Article(id=1241686768404197594, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241686759470329942, articleNumber=null, orderNo=null, doi=10.16579/j.issn.1001.9669.2025.09.022, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1747497600000, receivedDateStr=2025-05-18, revisedDate=1753977600000, revisedDateStr=2025-08-01, acceptedDate=null, acceptedDateStr=null, onlineDate=1773970795012, onlineDateStr=2026-03-20, pubDate=1757865600000, pubDateStr=2025-09-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773970795012, onlineIssueDateStr=2026-03-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773970795012, creator=13701087609, updateTime=1773970795012, updator=13701087609, issue=Issue{id=1241686759470329942, tenantId=1146029695717560320, journalId=1227999626482147330, year='2025', volume='47', issue='9', pageStart='1', pageEnd='249', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773970792882, creator=13701087609, updateTime=1773970911747, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241687258093375901, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241686759470329942, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241687258093375902, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241686759470329942, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=221, endPage=232, ext={EN=ArticleExt(id=1241686768852988141, articleId=1241686768404197594, tenantId=1146029695717560320, journalId=1227999626482147330, language=EN, title=Nonlinear-Wiener-process-based remaining useful life prediction method for stochastic deteriorating devices with multiple modes, columnId=null, journalTitle=Journal of Mechanical Strength, columnName=null, runingTitle=null, highlight=null, articleAbstract=

The challenge in predicting the remaining useful life (RUL) of multi-mode stochastic degradation equipment lies in establishing a class of stochastic degradation models capable of characterizing multiple distinct degradation modes and deriving the remaining useful life distribution of the equipment under such multi-mode stochastic degradation models.First, a generalized stochastic degradation model based on the nonlinear Wiener process was developed, achieving a unified characterization of multi-mode stochastic degradation processes. Second, a maximum likelihood estimation (MLE) method for model parameters was proposed, utilizing historical degradation data from similar equipment. Third, an analytical approximate solution for the probability density function (PDF) of the remaining useful life distribution of multi-mode stochastic degradation equipment was derived under the first hitting time (FHT) framework. Finally, a sequential Bayesian framework for model parameter updating was constructed, enabling online prediction of the remaining useful life of in-service equipment.Numerical simulation analyses and an application case study on bearing remaining useful life prediction demonstrate that the proposed method can effectively model the multi-mode stochastic degradation processes of stochastic degradation equipment and accurately predict the remaining useful life, thereby providing predictive information to support subsequent maintenance decision-making for the system.

, correspAuthors=null, authorNote=null, correspAuthorsNote=
ZHANG Zhengxin, E-mail:
, 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=Mengcao LI, Zhengxin ZHANG, Xiaosheng SI, Lei FENG, Jianxun ZHANG), CN=ArticleExt(id=1241686793725211030, articleId=1241686768404197594, tenantId=1146029695717560320, journalId=1227999626482147330, language=CN, title=基于非线性Wiener过程的多模式随机退化设备剩余使用寿命预测方法, columnId=0, journalTitle=机械强度, columnName=, runingTitle=null, highlight=null, articleAbstract=

多模式随机退化设备剩余使用寿命(Remaining Useful Life,RUL)预测的难点在于建立一类能够刻画多种不同退化模式的随机退化模型,并求解多模式随机退化模型下设备的RUL分布。首先,建立了一类基于非线性Wiener过程的一般化随机退化模型,实现了多模式随机退化过程统一刻画。其次,提出了基于同类设备历史退化数据的模型参数极大似然估计(Maximum Likelihood Estimation,MLE)方法。再次,推导了首达时间意义下多模式随机退化设备RUL分布的概率密度函数(Probability Density Function,PDF)的解析近似解。最后,构建了模型参数更新的序贯贝叶斯架构,实现了在役设备RUL的在线预测。数值仿真分析及轴承RUL预测的应用实例表明,所提方法能够有效建模随机退化设备的多模式随机退化过程,并准确预测设备的RUL,为系统后续的维修决策提供预测信息依据。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
张正新,男,1987年生,云南曲靖人,博士;主要研究方向为随机退化系统剩余寿命预测与健康管理;E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Jes/MRT+xJI9ret3+5NTaA==, magXml=E4vqe93qJJAXH721Wr1SMw==, pdfUrl=null, pdf=13Dtqh8kGN/HfFaetI/ihA==, pdfFileSize=3257570, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=J+GxesQqHFE1BrFllFAYcQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=wgFw7+4Mk5z9YEM3DFkM8g==, mapNumber=null, authorCompany=null, fund=null, authors=

李梦草,女,1999年生,河南开封人,在读硕士研究生;主要研究方向为随机退化系统剩余寿命预测与健康管理;E-mail:

, authorsList=李梦草, 张正新, 司小胜, 冯磊, 张建勋)}, authors=[Author(id=1241810827536302853, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dreamgrassli@foxmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241810827632771850, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810827536302853, language=EN, stringName=Mengcao LI, firstName=Mengcao, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Rocket Force University of Engineering, Xi'an 710025, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241810827712463629, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810827536302853, language=CN, stringName=李梦草, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=火箭军工程大学,西安 710025, bio={"content":"

李梦草,女,1999年生,河南开封人,在读硕士研究生;主要研究方向为随机退化系统剩余寿命预测与健康管理;E-mail:

