Article(id=1228805360367108377, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, articleNumber=null, orderNo=null, doi=10.16385/j.cnki.issn.1004-4523.2025.06.009, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1728576000000, receivedDateStr=2024-10-11, revisedDate=1734278400000, revisedDateStr=2024-12-16, acceptedDate=null, acceptedDateStr=null, onlineDate=1770899628011, onlineDateStr=2026-02-12, pubDate=1749484800000, pubDateStr=2025-06-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770899628011, onlineIssueDateStr=2026-02-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770899628011, creator=13701087609, updateTime=1770899628011, updator=13701087609, issue=Issue{id=1228805359561802007, tenantId=1146029695717560320, journalId=1225147924628267009, year='2025', volume='38', issue='6', pageStart='1133', pageEnd='1362', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1770899627819, creator=13701087609, updateTime=1770901542852, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1228813391846896476, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1228813391846896477, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1212, endPage=1220, ext={EN=ArticleExt(id=1228805360589406490, articleId=1228805360367108377, tenantId=1146029695717560320, journalId=1225147924628267009, language=EN, title=A relation network-based method for early bearing fault detection, columnId=null, journalTitle=Journal of Vibration Engineering, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Bearings are critical bogie components, making their early fault detection particularly important. This paper proposes an early fault detection method for bearings based on a relation network (RN). A health status detection relation network model is designed to effectively extract bearing condition features and measure the nonlinear distance between these features. In the offline modeling phase, normal samples from the bearing are collected for training, allowing the model to learn the nonlinear distances among the healthy state sample features. During the online monitoring phase, samples from the current operating state are acquired, and a relation score is obtained as a health indicator for the bearing condition. The 3σ criterion is then applied to determine the health indicator threshold for detecting the bearing health status and identifying faults promptly. Experiments were conducted on the XJTU-SY rolling bearing full-lifecycle dataset. Results show that, compared to methods like root mean square, kurtosis, and stacked autoencoders, the health indicator of the proposed method is more sensitive to early faults and exhibits better monotonicity and trend. Furthermore, in comparison with methods such as Isolation Forest, Support Vector Machine, and stacked autoencoders, the proposed method detects the first fault occurrence earlier, demonstrating considerable practical value.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Ran ZHANG, Zhihong ZHAO, Shaopu YANG), CN=ArticleExt(id=1228805362556535137, articleId=1228805360367108377, tenantId=1146029695717560320, journalId=1225147924628267009, language=CN, title=一种轴承早期故障检测的关系网络方法, columnId=0, journalTitle=振动工程学报, columnName=, runingTitle=null, highlight=null, articleAbstract=

轴承作为转向架的关键部件之一,对其进行早期故障检测尤为重要。提出一种基于关系网络(relation network,RN)的轴承早期故障检测方法。设计了一种可以有效提取轴承状态特征、度量特征间非线性距离的健康状态检测关系网络模型。离线建模阶段,获取待检测轴承离线正常样本进行训练,学习健康状态样本特征之间的非线性距离;在线检测阶段,获取当前运行状态样本进行检测,得到关系得分作为轴承状态的健康指标。利用3σ准则得到健康指标的健康阈值,用以检测轴承的健康状态,及时发现故障。在XJTU-SY滚动轴承全寿命数据集上进行试验,试验结果表明,与均方根、峭度、堆叠自编码器等方法相比,本文方法所得健康指标对早期故障更为敏感,并且具有更好的单调性与趋势性;与孤立森林、支持向量机、堆叠自编码器等方法相比,本文方法所得首次故障时间更早,具有一定的应用价值。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
赵志宏(1972—),男,博士,教授。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=vJQKVUsClti2fgoSVs6V/g==, magXml=mQPGjAx40PP9FgnNcyCZLA==, pdfUrl=null, pdf=tYaME2K5bbmIRi9HSiCPcg==, pdfFileSize=1771670, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=4+cdYl7j5vStYPGVApnWzg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=NvUToubk46XaLieCZgkM0A==, mapNumber=null, authorCompany=null, fund=null, authors=

张然(1997—),女,博士研究生。E-mail:

, authorsList=张然, 赵志宏, 杨绍普)}, authors=[Author(id=1228805363152126350, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Sjz_zhangran@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228805363269566872, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, authorId=1228805363152126350, language=EN, stringName=Ran ZHANG, firstName=Ran, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Traffic and Transportation,Shijiazhuang Tiedao University,Shijiazhuang 050043,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805363361841565, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, authorId=1228805363152126350, language=CN, stringName=张然, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.石家庄铁道大学交通运输学院,河北 石家庄 050043, bio={"content":"

张然(1997—),女,博士研究生。E-mail:

"}, bioImg=null, bioContent=

张然(1997—),女,博士研究生。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805362824970612, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, xref=1., ext=[AuthorCompanyExt(id=1228805362837553526, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805362824970612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Traffic and Transportation,Shijiazhuang Tiedao University,Shijiazhuang 050043,China), AuthorCompanyExt(id=1228805362845942135, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805362824970612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.石家庄铁道大学交通运输学院,河北 石家庄 050043)])]), Author(id=1228805363470893478, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hb_zhaozhihong@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228805363588334001, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, authorId=1228805363470893478, language=EN, stringName=Zhihong ZHAO, firstName=Zhihong, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.School of Information Science and Technology,Shijiazhuang Tiedao University,Shijiazhuang 050043,China
3.State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures,Shijiazhuang Tiedao University,Shijiazhuang 050043,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805363680608696, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, authorId=1228805363470893478, language=CN, stringName=赵志宏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.石家庄铁道大学信息科学与技术学院,河北 石家庄 050043
3.石家庄铁道大学省部共建交通工程结构力学行为与系统安全国家重点实验室,河北 石家庄 050043, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805362917245309, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, xref=2., ext=[AuthorCompanyExt(id=1228805362925633919, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805362917245309, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Information Science and Technology,Shijiazhuang Tiedao University,Shijiazhuang 050043,China), AuthorCompanyExt(id=1228805362942411136, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805362917245309, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.石家庄铁道大学信息科学与技术学院,河北 石家庄 050043)]), AuthorCompany(id=1228805363022102916, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, xref=3., ext=[AuthorCompanyExt(id=1228805363047268743, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805363022102916, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures,Shijiazhuang Tiedao University,Shijiazhuang 050043,China), AuthorCompanyExt(id=1228805363068240265, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805363022102916, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.石家庄铁道大学省部共建交通工程结构力学行为与系统安全国家重点实验室,河北 石家庄 050043)])]), Author(id=1228805363760300479, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, 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=1228805363839992264, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, authorId=1228805363760300479, language=EN, stringName=Shaopu YANG, firstName=Shaopu, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures,Shijiazhuang Tiedao University,Shijiazhuang 050043,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805363915489740, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, authorId=1228805363760300479, language=CN, stringName=杨绍普, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.石家庄铁道大学省部共建交通工程结构力学行为与系统安全国家重点实验室,河北 石家庄 050043, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805363022102916, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, xref=3., ext=[AuthorCompanyExt(id=1228805363047268743, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805363022102916, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures,Shijiazhuang Tiedao University,Shijiazhuang 050043,China), AuthorCompanyExt(id=1228805363068240265, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805363022102916, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.石家庄铁道大学省部共建交通工程结构力学行为与系统安全国家重点实验室,河北 石家庄 050043)])])], keywords=[Keyword(id=1228805364003570132, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, orderNo=1, keyword=early fault detection), Keyword(id=1228805364095844827, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, orderNo=2, keyword=relation network), Keyword(id=1228805364263616993, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, orderNo=3, keyword=health indicator), Keyword(id=1228805364364280295, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, orderNo=4, keyword=bidirectional gated recurrent units), Keyword(id=1228805364443972078, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, orderNo=1, keyword=早期故障检测), Keyword(id=1228805364544635379, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, orderNo=2, keyword=关系网络), Keyword(id=1228805364628521468, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, orderNo=3, keyword=健康指标), Keyword(id=1228805364716601858, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, orderNo=4, keyword=双向门控循环单元)], refs=[Reference(id=1228805368021713661, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=5, pageStart=94, pageEnd=104, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=雷亚国, 贾峰, 孔德同, journalName=机械工程学报, refType=null, unstructuredReference=雷亚国,贾峰, 孔德同,等.大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5):94-104., articleTitle=大数据下机械智能故障诊断的机遇与挑战, refAbstract=null), Reference(id=1228805368109794052, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=5, pageStart=94, pageEnd=104, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=LEI Yaguo, JIA Feng, KONG Detong, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=LEI Yaguo, JIA Feng, KONG Detong, et al.Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104., articleTitle=Opportunities and challenges of machinery intelligent fault diagnosis in big data era, refAbstract=null), Reference(id=1228805368197874439, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2018, volume=48, issue=5, pageStart=801, pageEnd=806, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=佘道明, 贾民平, 张菀, journalName=东南大学学报(自然科学版), refType=null, unstructuredReference=佘道明,贾民平, 张菀. 一种新型深度自编码网络的滚动轴承健康评估方法[J]. 东南大学学报(自然科学版), 2018, 48(5):801-806., articleTitle=一种新型深度自编码网络的滚动轴承健康评估方法, refAbstract=null), Reference(id=1228805368302732044, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2018, volume=48, issue=5, pageStart=801, pageEnd=806, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=SHE Daoming, JIA Minping, ZHANG Wan, journalName=Journal of Southeast University (Natural Science Edition), refType=null, unstructuredReference=SHE Daoming, JIA Minping, ZHANG Wan. Deep auto-encoder network method for health assessment of rolling bearings[J]. Journal of Southeast University (Natural Science Edition), 2018, 48(5): 801-806., articleTitle=Deep auto-encoder network method for health assessment of rolling bearings, refAbstract=null), Reference(id=1228805368407589651, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2017, volume=28, issue=5, pageStart=550, pageEnd=558, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=张全德, 陈果, 林桐, journalName=中国机械工程, refType=null, unstructuredReference=张全德,陈果, 林桐,等.基于自组织神经网络的滚动轴承状态评估方法[J]. 中国机械工程, 2017, 28(5):550-558., articleTitle=基于自组织神经网络的滚动轴承状态评估方法, refAbstract=null), Reference(id=1228805368491475736, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2017, volume=28, issue=5, pageStart=550, pageEnd=558, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=ZHANG Quande, CHEN Guo, LIN Tong, journalName=China Mechanical Engineering, refType=null, unstructuredReference=ZHANG Quande, CHEN Guo, LIN Tong, et al.Condition assessment for rolling bearings based on SOM[J]. China Mechanical Engineering, 2017, 28(5): 550-558., articleTitle=Condition assessment for rolling bearings based on SOM, refAbstract=null), Reference(id=1228805368604721950, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2006, volume=18, issue=7, pageStart=1527, pageEnd=1554, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=HINTON G E, OSINDERO S, TEH Y W, journalName=Neural Computation, refType=null, unstructuredReference=HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554., articleTitle=A fast learning algorithm for deep belief nets, refAbstract=null), Reference(id=1228805368676025125, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2020, volume=54, issue=null, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=CHEN L T, XU G H, ZHANG S C, journalName=Journal of Manufacturing Systems, refType=null, unstructuredReference=CHEN L T, XU G H, ZHANG S C, et al.Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks[J]. Journal of Manufacturing Systems, 2020, 54: 1-11., articleTitle=Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks, refAbstract=null), Reference(id=1228805368768299818, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=1, pageStart=302, pageEnd=314, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=毛文涛, 田思雨, 窦智, journalName=自动化学报, refType=null, unstructuredReference=毛文涛,田思雨, 窦智,等.一种基于深度迁移学习的滚动轴承早期故障在线检测方法[J]. 自动化学报, 2022, 48(1):302-314., articleTitle=一种基于深度迁移学习的滚动轴承早期故障在线检测方法, refAbstract=null), Reference(id=1228805368889934640, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=1, pageStart=302, pageEnd=314, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=MAO Wentao, TIAN Siyu, DOU Zhi, journalName=Acta Automatica Sinica, refType=null, unstructuredReference=MAO Wentao, TIAN Siyu, DOU Zhi, et al.A new deep transfer learning-based online detection method of rolling bearing early fault[J]. Acta Automatica Sinica, 2022, 48(1): 302-314., articleTitle=A new deep transfer learning-based online detection method of rolling bearing early fault, refAbstract=null), Reference(id=1228805368990597945, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=10, pageStart=1234, pageEnd=1243, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=赵志宏, 李乐豪, 杨绍普, journalName=中国机械工程, refType=null, unstructuredReference=赵志宏,李乐豪, 杨绍普,等.