Article(id=1203753461679628367, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1203753457208504777, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2402488, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1712419200000, receivedDateStr=2024-04-07, revisedDate=1730822400000, revisedDateStr=2024-11-06, acceptedDate=null, acceptedDateStr=null, onlineDate=1764926789922, onlineDateStr=2025-12-05, pubDate=1737129600000, pubDateStr=2025-01-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1764926789922, onlineIssueDateStr=2025-12-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1764926789922, creator=13701087609, updateTime=1764926789922, updator=13701087609, issue=Issue{id=1203753457208504777, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='2', pageStart='439', pageEnd='878', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1764926788856, creator=13701087609, updateTime=1764928745558, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1203761664261858014, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1203753457208504777, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1203761664261858015, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1203753457208504777, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=567, endPage=573, ext={EN=ArticleExt(id=1203753462170361973, articleId=1203753461679628367, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Life Prediction Based on ASFF-AAKR and CNN-BILSTM Rolling Bearings, columnId=1156262732765717457, journalTitle=Science Technology and Engineering, columnName=Papers·Mechanical and Instrumental Industry, runingTitle=null, highlight=null, articleAbstract=

To address the issues of low accuracy in rolling bearing life prediction and the difficulty of constructing health indicators, a bearing remaining life prediction model based on ASFF (adaptively spatial feature fusion) and AAKR (auto associative kernel regression) combined with CNN (convolutional neural networks) and BILSTM (bi-directional long-short term memory networks) was proposed. Firstly, the multidimensional features were extracted in the time domain, frequency domain, and time-frequency domain, and the sensitive features were screened using monotonicity and trend. Secondly, the sensitive features were feature fused using ASFF-AAKR to construct the health indicators. Finally, the health indicators were inputted into CNN and BILSTM to realize the life prediction of rolling bearings. The results show that the constructed life prediction model is better than other models, and the method has lower error and higher life prediction accuracy.

, correspAuthors=Song-shou LIU, 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=Yong-chao ZHANG, Song-shou LIU, Yu-xi CHEN, Hai-kun YANG, Qing-guang CHEN), CN=ArticleExt(id=1203753465341256085, articleId=1203753461679628367, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于ASFF-AAKR和CNN-BILSTM滚动轴承寿命预测, columnId=1156262732954461139, journalTitle=科学技术与工程, columnName=论文·机械、仪表工业, runingTitle=null, highlight=null, articleAbstract=

针对滚动轴承寿命预测精度低,构建健康指标困难的问题。提出了一种基于自适应特征融合(adaptively spatial feature fusion,ASFF)和自联想核回归模型(auto associative kernel regression, AAKR)与卷积神经网络(convolutional neural networks, CNN)和双向长短期记忆网络(bi-directional long-short term memory,BILSTM)的轴承剩余寿命预测模型。首先,在时域、频域和时频域提取多维特征,利用单调性和趋势性筛选敏感特征;其次利用ASFF-AAKR对敏感特征进行特征融合构建健康指标;最后,将健康指标输入到CNN和BILSTM中,实现对滚动轴承的寿命预测。结果表明:所构建的寿命预测模型优于其他模型,该方法具有更低的误差、寿命预测精度更高。

, correspAuthors=刘嵩寿, authorNote=null, correspAuthorsNote=
* 刘嵩寿(1998—),男,汉族,山东潍坊人,硕士研究生。研究方向:机电装备状态评估与寿命预测。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=LWJ5Lm9t5uOylgbdafmPHw==, magXml=vTuVoqCFMG7/3AGmKUXlAw==, pdfUrl=null, pdf=pzR9nk431CJ2NbEogva9KQ==, pdfFileSize=9763981, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ntZnlb/7IXFRgOF8ytxzPw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=pQV3gIZd96TrKW2VeS4fLw==, mapNumber=null, authorCompany=null, fund=null, authors=

张永超(1977—),男,汉族,山东青岛人,硕士,副教授。研究方向:机电智能控制、流体机械。E-mail:

, authorsList=张永超, 刘嵩寿, 陈昱锡, 杨海昆, 陈庆光)}, authors=[Author(id=1203787151801561343, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jdxzyc@sdust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1203787151948361999, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787151801561343, language=EN, stringName=Yong-chao ZHANG, firstName=Yong-chao, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1203787152120328482, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787151801561343, language=CN, stringName=张永超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=山东科技大学机械电子工程学院, 青岛 266590, bio={"content":"