"}, bioImg=null, bioContent=

李梦草,女,1999年生,河南开封人,在读硕士研究生;主要研究方向为随机退化系统剩余寿命预测与健康管理;E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241810827364336384, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, xref=null, ext=[AuthorCompanyExt(id=1241810827372724993, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Rocket Force University of Engineering, Xi'an 710025, China), AuthorCompanyExt(id=1241810827376919298, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=火箭军工程大学,西安 710025)])]), Author(id=1241810829306299150, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangzx.2006@tsinghua.org.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241810829394379537, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810829306299150, language=EN, stringName=Zhengxin ZHANG, firstName=Zhengxin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Rocket Force University of Engineering, Xi'an 710025, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241810829474071313, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810829306299150, language=CN, stringName=张正新, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=火箭军工程大学,西安 710025, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241810827364336384, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, xref=null, ext=[AuthorCompanyExt(id=1241810827372724993, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Rocket Force University of Engineering, Xi'an 710025, China), AuthorCompanyExt(id=1241810827376919298, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=火箭军工程大学,西安 710025)])]), Author(id=1241810829557957396, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241810829683786519, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810829557957396, language=EN, stringName=Xiaosheng SI, firstName=Xiaosheng, middleName=null, lastName=SI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Rocket Force University of Engineering, Xi'an 710025, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241810829776061209, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810829557957396, language=CN, stringName=司小胜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=火箭军工程大学,西安 710025, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241810827364336384, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, xref=null, ext=[AuthorCompanyExt(id=1241810827372724993, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Rocket Force University of Engineering, Xi'an 710025, China), AuthorCompanyExt(id=1241810827376919298, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=火箭军工程大学,西安 710025)])]), Author(id=1241810829859947291, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241810829952221982, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810829859947291, language=EN, stringName=Lei FENG, firstName=Lei, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Rocket Force University of Engineering, Xi'an 710025, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241810830170325792, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810829859947291, language=CN, stringName=冯磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=火箭军工程大学,西安 710025, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241810827364336384, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, xref=null, ext=[AuthorCompanyExt(id=1241810827372724993, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Rocket Force University of Engineering, Xi'an 710025, China), AuthorCompanyExt(id=1241810827376919298, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=火箭军工程大学,西安 710025)])]), Author(id=1241810830409401123, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241810830564590375, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810830409401123, language=EN, stringName=Jianxun ZHANG, firstName=Jianxun, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Rocket Force University of Engineering, Xi'an 710025, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241810830640087848, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, authorId=1241810830409401123, language=CN, stringName=张建勋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=火箭军工程大学,西安 710025, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241810827364336384, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, xref=null, ext=[AuthorCompanyExt(id=1241810827372724993, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Rocket Force University of Engineering, Xi'an 710025, China), AuthorCompanyExt(id=1241810827376919298, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=火箭军工程大学,西安 710025)])])], keywords=[Keyword(id=1241810830807860011, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, orderNo=1, keyword=Prognostics and health management), Keyword(id=1241810830916911917, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, orderNo=2, keyword=Remaining useful life prediction), Keyword(id=1241810831059518254, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, orderNo=3, keyword=Multiple modes degradation modeling), Keyword(id=1241810831231484719, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, orderNo=4, keyword=Nonlinear Wiener process), Keyword(id=1241810831315370800, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, orderNo=5, keyword=Reliability), Keyword(id=1241810831386673970, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, orderNo=1, keyword=预测与健康管理), Keyword(id=1241810831525086004, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, orderNo=2, keyword=剩余使用寿命预测), Keyword(id=1241810831625749302, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, orderNo=3, keyword=多模式退化建模), Keyword(id=1241810831684469560, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, orderNo=4, keyword=非线性维纳过程), Keyword(id=1241810831801910073, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, orderNo=5, keyword=可靠性)], refs=[Reference(id=1241810838785426276, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=9, pageStart=2119, pageEnd=2141, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=李天梅, 司小胜, 刘翔, journalName=自动化学报, refType=null, unstructuredReference=李天梅,司小胜,刘翔,. 大数据下数模联动的随机退化设备剩余寿命预测技术[J]. 自动化学报202248(9):2119-2141., articleTitle=大数据下数模联动的随机退化设备剩余寿命预测技术, refAbstract=null), Reference(id=1241810838844146533, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=9, pageStart=2119, pageEnd=2141, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=LI Tianmei, SI Xiaosheng, LIU Xiang, journalName=Acta Automatica Sinica, refType=null, unstructuredReference=LI TianmeiSI XiaoshengLIU Xianget al. Data-model interactive remaining useful life prediction technologies for stochastic degrading devices with big data[J]. Acta Automatica Sinica202248(9):2119-2141.(In Chinese), articleTitle=Data-model interactive remaining useful life prediction technologies for stochastic degrading devices with big data, refAbstract=null), Reference(id=1241810838907061094, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=20, pageStart=29, pageEnd=37, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=李乃鹏, 蔡潇, 雷亚国, journalName=机械工程学报, refType=null, unstructuredReference=李乃鹏,蔡潇,雷亚国,. 一种融合多传感器数据的数模联动机械剩余寿命预测方法[J]. 机械工程学报202157(20):29-37., articleTitle=一种融合多传感器数据的数模联动机械剩余寿命预测方法, refAbstract=null), Reference(id=1241810838961587047, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=20, pageStart=29, pageEnd=37, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=LI Naipeng, CAI Xiao, LEI Yaguo, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=LI NaipengCAI XiaoLEI Yaguoet al. A model-data-fusion remaining useful life prediction method with multi-sensor fusion for machinery[J]. Journal of Mechanical Engineering202157(20):29-37.(In Chinese), articleTitle=A model-data-fusion remaining useful life prediction method with multi-sensor fusion for machinery, refAbstract=null), Reference(id=1241810839045473128, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2023, volume=233, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=KAMEI S, TAGHIPOUR S, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=KAMEI STAGHIPOUR S. A comparison study of centralized and decentralized federated learning approaches utilizing the transformer architecture for estimating remaining useful life[J]. Reliability Engineering & System Safety2023233:109130., articleTitle=A comparison study of centralized and decentralized federated learning approaches utilizing the transformer architecture for estimating remaining useful life, refAbstract=null), Reference(id=1241810839116776297, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2022, volume=218, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=ZIO E, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=ZIO E. Prognostics and Health Management (PHM):where are we and where do we (need to) go in theory and practice[J]. Reliability Engineering & System Safety2022218:108119., articleTitle=Prognostics and Health Management (PHM):where are we and where do we (need to) go in theory and practice, refAbstract=null), Reference(id=1241810839179690858, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=5, pageStart=1024, pageEnd=1032, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=吴定海, 任国全, 王怀光, journalName=机械强度, refType=null, unstructuredReference=吴定海,任国全,王怀光,. 基于卷积神经网络的机械故障诊断方法综述[J]. 机械强度202042(5):1024-1032., articleTitle=基于卷积神经网络的机械故障诊断方法综述, refAbstract=null), Reference(id=1241810839263576939, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=5, pageStart=1024, pageEnd=1032, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=WU Dinghai, REN Guoquan, WANG Huaiguang, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=WU DinghaiREN GuoquanWANG Huaiguanget al. The review of mechanical fault diagnosis methods based on convolutional neural network[J]. Journal of Mechanical Strength202042(5):1024-1032.(In Chinese), articleTitle=The review of mechanical fault diagnosis methods based on convolutional neural network, refAbstract=null), Reference(id=1241810839318102892, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2023, volume=10, issue=6, pageStart=1615, pageEnd=1635, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=KHAN A, AZAD M M, SOHAIL M, journalName=International Journal of Precision Engineering and Manufacturing-Green Technology, refType=null, unstructuredReference=KHAN AAZAD M MSOHAIL Met al. A review of physics-based models in prognostics and health management of laminated composite structures[J]. International Journal of Precision Engineering and Manufacturing-Green Technology202310(6):1615-1635., articleTitle=A review of physics-based models in prognostics and health management of laminated composite structures, refAbstract=null), Reference(id=1241810839401988973, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=4, pageStart=969, pageEnd=976, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=钟建华, 黄聪, 钟舜聪, journalName=机械强度, refType=null, unstructuredReference=钟建华,黄聪,钟舜聪,. 基于t-SNE降维方法的滚动轴承剩余寿命预测[J]. 机械强度202446(4):969-976., articleTitle=基于t-SNE降维方法的滚动轴承剩余寿命预测, refAbstract=null), Reference(id=1241810839464903534, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=4, pageStart=969, pageEnd=976, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=ZHONG Jianhua, HUANG Cong, ZHONG Shuncong, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=ZHONG JianhuaHUANG CongZHONG Shunconget al. Remaining useful life of rolling bearing based on t-SNE[J]. Journal of Mechanical Strength202446(4):969-976.(In Chinese), articleTitle=Remaining useful life of rolling bearing based on t-SNE, refAbstract=null), Reference(id=1241810839532012399, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=冯磊, 张正新, 李天梅, journalName=中北大学学报(自然科学版), refType=null, unstructuredReference=冯磊,张正新,李天梅,. 数据驱动的闭环控制系统剩余寿命预测方法综述[J]. 中北大学学报(自然科学版)202445(1):1-11., articleTitle=数据驱动的闭环控制系统剩余寿命预测方法综述, refAbstract=null), Reference(id=1241810839603315568, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=FENG Lei, ZHANG Zhengxin, LI Tianmei, journalName=Journal of North University of China(Natural Science Edition), refType=null, unstructuredReference=FENG LeiZHANG ZhengxinLI Tianmeiet al. A review of data-driven remaining useful life prediction methods for closed-loop control system[J]. Journal of North University of China(Natural Science Edition)202445(1):1-11.(In Chinese), articleTitle=A review of data-driven remaining useful life prediction methods for closed-loop control system, refAbstract=null), Reference(id=1241810839662035825, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2024, volume=209, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=LI H Q, ZHANG Z X, LI T M, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=LI H QZHANG Z XLI T Met al. A review on physics-informed data-driven remaining useful life prediction:challenges and opportunities[J]. Mechanical Systems and Signal Processing2024209:111120., articleTitle=A review on physics-informed data-driven remaining useful life prediction:challenges and opportunities, refAbstract=null), Reference(id=1241810839724950386, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2024, volume=252, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=DE BEAULIEU M H, JHA M S, GARNIER H, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=DE BEAULIEU M HJHA M SGARNIER Het al. Remaining useful life prediction based on physics-informed data augmentation[J]. Reliability Engineering & System Safety2024252:110451., articleTitle=Remaining useful life prediction based on physics-informed data augmentation, refAbstract=null), Reference(id=1241810839792059251, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2018, volume=271, issue=3, pageStart=775, pageEnd=796, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=ZHANG Z X, SI X S, HU C H, journalName=European Journal of Operational Research, refType=null, unstructuredReference=ZHANG Z XSI X SHU C Het al. Degradation data analysis and remaining useful life estimation:a review on Wiener-process-based methods[J]. European Journal of Operational Research2018271(3):775-796., articleTitle=Degradation data analysis and remaining useful life estimation:a review on Wiener-process-based methods, refAbstract=null), Reference(id=1241810839859168116, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=64, pageEnd=68, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=GUAN Q L, WEI X K, journalName=null, refType=null, unstructuredReference=GUAN Q LWEI X K. The statistical data-driven remaining useful life prediction:a review on the Wiener process-based method[C]//2023 Prognostics and Health Management Conference (PHM).New York:IEEE,2023:64-68., articleTitle=The statistical data-driven remaining useful life prediction:a review on the Wiener process-based method, refAbstract=null), Reference(id=1241810839917888373, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2013, volume=231, issue=3, pageStart=631, pageEnd=644, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=SI X S, CHEN M Y, WANG W B, journalName=European Journal of Operational Research, refType=null, unstructuredReference=SI X SCHEN M YWANG W Bet al. Specifying measurement errors for required lifetime estimation performance[J]. European Journal of Operational Research2013231(3):631-644., articleTitle=Specifying measurement errors for required lifetime estimation performance, refAbstract=null), Reference(id=1241810840022745974, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2005, volume=37, issue=6, pageStart=543, pageEnd=557, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=GEBRAEEL N Z, LAWLEY M A, LI R, journalName=IIE Transactions, refType=null, unstructuredReference=GEBRAEEL N ZLAWLEY M ALI Ret al. Residual-life distributions from component degradation signals:a Bayesian approach[J]. IIE Transactions200537(6):543-557., articleTitle=Residual-life distributions from component degradation signals:a Bayesian approach, refAbstract=null), Reference(id=1241810840102437751, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2015, volume=64, issue=2, pageStart=687, pageEnd=700, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=HUANG Z Y, XU Z G, WANG W H, journalName=IEEE Transactions on Reliability, refType=null, unstructuredReference=HUANG Z YXU Z GWANG W Het al. Remaining useful life prediction for a nonlinear heterogeneous Wiener process model with an adaptive drift[J]. IEEE Transactions on Reliability201564(2):687-700., articleTitle=Remaining useful life prediction for a nonlinear heterogeneous Wiener process model with an adaptive drift, refAbstract=null), Reference(id=1241810840165352312, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2022, volume=217, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=SI X S, LI T M, ZHANG J X, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=SI X SLI T MZHANG J Xet al. Nonlinear degradation modeling and prognostics:a Box-Cox transformation perspective[J].Reliability Engineering & System Safety2022217:108120., articleTitle=Nonlinear degradation modeling and prognostics:a Box-Cox transformation perspective, refAbstract=null), Reference(id=1241810840224072569, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2021, volume=212, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=YU W N, TU W B, KIM I Y, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=YU W NTU W BKIM I Yet al. A nonlinear-drift-driven Wiener process model for remaining useful life estimation considering three sources of variability[J]. Reliability Engineering & System Safety2021212:107631., articleTitle=A nonlinear-drift-driven Wiener process model for remaining useful life estimation considering three sources of variability, refAbstract=null), Reference(id=1241810840320541562, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2012, volume=61, issue=1, pageStart=50, pageEnd=67, url=null, language=null, rfNumber=[18], rfOrder=22, authorNames=SI X S, WANG W B, HU C H, journalName=IEEE Transactions on Reliability, refType=null, unstructuredReference=SI X SWANG W BHU C Het al. Remaining useful life estimation based on a nonlinear diffusion degradation process[J]. IEEE Transactions on Reliability201261(1):50-67., articleTitle=Remaining useful life estimation based on a nonlinear diffusion degradation process, refAbstract=null), Reference(id=1241810840391844731, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2019, volume=68, issue=2, pageStart=689, pageEnd=709, url=null, language=null, rfNumber=[19], rfOrder=23, authorNames=ZHANG J X, HU C H, HE X, journalName=IEEE Transactions on Reliability, refType=null, unstructuredReference=ZHANG J XHU C HHE Xet al. A novel lifetime estimation method for two-phase degrading systems[J]. IEEE Transactions on Reliability201968(2):689-709., articleTitle=A novel lifetime estimation method for two-phase degrading systems, refAbstract=null), Reference(id=1241810840500896636, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2017, volume=66, issue=3, pageStart=924, pageEnd=938, url=null, language=null, rfNumber=[20], rfOrder=24, authorNames=WEN Y X, WU J G, YUAN Y, journalName=IEEE Transactions on Reliability, refType=null, unstructuredReference=WEN Y XWU J GYUAN Y. Multiple-phase modeling of degradation signal for condition monitoring and remaining useful life prediction[J]. IEEE Transactions on Reliability201766(3):924-938., articleTitle=Multiple-phase modeling of degradation signal for condition monitoring and remaining useful life prediction, refAbstract=null), Reference(id=1241810840563811197, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2021, volume=68, issue=3, pageStart=2521, pageEnd=2531, url=null, language=null, rfNumber=[21], rfOrder=25, authorNames=CHEN Z H, WU M, ZHAO R, journalName=IEEE Transactions on Industrial Electronics, refType=null, unstructuredReference=CHEN Z HWU MZHAO Ret al. Machine remaining useful life prediction via an attention-based deep learning approach[J]. IEEE Transactions on Industrial Electronics202168(3):2521-2531., articleTitle=Machine remaining useful life prediction via an attention-based deep learning approach, refAbstract=null), Reference(id=1241810840647697278, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2008, volume=40, issue=7, pageStart=629, pageEnd=639, url=null, language=null, rfNumber=[22], rfOrder=26, authorNames=ELWANY A H, GEBRAEEL N Z, journalName=IIE Transactions, refType=null, unstructuredReference=ELWANY A HGEBRAEEL N Z. Sensor-driven prognostic models for equipment replacement and spare parts inventory[J]. IIE Transactions200840(7):629-639., articleTitle=Sensor-driven prognostic models for equipment replacement and spare parts inventory, refAbstract=null), Reference(id=1241810840710611839, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2012, volume=221, issue=2, pageStart=360, pageEnd=367, url=null, language=null, rfNumber=[23], rfOrder=27, authorNames=YE Z S, SHEN Y, XIE M, journalName=European Journal of Operational Research, refType=null, unstructuredReference=YE Z SSHEN YXIE M. Degradation-based burn-in with preventive maintenance[J]. European Journal of Operational Research2012221(2):360-367., articleTitle=Degradation-based burn-in with preventive maintenance, refAbstract=null), Reference(id=1241810840794497920, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=6, pageStart=1472, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=28, authorNames=ZHANG J X, SI X S, DU D B, journalName=Sensors, refType=null, unstructuredReference=ZHANG J XSI X SDU D Bet al. Lifetime estimation for multi-phase deteriorating process with random abrupt jumps[J]. Sensors201919(6):1472., articleTitle=Lifetime estimation for multi-phase deteriorating process with random abrupt jumps, refAbstract=null), Reference(id=1241810840865801089, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2019, volume=3, issue=1, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[25], rfOrder=29, authorNames=MELCHERS R E, journalName=NPJ Materials Degradation, refType=null, unstructuredReference=MELCHERS R E. Predicting long-term corrosion of metal alloys in physical infrastructure[J]. NPJ Materials Degradation20193(1):1-7., articleTitle=Predicting long-term corrosion of metal alloys in physical infrastructure, refAbstract=null), Reference(id=1241810840928715650, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2018, volume=99, issue=null, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[26], rfOrder=30, authorNames=WANG D, TSUI K L, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=WANG DTSUI K L. Two novel mixed effects models for prognostics of rolling element bearings[J]. Mechanical Systems and Signal Processing201899:1-13., articleTitle=Two novel mixed effects models for prognostics of rolling element bearings, refAbstract=null), Reference(id=1241810841000018819, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=23, pageStart=96, pageEnd=104, url=null, language=null, rfNumber=[27], rfOrder=31, authorNames=王宇, 刘秋发, 彭一真, journalName=机械工程学报, refType=null, unstructuredReference=王宇,刘秋发,彭一真. 