一种无监督的轴承健康指标及早期故障检测方法[J]. 中国机械工程, 2022, 33(10):1234-1243., articleTitle=一种无监督的轴承健康指标及早期故障检测方法, refAbstract=null), Reference(id=1228805369078678332, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=10, pageStart=1234, pageEnd=1243, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=ZHAO Zhihong, LI Lehao, YANG Shaopu, journalName=China Mechanical Engineering, refType=null, unstructuredReference=ZHAO Zhihong, LI Lehao, YANG Shaopu, et al.An unsupervised bearing health indicator and early fault detection method[J]. China Mechanical Engineering, 2022, 33(10): 1234-1243., articleTitle=An unsupervised bearing health indicator and early fault detection method, refAbstract=null), Reference(id=1228805369175147330, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2021, volume=107, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=YE Z, YU J B, journalName=Applied Soft Computing, refType=null, unstructuredReference=YE Z, YU J B. Health condition monitoring of machines based on long short-term memory convolutional autoencoder[J]. Applied Soft Computing, 2021, 107: 107379., articleTitle=Health condition monitoring of machines based on long short-term memory convolutional autoencoder, refAbstract=null), Reference(id=1228805369250644809, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2021, volume=44, issue=2, pageStart=422, pageEnd=446, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=李凡长, 刘洋, 吴鹏翔, journalName=计算机学报, refType=null, unstructuredReference=李凡长,刘洋, 吴鹏翔,等.元学习研究综述[J]. 计算机学报, 2021, 44(2):422-446., articleTitle=元学习研究综述, refAbstract=null), Reference(id=1228805369330336588, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2021, volume=44, issue=2, pageStart=422, pageEnd=446, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=LI Fanzhang, LIU Yang, WU pengxiang, journalName=Chinese Journal of Computers, refType=null, unstructuredReference=LI Fanzhang, LIU Yang, WU pengxiang, et al.A survey on recent advances in meta-learning[J]. Chinese Journal of Computers, 2021, 44(2): 422-446., articleTitle=A survey on recent advances in meta-learning, refAbstract=null), Reference(id=1228805369443582803, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1199, pageEnd=1208, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=SUNG F, YANG Y X, ZHANG L, journalName=null, refType=null, unstructuredReference=SUNG F, YANG Y X, ZHANG L, et al.Learning to compare: relation network for few-shot learning[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, IEEE, 2018: 1199-1208., articleTitle=Learning to compare: relation network for few-shot learning, refAbstract=null), Reference(id=1228805369523274585, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2020, volume=166, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=WU J Y, ZHAO Z B, SUN C, journalName=Measurement, refType=null, unstructuredReference=WU J Y, ZHAO Z B, SUN C, et al.Few-shot transfer learning for intelligent fault diagnosis of machine[J]. Measurement, 2020, 166: 108202., articleTitle=Few-shot transfer learning for intelligent fault diagnosis of machine, refAbstract=null), Reference(id=1228805369598772062, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=2, pageStart=55, pageEnd=65, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=吕枫, 王义, 阮胡林, journalName=仪器仪表学报, refType=null, unstructuredReference=吕枫,王义, 阮胡林,等.深度嵌入关系空间下齿轮箱标记样本扩充及其半监督故障诊断方法[J]. 仪器仪表学报, 2021, 42(2):55-65., articleTitle=深度嵌入关系空间下齿轮箱标记样本扩充及其半监督故障诊断方法, refAbstract=null), Reference(id=1228805369674269542, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=2, pageStart=55, pageEnd=65, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=LYU Feng, WANG Yi, RUAN Hulin, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=LYU Feng, WANG Yi, RUAN Hulin, et al.Labeled sample augmentation based on deep embedding relation space for semi-supervised fault diagnosis of gearbox[J]. Chinese Journal of Scientific Instrument, 2021, 42(2): 55-65., articleTitle=Labeled sample augmentation based on deep embedding relation space for semi-supervised fault diagnosis of gearbox, refAbstract=null), Reference(id=1228805369766544235, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=7, pageStart=1549, pageEnd=1557, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=赵志宏, 张然, 孙诗胜, journalName=自动化学报, refType=null, unstructuredReference=赵志宏,张然, 孙诗胜. 基于关系网络的轴承剩余使用寿命预测方法[J]. 自动化学报, 2023, 49(7):1549-1557., articleTitle=基于关系网络的轴承剩余使用寿命预测方法, refAbstract=null), Reference(id=1228805369883984755, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=7, pageStart=1549, pageEnd=1557, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=ZHAO Zhihong, ZHANG Ran, SUN Shisheng, journalName=Acta Automatica Sinica, refType=null, unstructuredReference=ZHAO Zhihong, ZHANG Ran, SUN Shisheng. Bearing remaining useful life prediction based on relation network[J]. Acta Automatica Sinica, 2023, 49(7): 1549-1557., articleTitle=Bearing remaining useful life prediction based on relation network, refAbstract=null), Reference(id=1228805369997230969, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=BISHAY M, ZOUMPOURLIS G, PATRAS I, journalName=null, refType=null, unstructuredReference=BISHAY M, ZOUMPOURLIS G, PATRAS I. TARN: temporal attentive relation network for few-shot and zero-shot action recognition[EB/OL]. (2019-07-21)[2024-10-11]. https://arxiv.org/abs/1907.09021v1., articleTitle=TARN: temporal attentive relation network for few-shot and zero-shot action recognition, refAbstract=null), Reference(id=1228805370093699969, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=19, pageStart=164, pageEnd=170, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=王晓茹, 张珩, journalName=计算机工程与应用, refType=null, unstructuredReference=王晓茹, 张珩. 基于注意力机制和图卷积的小样本分类网络[J]. 计算机工程与应用, 2021, 57(19):164-170., articleTitle=基于注意力机制和图卷积的小样本分类网络, refAbstract=null), Reference(id=1228805370190168964, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=19, pageStart=164, pageEnd=170, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=WANG Xiaoru, ZHANG Heng, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=WANG Xiaoru, ZHANG Heng. Relation network based on attention mechanism and graph convolution for few-shot learning[J]. Computer Engineering and Applications, 2021, 57(19): 164-170., articleTitle=Relation network based on attention mechanism and graph convolution for few-shot learning, refAbstract=null), Reference(id=1228805370278249354, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2019, volume=55, issue=16, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=雷亚国, 韩天宇, 王彪, journalName=机械工程学报, refType=null, unstructuredReference=雷亚国,韩天宇, 王彪,等.XJTU-SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报, 2019, 55(16):1-6., articleTitle=XJTU-SY滚动轴承加速寿命试验数据集解读, refAbstract=null), Reference(id=1228805370378912657, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2019, volume=55, issue=16, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=LEI Yaguo, HAN Tianyu, WANG Biao, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=LEI Yaguo, HAN Tianyu, WANG Biao, et al.XJTU-SY rolling element bearing accelerated life test datasets: a tutorial[J]. Journal of Mechanical Engineering, 2019, 55(16): 1-6., articleTitle=XJTU-SY rolling element bearing accelerated life test datasets: a tutorial, refAbstract=null), Reference(id=1228805370471187351, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2013, volume=227, issue=12, pageStart=2849, pageEnd=2860, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=CHEN X F, SHEN Z J, HE Z J, journalName=Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, refType=null, unstructuredReference=CHEN X F, SHEN Z J, HE Z J, et al.Remaining life prognostics of rolling bearing based on relative features and multivariable support vector machine[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2013, 227(12): 2849-2860., articleTitle=Remaining life prognostics of rolling bearing based on relative features and multivariable support vector machine, refAbstract=null), Reference(id=1228805370567656352, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=5, pageStart=43, pageEnd=46, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=袁云龙, journalName=新技术新工艺, refType=null, unstructuredReference=袁云龙. 基于峭度-小波包分析的滚动轴承故障诊断[J]. 新技术新工艺,2008(5):43-46., articleTitle=基于峭度-小波包分析的滚动轴承故障诊断, refAbstract=null), Reference(id=1228805370680902566, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=5, pageStart=43, pageEnd=46, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=YUAN Yunlong, journalName=New Technology & New Process, refType=null, unstructuredReference=YUAN Yunlong. Fault diagnosis of rolling bearing based on kurtosis-wavelet packet analysis[J]. New Technology & New Process,2008(5): 43-46., articleTitle=Fault diagnosis of rolling bearing based on kurtosis-wavelet packet analysis, refAbstract=null), Reference(id=1228805370756400042, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2022, volume=16, issue=1, pageStart=163, pageEnd=175, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=李贝贝, 彭力, journalName=计算机科学与探索, refType=null, unstructuredReference=李贝贝, 彭力. 基于改进自编码网络的轴承振动异常检测[J]. 