张永超(1977—),男,汉族,山东青岛人,硕士,副教授。研究方向:机电智能控制、流体机械。E-mail:

"}, bioImg=null, bioContent=

张永超(1977—),男,汉族,山东青岛人,硕士,副教授。研究方向:机电智能控制、流体机械。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1203787151658954986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, xref=null, ext=[AuthorCompanyExt(id=1203787151675732204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1203787151679926510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山东科技大学机械电子工程学院, 青岛 266590)])]), Author(id=1203787152267129143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1057547479@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1203787152392958273, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787152267129143, language=EN, stringName=Song-shou LIU, firstName=Song-shou, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1203787152535564625, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787152267129143, language=CN, stringName=刘嵩寿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=山东科技大学机械电子工程学院, 青岛 266590, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1203787151658954986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, xref=null, ext=[AuthorCompanyExt(id=1203787151675732204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1203787151679926510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山东科技大学机械电子工程学院, 青岛 266590)])]), Author(id=1203787153693192538, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, 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=1203787153839993194, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787153693192538, language=EN, stringName=Yu-xi CHEN, firstName=Yu-xi, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1203787154016153982, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787153693192538, language=CN, stringName=陈昱锡, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=山东科技大学机械电子工程学院, 青岛 266590, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1203787151658954986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, xref=null, ext=[AuthorCompanyExt(id=1203787151675732204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1203787151679926510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山东科技大学机械电子工程学院, 青岛 266590)])]), Author(id=1203787154234257803, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, 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=1203787154330726811, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787154234257803, language=EN, stringName=Hai-kun YANG, firstName=Hai-kun, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1203787154452361636, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787154234257803, language=CN, stringName=杨海昆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=山东科技大学机械电子工程学院, 青岛 266590, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1203787151658954986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, xref=null, ext=[AuthorCompanyExt(id=1203787151675732204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1203787151679926510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山东科技大学机械电子工程学院, 青岛 266590)])]), Author(id=1203787154578190774, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, 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=1203787154745962947, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787154578190774, language=EN, stringName=Qing-guang CHEN, firstName=Qing-guang, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1203787154846626258, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, authorId=1203787154578190774, language=CN, stringName=陈庆光, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=山东科技大学机械电子工程学院, 青岛 266590, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1203787151658954986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, xref=null, ext=[AuthorCompanyExt(id=1203787151675732204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1203787151679926510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山东科技大学机械电子工程学院, 青岛 266590)])])], keywords=[Keyword(id=1203787155056341484, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, orderNo=1, keyword=rolling bearing), Keyword(id=1203787155207336444, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, orderNo=2, keyword=adaptive feature fusion), Keyword(id=1203787155358331405, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, orderNo=3, keyword=auto associative kernel regression), Keyword(id=1203787155454800412, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, orderNo=4, keyword=convolutional neural network), Keyword(id=1203787155568046634, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, orderNo=5, keyword=bidirectional long short-term memory network), Keyword(id=1203787155714847285, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, orderNo=6, keyword=remaining life prediction), Keyword(id=1203787155811316292, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, orderNo=1, keyword=滚动轴承), Keyword(id=1203787155928756821, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, orderNo=2, keyword=自适应特征融合), Keyword(id=1203787156029420129, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, orderNo=3, keyword=自联想核回归), Keyword(id=1203787156159443564, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, orderNo=4, keyword=卷积神经网络), Keyword(id=1203787156276884087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, orderNo=5, keyword=双向长短期记忆网络), Keyword(id=1203787156440461955, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, orderNo=6, keyword=剩余寿命预测)], refs=[Reference(id=1203787161490404334, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2023, volume=12, issue=1, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Zhang