\mathrm{{sp}}$ 越靠前,可获得的有效信息越少, 建模难度就越大。由表3可知: sp 值越小, PSO-ELM 方法和 SSA-ELM 方法的预测结果误差越大;与之相比,训练数据的变动基本未对 VMD-ISSA-ELM 方法产生影响。在不同电池、 不同起点下, 本文所提方法预测的 AE、MAE 和 RMSE 值是 3 种方法中最小的, 预测效果较稳定, 其中 MAE 和 RMSE 值分别控制在 1.58%和 2.14% 以内, 最低可达 0.62%和 0.85%。
总体结果表明, 在不同电池和不同训练数据集下, 本文所提方法可以提供较为准确的 RUL 预测。 以 B5 号电池为例, VMD-ISSA-ELM 方法的 RUL 预测误差为 0, 不同起点下预测曲线的 MAE 和 RMSE 值分别为 1.34%、0.62%和 1.71%、0.85%,均为同条件下最低值。由预测结果可以判断, VMD-ISSA-ELM 方法鲁棒性良好, 具有更好的电池寿命预测能力。
为进一步验证本文方法的有效性, 将文献[23]和文献[4]中提到的基于 Elman 神经网络方法和 ALO-SVR 方法与本文方法进行对比。选取电池 B5、B6、 B7、B18 作为实验对象, 起点设置为 80 (B5、B6、 B7)和 65(B18),以预测结果的 MAE 和 RMSE 作为评判标准。3 种方法对电池 B5、B6、B7、B18 的 RUL 预测结果 MAE、RMSE 对比如图6所示。可见:与 Elman 方法和 ALO-SVR 方法相比, VMD-ISSA-ELM 在 RUL 预测精度和稳定性方面具有较大优势。
本文提出 1 种基于 VMD-ISSA-ELM 方法来预测锂离子电池的剩余使用寿命, 通过创新性研究和探索得出结论如下。
(1)利用 VMD 和 AC 重构电池的容量序列,完成对原始数据的预处理, 可有效降低容量回升现象的影响,避免噪声分量干扰,有效减少预测误差。
(2)通过引入Tent混沌映射、正余弦思想及Levy 飞行策略, 分别对 SSA 中的种群初始化过程、生产者位置更新和跟随者位置更新这 3 个关键步骤进行优化, 可提高 SSA 的全局搜索能力和局部寻优能力。
(3)通过重构后的降噪数据训练 ELM 模型,结合 ISSA 寻优得到的模型最佳参数建立 VMD-ISSA-ELM 方法, 并完成对电池的 RUL 预测。基于 NASA 数据集的测试实验结果表明, 与其他方法相比, 本文所提方法可以获得精确的 RUL 预测值, 预测结果的 MAE 和 RMSE 分别在 1.58%和 2.14%内,最优值分别为 0.62%和 0.85%。
  • 河北省自然科学基金资助项目(E2019202328)
参考文献 引证文献
排序方式:
[1]
姚芳, 张楠, 黄凯. 锂离子电池状态估算与寿命预测综述[J]. 电源学报, 2020. 18(3): 175-183.
Yao Fang, Zhang Nan, Huang Kai. Review of state estimation and life prediction for lithiumion batteries[J]. Journal of Power Supply, 2020. 18(3): 175-183 (in Chinese).
[2]
Zhang Kai, Zhao Peng, Sun Canfei, et al. Remaining useful life prediction of aircraft lithium-ion batteries based on F-distribution particle filter and kernel smoothing algorithm[J]. Chinese Journal of Aeronautics, 2020. 33(5): 1517-1531.
[3]
张若可, 郭永芳, 余湘媛, 等. 基于数据驱动的锂离子电池 RUL 预测综述[J]. 电源学报, 2023. 21(5): 182-190.
Zhang Ruoke, Guo Yongfang, Yu Xiangyuan, et al. Review of data-driven RUL prediction for Lithium-ion batteries[J]. Journal of Power Supply, 2023. 21(5): 182-190 (in Chinese).
[4]
王瀛洲, 倪裕隆, 郑宇清, 等. 基于ALO-SVR 的锂离子电池剩余使用寿命预测[J]. 中国电机工程学报, 2021. 41(4): 1445-1457.
Wang Yingzhou, Ni Yulong, Zheng Yuqing, et al. Remaining useful life prediction of lithium-ion batteries based on support vector regression optimized and ant lion optimizations[J]. Proceedings of the CSEE, 2021. 41(4): 1445-1457 (in Chinese).
[5]
徐波, 雷敏, 王钋. 基于TRNN和FA-PF融合的锂离子电池 RUL 预测[J]. 电源学报, 2023. 21(2): 138-145.
Xu Bo, Lei Min, Wang Po. RUL prediction of lithium-ion battery based on fusion of TRNN and FA-PF[J]. Journal of Power Supply, 2023. 21(2): 138-145 (in Chinese).
[6]
Qiu Xianghui, Wu Weixiong, Wang Shuangfeng. Remaining useful life prediction of lithium-ion battery based on improved cuckoo search particle filter and a novel state of charge estimation method[J]. Journal of Power Sources, 2020. 450: 227700.
[7]
杨战社, 王云浩, 孔晨再. 基于GWO-SVR的锂电池剩余使用寿命预测[J]. 电源学报, 2023. 21(2): 154-162.