计算机科学与探索, 2022, 16(1):163-175., articleTitle=基于改进自编码网络的轴承振动异常检测, refAbstract=null), Reference(id=1228805370878034863, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2022, volume=16, issue=1, pageStart=163, pageEnd=175, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=LI Beibei, PENG Li, journalName=Journal of Frontiers of Computer Science and Technology, refType=null, unstructuredReference=LI Beibei, PENG Li. Bearing vibration abnormal detection based on improved autoencoder network[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(1): 163-175., articleTitle=Bearing vibration abnormal detection based on improved autoencoder network, refAbstract=null), Reference(id=1228805370970309558, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=4, pageStart=1447, pageEnd=1456, url=null, language=null, rfNumber=[20], rfOrder=31, authorNames=李新鹏, 高欣, 阎博, journalName=电网技术, refType=null, unstructuredReference=李新鹏,高欣, 阎博,等.基于孤立森林算法的电力调度流数据异常检测方法[J]. 电网技术, 2019, 43(4):1447-1456., articleTitle=基于孤立森林算法的电力调度流数据异常检测方法, refAbstract=null), Reference(id=1228805371075167159, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=4, pageStart=1447, pageEnd=1456, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=LI Xinpeng, GAO Xin, YAN Bo, journalName=Power System Technology, refType=null, unstructuredReference=LI Xinpeng, GAO Xin, YAN Bo, et al.An approach of data anomaly detection in power dispatching streaming data based on isolation forest algorithm[J]. Power System Technology, 2019, 43(4): 1447-1456., articleTitle=An approach of data anomaly detection in power dispatching streaming data based on isolation forest algorithm, refAbstract=null), Reference(id=1228805371175830458, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2017, volume=25, issue=4, pageStart=555, pageEnd=560, url=null, language=null, rfNumber=[21], rfOrder=33, authorNames=戴海发, 卞鸿巍, 马恒, journalName=中国惯性技术学报, refType=null, unstructuredReference=戴海发,卞鸿巍, 马恒,等.基于一类SVM的综合导航系统信息故障检测方法[J]. 中国惯性技术学报, 2017, 25(4):555-560., articleTitle=基于一类SVM的综合导航系统信息故障检测方法, refAbstract=null), Reference(id=1228805371293270974, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, doi=null, pmid=null, pmcid=null, year=2017, volume=25, issue=4, pageStart=555, pageEnd=560, url=null, language=null, rfNumber=[21], rfOrder=34, authorNames=DAI Haifa, BIAN Hongwei, MA Heng, journalName=Journal of Chinese Inertial Technology, refType=null, unstructuredReference=DAI Haifa, BIAN Hongwei, MA Heng, et al.Information fault detection for integrated navigation systems using one-class support vector machine[J]. Journal of Chinese Inertial Technology, 2017, 25(4): 555-560., articleTitle=Information fault detection for integrated navigation systems using one-class support vector machine, refAbstract=null)], funds=[Fund(id=1228805367732306659, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, awardId=12393783, language=CN, fundingSource=国家自然科学基金资助项目(12393783), fundOrder=null, country=null), Fund(id=1228805367807804139, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, awardId=12172234, language=CN, fundingSource=国家自然科学基金资助项目(12172234), fundOrder=null, country=null), Fund(id=1228805367895884530, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, awardId=12032017, language=CN, fundingSource=国家自然科学基金资助项目(12032017), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1228805362824970612, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, xref=1., ext=[AuthorCompanyExt(id=1228805362837553526, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805362824970612, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Traffic and Transportation,Shijiazhuang Tiedao University,Shijiazhuang 050043,China), AuthorCompanyExt(id=1228805362845942135, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805362824970612, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.石家庄铁道大学交通运输学院,河北 石家庄 050043)]), AuthorCompany(id=1228805362917245309, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, xref=2., ext=[AuthorCompanyExt(id=1228805362925633919, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805362917245309, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Information Science and Technology,Shijiazhuang Tiedao University,Shijiazhuang 050043,China), AuthorCompanyExt(id=1228805362942411136, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805362917245309, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.石家庄铁道大学信息科学与技术学院,河北 石家庄 050043)]), AuthorCompany(id=1228805363022102916, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, xref=3., ext=[AuthorCompanyExt(id=1228805363047268743, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805363022102916, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures,Shijiazhuang Tiedao University,Shijiazhuang 050043,China), AuthorCompanyExt(id=1228805363068240265, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, companyId=1228805363022102916, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.石家庄铁道大学省部共建交通工程结构力学行为与系统安全国家重点实验室,河北 石家庄 050043)])], figs=[ArticleFig(id=1228805364913734159, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 1, caption=Relation network structure, figureFileSmall=gnLdxU3m6Dee8X/32ZVMOQ==, figureFileBig=4+cdYl7j5vStYPGVApnWzg==, tableContent=null), ArticleFig(id=1228805365001814550, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图1, caption=关系网络结构, figureFileSmall=gnLdxU3m6Dee8X/32ZVMOQ==, figureFileBig=4+cdYl7j5vStYPGVApnWzg==, tableContent=null), ArticleFig(id=1228805365207335462, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 2, caption=Structure diagram of GRU, figureFileSmall=qNGkC0new2kCjilz7mp7Og==, figureFileBig=KeYr2FMEkfdTk31KGhNSIQ==, tableContent=null), ArticleFig(id=1228805365291221546, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图2, caption=GRU结构图, figureFileSmall=qNGkC0new2kCjilz7mp7Og==, figureFileBig=KeYr2FMEkfdTk31KGhNSIQ==, tableContent=null), ArticleFig(id=1228805365387690547, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 3, caption=Structure of relation network model, figureFileSmall=BiyAwDI2kEPmvKJPQ1Fmvg==, figureFileBig=brGO0zFY6B+w0KWmm7u/dA==, tableContent=null), ArticleFig(id=1228805365479965242, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图3, caption=关系网络模型结构, figureFileSmall=BiyAwDI2kEPmvKJPQ1Fmvg==, figureFileBig=brGO0zFY6B+w0KWmm7u/dA==, tableContent=null), ArticleFig(id=1228805365551268417, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 4, caption=Flowchart of bearing health status detection based on relation network, figureFileSmall=c89HtmdvWXv9B2tD3xEWdA==, figureFileBig=5d9x9OetnqrO4WhFZ1JfTQ==, tableContent=null), ArticleFig(id=1228805365630960196, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图4, caption=基于关系网络的轴承健康状态检测流程图, figureFileSmall=c89HtmdvWXv9B2tD3xEWdA==, figureFileBig=5d9x9OetnqrO4WhFZ1JfTQ==, tableContent=null), ArticleFig(id=1228805365744206411, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 5, caption=Testbed of rolling bearings, figureFileSmall=On/8c1G5Nc4f0MSDtfXmbw==, figureFileBig=PZO1romGvXM4SZVE/tZYXA==, tableContent=null), ArticleFig(id=1228805365840675409, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图5, caption=滚动轴承试验台, figureFileSmall=On/8c1G5Nc4f0MSDtfXmbw==, figureFileBig=PZO1romGvXM4SZVE/tZYXA==, tableContent=null), ArticleFig(id=1228805365928755801, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 6, caption=Bearing time-domain vibration signal, figureFileSmall=lJEjKPpSc9flyVVUNI2O0w==, figureFileBig=10aNd3oQI81IekjV94W5dg==, tableContent=null), ArticleFig(id=1228805366016836193, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图6, caption=轴承时域振动信号, figureFileSmall=lJEjKPpSc9flyVVUNI2O0w==, figureFileBig=10aNd3oQI81IekjV94W5dg==, tableContent=null), ArticleFig(id=1228805366096527976, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 7, caption=Health status detection results, figureFileSmall=13CH5gdpW+zCxEXj1BnWUA==, figureFileBig=IthtCsuC0t36SDhjnmLadA==, tableContent=null), ArticleFig(id=1228805366302048885, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图7, caption=健康状态检测结果, figureFileSmall=13CH5gdpW+zCxEXj1BnWUA==, figureFileBig=IthtCsuC0t36SDhjnmLadA==, tableContent=null), ArticleFig(id=1228805366390129278, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 8, caption=Early fault detection results, figureFileSmall=5DfcqqepibWgdS+NYtA06A==, figureFileBig=syhcM7ebOvW1c7n9If+L0Q==, tableContent=null), ArticleFig(id=1228805366490792580, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图8, caption=早期故障检测结果, figureFileSmall=5DfcqqepibWgdS+NYtA06A==, figureFileBig=syhcM7ebOvW1c7n9If+L0Q==, tableContent=null), ArticleFig(id=1228805366767616658, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 9, caption=Partial sample spectrum of bearing 1_1, figureFileSmall=+JyLS0CkfCmmlKsoYcvS7w==, figureFileBig=IgaevfAvlaOUaGP37ZhT8w==, tableContent=null), ArticleFig(id=1228805366872474265, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图9, caption=轴承1_1部分样本频谱, figureFileSmall=+JyLS0CkfCmmlKsoYcvS7w==, figureFileBig=IgaevfAvlaOUaGP37ZhT8w==, tableContent=null), ArticleFig(id=1228805366964748964, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Fig. 10, caption=Partial sample spectrum of bearing 1_3, figureFileSmall=Y7dJ965c2O4Fura7tZKdUA==, figureFileBig=h9NInKkog3diOZP51l3dww==, tableContent=null), ArticleFig(id=1228805367057023663, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=图10, caption=轴承1_3部分样本频谱, figureFileSmall=Y7dJ965c2O4Fura7tZKdUA==, figureFileBig=h9NInKkog3diOZP51l3dww==, tableContent=null), ArticleFig(id=1228805367161881272, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Tab.1, caption=