非均匀监测条件下滚动轴承剩余寿命预测方法[J]. 机械工程学报202359(23):96-104., articleTitle=非均匀监测条件下滚动轴承剩余寿命预测方法, refAbstract=null), Reference(id=1241810841067127684, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=23, pageStart=96, pageEnd=104, url=null, language=null, rfNumber=[27], rfOrder=32, authorNames=WANG Yu, LIU Qiufa, PENG Yizhen, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=WANG YuLIU QiufaPENG Yizhen. A remaining useful life prediction approach with nonuniform monitoring conditions for rolling bearings[J]. Journal of Mechanical Engineering202359(23):96-104.(In Chinese), articleTitle=A remaining useful life prediction approach with nonuniform monitoring conditions for rolling bearings, refAbstract=null), Reference(id=1241810841138430853, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2023, volume=39, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=33, authorNames=ZHANG K P, CHANG Z M, HAO S Y, journalName=Acta Mechanica Sinica, refType=null, unstructuredReference=ZHANG K PCHANG Z MHAO S Yet al. Nonlinear characteristics and analysis of an exponential variable cross-section beam-based micro-gyroscope with electrostatic driven[J]. Acta Mechanica Sinica202339(3):522371., articleTitle=Nonlinear characteristics and analysis of an exponential variable cross-section beam-based micro-gyroscope with electrostatic driven, refAbstract=null), Reference(id=1241810841213928326, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2018, volume=6, issue=null, pageStart=17729, pageEnd=17740, url=null, language=null, rfNumber=[29], rfOrder=34, authorNames=ZHANG L J, MU Z Q, SUN C Y, journalName=IEEE Access, refType=null, unstructuredReference=ZHANG L JMU Z QSUN C Y. Remaining useful life prediction for lithium-ion batteries based on exponential model and particle filter[J]. IEEE Access20186:17729-17740., articleTitle=Remaining useful life prediction for lithium-ion batteries based on exponential model and particle filter, refAbstract=null), Reference(id=1241810842698711943, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2022, volume=17, issue=4, pageStart=32, pageEnd=40, url=null, language=null, rfNumber=[30], rfOrder=35, authorNames=李彦梅, 刘惠汉, 张朝龙, journalName=电气工程学报, refType=null, unstructuredReference=李彦梅,刘惠汉,张朝龙,. 基于双高斯模型的锂电池剩余使用寿命预测方法[J]. 电气工程学报202217(4):32-40., articleTitle=基于双高斯模型的锂电池剩余使用寿命预测方法, refAbstract=null), Reference(id=1241810842853901192, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2022, volume=17, issue=4, pageStart=32, pageEnd=40, url=null, language=null, rfNumber=[30], rfOrder=36, authorNames=LI Yanmei, LIU Huihan, ZHANG Chaolong, journalName=Journal of Electrical Engineering, refType=null, unstructuredReference=LI YanmeiLIU HuihanZHANG Chaolonget al. Lithiumion battery RUL prediction method based on double Gaussian model[J].Journal of Electrical Engineering202217(4):32-40.(In Chinese), articleTitle=Lithiumion battery RUL prediction method based on double Gaussian model, refAbstract=null), Reference(id=1241810842929398665, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=159, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=37, authorNames=司小胜, 胡昌华, journalName=数据驱动的设备剩余寿命预测理论及应用, refType=null, unstructuredReference=司小胜,胡昌华. 数据驱动的设备剩余寿命预测理论及应用[M]. 北京:国防工业出版社,2016:159., articleTitle=null, refAbstract=null), Reference(id=1241810843017479050, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=159, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=38, authorNames=SI Xiaosheng, HU Changhua, journalName=Data-driven remaining useful life prediction theory and applications for equipment, refType=null, unstructuredReference=SI XiaoshengHU Changhua. Data-driven remaining useful life prediction theory and applications for equipment[M]. Beijing:National Defense Industry Press,2016:159.(In Chinese), articleTitle=null, refAbstract=null), Reference(id=1241810843084587915, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2017, volume=354, issue=6, pageStart=2477, pageEnd=2499, url=null, language=null, rfNumber=[32], rfOrder=39, authorNames=ZHANG Z X, HU C H, SI X S, journalName=Journal of the Franklin Institute, refType=null, unstructuredReference=ZHANG Z XHU C HSI X Set al. Stochastic degradation process modeling and remaining useful life estimation with flexible random-effects[J]. Journal of the Franklin Institute2017354(6):2477-2499., articleTitle=Stochastic degradation process modeling and remaining useful life estimation with flexible random-effects, refAbstract=null), Reference(id=1241810843164279692, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2014, volume=84, issue=3, pageStart=545, pageEnd=563, url=null, language=null, rfNumber=[33], rfOrder=40, authorNames=WANG X L, GUO B, CHENG Z J, journalName=Journal of Statistical Computation and Simulation, refType=null, unstructuredReference=WANG X LGUO BCHENG Z J. Residual life estimation based on bivariate Wiener degradation process with time-scale transformations[J]. Journal of Statistical Computation and Simulation201484(3):545-563., articleTitle=Residual life estimation based on bivariate Wiener degradation process with time-scale transformations, refAbstract=null), Reference(id=1241810843227194253, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=4, pageStart=786, pageEnd=792, url=null, language=null, rfNumber=[34], rfOrder=41, authorNames=李博阳, 姚德臣, 刘恒畅, journalName=机械强度, refType=null, unstructuredReference=李博阳,姚德臣,刘恒畅,. 基于双向堆叠简单循环单元的滚动轴承寿命预测[J]. 机械强度202143(4):786-792., articleTitle=基于双向堆叠简单循环单元的滚动轴承寿命预测, refAbstract=null), Reference(id=1241810843298497422, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=4, pageStart=786, pageEnd=792, url=null, language=null, rfNumber=[34], rfOrder=42, authorNames=LI Boyang, YAO Dechen, LIU Hengchang, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=LI BoyangYAO DechenLIU Hengchanget al. Life prediction of rolling bearing based on bidirectional stacking simple recurrent unit[J]. Journal of Mechanical Strength202143(4):786-792.(In Chinese), articleTitle=Life prediction of rolling bearing based on bidirectional stacking simple recurrent unit, refAbstract=null), Reference(id=1241810843357217679, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2020, volume=69, issue=1, pageStart=401, pageEnd=412, url=null, language=null, rfNumber=[35], rfOrder=43, authorNames=WANG B, LEI Y G, LI N P, journalName=IEEE Transactions on Reliability, refType=null, unstructuredReference=WANG BLEI Y GLI N Pet al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J].IEEE Transactions on Reliability202069(1):401-412., articleTitle=A hybrid prognostics approach for estimating remaining useful life of rolling element bearings, refAbstract=null), Reference(id=1241810843420132240, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2021, volume=70, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[36], rfOrder=44, authorNames=MENG J D, YAN C F, CHEN G Y, journalName=IEEE Transactions on Instrumentation and Measurement, refType=null, unstructuredReference=MENG J DYAN C FCHEN G Yet al. Health indicator of bearing constructed by RMS-CUMSUM and GRRMD-CUMSUM with multifeatures of envelope spectrum[J]. IEEE Transactions on Instrumentation and Measurement202170:3510216., articleTitle=Health indicator of bearing constructed by RMS-CUMSUM and GRRMD-CUMSUM with multifeatures of envelope spectrum, refAbstract=null), Reference(id=1241810843478852497, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=8, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[37], rfOrder=45, authorNames=MENG J D, YAN C F, WEN T, journalName=Measurement Science and Technology, refType=null, unstructuredReference=MENG J DYAN C FWEN Tet al. Real-time identification of performance degradation stages of rolling element bearings by RVCFI[J]. Measurement Science and Technology202233(8):085021., articleTitle=Real-time identification of performance degradation stages of rolling element bearings by RVCFI, refAbstract=null), Reference(id=1241810843537572754, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=6, pageStart=165, pageEnd=171, url=null, language=null, rfNumber=[38], rfOrder=46, authorNames=王贡献, 张腾, 胡志辉, journalName=噪声与振动控制, refType=null, unstructuredReference=王贡献,张腾,胡志辉,. 基于RMS子线区间拟合法的轴承剩余寿命预测[J]. 噪声与振动控制202444(6):165-171., articleTitle=基于RMS子线区间拟合法的轴承剩余寿命预测, refAbstract=null), Reference(id=1241810843604681619, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=6, pageStart=165, pageEnd=171, url=null, language=null, rfNumber=[38], rfOrder=47, authorNames=WANG Gongxian, ZHANG Teng, HU Zhihui, journalName=Noise and Vibration Control, refType=null, unstructuredReference=WANG GongxianZHANG TengHU Zhihuiet al. Bearing residual life prediction based on RMS sublinear interval fitting method[J]. Noise and Vibration Control202444(6):165-171.(In Chinese), articleTitle=Bearing residual life prediction based on RMS sublinear interval fitting method, refAbstract=null), Reference(id=1241810843671790484, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, doi=null, pmid=null, pmcid=null, year=2014, volume=63, issue=1, pageStart=208, pageEnd=222, url=null, language=null, rfNumber=[39], rfOrder=48, authorNames=WANG Z Q, HU C H, WANG W B, journalName=IEEE Transactions on Reliability, refType=null, unstructuredReference=WANG Z QHU C HWANG W Bet al. An additive Wiener process-based prognostic model for hybrid deteriorating systems[J]. IEEE Transactions on Reliability201463(1):208-222., articleTitle=An additive Wiener process-based prognostic model for hybrid deteriorating systems, refAbstract=null)], funds=[Fund(id=1241810838579905378, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, awardId=62233017; 62373369; 62450056; 62373368, language=EN, fundingSource=National Natural Science Foundation of China(62233017; 62373369; 62450056; 62373368), fundOrder=null, country=null), Fund(id=1241810838630237027, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, awardId=62233017; 62373369; 62450056; 62373368, language=CN, fundingSource=国家自然科学基金项目(62233017; 62373369; 62450056; 62373368), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241810827364336384, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, xref=null, ext=[AuthorCompanyExt(id=1241810827372724993, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Rocket Force University of Engineering, Xi'an 710025, China), AuthorCompanyExt(id=1241810827376919298, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, companyId=1241810827364336384, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=火箭军工程大学,西安 710025)])], figs=[ArticleFig(id=1241810832204563258, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.1, caption=Degradation trajectories simulation-generated by the 1st group of parameters, figureFileSmall=TNIsveRJR1TQP38FtnBb3A==, figureFileBig=ZdA029H/CIcO16ZxeWA6Xg==, tableContent=null), ArticleFig(id=1241810833831953211, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图1, caption=基于第1组参数仿真生成的退化轨迹, figureFileSmall=TNIsveRJR1TQP38FtnBb3A==, figureFileBig=ZdA029H/CIcO16ZxeWA6Xg==, tableContent=null), ArticleFig(id=1241810833999725372, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.2, caption=Degradation trajectories simulation-generated by the 2nd group of parameters, figureFileSmall=/kjx1geAoBh1FzypQ2/sjA==, figureFileBig=iyZUca9JRZ1ryskumk2CMw==, tableContent=null), ArticleFig(id=1241810834066834237, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图2, caption=基于第2组参数仿真生成的退化轨迹, figureFileSmall=/kjx1geAoBh1FzypQ2/sjA==, figureFileBig=iyZUca9JRZ1ryskumk2CMw==, tableContent=null), ArticleFig(id=1241810834180080446, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.3, caption=Degradation trajectories simulation-generated by the 3rd group of parameters, figureFileSmall=vmZC5+FkReJgVB7seMRDGw==, figureFileBig=3LyjWwA+NePrAMDnXF2CBg==, tableContent=null), ArticleFig(id=1241810834263966527, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图3, caption=基于第3组参数仿真生成的退化轨迹, figureFileSmall=vmZC5+FkReJgVB7seMRDGw==, figureFileBig=3LyjWwA+NePrAMDnXF2CBg==, tableContent=null), ArticleFig(id=1241810834335269696, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.4, caption=Simulated and computed results under the 1st group of parameters, figureFileSmall=hNXxAcjjZymeJIwpz5lGHg==, figureFileBig=rUojronPg0bJf8odU8t/tQ==, tableContent=null), ArticleFig(id=1241810834494653249, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图4, caption=第1组参数下的仿真结果与计算结果, figureFileSmall=hNXxAcjjZymeJIwpz5lGHg==, figureFileBig=rUojronPg0bJf8odU8t/tQ==, tableContent=null), ArticleFig(id=1241810834628870978, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.5, caption=Simulated and computed results under the 2nd group of parameters, figureFileSmall=3Fq5Zq6GWPMom4JUkze6hg==, figureFileBig=d3r2iZZBvPa98+ii7xTRUQ==, tableContent=null), ArticleFig(id=1241810834821808963, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图5, caption=第2组参数下的仿真结果与计算结果, figureFileSmall=3Fq5Zq6GWPMom4JUkze6hg==, figureFileBig=d3r2iZZBvPa98+ii7xTRUQ==, tableContent=null), ArticleFig(id=1241810834888917828, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.6, caption=Simulated and computed results under the 3rd group of parameters, figureFileSmall=4pRvbYH256EYfNORXy+vpw==, figureFileBig=Dl16mJkLAxnu+Jm9WNBcYg==, tableContent=null), ArticleFig(id=1241810834968609605, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图6, caption=第3组参数下的仿真结果与计算结果, figureFileSmall=4pRvbYH256EYfNORXy+vpw==, figureFileBig=Dl16mJkLAxnu+Jm9WNBcYg==, tableContent=null), ArticleFig(id=1241810835077661510, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.7, caption=Probability density function of RUL without parameter updating, figureFileSmall=gzTfv3OA5/m9lQ50nyUBbQ==, figureFileBig=x4tLXFy7271hc9h+DR7TLQ==, tableContent=null), ArticleFig(id=1241810835153158983, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图7, caption=参数不更新时剩余使用寿命的概率密度函数, figureFileSmall=gzTfv3OA5/m9lQ50nyUBbQ==, figureFileBig=x4tLXFy7271hc9h+DR7TLQ==, tableContent=null), ArticleFig(id=1241810835241239368, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.8, caption=Probability density function of RUL with parameter updating, figureFileSmall=BNY3uBiXkXYf5w/xBOPonA==, figureFileBig=O4nq7IPmmaIvmyhfRqYnYg==, tableContent=null), ArticleFig(id=1241810835329319753, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图8, caption=参数更新时剩余使用寿命的概率密度函数, figureFileSmall=BNY3uBiXkXYf5w/xBOPonA==, figureFileBig=O4nq7IPmmaIvmyhfRqYnYg==, tableContent=null), ArticleFig(id=1241810835400622922, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.9, caption=Comparison of relative errors in RUL prediction without and with parameter updating, figureFileSmall=EFer+JTxw4YWkD2Xm53u/g==, figureFileBig=W+WewHp0iJQVcmt5Uf7X8A==, tableContent=null), ArticleFig(id=1241810835480314699, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图9, caption=参数更新前、后剩余使用寿命预测结果相对误差的对比, figureFileSmall=EFer+JTxw4YWkD2Xm53u/g==, figureFileBig=W+WewHp0iJQVcmt5Uf7X8A==, tableContent=null), ArticleFig(id=1241810835564200780, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.10, caption=Comparison of mean-squared errors in RUL prediction without and with parameter updating, figureFileSmall=Gr9o5cmnWiDoEXdI8HocTg==, figureFileBig=CPOYbt+hZlEA4aSyEFq3pg==, tableContent=null), ArticleFig(id=1241810835652281165, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图10, caption=参数更新前、后剩余使用寿命预测结果均方误差的对比, figureFileSmall=Gr9o5cmnWiDoEXdI8HocTg==, figureFileBig=CPOYbt+hZlEA4aSyEFq3pg==, tableContent=null), ArticleFig(id=1241810835727778638, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.11, caption=RMS curves of bearing vibration signal under working profile 1, figureFileSmall=viTZ1IVDO0XqwMf5QRUPng==, figureFileBig=oKQ4RMVyE+smYaQJ5awyQA==, tableContent=null), ArticleFig(id=1241810835803276111, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图11, caption=工况1下轴承振动信号的RMS曲线, figureFileSmall=viTZ1IVDO0XqwMf5QRUPng==, figureFileBig=oKQ4RMVyE+smYaQJ5awyQA==, tableContent=null), ArticleFig(id=1241810835878773584, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.12, caption=Shape similarity analysis of bearing degradation trajectories, figureFileSmall=CmGGDGTBZHyDvqPje0Dtfg==, figureFileBig=ztq/tZJ430NydJTabp8R/Q==, tableContent=null), ArticleFig(id=1241810835950076753, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图12, caption=轴承退化轨迹的形状相似度分析, figureFileSmall=CmGGDGTBZHyDvqPje0Dtfg==, figureFileBig=ztq/tZJ430NydJTabp8R/Q==, tableContent=null), ArticleFig(id=1241810836025574226, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.13, caption=Q-Q graphs of the increment of the bearing degradation, figureFileSmall=b570WK2X9+EpKvzyNGXnDw==, figureFileBig=uuv24i/vu2lFtUz1gibxRA==, tableContent=null), ArticleFig(id=1241810836084294483, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图13, caption=轴承退化量增量的Q-Q图, figureFileSmall=b570WK2X9+EpKvzyNGXnDw==, figureFileBig=uuv24i/vu2lFtUz1gibxRA==, tableContent=null), ArticleFig(id=1241810836147209044, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.14, caption=Convergence trajectories of partial parameters, figureFileSmall=Gdc0+5BG7dp3sWo2Zs+ykw==, figureFileBig=hjwDsqgVo9iHtMsnfDmHXg==, tableContent=null), ArticleFig(id=1241810836210123605, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图14, caption=部分参数的收敛轨迹, figureFileSmall=Gdc0+5BG7dp3sWo2Zs+ykw==, figureFileBig=hjwDsqgVo9iHtMsnfDmHXg==, tableContent=null), ArticleFig(id=1241810836273038166, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.15, caption=Predicted results of RUL of the bearing, figureFileSmall=ZUuxa8Wd9R2kgN9nCCljBQ==, figureFileBig=E4CTV8N9VWoaqoN0USQu7w==, tableContent=null), ArticleFig(id=1241810836361118551, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图15, caption=轴承的剩余使用寿命预测结果, figureFileSmall=ZUuxa8Wd9R2kgN9nCCljBQ==, figureFileBig=E4CTV8N9VWoaqoN0USQu7w==, tableContent=null), ArticleFig(id=1241810836415644504, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.16, caption=Predicted results of RUL based on M1 model, figureFileSmall=e9jtY9W9w4VeZGSY6HmvXg==, figureFileBig=3CtgJbnCbQi+c1io1oyBWg==, tableContent=null), ArticleFig(id=1241810836465976153, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图16, caption=基于模型M1的剩余使用寿命预测结果, figureFileSmall=e9jtY9W9w4VeZGSY6HmvXg==, figureFileBig=3CtgJbnCbQi+c1io1oyBWg==, tableContent=null), ArticleFig(id=1241810836537279322, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Fig.17, caption=Predicted results of RUL based on M2 model, figureFileSmall=T285BSaps3Y1kKapxn2hPw==, figureFileBig=ZMEdQCZTDp3TPWHr7EYiiQ==, tableContent=null), ArticleFig(id=1241810836600193883, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=图17, caption=基于模型M2的剩余使用寿命预测结果, figureFileSmall=T285BSaps3Y1kKapxn2hPw==, figureFileBig=ZMEdQCZTDp3TPWHr7EYiiQ==, tableContent=null), ArticleFig(id=1241810836663108444, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Tab.1, caption=