Yang Zhanshe, Wang Yunhao, Kong Chenzai. Prediction of remaining useful life of lithium-ion batteries based on GWO-SVR method[J]. Journal of Power Supply, 2023. 21(2): 154-162 (in Chinese).
[8]
刘月峰, 赵光权, 彭喜元. 多核相关向量机优化模型的锂电池剩余寿命预测方法[J]. 电子学报, 2019. 47(6): 1285-1292.
Liu Yuefeng, Zhao Guangquan, Peng Xiyuan. A lithium-ion battery remaining using life prediction method based on multi-kernel relevance vector machine optimized model[J]. Acta Electronica Sinica, 2019. 47(6): 1285-1292 (in Chinese).
[9]
Li Xiaoyu, Zhang Lei, Wang Zhenpo, et al. Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks[J]. Journal of Energy Storage, 2019. 21: 510-518.
[10]
Yang Hao, Wang Penglei, An Yabin, et al. Remaining useful life prediction based on denoising technique and deep neural network for lithium-ion capacitors[J]. eTransportation, 2020. 5: 100078.
[11]
Xu Xiaodong, Tang Shengjin, Yu Chuanqiang, et al. Remaining useful life prediction of lithium-ion batteries based on Wiener process under time-varying temperature condition[J]. Reliability Engineering & System Safety, 2021. 214: 107675.
[12]
Li Xiaoyu, Yuan Changgui, Wang Zhenpo. Multi-time-scale framework for prognostic health condition of lithium battery using modified Gaussian process regression and nonlinear regression[J]. Journal of Power Sources, 2020. 467: 228358.
[13]
张婷婷, 于明, 李宾, 等. 基于 Wavelet 降噪和支持向量机的锂离子电池容量预测研究[J]. 电工技术学报, 2020. 35(14): 3126-3136.
Zhang Tingting, Yu Ming, Li Bin, et al. Capacity prediction of lithium-ion batteries based on Wavelet noise reduction and support vector machine[J]. Transactions of China Electrotechnical Society, 2020. 35(14): 3126-3136 (in Chinese).
[14]
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.
[15]
陈则王, 李福胜, 林娅, 等. 基于 GA-ELM 的锂离子电池 RUL 间接预测方法[J]. 计量学报, 2020. 41(6): 735-742.
Chen Zewang, Li Fusheng, Lin Ya, et al. Indirect prediction method of RUL for lithium-ion battery based on GA-ELM[J]. Acta Metrologica Sinica, 2020. 41(6): 735-742 (in Chinese).
[16]
Xue Jiankai, Shen Bo. A novel swarm intelligence optimization approach: Sparrow search algorithm[J]. Systems Science & Control Engineering, 2020. 8(1): 22-34.
[17]
李雅丽, 王淑琴, 陈倩茹, 等. 若干新型群智能优化算法的对比研究[J]. 计算机工程与应用, 2020. 56(22): 1-12.
Li Yali, Wang Shuqin, Chen Qianru, et al. Comparative study of several new swarm intelligence optimization algorithms[J]. Computer Engineering and Applications, 2020. 56(22): 1-12 (in Chinese).
[18]
Zhu Yanlong, Yousefi N. Optimal parameter identification of PEMFC stacks using adaptive sparrow search algorithm[J]. International Journal of Hydrogen Energy, 2021. 46(14): 9541-9552.
[19]
Liu Bo, Rodriguez D. Renewable energy systems optimization by a new multi-objective optimization technique: A residential building[J]. Journal of Building Engineering, 2021. 35: 102094.
[20]
Zhou Shenghang, Xie Hao, Zhang Chuncheng, et al. Wavefront-shaping focusing based on a modified sparrow search algorithm[J]. Optik, 2021. 244: 167516.
[21]
Xu Bo, Zhou Fengxing, Li Huipeng, et al. Early fault feature extraction of bearings based on Teager energy operator and optimal VMD[J]. ISA Transactions, 2019. 86: 249-265.
[22]
胡天中, 余建波. 基于多尺度分解和深度学习的锂电池寿命预测[J]. 浙江大学学报(工学版), 2019. 53(10): 1852-1864.
Hu Tianzhong, Yu Jianbo. Life prediction of lithium-ion batteries based on multiscale decomposition and deep learning[J]. Journal of Zhejiang University (Engineering Science), 2019. 53(10): 1852-1864 (in Chinese).
[23]
Li Wenhua, Jiao Zhipeng, Du Le, et al. An indirect RUL prognosis for lithium-ion battery under vibration stress using Elman neural network[J]. International Journal of Hydrogen Energy, 2019. 44(23): 12270-12276.
2024年第22卷第6期
PDF下载
294
119
引用本文
BibTeX
文章信息
doi: 10.13234/j.issn.2095-2805.2024.6.188
  • 接收时间:2021-11-12
  • 首发时间:2025-07-19
  • 出版时间:2024-11-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2021-11-12
  • 修回日期:2022-01-21
  • 录用日期:2022-03-01
基金
Natural Science Foundation of Hebei Province under the grant E2019202328(E2019202328)
河北省自然科学基金资助项目(E2019202328)
作者信息
    1 省部共建电工装备可靠性与智能化国家重点实验室 (河北工业大学) 天津 300130
    2 河北省电磁场与电器可靠性重点实验室 (河北工业大学) 天津 300130
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.6.188
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