XJTU-SY bearing dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
工况轴承名称样本个数故障位置
工况1
(35 Hz、12 kN)
轴承1_1123外圈
轴承1_2161外圈
轴承1_3158外圈
轴承1_4122保持架
轴承1_552外圈、内圈
工况2
(37.5 Hz、11 kN)
轴承2_1491内圈
轴承2_2161外圈
轴承2_3533保持架
轴承2_442外圈
轴承2_5339外圈
工况3
(40 Hz、10 kN)
轴承3_12538外圈
轴承3_22496内圈、滚动体、保持架、外圈
轴承3_3371内圈
轴承3_41515内圈
轴承3_5114外圈
), ArticleFig(id=1228805367237378751, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=表1, caption=

XJTU-SY轴承数据集

, figureFileSmall=null, figureFileBig=null, tableContent=
工况轴承名称样本个数故障位置
工况1
(35 Hz、12 kN)
轴承1_1123外圈
轴承1_2161外圈
轴承1_3158外圈
轴承1_4122保持架
轴承1_552外圈、内圈
工况2
(37.5 Hz、11 kN)
轴承2_1491内圈
轴承2_2161外圈
轴承2_3533保持架
轴承2_442外圈
轴承2_5339外圈
工况3
(40 Hz、10 kN)
轴承3_12538外圈
轴承3_22496内圈、滚动体、保持架、外圈
轴承3_3371内圈
轴承3_41515内圈
轴承3_5114外圈
), ArticleFig(id=1228805367338042055, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Tab.2, caption=

Comparison of monotonicity and trend of different methods

, figureFileSmall=null, figureFileBig=null, tableContent=
轴承轴承1_1轴承1_3
单调性趋势性单调性趋势性
均方根0.46280.86080.42940.7583
峭度0.49580.07650.48070.6215
堆叠自编码器0.42970.87970.42300.7495
关系网络0.50810.85010.56410.8951
), ArticleFig(id=1228805367442899662, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=表2, caption=

不同方法的单调性、趋势性对比

, figureFileSmall=null, figureFileBig=null, tableContent=
轴承轴承1_1轴承1_3
单调性趋势性单调性趋势性
均方根0.46280.86080.42940.7583
峭度0.49580.07650.48070.6215
堆叠自编码器0.42970.87970.42300.7495
关系网络0.50810.85010.56410.8951
), ArticleFig(id=1228805367535174357, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=EN, label=Tab.3, caption=

Comparison of early fault detection among different methods

, figureFileSmall=null, figureFileBig=null, tableContent=
方法轴承1_1轴承1_3
首次故障时间/min误报警数首次故障时间/min误报警数
关系网络790590
堆叠自编码器790601
孤立森林9501370
一类支持向量机9441150
), ArticleFig(id=1228805367627449053, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805360367108377, language=CN, label=表3, caption=