Model parameters and their estimation results

, figureFileSmall=null, figureFileBig=null, tableContent=
bcμλ1fgμλ2σλ1σλ2σλ1λ2σB
第1组参数
1st group of parameters
真实值True value0.200 020.000 020.000 00.015 00.000 01.500 00.050 00.005 00.000 10.800 0
估计值Estimation value0.203 020.358 822.198 60.017 80.002 51.542 10.059 70.005 30.000 10.791 1
相对误差Relative error/%1.501.7910.9918.672.8119.406.000.001.11
第2组参数
2nd group of parameters
真实值True value0.250 030.000 050.000 00.015 00.000 010.000 00.100 00.100 00.000 12.000 0
估计值Estimation value0.250 530.051 458.621 00.017 5-0.071 510.290 00.118 80.101 70.000 11.986 1
相对误差Relative error/%0.200.1717.2416.672.9018.801.700.000.70
第3组参数
3rd group of parameters
真实值True value0.200 010.000 050.000 00.005 00.200 030.000 00.100 00.100 00.001 00.800 0
估计值Estimation value0.196 110.500 559.357 80.005 90.231 732.010 60.116 30.102 60.001 10.810 0
相对误差Relative error/%1.955.0118.7218.0015.856.7016.302.6010.001.25
), ArticleFig(id=1241810836721828701, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=表1, caption=

模型参数及其估计结果

, figureFileSmall=null, figureFileBig=null, tableContent=
bcμλ1fgμλ2σλ1σλ2σλ1λ2σB
第1组参数
1st group of parameters
真实值True value0.200 020.000 020.000 00.015 00.000 01.500 00.050 00.005 00.000 10.800 0
估计值Estimation value0.203 020.358 822.198 60.017 80.002 51.542 10.059 70.005 30.000 10.791 1
相对误差Relative error/%1.501.7910.9918.672.8119.406.000.001.11
第2组参数
2nd group of parameters
真实值True value0.250 030.000 050.000 00.015 00.000 010.000 00.100 00.100 00.000 12.000 0
估计值Estimation value0.250 530.051 458.621 00.017 5-0.071 510.290 00.118 80.101 70.000 11.986 1
相对误差Relative error/%0.200.1717.2416.672.9018.801.700.000.70
第3组参数
3rd group of parameters
真实值True value0.200 010.000 050.000 00.005 00.200 030.000 00.100 00.100 00.001 00.800 0
估计值Estimation value0.196 110.500 559.357 80.005 90.231 732.010 60.116 30.102 60.001 10.810 0
相对误差Relative error/%1.955.0118.7218.0015.856.7016.302.6010.001.25
), ArticleFig(id=1241810838202418014, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Tab.2, caption=

Prediction results of RUL under different parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
均方误差
Mean-squared error
相对误差
Relative error/%
不更新
Without update
更新后
With update
不更新
Without update
更新后
With update
第1组参数
1st group of parameters
83.888 063.351 36.165 31.916 8
第2组参数
2nd group of parameters
80.934 051.773 38.593 82.965 4
第3组参数
3rd group of parameters
86.347 955.095 16.942 52.146 9
), ArticleFig(id=1241810838286304095, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=表2, caption=

不同参数下剩余使用寿命的预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
均方误差
Mean-squared error
相对误差
Relative error/%
不更新
Without update
更新后
With update
不更新
Without update
更新后
With update
第1组参数
1st group of parameters
83.888 063.351 36.165 31.916 8
第2组参数
2nd group of parameters
80.934 051.773 38.593 82.965 4
第3组参数
3rd group of parameters
86.347 955.095 16.942 52.146 9
), ArticleFig(id=1241810838370190176, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=EN, label=Tab.3, caption=

Parameter estimation and RUL prediction results for bearings under different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型ModelsμaσaσBbcμλ1fgμλ2σλ1
M00.212 4-0.084 04.977 8-0.684 60.108 40.000 00.000 00.073 4
M10.958 20.019 60.237 00.014 4
M20.000 20.000 10.238 02.095 5
模型Modelsσλ2σλ1λ2Er(25%)Er(50%)Er(75%)Er(90%)Ems(25%)Ems(50%)Ems(75%)Ems(90%)
M00.000 00.000 210.26%15.30%18.77%19.89%190.877 3183.072 4126.756 9108.009 3
M121.62%45.77%60.60%74.61%905.796 91 121.340 3712.832 4857.608 1
M222.67%49.22%65.98%79.30%1 142.238 91 422.247 2911.161 31 139.932 5
), ArticleFig(id=1241810838445687649, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241686768404197594, language=CN, label=表3, caption=