不同方法早期故障检测对比

, figureFileSmall=null, figureFileBig=null, tableContent=
方法轴承1_1轴承1_3
首次故障时间/min误报警数首次故障时间/min误报警数
关系网络790590
堆叠自编码器790601
孤立森林9501370
一类支持向量机9441150
)], attaches=null, journal=Journal(id=1225147830491308032, delFlag=0, nameCn=振动工程学报, nameEn=Journal of Vibration Engineering, nameHistory1=null, nameHistory2=null, issn=1004-4523, eissn=null, cn=32-1349/TB, 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=null, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Vibration Engineering, journalRemark=null, publicationField=null, createdTime=1770027604939, updatedTime=1770169610881, createdBy=18614031015, updatedBy=18614031015, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=null, picEn=null, jcr=null, cjcr=null, exts=[JournalExt(id=1225743346702925905, language=CN, name=振动工程学报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国振动工程学会, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770169587064, updatedTime=1770169587064, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionEditorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionReviewUrl=https://www.manuscripts.com.cn/zdgcxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1225743346765840466, language=EN, name=Journal of Vibration Engineering, 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=1770169587079, updatedTime=1770169587079, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionEditorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionReviewUrl=https://www.manuscripts.com.cn/zdgcxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1225147924628267009, websiteList=[Website(id=1225150618881404985, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225147924628267009, 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/zdgcxb/CN, language=CN, createTime=1770028269739, createBy=18614031015, updateTime=1770028293069, updateBy=18614031015, name=振动工程学报-中文, tplId=1146099689490845704, title=振动工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225151164178673750, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=articleTextType, value=kx, createTime=1770028399748, updateTime=1770028399748, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164157702227, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=banner, value=null, createTime=1770028399743, updateTime=1770028399743, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164203839577, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=grayFlag, value=0, createTime=1770028399754, updateTime=1770028399754, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164145119314, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=logo, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic?fileId=L7mSU8YPwm66NWFMoTG4aQ==, createTime=1770028399740, updateTime=1770028399740, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164212228187, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=minRunFlag, value=0, createTime=1770028399756, updateTime=1770028399756, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164170285141, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/file/pic, createTime=1770028399746, updateTime=1770028399746, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164208033882, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=silenceFlag, value=0, createTime=1770028399755, updateTime=1770028399755, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164166090836, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770028399745, updateTime=1770028399745, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164187062359, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=themeColor, value=null, createTime=1770028399750, updateTime=1770028399750, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164195450968, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=themeStyle, value=null, createTime=1770028399752, updateTime=1770028399752, creator=18614031015, updator=18614031015)]), Website(id=1225150619003039804, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225147924628267009, 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/zdgcxb/EN, language=EN, createTime=1770028269768, createBy=18614031015, updateTime=1770028309190, updateBy=18614031015, name=振动工程学报-英文, tplId=1146101810881728533, title=Journal of Vibration Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225151193366835296, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=articleTextType, value=kx, createTime=1770028406707, updateTime=1770028406707, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193350058077, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=banner, value=null, createTime=1770028406703, updateTime=1770028406703, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193387806819, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=grayFlag, value=0, createTime=1770028406712, updateTime=1770028406712, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193341669468, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=logo, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic?fileId=L7mSU8YPwm66NWFMoTG4aQ==, createTime=1770028406701, updateTime=1770028406701, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193400389733, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=minRunFlag, value=0, createTime=1770028406715, updateTime=1770028406715, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193362640991, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic, createTime=1770028406706, updateTime=1770028406706, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193392001124, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=silenceFlag, value=0, createTime=1770028406713, updateTime=1770028406713, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193354252382, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770028406704, updateTime=1770028406704, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193371029601, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=themeColor, value=null, createTime=1770028406708, updateTime=1770028406708, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193379418210, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=themeStyle, value=null, createTime=1770028406710, updateTime=1770028406710, creator=18614031015, updator=18614031015)])], journalTitle=振动工程学报, weixinUrl=null, journalUrl=http://zdgcxb.csve.org.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Vibration Engineering, journalPhotoCn=null, journalPhotoEn=null, 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/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2025.06.009, detailUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/10.16385/j.cnki.issn.1004-4523.2025.06.009, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/PDF/10.16385/j.cnki.issn.1004-4523.2025.06.009, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/PDF/10.16385/j.cnki.issn.1004-4523.2025.06.009, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
一种轴承早期故障检测的关系网络方法
收藏切换
PDF下载
张然 1 , 赵志宏 2, 3 , 杨绍普 3
振动工程学报 | 2025,38(6): 1212-1220
收起
收藏切换
振动工程学报 | 2025, 38(6): 1212-1220
一种轴承早期故障检测的关系网络方法
全屏
张然1 , 赵志宏2, 3 , 杨绍普3
作者信息
  • 1.石家庄铁道大学交通运输学院,河北 石家庄 050043
  • 2.石家庄铁道大学信息科学与技术学院,河北 石家庄 050043
  • 3.石家庄铁道大学省部共建交通工程结构力学行为与系统安全国家重点实验室,河北 石家庄 050043
  • 张然(1997—),女,博士研究生。E-mail:

通讯作者:

赵志宏(1972—),男,博士,教授。E-mail:
A relation network-based method for early bearing fault detection
Ran ZHANG1 , Zhihong ZHAO2, 3 , Shaopu YANG3
Affiliations
  • 1.School of Traffic and Transportation,Shijiazhuang Tiedao University,Shijiazhuang 050043,China
  • 2.School of Information Science and Technology,Shijiazhuang Tiedao University,Shijiazhuang 050043,China
  • 3.State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures,Shijiazhuang Tiedao University,Shijiazhuang 050043,China
出版时间: 2025-06-10 doi: 10.16385/j.cnki.issn.1004-4523.2025.06.009
文章导航
收藏切换

轴承作为转向架的关键部件之一,对其进行早期故障检测尤为重要。提出一种基于关系网络(relation network,RN)的轴承早期故障检测方法。设计了一种可以有效提取轴承状态特征、度量特征间非线性距离的健康状态检测关系网络模型。离线建模阶段,获取待检测轴承离线正常样本进行训练,学习健康状态样本特征之间的非线性距离;在线检测阶段,获取当前运行状态样本进行检测,得到关系得分作为轴承状态的健康指标。利用3σ准则得到健康指标的健康阈值,用以检测轴承的健康状态,及时发现故障。在XJTU-SY滚动轴承全寿命数据集上进行试验,试验结果表明,与均方根、峭度、堆叠自编码器等方法相比,本文方法所得健康指标对早期故障更为敏感,并且具有更好的单调性与趋势性;与孤立森林、支持向量机、堆叠自编码器等方法相比,本文方法所得首次故障时间更早,具有一定的应用价值。

早期故障检测  /  关系网络  /  健康指标  /  双向门控循环单元

Bearings are critical bogie components, making their early fault detection particularly important. This paper proposes an early fault detection method for bearings based on a relation network (RN). A health status detection relation network model is designed to effectively extract bearing condition features and measure the nonlinear distance between these features. In the offline modeling phase, normal samples from the bearing are collected for training, allowing the model to learn the nonlinear distances among the healthy state sample features. During the online monitoring phase, samples from the current operating state are acquired, and a relation score is obtained as a health indicator for the bearing condition. The 3σ criterion is then applied to determine the health indicator threshold for detecting the bearing health status and identifying faults promptly. Experiments were conducted on the XJTU-SY rolling bearing full-lifecycle dataset. Results show that, compared to methods like root mean square, kurtosis, and stacked autoencoders, the health indicator of the proposed method is more sensitive to early faults and exhibits better monotonicity and trend. Furthermore, in comparison with methods such as Isolation Forest, Support Vector Machine, and stacked autoencoders, the proposed method detects the first fault occurrence earlier, demonstrating considerable practical value.

early fault detection  /  relation network  /  health indicator  /  bidirectional gated recurrent units
张然, 赵志宏, 杨绍普. 一种轴承早期故障检测的关系网络方法. 振动工程学报, 2025 , 38 (6) : 1212 -1220 . DOI: 10.16385/j.cnki.issn.1004-4523.2025.06.009
Ran ZHANG, Zhihong ZHAO, Shaopu YANG. A relation network-based method for early bearing fault detection[J]. Journal of Vibration Engineering, 2025 , 38 (6) : 1212 -1220 . DOI: 10.16385/j.cnki.issn.1004-4523.2025.06.009
轴承作为转向架中的关键零部件,在长期运转过程中容易出现各种故障。若不及时进行检测和处理,可能会导致严重的经济损失,甚至危及人身安全。因此,对轴承的健康状态进行实时检测,及时发现早期故障具有重要意义[1-2]
采用时域统计特征中均方根、峭度等单一指标检测轴承健康状态,存在抗干扰能力差、故障敏感度低等问题,不能有效反映轴承健康状态。随着智能传感技术与机器学习技术的快速发展,针对轴承健康状态检测,目前已有不少研究成果。张全德等[3]提出一种基于自组织神经网络的轴承健康状态评估方法,首先利用主成分分析方法对提取到的多特征数据进行预处理,然后通过自组织神经网络融合多特征数据输出健康指标,最终实现轴承状态评估。基于机器学习的方法,虽然取得一定进展,但仍然依赖专家经验手工提取特征,泛化性较差。随着深度学习理论被HINTON等[4]提出后,很多学者将深度神经网络应用于轴承健康状态检测与早期故障检测中。CHEN等[5]采用卷积神经网络(convolutional neural networks, CNN)和长短时记忆网络(long short-term memory, LSTM)相结合,端到端地构建轴承健康指标,以表示轴承性能退化趋势。毛文涛等[6]构建出一种多域迁移深度自编码器,用来提取有效的早期故障特征,该方法通过引入深度迁移学习来解决轴承早期故障在线检测问题。赵志宏等[7]提出一种深度可分离卷积自编码器模型,能够无监督地生成轴承健康指标并及时检测出早期故障。YE等[8]提出一种长短时记忆卷积自编码器用来学习轴承健康特征,采用多变量高斯分布生成健康指数来量化轴承健康状态。虽然深度学习方法在轴承健康状态检测与早期故障检测领域已经取得进展,但过于依赖大量轴承全寿命数据进行训练与测试,存在鲁棒性与泛化性较差的问题,难以适应未学习的任务。在实际工程中,轴承全寿命数据极难获取,导致深度神经网络模型训练困难,无法适用于工程实践中。
元学习方法[9]能够利用已学习到的知识经验,快速适应未学习到的新任务,弥补了深度神经网络鲁棒性和泛化性较差、对新任务适应性较差的问题,相比深度学习技术,元学习方法能够使用少量训练样本得到较好的模型参数,更有利于在工程实践中的应用。因此,很多专家学者利用元学习方法解决轴承故障诊断与健康评估问题。其中,关系网络[10]这一基于度量的元学习方法通过其独特的非线性距离度量方式,被广泛应用。WU等[11]利用关系网络实现轴承故障诊断,试验结果表明关系网络在小样本学习中具有一定的优势。吕枫等[12]通过关系网络学习少量有标记样本的嵌入空间,从而为无标记样本赋予伪标签,实现了有标记样本集扩充。赵志宏等[13]通过关系网络有监督地学习轴承运行初期与全寿命数据间的相似性,获得轴承健康指标,实现轴承寿命预测。
本文提出一种基于关系网络的轴承早期故障检测方法,设计了一种基于关系网络的轴承健康状态检测模型。离线建模阶段,获取待检测轴承离线正常样本作为训练样本,利用嵌入模块中的CNN与双向门控循环单元(bidirectional gated recurrent unit,BiGRU)提取轴承状态特征,利用关系模块中的CNN度量健康样本特征间的非线性距离;在线检测阶段,获取待检测轴承的在线运行样本作为测试样本,通过度量在线运行样本特征与离线健康样本特征之间的非线性距离,获取关系得分,即为健康指标,可用于检测轴承健康状态,判断是否发生早期故障。与已有健康状态检测方法对比,所得健康指标具有更好的单调性、趋势性;与已有早期故障检测方法对比,所得首次故障时间更早,误报警数更少。
关系网络是针对少量训练样本可用情况下,为实现图像识别[14-15]而开发的,常被用来解决小样本下的分类问题。关系网络的结构如图1所示,由嵌入模块和关系模块组成。嵌入模块用来提取样本特征,关系模块中的卷积神经网络被用来进行非线性距离度量,以实现样本间距离的更准确表达。
在关系网络中,首先将支撑集样本xi与查询集样本xj输入到嵌入模块fϕ()中,得到样本xixj的特征向量:
Fi=fϕ(xi)
Fj=fϕ(xj)
式中,FiFj分别为输入样本xixj的特征向量;fϕ()为嵌入模块,用来提取输入样本xixj的特征,其中ϕ为相应的参数。
然后通过拼接运算符ZFiFj耦合在一起,计算公式为:
Fconij=Z(Fi,Fj)=Z(fϕ(xi),fϕ(xj))
式中,Fconij表示耦合后的特征向量。
最后将耦合后的特征向量Fconij输入到关系模块gφ()中,生成关系得分rij
rij=gφ(Fconij)=gφ(Z(fϕ(xi),fϕ(xj)))
式中,rij表示样本xixj之间的距离,即预测关系得分;gφ()为关系模块,用来度量特征向量FiFj之间的非线性距离,从而获取关系得分,其中φ为相应的参数。
损失函数采用均方误差(MSE),计算公式为:
Lloss=i=1mj=1n(rijrijreal)2
式中,m表示样本xi的数量;n表示样本xj的数量;rijreal表示样本xixj之间的真实关系得分。
在实际环境中,转向架轴承的故障样本十分稀缺,传统的机器学习方法可能无法在仅有健康状态样本的情况下有效检测早期故障。而关系网络能够在少量样本的情况下,通过有效的特征提取和非线性距离度量,学习到健康状态样本之间的相似性。在轴承运行过程中实时检测数据,通过对比轴承已知健康状态样本与当前运行状态样本的非线性距离,可以实时准确地判断轴承的健康状况,及时发现早期故障并进行维护管理。
门控循环单元(gated recurrent unit,GRU)是LSTM的一种变体,将LSTM最初的输入门、输出门和遗忘门合并为重置门和更新门,结构如图2所示。GRU相比LSTM模型,结构更简单,模型参数更少,不仅解决了循环神经网络梯度消失和梯度爆炸的问题,同时又能使模型训练时间更短。GRU计算公式为:
zt=σ(Wz[ht1,xt])
rt=σ(Wr[ht1,xt])
h~t=tanh(W[rtht1,xt])
ht=(1zt)ht1+zth~t
式中,WzWrW为GRU的权重矩阵;ht1表示t−1时刻隐藏状态;ht~表示候选隐藏状态;ht表示当前隐藏状态;ztrt分别表示更新门和重置门;xtt时刻模型的输入状态;σ和tanh分别表示Sigmoid激活函数和tanh激活函数;“”为哈达玛乘积。
BiGRU在GRU的基础上进一步扩展,能够通过双向循环结构同时捕捉时间序列数据中过去与未来的相关信息,尤其适用于动态、序列化的数据特征提取。轴承的振动信号是典型的时间序列数据,包含了轴承运行过程中连续的状态变化信息。这些信号具有时间上的依赖性,当前时刻的信号特征可能受到过去状态的影响,并对未来状态产生影响。BiGRU利用其双向循环结构,能够同时捕捉振动信号的过去和未来信息,充分挖掘信号中的时间依赖特性。这种双向特征提取方式使其特别适合分析轴承振动信号。并且,轴承的早期故障通常表现为微弱的特征信号,通过双向建模和门控机制,BiGRU能够放大这些关键特征,提高早期故障的识别精度。
本文提出一种基于关系网络的健康状态检测模型,其中关系网络模型结构如图3所示。嵌入模块由3个卷积层,2个池化层和一个BiGRU层组成。每层卷积操作后都进行了批标准化,用以避免梯度爆炸。选取ReLU激活函数,将神经元的输入映射到输出端,增加了神经网络模型的非线性。为了从原始输入信号中提取全局特征,第一个卷积层采用了1×10的大卷积核,其余卷积层均使用1×3的小卷积核,便于从中提取局部信息。相比BiLSTM而言,BiGRU参数更少,训练速度更快且不易过拟合,更适合提取轴承时序特征。
关系模块由2个卷积模块和2个全连接层组成。除输出层为Sigmoid激活函数之外,其他层均为ReLU激活函数,以便得到两个输入样本之间的关系得分。
本文提出基于关系网络的轴承健康状态检测方法,该方法能够在仅有少量轴承离线正常样本的情况下,通过学习健康状态样本之间的非线性距离,对未知运行状态样本进行健康评估,并获得良好的检测结果。
基于关系网络的轴承健康状态检测流程如图4所示,分为离线建模阶段和在线检测阶段。首先,通过离线建模阶段学习已知健康状态样本之间的非线性距离,获取关系网络模型参数;然后,通过度量离线建模阶段健康状态样本与在线检测阶段所得未知状态样本之间的非线性距离,计算关系得分,获取健康指标。具体步骤如下:
步骤1:采集轴承全寿命数据,对所得振动信号进行等长截断与快速傅里叶变换,得到频谱信号。
步骤2:将轴承的第1个样本作为支撑集S,除第一个样本外,将轴承运行初始的少量健康样本作为查询集Q,并将查询集Q的健康指标记为“0”,将剩余全寿命数据作为测试集Y
步骤3:构建关系网络模型,包括嵌入模块、关系模块。
步骤4:离线建模阶段,将支撑集S的样本与查询集Q的样本,输入关系网络模型,采用均方误差作为损失函数值,利用BP反向传播算法训练模型,获取模型参数。
步骤5:在线检测阶段,将支撑集S的样本与测试集Y的未知状态样本输入训练好的关系网络模型中,计算测试集样本与支撑集样本的关系得分,即健康指标。关系得分取值在[0,1]之间,该数值不仅表示两个特征之间的非线性距离,而且表示当前运行状态样本的健康程度,由于设定的查询集Q的健康指标为“0”,所以越接近0,轴承运行状态越健康,反之,则越接近失效状态。
在实际应用中,找到轴承故障起始点是十分重要的。因此根据本文所获取的正常运行状态样本的健康指标,使用遵循高斯分布的3σ准则方法,设置正常值与3倍标准差之和作为健康阈值,通过健康阈值确定轴承故障起始点。
为了防止环境噪声、非故障因素引起的瞬态波动等偶然扰动造成健康指标突变,从而被误判为故障。本文设定在线检测样本健康指标小于健康阈值,即检测为健康。如果在线检测样本健康指标大于健康阈值不足3次,则按误报警处理。如果在线检测样本健康指标连续3次大于健康阈值,则认定为故障。
采用XJTU-SY滚动轴承全寿命数据集[16]对本文所提方法进行试验验证。XJTU-SY数据集如表1所示,共包含3种工况,每种工况下5个轴承,共15个轴承。每个轴承均为从开始运行到轴承失效停止运行的完整数据。滚动轴承试验台如图5所示,采样频率为25.6 kHz,每隔1 min采集一次,采样时间为1.28 s。通过进行多次加速退化试验分别获得每个轴承在整个运行期间的水平和垂直振动信号,本文主要针对水平方向振动信号进行试验,因为水平方向添加了荷载,包含更多的轴承退化信息,更有利于实现轴承健康评估。
不同的轴承有不同的退化趋势,既有缓慢退化型轴承也有突然失效型轴承。如图6所示为轴承1_1与轴承1_3水平方向振动信号的时域图。从图6中可以看出,随着运转时间的增加,轴承1_1的幅值突然增大,退化趋势为突然失效型,轴承1_3的幅值缓慢增加,退化趋势为缓慢退化型。因此,本文以轴承1_1和1_3为例,验证本文方法在两种不同退化趋势下的有效性与泛化性。
图6中可以看出,轴承1_1与1_3在前20 min时域信号均保持稳定,未出现退化。因此,离线建模阶段,分别采用轴承1_1与1_3中第1 min样本的频谱作为支撑集,第2~20 min健康状态样本的频谱作为查询集。在线检测阶段,以轴承1_1与1_3第20 min后未知状态样本的频谱作为测试集进行健康状态检测与早期故障检测,得到轴承健康指标与早期故障发生时间。
为验证本文所提方法的有效性,将引入传统时域指标与深度学习方法作为对比用于检测轴承健康状态。传统时域指标中均方根(RMS)[17]与峭度[18]常常作为参考指标用以检测轴承健康状态。轴承信号的RMS值会随着故障程度的变化而变化,峭度对振动信号的冲击较为敏感。深度学习方法中堆叠自编码器(stacked autoencoder,SAE)[19]作为经典的无监督方法用于构建轴承健康指标与早期故障检测。因此,将本文方法所得健康指标与均方根、峭度、堆叠自编码器方法所构建的健康指标进行单调性、趋势性对比,进一步验证本文所提方法的优势。其计算过程如下:
(1)单调性:
Mon(H)=|NpositiveNnegative|K1
式中,Mon(H)表示单调性,用于衡量健康指标H的单调性程度,其中H为健康指标序列;KH的总样本数; NpositiveH对时间求导大于0的数量;NnegativeH对时间求导小于0的数量。单调性指标描述了健康指标与运行时间之间单调上升或者单调下降的相关程度,取值范围在[0,1]内,其值越大,说明构建的H单调性越好。
(2)趋势性:
Tred(H,T)=|k=1K(HkH¯)(tkT¯)|k=1K(HkH¯)2k=1K(tkT¯)2
式中,Tred(H,T)表示健康指标H与时间T之间的线性相关性;T为健康指标对应的时间序列;Hk为第k个健康指标;H¯为健康指标的均值;tk为第k个健康指标对应的时间;T¯为时间序列的均值。趋势性指标描述了健康指标与运行时间的线性相关度,取值范围在[0,1]内,其值越大,说明H线性相关性越好。
为使检测结果对比清晰,将所得指标均归一化至[0,1]区间内,轴承1_1与轴承1_3采用均方根、峭度、堆叠自编码器与关系网络方法所得的检测结果对比如图7所示。
图7中可以看出,对于不同的轴承退化趋势,本文方法获取的健康指标都可以准确反映出轴承退化的趋势。更能够通过健康指标的突变将早期故障有效地表征出来,有利于实现早期故障检测。
使用均方根、峭度、堆叠自编码器与关系网络方法获取轴承健康指标,计算指标的单调性、趋势性,对比结果如表2所示,可以看到基于关系网络的健康指标单调性、趋势性均优于均方根、峭度与堆叠自编码器方法,可以更好地反映轴承随着运行时间增加,性能退化的趋势。
使用本文提出的早期故障检测方法,对轴承1_1与轴承1_3的健康指标进行早期故障检测,在线检测结果如图8所示。图8中健康指标低于阈值即为健康状态,连续3次高于阈值即为故障状态,健康指标与阈值的相交点即为早期故障的发生时刻,高于阈值不足3次则按误报警处理。可以看到无论是缓慢退化型还是突然失效型退化趋势,本文方法均能对早期故障进行及时报警,并不存在误报警情况,验证了所提早期故障检测方法的有效性。
为进一步验证本文方法的优势,将本文所提方法与孤立森林(isolation forest,iForest)[20]、一类支持向量机(support vector machines,SVM)[21]、SAE[19]等异常检测方法进行对比。对比方法介绍如下:
(1)iForest是一种基于决策树的无监督异常检测方法,该算法通过构建多棵随机分裂的二叉树来递归地划分数据空间,样本的“异常程度”由其在树中被隔离所需的分裂次数决定。孤立树的数量为100,构建孤立树所需的最大数据点数为256。