不同模型下轴承的参数估计与剩余使用寿命的预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型ModelsμaσaσBbcμλ1fgμλ2σλ1
M00.212 4-0.084 04.977 8-0.684 60.108 40.000 00.000 00.073 4
M10.958 20.019 60.237 00.014 4
M20.000 20.000 10.238 02.095 5
模型Modelsσλ2σλ1λ2Er(25%)Er(50%)Er(75%)Er(90%)Ems(25%)Ems(50%)Ems(75%)Ems(90%)
M00.000 00.000 210.26%15.30%18.77%19.89%190.877 3183.072 4126.756 9108.009 3
M121.62%45.77%60.60%74.61%905.796 91 121.340 3712.832 4857.608 1
M222.67%49.22%65.98%79.30%1 142.238 91 422.247 2911.161 31 139.932 5
)], attaches=null, journal=Journal(id=1227999351742652416, delFlag=0, nameCn=机械强度, nameEn=Journal of Mechanical Strength, nameHistory1=null, nameHistory2=null, issn=1001-9669, eissn=null, cn=41-1134/TH, coden=null, periodic=0, language=CN, oaType=null, 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=9ETNXOzwmuGm49pLRqXxWw==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Mechanical Strength, journalRemark=null, publicationField=null, createdTime=1770707460585, updatedTime=1770707700588, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=9ETNXOzwmuGm49pLRqXxWw==, picEn=sS2ogjwdwM8GMbFtuWTIkA==, jcr=null, cjcr=null, exts=[JournalExt(id=1228000358505578506, language=CN, name=机械强度, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770707700611, updatedTime=1770707700611, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=aa1eff81-489d-4951, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=df5d5e38-1d45-4fcd-b, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=49f73d27-439e-4d5b, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1228000358551715851, language=EN, name=Journal of Mechanical Strength, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770707700622, updatedTime=1770707700622, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=aa1eff81-489d-4951, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=df5d5e38-1d45-4fcd-b, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=49f73d27-439e-4d5b, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1227999626482147330, websiteList=[Website(id=1228000871984853626, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227999626482147330, 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/jxqd/CN, language=CN, createTime=1770707823034, createBy=18614031015, updateTime=1770707851936, updateBy=18614031015, name=机械强度-中文, tplId=1146099689490845704, title=机械强度, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001259580486284, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=articleTextType, value=kx, createTime=1770707915444, updateTime=1770707915444, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259555320457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=banner, value=null, createTime=1770707915438, updateTime=1770707915438, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259605652111, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=grayFlag, value=0, createTime=1770707915450, updateTime=1770707915450, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259542737544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=logo, value=https://castjournals.cast.org.cn/joweb/jxqd/CN/file/pic?fileId=wrginrTxTIens2Yn6gXaKA==, createTime=1770707915435, updateTime=1770707915435, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259622429329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=minRunFlag, value=0, createTime=1770707915454, updateTime=1770707915454, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259572097675, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jxqd/CN/file/pic, createTime=1770707915442, updateTime=1770707915442, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259614040720, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=silenceFlag, value=0, createTime=1770707915452, updateTime=1770707915452, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259567903370, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770707915441, updateTime=1770707915441, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259588874893, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=themeColor, value=null, createTime=1770707915446, updateTime=1770707915446, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259597263502, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=themeStyle, value=null, createTime=1770707915448, updateTime=1770707915448, creator=18614031015, updator=18614031015)]), Website(id=1228000872056156796, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227999626482147330, 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/jxqd/EN, language=EN, createTime=1770707823051, createBy=18614031015, updateTime=1770707871019, updateBy=18614031015, name=机械强度-英文, tplId=1146101810881728533, title=Journal of Mechanical Strength, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001314525868694, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=articleTextType, value=kx, createTime=1770707928544, updateTime=1770707928544, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314504897171, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=banner, value=null, createTime=1770707928539, updateTime=1770707928539, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314542645913, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=grayFlag, value=0, createTime=1770707928548, updateTime=1770707928548, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314496508562, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=logo, value=https://castjournals.cast.org.cn/joweb/jxqd/EN/file/pic?fileId=wrginrTxTIens2Yn6gXaKA==, createTime=1770707928537, updateTime=1770707928537, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314555228827, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=minRunFlag, value=0, createTime=1770707928551, updateTime=1770707928551, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314517480085, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jxqd/EN/file/pic, createTime=1770707928542, updateTime=1770707928542, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314551034522, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=silenceFlag, value=0, createTime=1770707928550, updateTime=1770707928550, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314513285780, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770707928541, updateTime=1770707928541, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314530062999, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=themeColor, value=null, createTime=1770707928545, updateTime=1770707928545, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314538451608, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=themeStyle, value=null, createTime=1770707928547, updateTime=1770707928547, creator=18614031015, updator=18614031015)])], journalTitle=机械强度, weixinUrl=null, journalUrl=https://www.jxqd.net.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Mechanical Strength, journalPhotoCn=9ETNXOzwmuGm49pLRqXxWw==, journalPhotoEn=sS2ogjwdwM8GMbFtuWTIkA==, 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=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/jxqd/CN/10.16579/j.issn.1001.9669.2025.09.022, detailUrlEn=https://castjournals.cast.org.cn/joweb/jxqd/EN/10.16579/j.issn.1001.9669.2025.09.022, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jxqd/CN/PDF/10.16579/j.issn.1001.9669.2025.09.022, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jxqd/EN/PDF/10.16579/j.issn.1001.9669.2025.09.022, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于非线性Wiener过程的多模式随机退化设备剩余使用寿命预测方法
收藏切换
PDF下载
李梦草 , 张正新 , 司小胜 , 冯磊 , 张建勋
机械强度 | 2025,47(9): 221-232
收起
收藏切换
机械强度 | 2025, 47(9): 221-232
基于非线性Wiener过程的多模式随机退化设备剩余使用寿命预测方法
全屏
李梦草 , 张正新 , 司小胜, 冯磊, 张建勋
作者信息
  • 火箭军工程大学,西安 710025
  • 李梦草,女,1999年生,河南开封人,在读硕士研究生;主要研究方向为随机退化系统剩余寿命预测与健康管理;E-mail:

通讯作者:

张正新,男,1987年生,云南曲靖人,博士;主要研究方向为随机退化系统剩余寿命预测与健康管理;E-mail:
Nonlinear-Wiener-process-based remaining useful life prediction method for stochastic deteriorating devices with multiple modes
Mengcao LI , Zhengxin ZHANG , Xiaosheng SI, Lei FENG, Jianxun ZHANG
Affiliations
  • Rocket Force University of Engineering, Xi'an 710025, China
出版时间: 2025-09-15 doi: 10.16579/j.issn.1001.9669.2025.09.022
文章导航
收藏切换

多模式随机退化设备剩余使用寿命(Remaining Useful Life,RUL)预测的难点在于建立一类能够刻画多种不同退化模式的随机退化模型,并求解多模式随机退化模型下设备的RUL分布。首先,建立了一类基于非线性Wiener过程的一般化随机退化模型,实现了多模式随机退化过程统一刻画。其次,提出了基于同类设备历史退化数据的模型参数极大似然估计(Maximum Likelihood Estimation,MLE)方法。再次,推导了首达时间意义下多模式随机退化设备RUL分布的概率密度函数(Probability Density Function,PDF)的解析近似解。最后,构建了模型参数更新的序贯贝叶斯架构,实现了在役设备RUL的在线预测。数值仿真分析及轴承RUL预测的应用实例表明,所提方法能够有效建模随机退化设备的多模式随机退化过程,并准确预测设备的RUL,为系统后续的维修决策提供预测信息依据。

预测与健康管理  /  剩余使用寿命预测  /  多模式退化建模  /  非线性维纳过程  /  可靠性

The challenge in predicting the remaining useful life (RUL) of multi-mode stochastic degradation equipment lies in establishing a class of stochastic degradation models capable of characterizing multiple distinct degradation modes and deriving the remaining useful life distribution of the equipment under such multi-mode stochastic degradation models.First, a generalized stochastic degradation model based on the nonlinear Wiener process was developed, achieving a unified characterization of multi-mode stochastic degradation processes. Second, a maximum likelihood estimation (MLE) method for model parameters was proposed, utilizing historical degradation data from similar equipment. Third, an analytical approximate solution for the probability density function (PDF) of the remaining useful life distribution of multi-mode stochastic degradation equipment was derived under the first hitting time (FHT) framework. Finally, a sequential Bayesian framework for model parameter updating was constructed, enabling online prediction of the remaining useful life of in-service equipment.Numerical simulation analyses and an application case study on bearing remaining useful life prediction demonstrate that the proposed method can effectively model the multi-mode stochastic degradation processes of stochastic degradation equipment and accurately predict the remaining useful life, thereby providing predictive information to support subsequent maintenance decision-making for the system.

Prognostics and health management  /  Remaining useful life prediction  /  Multiple modes degradation modeling  /  Nonlinear Wiener process  /  Reliability
李梦草, 张正新, 司小胜, 冯磊, 张建勋. 基于非线性Wiener过程的多模式随机退化设备剩余使用寿命预测方法. 机械强度, 2025 , 47 (9) : 221 -232 . DOI: 10.16579/j.issn.1001.9669.2025.09.022
Mengcao LI, Zhengxin ZHANG, Xiaosheng SI, Lei FENG, Jianxun ZHANG. Nonlinear-Wiener-process-based remaining useful life prediction method for stochastic deteriorating devices with multiple modes[J]. Journal of Mechanical Strength, 2025 , 47 (9) : 221 -232 . DOI: 10.16579/j.issn.1001.9669.2025.09.022
航空航天、轨道交通、能源动力、国防武器等领域的设备对保障国家经济发展和国家安全意义重大。在运行过程中,这些设备会因受到磨损、冲击、外界环境等因素的影响而不可避免地发生性能退化,并逐步累积引发失效[1-3]。这种在外界环境和内部损耗作用下逐渐失效的设备一般称之为随机退化设备。工程实际中随机退化设备的失效特别是突发失效,极有可能导致事故发生,造成不可估量的经济损失和难以挽回的后果。例如,2019年3月,美国西南航空公司1380次航班一架飞机因发动机叶片疲劳断裂导致飞行途中左侧引擎突然爆炸,导致乘客1人死亡,7人受伤。若能够在随机退化设备性能退化早期,尤其在尚未造成重大危害时,对运行设备的各项数据进行监测,根据状态监测信息及时发现异常或者定时对设备的健康状态进行评估,预测设备的剩余使用寿命(Remaining Useful Life, RUL),进而针对性地采取防控措施,即应用预测与健康管理(Prognostics and Health Management, PHM)技术,就能有效预防与避免灾难性事故的发生,降低设备的运维成本[4-5]
RUL预测作为连接设备状态感知与健康管理优化的核心,能为设备后续健康管理活动提供理论依据和信息支撑,是PHM中的一项关键技术,已成为可靠性领域研究的热点问题。根据技术路径的区别,可将已有随机退化设备RUL预测方法分为基于机制模型的方法[6]、数据驱动的方法[7-8]及机制-模型融合的方法[9-10]。随着工业设备及其部件日趋复杂,其失效机制模型难以建立,而设备监测数据获取技术以及人工智能的发展,为数据驱动的RUL预测方法提供了数据和模型支撑,让数据驱动装备RUL预测方法成为主流。其中,基于机器学习的方法通常只能得到设备RUL的点估计结果,不能有效表征预测结果的不确定性;相比之下,以概率论与随机过程为基础的统计数据驱动方法可解释性强,可以提供表征RUL预测结果的不确定性的概率分布,从而匹配以评估设备运行随机失效风险为基础的健康管理优化决策体系。基于Wiener过程的随机退化设备RUL预测方法是统计数据驱动方法的典型代表,适用于非单调随机退化设备,近年来得到广泛的关注及应用[11-12]。基于Wiener过程的退化建模的关键是确定漂移系数和扩散系数的函数形式。在退化过程呈线性退化特性时,通常假设漂移系数和扩散系数是固定的。SI等[13]使用线性Wiener过程退化模型,基于贝叶斯推断和期望最大化算法,将测量误差视为不确定性的一个来源,得到了RUL的闭式解析概率密度函数(Probability Density Function, PDF)。线性模型实现了预测过程中不确定性的有效降低。GEBRAEEL等[14]、HUANG等[15]分别通过线性化指数模型、时间尺度变换,SI等[16]通过Box-Cox变换,将设备的退化转换为线性Wiener过程。但是,对于无法线性化的随机退化过程,选择合适的漂移系数和扩散函数是退化建模的重要任务。YU等[17]开发了一个考虑三源不确定性的通用非线性Wiener过程模型,推导了RUL的PDF,并计算了估计的RUL。SI等[18]56提出了漂移系数为指数函数和幂函数的非线性Wiener过程模型。多阶段Wiener过程的退化模型也受到了广泛关注。ZHANG等[19]提出了一种新的基于两阶段的Wiener过程模型,并充分考虑了变点退化状态的不确定性,得到了RUL分布的显示表达式。WEN等[20]提出了一种贝叶斯多阶段建模方法,将多阶段模型转化为新的状态空间模型,从而进行后续的RUL预测。对于采用常见函数形式的漂移系数难以表征的退化过程,CHEN等[21]首先使用长短期记忆(Long Short-Term Memory, LSTM)网络学习退化趋势函数,然后采用迁移学习框架在线更新原始网络。
设备的退化过程通常由特定形式的性能退化趋势曲线来表征。本文将设备某类特定形式的退化过程称为一种退化模式。受设备个体差异性、工作环境改变等内、外部因素的影响,同类设备可能会呈现出不同类型的退化轨迹,这类设备称为多模式随机退化设备。例如,文献[22-23]中的线性退化模型描述的退化过程具有线性退化模式;文献[18]56中的指数和幂函数退化模型描述的退化过程具有指数与幂函数退化模式;文献[24]中的多阶段退化模型,描述的退化过程具有多阶段随机退化模式。生产过程导致的个体差异以及服役过程中载荷环境的不同,同类设备不同个体的退化过程常具有不同形式的退化趋势曲线,呈复杂的多模式退化特性。MELCHERS[25]研究了金属合金的腐蚀退化过程,发现不同工作条件下,合金腐蚀退化随暴露时间呈现出线性、非线性凸函数、非线性凹函数、先线性后非线性、先非线性后线性、先凸函数后凹函数等多种不同的退化模式;WANG等[26]研究了滚动轴承的退化过程,发现滚动轴承的退化是内圈、外圈、滚子、保持架、润滑油等多个零件共同相互作用的结果,不同零件对整体性能退化贡献不同,导致同类轴承不同个体的退化趋势具有明显不同的阶段特征和退化模式差异。然而,现有设备退化过程模型通常针对单一的退化模式,特别是基于Wiener过程建模的方法,难以对设备的多模式随机退化过程进行描述,相应的模型和方法不能直接用于多退化模式下的设备退化过程建模与RUL预测。因此,亟须开展多模式随机退化设备RUL预测方法研究。
多模式随机退化设备RUL预测的难点在于建立一类同时能够刻画多种不同随机退化模式的随机退化模型,并求解多模式随机退化模型下设备的RUL分布。为此,本文首先基于非线性Wiener过程构建了一类多模式随机退化过程模型,在非线性Wiener过程模型的基础上,引入了基于Sigmoid函数的退化趋势函数校准项,通过改变Sigmoid函数的参数,实现设备不同模式退化过程的一般化描述,并分别通过固定参数与随机参数刻画同类设备的共性退化特征与单个设备的个性退化特征;其次,提出了基于同类设备历史退化数据的模型参数极大似然估计(Maximum Likelihood Estimation, MLE)方法,实现了模型固定参数以及随机参数先验分布的估计;之后,推导了首达时间(First Hitting Time, FHT)意义下多模式随机退化设备寿命及RUL分布的PDF的解析近似解,并构建了模型参数更新的序贯贝叶斯架构,实现了在役设备退化模型参数以及RUL分布的高效在线更新。最后,通过数值仿真以及轴承RUL预测的应用实例对所提方法的有效性进行了验证。
本文结构如下:第1节给出了多模式随机退化过程建模的整体思路;第2节介绍了基于同类设备历史退化数据的模型固定参数与先验分布超参数估计方法,以及基于在役设备状态监测数据的随机参数在线序贯贝叶斯更新方法;第3节推导了FHT意义下设备RUL分布的PDF,以及基于序贯贝叶斯更新的多模式随机退化设备RUL在线预测结果;第4节分别通过数值仿真与轴承RUL预测的应用实例对所提方法进行说明与验证;第5节对全文进行了总结,并梳理了下一步可能的研究方向。
由于Wiener过程可实现对非单调性过程的退化描述,所以本文考虑基于非线性Wiener过程建立一般化的多模式随机退化过程模型。具体的,令设备在t时刻的退化量为X(t),则设备的非线性随机过程{X(t);t≥0}可描述为
式中,a为设备的初始退化水平,为不失一般性,令a=0;μ(τθ)为漂移系数函数,表示退化的确定性趋势;θ为漂移系数函数的参数向量;σB为扩散系数,表示随机性水平;B(t)为标准布朗运动(Standard Brownian Motion, SBM)的变化量,t≥0。
退化过程{X(t);t≥0}是由标准布朗运动{B(t);t≥0}驱动的随机过程,用于刻画设备退化的时变随机动态。μ(τθ)是时间t的非线性函数,用于表征模型的时变特征。当选择不同形式的函数时,μ(τθ)可以描述不同的随机退化模式。在现有的模型中,通常将μ(τθ)设置为固定参数、幂函数、指数函数等,分别用于描述线性与非线性随机退化模型。其中,指数形式的漂移系数函数在轴承[27]、惯性导航设备[28]、锂离子电池[29-30]等设备中有着广泛的应用。因此,本文基于指数非线性Wiener过程模型进行多模式随机退化过程建模和RUL预测。
为便于描述设备可能出现的多种退化过程,本文采用如式(2)所示的退化模型,为
式中,λT=[dh];指数项[h exp(ft+g)]用于描述模型的迅速增长趋势,其中,h为快速增长的幅值;f为快速增长的速率;g为快速增长的起始时刻;修正项{d[1+exp(-bt+c)]-1}基于Sigmoid函数曲线独特的S形特征可以灵活地表示设备的局部线性与非线性退化趋势,其中,d为修正模式的最大幅值;b为局部退化速率;c为退化模式修正起始时间。
该退化模型结合了指数函数刻画非线性随机退化过程优势和Sigmoid函数的S形特性,通过合适的模型参数设置,即可实现多模式随机退化过程的描述。仿真试验中将对此进行详细说明。
注解1.1 所提模型主要针对的是呈非线性退化趋势的多模式随机退化设备,若需考虑线性退化趋势,可将描述快速增长趋势的指数非线性项{h exp(ft+g)}替换为幂函数htf,即
若替换后的模型[式(4)]中参数满足d=0、h≠0、 f=1,则可用于描述具有线性趋势的随机退化过程。式(2)对应的漂移系数函数可表示为
式中,f(tθ)为f(tθ)关于时间t的导数,可表示为
由于制造过程中材料、工艺等的非一致性,以及工作载荷、工作环境等方面的差异,设备的退化过程经常呈现一定的个体差异性。为此,进一步假设模型[式(2)]中的参数λ为随机参数,描述设备退化的个体差异性。本文中,为便于计算,假设参数λ服从均值为μλ,协方差矩阵为Σλ的二元正态分布,即λ~NBV(μλΣλ)。同时,令模型参数向量θ=[bcfg]及扩散系数σB为固定的常数,表示同类设备的相似退化特性。
第1节建立的基于非线性Wiener过程的多模式随机退化模型中,漂移系数函数中的固定参数θ=[bcfg]、参数向量λ的分布参数μλΣλ,以及扩散系数σB都是未知的。本节探讨基于同类设备历史退化数据的模型参数估计方法,以及基于服役设备状态监测数据的参数贝叶斯更新方法。为简化符号,将所有待估计的符号记为Θ={μλΣλθσB}。
假设共有来自N个设备的状态监测数据,第i个设备在第j个时刻tij的状态监测数据为xij。根据式(2)定义的退化模型可知
进一步,令为第i个设备所有的状态监测数据,其中,mi表示第i个设备退化监测总次数,并将所有同类个体设备的历史退化数据记为X={x1x2,…,xN}表示所有状态监测数据的集合。不失一般性,假定不同设备间状态监测数据相互独立。根据SBM和正态分布的性质,第i个设备的状态监测数据xi服从多元正态分布xiNMV(μiΣi),且其均值μi和协方差矩阵Σi分别为
其中,
式中,均值向量μi为参数μλθ的函数;协方差矩阵Σi为参数Σλθ的函数。
进而,给定全部N个设备的历史状态监测数据X后,未知参数Θ的对数似然函数可表示为
极大化式(10)中的对数似然函数,即可得参数Θ的估计值,即
然而,对数似然函数(Θ|X)中未知参数较多,难以通过常见优化算法直接高效计算。为此,进一步令(Θ|X)对于μλ求取一阶偏导数,即
若给定ΣλθσB,令式(12)中的偏导数为零,并求解所得方程,即可得到μλ的MLE结果,即
式(13)表明,可由Θ中的其他参数进行完全表示。为此,将式(13)代入式(10),可得关于参数ΣλθσB的剖面似然函数,即
通过极大化式(14)中的剖面似然函数,可以得到ΣλθσB的MLE结果。剖面似然函数的极大化通常通过单纯形法、智能优化等常见优化算法实现。进一步,将代入式(13),即可直接得到。这样就得到了表征同类设备共性退化特征的模型参数的估计值,以及表示设备退化个体差异性的参数
当所有设备的状态监测数据的监测时刻和监测数目的大小都相同时,意味着miFiΣi不再与设备编号有关,记mi=mFi=FΣi=Σ,则式(14)可变为
此时,有
式中,
注解2.1 为了避免模型复杂度过高、数据误差较大等因素导致的过拟合问题,一方面可以通过赤池准则(Akaike Information Criteria, AIC)或贝叶斯信息准则(Bayesian Information Criteria, BIC)对模型进行优选;另一方面,可以在模型参数估计过程中,考虑增加关于线性可加模型全体参数Θ2范数正则化项2(Θ)或系数λ1范数正则化项1(λ),即通过式(17)进行参数估计,即
式中,γ1γ2为超参数,可通过交叉验证确定。
如前文所述,设备的随机退化过程存在一定的个体差异性。为提高服役设备退化建模与RUL预测的准确性,本小节中将第2.1节中基于同类设备历史退化数据得到的随机向量λ所服从的分布作为先验分布,并通过服役设备在线监测数据对随机参数向量λ进行在线贝叶斯更新。其中,λ=[λ1λ2]T的均值和协方差矩阵可分别表示为,且σλ1λ2σλ2λ1相等。
为统一符号,假设随机参数向量λ的先验分布是二元正态分布NBV(μλ,0Σλ,0),其中,。同时,对于服役个体设备,令截止至tk时刻所有状态监测数据为x1:k=[x1x2,…,xk]T。根据贝叶斯定理以及正态分布的性质,给定x1:k和先验分布p(λ)后,随机参数向量λ的后验分布p(λ|x1:k)仍为二元正态分布,且其均值向量和协方差矩阵分别为
式中,Σ1:k分别为
从式(18)、式(19)中的参数贝叶斯更新结果可以看出,每当有新的状态监测数据可用时,需要基于截至当前时刻tk所有的状态监测数据x1:k,以及对应的Σ1:k去计算随机参数的后验分布参数μλkΣλk。随着设备状态监测数据的累积,Σ1:k的维度将随之不断增加,这将增加中矩阵求逆的难度,影响参数更新的效率。对于状态监测数据较多的设备,可采用序贯贝叶斯的思路提高参数更新的速度和精度。
根据贝叶斯公式,可知
式中,p(xk|x1:k-1λ)为给定x1:k-1λ条件下xk的概率分布;p(λ|x1:k-1)为给定x1:k-1条件下λ的后验分布。本质上,式(20)刻画了tk-1tk这2个连续状态监测时刻下参数后验估计的递归关系。根据式(1)所定义的基于非线性Wiener过程模型的性质,可知p(xk|x1:k-1λ)为正态分布,且其均值和方差分别为xk-1+λTΔfk,其中Δfk=f(tkθ)-f(tk-1θ),Δtk=tk-tk-1
由正态分布的共轭性质可知,任何时刻λ的后验分布均为二元正态分布。记tk-1时刻x1:k-1给定条件下和tk时刻在x1:k给定条件下λ的后验均值和后验协方差矩阵分别为μλk-1Σλk-1以及μλkΣλk。则μλkΣλkμλk-1Σλk-1的关系可由定理2.1给出。
定理2.1 对于服役设备来说,截止到当前时刻tk已测量到k个状态监测数据x1:k,则基于x1:k,模型[式(2)]中随机参数λ后验分布的均值和协方差矩阵更新为