(2)SVM是一种二分类模型,通过核函数映射将样本映射到高维空间中的一个“超球体”或“超平面”内,将该类的正常样本与异常样本分隔开。
(3)SAE是一种基于神经网络的无监督学习方法。SAE通过训练,能够较好重建正常样本,但对异常样本的重建误差较大。因此,通过计算样本的重建误差,可以实现异常检测。本文所用堆叠自编码器网络结构为:1024-512-32。
使用关系网络、堆叠自编码器、孤立森林、一类支持向量机方法进行早期故障检测对比试验,得到的首次故障时间与误报警数如表3所示。孤立森林和SVM的首次故障时间均晚于本文方法,存在较大的延迟,并且SVM还存在较大的误报警数。SAE方法虽然针对突然失效型轴承的首次故障时间与本文方法一致,也不存在误报警情况,但是针对缓慢退化型轴承,首次故障时间晚于本文方法1 min,并且存在误报警情况。本文方法所得首次故障时间更早,并且不存在误报警情况,在早期故障检测中具有一定的优越性。
由试验结果可知,轴承1_1的初始故障发生在第79 min,轴承1_3的初始故障发生在第59 min。其中,轴承1_1和1_3均为工况1下轴承的外圈故障,其故障频率理论值为107.91 Hz。
为进一步验证本文所提方法的正确性,对样本的频谱信号进行分析。轴承1_1的部分时刻频谱信号如图9所示,可以看出,第1、2、78 min的频谱信号相似度较高,即非线性距离较小,通过关系网络进行特征拼接后,关系得分数值更接近于0。在第79 min的频谱信号中出现了与外圈故障频率接近的倍频成分,其中10倍频1087 Hz成分为峰值,说明第79 min时发生了外圈故障。由于第79 min与第1 min相似度较低,即非线性距离较大,导致关系得分数值发生突变,开始远离0,进而实现轴承早期故障检测。同理,通过图10可以看出,轴承1_3第58 min的频谱与第1 min的频谱相似度较高,关系得分接近于0,第59 min时峰值突然增大,同样出现了外圈故障频率的倍频成分,说明第59 min时发生了外圈故障。由于第59 min与第1 min相似度较低,关系得分发生突变,因此,及时检测出了轴承的早期故障。
从上述分析中可以发现,本文方法通过度量轴承运行第1 min与其他不同时刻的样本之间的相似性,实现健康指标的构建与早期故障检测,并且早期故障发生时,健康指标均会产生较大突变,说明本文方法具有一定的可行性与有效性。
本文针对轴承健康状态检测问题,提出了一种基于关系网络的轴承早期故障检测方法。并在XJTU-SY轴承数据集上进行验证。主要结论如下:
(1)关系网络可有效提取轴承状态特征,并准确度量特征间的非线性距离,在仅有待检测轴承少量正常样本的情况下,可实现轴承的健康状态检测。
(2)本文方法所得健康指标,不仅能够反映轴承退化趋势,还能在早期故障发生时,产生明显的突变,方便更加及时准确地检测出轴承的早期故障。
(3)本文所提方法构建的健康指标与RMS、峭度、SAE方法所得健康指标相比,具有更好的单调性和趋势性。
(4)本文所提方法与孤立森林、SVM、SAE方法相比,首次故障时间更早,并且不会出现误报警情况。
  • 国家自然科学基金资助项目(12393783)
  • 国家自然科学基金资助项目(12172234)
  • 国家自然科学基金资助项目(12032017)
参考文献 引证文献
排序方式:
[1]
雷亚国,贾峰, 孔德同,等.大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5):94-104.
LEI Yaguo, JIA Feng, KONG Detong, et al.Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104.
[2]
佘道明,贾民平, 张菀. 一种新型深度自编码网络的滚动轴承健康评估方法[J]. 东南大学学报(自然科学版), 2018, 48(5):801-806.
SHE Daoming, JIA Minping, ZHANG Wan. Deep auto-encoder network method for health assessment of rolling bearings[J]. Journal of Southeast University (Natural Science Edition), 2018, 48(5): 801-806.
[3]
张全德,陈果, 林桐,等.基于自组织神经网络的滚动轴承状态评估方法[J]. 中国机械工程, 2017, 28(5):550-558.
ZHANG Quande, CHEN Guo, LIN Tong, et al.Condition assessment for rolling bearings based on SOM[J]. China Mechanical Engineering, 2017, 28(5): 550-558.
[4]
HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[5]
CHEN L T, XU G H, ZHANG S C, et al.Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks[J]. Journal of Manufacturing Systems, 2020, 54: 1-11.
[6]
毛文涛,田思雨, 窦智,等.一种基于深度迁移学习的滚动轴承早期故障在线检测方法[J]. 自动化学报, 2022, 48(1):302-314.
MAO Wentao, TIAN Siyu, DOU Zhi, et al.A new deep transfer learning-based online detection method of rolling bearing early fault[J]. Acta Automatica Sinica, 2022, 48(1): 302-314.
[7]
赵志宏,李乐豪, 杨绍普,等.一种无监督的轴承健康指标及早期故障检测方法[J]. 中国机械工程, 2022, 33(10):1234-1243.
ZHAO Zhihong, LI Lehao, YANG Shaopu, et al.An unsupervised bearing health indicator and early fault detection method[J]. China Mechanical Engineering, 2022, 33(10): 1234-1243.
[8]
YE Z, YU J B. Health condition monitoring of machines based on long short-term memory convolutional autoencoder[J]. Applied Soft Computing, 2021, 107: 107379.
[9]
李凡长,刘洋, 吴鹏翔,等.元学习研究综述[J]. 计算机学报, 2021, 44(2):422-446.
LI Fanzhang, LIU Yang, WU pengxiang, et al.A survey on recent advances in meta-learning[J]. Chinese Journal of Computers, 2021, 44(2): 422-446.
[10]
SUNG F, YANG Y X, ZHANG L, et al.Learning to compare: relation network for few-shot learning[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, IEEE, 2018: 1199-1208.
[11]
WU J Y, ZHAO Z B, SUN C, et al.Few-shot transfer learning for intelligent fault diagnosis of machine[J]. Measurement, 2020, 166: 108202.
[12]
吕枫,王义, 阮胡林,等.深度嵌入关系空间下齿轮箱标记样本扩充及其半监督故障诊断方法[J]. 仪器仪表学报, 2021, 42(2):55-65.
LYU Feng, WANG Yi, RUAN Hulin, et al.Labeled sample augmentation based on deep embedding relation space for semi-supervised fault diagnosis of gearbox[J]. Chinese Journal of Scientific Instrument, 2021, 42(2): 55-65.
[13]
赵志宏,张然, 孙诗胜. 基于关系网络的轴承剩余使用寿命预测方法[J]. 自动化学报, 2023, 49(7):1549-1557.
ZHAO Zhihong, ZHANG Ran, SUN Shisheng. Bearing remaining useful life prediction based on relation network[J]. Acta Automatica Sinica, 2023, 49(7): 1549-1557.
[14]
BISHAY M, ZOUMPOURLIS G, PATRAS I. TARN: temporal attentive relation network for few-shot and zero-shot action recognition[EB/OL]. (2019-07-21)[2024-10-11]. https://arxiv.org/abs/1907.09021v1.
[15]
王晓茹, 张珩. 基于注意力机制和图卷积的小样本分类网络[J]. 计算机工程与应用, 2021, 57(19):164-170.
WANG Xiaoru, ZHANG Heng. Relation network based on attention mechanism and graph convolution for few-shot learning[J]. Computer Engineering and Applications, 2021, 57(19): 164-170.
[16]
雷亚国,韩天宇, 王彪,等.XJTU-SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报, 2019, 55(16):1-6.
LEI Yaguo, HAN Tianyu, WANG Biao, et al.XJTU-SY rolling element bearing accelerated life test datasets: a tutorial[J]. Journal of Mechanical Engineering, 2019, 55(16): 1-6.
[17]
CHEN X F, SHEN Z J, HE Z J, et al.Remaining life prognostics of rolling bearing based on relative features and multivariable support vector machine[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2013, 227(12): 2849-2860.
[18]
袁云龙. 基于峭度-小波包分析的滚动轴承故障诊断[J]. 新技术新工艺,2008(5):43-46.
YUAN Yunlong. Fault diagnosis of rolling bearing based on kurtosis-wavelet packet analysis[J]. New Technology & New Process,2008(5): 43-46.
[19]
李贝贝, 彭力. 基于改进自编码网络的轴承振动异常检测[J]. 计算机科学与探索, 2022, 16(1):163-175.
LI Beibei, PENG Li. Bearing vibration abnormal detection based on improved autoencoder network[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(1): 163-175.
[20]
李新鹏,高欣, 阎博,等.基于孤立森林算法的电力调度流数据异常检测方法[J]. 电网技术, 2019, 43(4):1447-1456.
LI Xinpeng, GAO Xin, YAN Bo, et al.An approach of data anomaly detection in power dispatching streaming data based on isolation forest algorithm[J]. Power System Technology, 2019, 43(4): 1447-1456.
[21]
戴海发,卞鸿巍, 马恒,等.基于一类SVM的综合导航系统信息故障检测方法[J]. 中国惯性技术学报, 2017, 25(4):555-560.
DAI Haifa, BIAN Hongwei, MA Heng, et al.Information fault detection for integrated navigation systems using one-class support vector machine[J]. Journal of Chinese Inertial Technology, 2017, 25(4): 555-560.
2025年第38卷第6期
PDF下载
101
47
引用本文
BibTeX
文章信息
doi: 10.16385/j.cnki.issn.1004-4523.2025.06.009
  • 接收时间:2024-10-11
  • 首发时间:2026-02-12
  • 出版时间:2025-06-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-10-11
  • 修回日期:2024-12-16
基金
国家自然科学基金资助项目(12393783)
国家自然科学基金资助项目(12172234)
国家自然科学基金资助项目(12032017)
作者信息
    1.石家庄铁道大学交通运输学院,河北 石家庄 050043
    2.石家庄铁道大学信息科学与技术学院,河北 石家庄 050043
    3.石家庄铁道大学省部共建交通工程结构力学行为与系统安全国家重点实验室,河北 石家庄 050043

通讯作者:

赵志宏(1972—),男,博士,教授。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2025.06.009
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