基于定理2.1,一旦得到新的状态监测数据,就可以更新设备退化模型的随机向量λ。序贯贝叶斯公式保证了随机参数更新依赖于截至当前时刻所有的状态监测数据,有助于提高RUL预测的准确性。需要说明的是,选择二元正态分布作为先验分布是出于其适用范围与计算效率的考虑,根据实际需要,也可以构建其他形式先验分布。
虽然设备的退化轨迹会呈现不同类型的趋势,即具有不同的退化模式,但大部分文献认为设备失效统一表现为其退化量超过固定预设的失效阈值。因此,本文主要针对单一的失效模式,即单个确定失效阈值定义设备的失效和预测设备的RUL。通常情况下,通过设备首次达到失效阈值的时间来定义设备的寿命,能够保证设备的安全性与寿命预测的准确度。为此,本文基于首达时间概念对寿命以及RUL进行定义。具体地,将设备的寿命T定义为
相应地,将设备tk时刻的剩余寿命Lk定义为
式中,tlk分别为随机变量TLk的一个实现;ω为失效阈值,一般可根据设计指南、工业标准与设备历史运行情况获得。
通过上述定义,基于随机退化过程预测设备RUL的关键在于求解寿命T的PDF,即fT(t),进而实现对剩余寿命Lk的概率分布的预测。为此,给出引理3.1。
引理3.1[31] 对于随机退化过程{X(t);t≥0},若μ(tθ)是时间t的连续函数,则{X(t);t≥0}首达失效阈值ω时间的PDF可表示为
式中,SB(t)是标准布朗运动过程{B(t);t≥0}的首达时变边界,即
基于引理3.1,可以对模型[式(2)]描述的随机退化设备的寿命分布的PDF进行求解。不考虑设备随机退化的个体差异时,若设备的退化过程由式(2)描述的随机退化过程{X(t);t≥0}表征,则首达时间意义下设备的寿命分布的PDF计算式为
考虑tk时刻设备RUL分布的PDF的求解问题。若tk时刻设备的退化水平为xk,由SBM过程的马尔科夫特性,对于任意ttk,设备退化可表示为
此时,若t为{X(t);t≥0}首达失效阈值的时间,则t-tk即为设备tk时刻的RUL。引入变换lk=t-tk,则Z(lk)=X(lk+tk)-xk也是一个随机过程,且其演化规律为
因此,tk时刻设备的RUL等于随机过程{Z(lk);lk≥0}首达阈值ωk=ω-xk的时间。对于{Z(lk);lk≥0},有
式中,f(lk+tkθ)对变量lk的偏导数。
基于引理3.1,若tk时刻设备的退化状态为xk,则由模型[式(2)]所描述随机退化设备此时的RUL分布的PDF可表示为
式中,ωk=ω-xkη(lk)=λT[f(lk+tkθ)-f(tkθ)]。
以上寿命和RUL分布结果未考虑设备随机退化的个体差异性,通常基于同类设备的历史退化数据估计模型参数,不能保证模型与服役设备状态监测数据的匹配。本节进一步探讨服役设备RUL的在线预测方法,即求解给定状态监测数据X1:k后设备寿命与RUL的条件概率分布
根据第2.2节中的结论可知,p(λ|x1:k)为均值与协方差矩阵分别为μλ,kΣλ,k的二元正态分布λ|x1:kNBV(μλ,kΣλ,k)。为方便推导寿命和RUL的PDF解析形式,给出引理3.2。
引理3.2[32] 令随机向量ρ服从均值和协方差矩阵为μρΣρn元正态分布,ρNMV(μρΣρ),v1v2c均为给定常值,abn维列向量,关于随机向量ρ的函数,有
式中,Eρ(·)为对随机变量ρ取期望;I为单位阵,且满足IRn×n
利用引理3.2,设备的寿命T与剩余寿命Lk的PDF可分别按照定理3.1和定理3.2进行求解。
定理3.1 对于式(2)刻画的随机退化过程{X(t);t≥0},使用λT=[dh]表示同类设备个体间的差异性,此时设备首达时间意义下的寿命分布的PDF的计算式为
式中,aT=[f(tθ)-t f(tθ)]T
将式(27)代入引理3.2,即可证明定理3.1。
定理3.2 若设备tk时刻的退化状态为xk,则由模型[式(2)]所描述随机退化设备的此时的RUL分布的PDF可表示为
式中,f*(lkθ)可由f*(lkθ)=f(tk+lkθ)-f(tkθ)计算,且
利用第2节的方法得到了θσB的离线估计结果,并根据式(21)、式(22)在线更新μλkΣλk后,即可分别根据式(33)、式(34)实现设备寿命与RUL的更新。
为展示所提退化模型刻画多模式随机退化过程的能力,首先基于欧拉离散化方法,在不同参数设置下近似产生退化轨迹{X(t);t≥0}。欧拉离散化的具体表达式[33]
式中,xk+1=X[(k+1)Δt];xk=X(kΔt);Δt为离散化步长;Y~N(0,1)。
令Δt=1,分别用表1所列3组不同参数值生成10组长度为250的退化轨迹,结果依次如图1~图3所示。由图1~图3可知,不同参数下,退化轨迹的趋势差异显著。可见,本文提出的模型能够很好地对设备的多模式退化过程进行描述,为实现多退化模式下设备RUL的精准预测奠定了基础。
为验证参数估计结果的有效性,在3组不同设定下用所提方法进行模型参数的MLE。具体地,分别从图1~图3所示的10条退化轨迹中,随机选择其中9条对应的数据作为同类设备的历史退化数据,利用第2.1节中所述方法估计模型参数,参数真实值Θ、估计结果及二者的相对误差如表1所示。由表1可知,参数估计的相对误差均在20%以内,表明所提方法能够提供可靠的参数估计结果。
为验证首达时间意义下寿命分布近似计算式的准确性,分别基于表1中3组模型参数利用式(35)生成1 000条退化轨迹,并统计退化轨迹首次到达失效阈值的时间,作为设备的寿命T,并将T的统计直方图与由式(33)计算得到的设备寿命分布PDF曲线进行对比。由图4~图6可知,不同参数下仿真得到的设备寿命分布直方图与基于寿命分布近似计算式计算得到的PDF曲线高度重合,从而验证了寿命分布近似计算式的准确性。
为进一步验证所提模型方法RUL预测的准确性以及序贯贝叶斯更新方法对RUL预测性能的提升作用,选择相对误差(Relative Error, RE)与均方误差(Mean-Squared Error, MSE)2个常用指标评估所提模型方法性能,其计算式为
式中,E(Lk)、分别为tk时刻的RUL预测值的期望值、真实值;为基于截至tk时刻的退化数据所得RUL的PDF,其可由式(34)计算得到。
在3组不同参数下,依次用图1~图3中未用于参数估计的退化轨迹(蓝色曲线)模拟在役设备的退化轨迹。首先,基于离线估计的参数,利用式(34)计算不同时刻RUL的PDF;其次,先利用式(21)和式(22)对模型参数进行更新,再将更新后的μλΣλ代入式(34)对RUL分布进行在线更新。限于篇幅,这里仅给出第1组参数下不更新和更新参数时RUL分布的PDF,所得结果分别如图7图8所示。对比图7图8可知,图8中预测的RUL值跟真实值更为接近。根据图7图8中RUL的预测值和真实值,可进一步评估预测RUL的相对误差、均方误差,结果如图9图10所示。由图9图10表2可知,对参数进行序贯贝叶斯更新后,RUL预测的相对误差和均方误差值均有显著下降,表明所提RUL预测模型方法和序贯贝叶斯方法的有效性。
滚动轴承是船舶、航空发动机等多种工程机械设备的关键零部件,容易发生故障导致设备失效。因此,基于轴承的状态监测数据对其进行RUL预测,对提高设备的可靠性至关重要。随着使用时长的累积,轴承外圈、内圈、保持架、滚子等部位会发生磨损及裂纹等缺陷,导致轴承性能下降[34]。振动信号中包含着轴承的退化信息,常被用作轴承的状态监测数据。本文以西安交通大学与长兴苏扬科技有限公司提供的公开轴承加速退化试验数据作为轴承状态监测数据,对所提方法进行说明与验证。
所选数据集共包含3种工况条件下各5个轴承的全寿命周期振动数据,第i种工况下第j个轴承记为“轴承i-j”,数据集的具体介绍参考文献[35]。因轴承的振动信号中提取均方根值(Root Mean Square, RMS)能够直接表征振动能量强度,与轴承的疲劳损伤成正相关,且单调性较好[36-37],因此选择均方根值作为健康状态指标,表征轴承的退化过程[38],并基于均方根值对所提方法进行实例验证。工况1下5个轴承振动数据的RMS如图11所示。
图11中,轴承1-1、1-2、1-3的退化是由外圈故障导致的。轴承1-4的退化是由保持架故障造成的,轴承1-5的退化是由内圈与外圈同时发生故障导致的。轴承1-1、1-2、1-3、1-5对应退化轨迹之间相似度显然大于其与轴承1-4的退化轨迹之间的相似度。进一步,通过动态时间规整(Dynamic Time Wrapping, DTW)定量计算所有工况下轴承退化轨迹的相似性,计算结果归一化后进行分层聚类分析,所得结果如图12所示。由图12可知,相同故障部位导致的退化曲线整体上相似度更高,不同部位导致的退化曲线差异性较大。由此可见,考虑多模式随机退化过程建模十分必要。
同时,无论是内圈、外圈还是保持架故障导致的轴承失效,试验中均采用振动的幅值是否超过正常轴承振动幅值的相同倍数来判定失效。因此,可近似认为轴承的失效阈值是恒定的。
首先验证所提模型对轴承数据集的适用性。基于非线性Wiener过程的性质,给定一组具体的退化试验数据,可采取如下步骤初步验证模型适用性:第1步,去除退化数据中的非线性趋势项。采用最小二乘法等拟合退化轨迹的非线性趋势项,再从原始退化轨迹中去除趋势项,得到随机项;第2步,验证随机项增量序列的正态性。通过Shapiro-Wilk检验或者Kolmogorov-Smirnov检验,验证随机项的增量是否满足正态性(亦可通过Q-Q图进行可视化检查);第3步,验证随机项增量的独立性。采用Ljung-Box检验验证随机项增量的独立性,或基于自相关函数(Auto-Correlation Function,ACF)图对随机项增量的独立性进行可视化验证;第4步,验证随机项方差与时间间隔的比例关系。将增量按时间间隔分布,计算每组的样本方差,然后对样本方差和时间间隔进行线性回归,再通过t检验或F检验进行验证。图13中给出了2个代表性轴承正态性检验的Q-Q图,可见轴承性能退化轨迹随机项的增量满足正态假设。
选取第1种工况轴承1-2、1-3、1-4、1-5的退化数据作为历史退化数据,用于估计未知参数。部分参数MLE收敛的过程如图14所示,由图14可知,在经历一定次数迭代后,MLE所得的参数的估计值收敛,参数估计的结果如表3所示。
基于第4.2.2节中的参数估计结果,即可对轴承1-1的RUL进行预测,预测结果如图15所示。随着退化轨迹的累积,RUL预测的结果呈明显的收敛趋势,分布越来越集中,表明预测不确定性随观测数据增加而显著降低。为验证所提的退化模型对设备RUL预测的优越性,与两类文献中常用的模型指数函数模型和幂函数模型进行对比[39]。本文所提模型记为M0,指数函数模型记为模型M1,幂函数模型记为模型M2,其表达式分别为
式中,a为随机参数,用来表征设备个体之间的差异,且服从均值为μa、方差为的高斯分布;b为固定参数,用以刻画同类设备的共性特征。
使用模型M1和模型M2分别对上文提到的轴承的状态监测数据进行参数估计、参数更新和RUL预测,结果如图16图17所示。由图16图17可知,两者RUL预测精度均不如模型M0
进一步,计算M0、M1、M2共3种不同模型下轴承在25%、50%、75%、90%寿命时RUL预测的相对误差和均方误差量化评价指标,如表3所示。可见,所提模型下RUL预测结果的相对误差和均方误差在RUL预测的整个周期中均小于模型M1与模型M2,表明本文方法具有更高的RUL预测精度和预测准确度。
针对多模式随机退化设备RUL预测问题,提出了一种基于非线性Wiener过程的统一退化建模方法,综合MLE与序贯贝叶斯更新,实现了多模式退化过程的精确刻画与设备RUL在线预测,通过数值仿真与轴承退化数据的实例分析,验证了所提方法的有效性和工程适用性。主要研究内容和结论如下:
1)通过构建以Sigmoid函数和指数函数为基础的非线性Wiener过程模型,实现了对设备多模式退化轨迹的统一描述。基于同类设备历史退化数据的MLE方法,能够准确辨识模型中的固定参数与先验分布超参数。
2)在首达时间框架下,推导了多模式随机退化设备RUL的PDF的解析近似解;进一步提出的序贯贝叶斯参数更新方法,可动态融合在役设备的实时监测数据,显著提升了RUL预测的在线精度与适应性。
3)仿真与轴承实例表明,所提方法在多模式退化建模和RUL预测中均优于传统单一模式模型,其预测结果的相对误差与均方误差较传统模型显著降低。当前研究聚焦单一失效模式的场景,完整构建了设备可能存在的多种退化模式的统一建模与RUL预测方法;多失效模式下的退化建模与RUL预测是值得进一步研究的重要内容。
  • 国家自然科学基金项目(62233017; 62373369; 62450056; 62373368)
参考文献 引证文献
排序方式:
[1]
李天梅,司小胜,刘翔,. 大数据下数模联动的随机退化设备剩余寿命预测技术[J]. 自动化学报202248(9):2119-2141.
LI TianmeiSI XiaoshengLIU Xianget al. Data-model interactive remaining useful life prediction technologies for stochastic degrading devices with big data[J]. Acta Automatica Sinica202248(9):2119-2141.(In Chinese)
[2]
李乃鹏,蔡潇,雷亚国,. 一种融合多传感器数据的数模联动机械剩余寿命预测方法[J]. 机械工程学报202157(20):29-37.
LI NaipengCAI XiaoLEI Yaguoet al. A model-data-fusion remaining useful life prediction method with multi-sensor fusion for machinery[J]. Journal of Mechanical Engineering202157(20):29-37.(In Chinese)
[3]
KAMEI STAGHIPOUR S. A comparison study of centralized and decentralized federated learning approaches utilizing the transformer architecture for estimating remaining useful life[J]. Reliability Engineering & System Safety2023233:109130.
[4]
ZIO E. Prognostics and Health Management (PHM):where are we and where do we (need to) go in theory and practice[J]. Reliability Engineering & System Safety2022218:108119.
[5]
吴定海,任国全,王怀光,. 基于卷积神经网络的机械故障诊断方法综述[J]. 机械强度202042(5):1024-1032.
WU DinghaiREN GuoquanWANG Huaiguanget al. The review of mechanical fault diagnosis methods based on convolutional neural network[J]. Journal of Mechanical Strength202042(5):1024-1032.(In Chinese)
[6]
KHAN AAZAD M MSOHAIL Met al. A review of physics-based models in prognostics and health management of laminated composite structures[J]. International Journal of Precision Engineering and Manufacturing-Green Technology202310(6):1615-1635.
[7]
钟建华,黄聪,钟舜聪,. 基于t-SNE降维方法的滚动轴承剩余寿命预测[J]. 机械强度202446(4):969-976.
ZHONG JianhuaHUANG CongZHONG Shunconget al. Remaining useful life of rolling bearing based on t-SNE[J]. Journal of Mechanical Strength202446(4):969-976.(In Chinese)
[8]
冯磊,张正新,李天梅,. 数据驱动的闭环控制系统剩余寿命预测方法综述[J]. 中北大学学报(自然科学版)202445(1):1-11.
FENG LeiZHANG ZhengxinLI Tianmeiet al. A review of data-driven remaining useful life prediction methods for closed-loop control system[J]. Journal of North University of China(Natural Science Edition)202445(1):1-11.(In Chinese)
[9]
LI H QZHANG Z XLI T Met al. A review on physics-informed data-driven remaining useful life prediction:challenges and opportunities[J]. Mechanical Systems and Signal Processing2024209:111120.
[10]
DE BEAULIEU M HJHA M SGARNIER Het al. Remaining useful life prediction based on physics-informed data augmentation[J]. Reliability Engineering & System Safety2024252:110451.
[11]
ZHANG Z XSI X SHU C Het al. Degradation data analysis and remaining useful life estimation:a review on Wiener-process-based methods[J]. European Journal of Operational Research2018271(3):775-796.
[12]
GUAN Q LWEI X K. The statistical data-driven remaining useful life prediction:a review on the Wiener process-based method[C]//2023 Prognostics and Health Management Conference (PHM).New York:IEEE,2023:64-68.
[13]
SI X SCHEN M YWANG W Bet al. Specifying measurement errors for required lifetime estimation performance[J]. European Journal of Operational Research2013231(3):631-644.
[14]
GEBRAEEL N ZLAWLEY M ALI Ret al. Residual-life distributions from component degradation signals:a Bayesian approach[J]. IIE Transactions200537(6):543-557.
[15]
HUANG Z YXU Z GWANG W Het al. Remaining useful life prediction for a nonlinear heterogeneous Wiener process model with an adaptive drift[J]. IEEE Transactions on Reliability201564(2):687-700.
[16]
SI X SLI T MZHANG J Xet al. Nonlinear degradation modeling and prognostics:a Box-Cox transformation perspective[J].Reliability Engineering & System Safety2022217:108120.
[17]
YU W NTU W BKIM I Yet al. A nonlinear-drift-driven Wiener process model for remaining useful life estimation considering three sources of variability[J]. Reliability Engineering & System Safety2021212:107631.
[18]
SI X SWANG W BHU C Het al. Remaining useful life estimation based on a nonlinear diffusion degradation process[J]. IEEE Transactions on Reliability201261(1):50-67.
[19]
ZHANG J XHU C HHE Xet al. A novel lifetime estimation method for two-phase degrading systems[J]. IEEE Transactions on Reliability201968(2):689-709.
[20]
WEN Y XWU J GYUAN Y. Multiple-phase modeling of degradation signal for condition monitoring and remaining useful life prediction[J]. IEEE Transactions on Reliability201766(3):924-938.
[21]
CHEN Z HWU MZHAO Ret al. Machine remaining useful life prediction via an attention-based deep learning approach[J]. IEEE Transactions on Industrial Electronics202168(3):2521-2531.
[22]
ELWANY A HGEBRAEEL N Z. Sensor-driven prognostic models for equipment replacement and spare parts inventory[J]. IIE Transactions200840(7):629-639.
[23]
YE Z SSHEN YXIE M. Degradation-based burn-in with preventive maintenance[J]. European Journal of Operational Research2012221(2):360-367.
[24]
ZHANG J XSI X SDU D Bet al. Lifetime estimation for multi-phase deteriorating process with random abrupt jumps[J]. Sensors201919(6):1472.
[25]
MELCHERS R E. Predicting long-term corrosion of metal alloys in physical infrastructure[J]. NPJ Materials Degradation20193(1):1-7.
[26]
WANG DTSUI K L. Two novel mixed effects models for prognostics of rolling element bearings[J]. Mechanical Systems and Signal Processing201899:1-13.
[27]
王宇,刘秋发,彭一真. 非均匀监测条件下滚动轴承剩余寿命预测方法[J]. 机械工程学报202359(23):96-104.
WANG YuLIU QiufaPENG Yizhen. A remaining useful life prediction approach with nonuniform monitoring conditions for rolling bearings[J]. Journal of Mechanical Engineering202359(23):96-104.(In Chinese)
[28]
ZHANG K PCHANG Z MHAO S Yet al. Nonlinear characteristics and analysis of an exponential variable cross-section beam-based micro-gyroscope with electrostatic driven[J]. Acta Mechanica Sinica202339(3):522371.
[29]
ZHANG L JMU Z QSUN C Y. Remaining useful life prediction for lithium-ion batteries based on exponential model and particle filter[J]. IEEE Access20186:17729-17740.
[30]
李彦梅,刘惠汉,张朝龙,. 基于双高斯模型的锂电池剩余使用寿命预测方法[J]. 电气工程学报202217(4):32-40.
LI YanmeiLIU HuihanZHANG Chaolonget al. Lithiumion battery RUL prediction method based on double Gaussian model[J].Journal of Electrical Engineering202217(4):32-40.(In Chinese)
[31]
司小胜,胡昌华. 数据驱动的设备剩余寿命预测理论及应用[M]. 北京:国防工业出版社,2016:159.
SI XiaoshengHU Changhua. Data-driven remaining useful life prediction theory and applications for equipment[M]. Beijing:National Defense Industry Press,2016:159.(In Chinese)
[32]
ZHANG Z XHU C HSI X Set al. Stochastic degradation process modeling and remaining useful life estimation with flexible random-effects[J]. Journal of the Franklin Institute2017354(6):2477-2499.
[33]
WANG X LGUO BCHENG Z J. Residual life estimation based on bivariate Wiener degradation process with time-scale transformations[J]. Journal of Statistical Computation and Simulation201484(3):545-563.
[34]
李博阳,姚德臣,刘恒畅,. 基于双向堆叠简单循环单元的滚动轴承寿命预测[J]. 机械强度202143(4):786-792.
LI BoyangYAO DechenLIU Hengchanget al. Life prediction of rolling bearing based on bidirectional stacking simple recurrent unit[J]. Journal of Mechanical Strength202143(4):786-792.(In Chinese)
[35]
WANG BLEI Y GLI N Pet al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J].IEEE Transactions on Reliability202069(1):401-412.
[36]
MENG J DYAN C FCHEN G Yet al. Health indicator of bearing constructed by RMS-CUMSUM and GRRMD-CUMSUM with multifeatures of envelope spectrum[J]. IEEE Transactions on Instrumentation and Measurement202170:3510216.
[37]
MENG J DYAN C FWEN Tet al. Real-time identification of performance degradation stages of rolling element bearings by RVCFI[J]. Measurement Science and Technology202233(8):085021.
[38]
王贡献,张腾,胡志辉,. 基于RMS子线区间拟合法的轴承剩余寿命预测[J]. 噪声与振动控制202444(6):165-171.
WANG GongxianZHANG TengHU Zhihuiet al. Bearing residual life prediction based on RMS sublinear interval fitting method[J]. Noise and Vibration Control202444(6):165-171.(In Chinese)
[39]
WANG Z QHU C HWANG W Bet al. An additive Wiener process-based prognostic model for hybrid deteriorating systems[J]. IEEE Transactions on Reliability201463(1):208-222.
2025年第47卷第9期
PDF下载
68
32
引用本文
BibTeX
文章信息
doi: 10.16579/j.issn.1001.9669.2025.09.022
  • 接收时间:2025-05-18
  • 首发时间:2026-03-20
  • 出版时间:2025-09-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-05-18
  • 修回日期:2025-08-01
基金
National Natural Science Foundation of China(62233017; 62373369; 62450056; 62373368)
国家自然科学基金项目(62233017; 62373369; 62450056; 62373368)
作者信息
    火箭军工程大学,西安 710025

通讯作者:

张正新,男,1987年生,云南曲靖人,博士;主要研究方向为随机退化系统剩余寿命预测与健康管理;E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jxqd/CN/10.16579/j.issn.1001.9669.2025.09.022
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