X, Yang J, Yang X, journalName=Processes, refType=null, unstructuredReference=Zhang X, Yang J, Yang X. Residual life prediction of rolling bearings based on a CEEMDAN algorithm fused with CNN-attention-based bidirectional LSTM modeling[J]. Processes, 2023, 12(1): 1-8., articleTitle=Residual life prediction of rolling bearings based on a CEEMDAN algorithm fused with CNN-attention-based bidirectional LSTM modeling, refAbstract=null), Reference(id=1203787161591067632, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2017, volume=48, issue=1, pageStart=11, pageEnd=20, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Deutsch J, He D, journalName=IEEE Transactions on Systems, Man, and Cybernetics: Systems, refType=null, unstructuredReference=Deutsch J, He D. Using deep learning-based approach to predict remaining useful life of rotating components[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017, 48(1): 11-20., articleTitle=Using deep learning-based approach to predict remaining useful life of rotating components, refAbstract=null), Reference(id=1203787161725285374, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2022, volume=121, issue=null, pageStart=349, pageEnd=364, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Yang C, Ma J, Wang X, journalName=ISA Transactions, refType=null, unstructuredReference=Yang C, Ma J, Wang X, et al. A novel based-performance degradation indicator RUL prediction model and its application in rolling bearing[J]. ISA Transactions, 2022, 121: 349-364., articleTitle=A novel based-performance degradation indicator RUL prediction model and its application in rolling bearing, refAbstract=null), Reference(id=1203787161842725891, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=1, pageStart=1, pageEnd=23, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=张金豹, 邹天刚, 王敏, journalName=机械科学与技术, refType=null, unstructuredReference=张金豹, 邹天刚, 王敏, 等. 滚动轴承剩余使用寿命预测综述[J]. 机械科学与技术, 2023, 42(1): 1-23., articleTitle=滚动轴承剩余使用寿命预测综述, refAbstract=null), Reference(id=1203787161997914115, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=1, pageStart=1, pageEnd=23, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Zhang Jinbao, Zou Tiangang, Wang Min, journalName=Mechanical Science and Technology for Aerospace Engineering, refType=null, unstructuredReference=Zhang Jinbao, Zou Tiangang, Wang Min, et al. Review on remaining useful life prediction of rolling bearing[J]. Mechanical Science and Technology for Aerospace Engineering, 2023, 42(1): 1-23., articleTitle=Review on remaining useful life prediction of rolling bearing, refAbstract=null), Reference(id=1203787162157297679, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2017, volume=83, issue=3, pageStart=549, pageEnd=567, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=Qian Y, Yan R, Gao R X, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=Qian Y, Yan R, Gao R X. A multi-time scale approach to remaining useful life prediction in rolling bearing[J]. Mechanical Systems and Signal Processing, 2017, 83(3): 549-567., articleTitle=A multi-time scale approach to remaining useful life prediction in rolling bearing, refAbstract=null), Reference(id=1203787162299904020, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2023, volume=72, issue=null, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Deng Y, Du S, Wang D, journalName=IEEE Transactions on Instrumentation and Measurement, refType=null, unstructuredReference=Deng Y, Du S, Wang D, et al. A calibration-based hybrid transfer learning framework for RUL prediction of rolling bearing across different machines[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-15., articleTitle=A calibration-based hybrid transfer learning framework for RUL prediction of rolling bearing across different machines, refAbstract=null), Reference(id=1203787162476064800, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=7, 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., articleTitle=null, refAbstract=null), Reference(id=1203787162618671143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Si Xiaosheng, Hu Changhua, journalName=Data-driven remaining useful life prediction theory and applications for equipment, refType=null, unstructuredReference=Si Xiaosheng, Hu Changhua. Data-driven remaining useful life prediction theory and applications for equipment[M]. Beijing: Natio-nal Defense Industry Press, 2016., articleTitle=null, refAbstract=null), Reference(id=1203787162786443312, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2022, volume=14, issue=6, pageStart=16878132221106609, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=Wang W, Zhao J, Ding G, journalName=Advances in Mechanical Engineering, refType=null, unstructuredReference=Wang W, Zhao J, Ding G. RUL prediction of rolling bearings based on improved empirical wavelet transform and convolutional neural network[J]. Advances in Mechanical Engineering, 2022, 14(6): 16878132221106609., articleTitle=RUL prediction of rolling bearings based on improved empirical wavelet transform and convolutional neural network, refAbstract=null), Reference(id=1203787164019568702, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=3, pageStart=372, pageEnd=387, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=Zhang Q, Ye Z, Shao S, journalName=Assembly Automation, refType=null, unstructuredReference=Zhang Q, Ye Z, Shao S, et al. Remaining useful life prediction of rolling bearings based on convolutional recurrent attention network[J]. Assembly Automation, 2022, 42(3): 372-387., articleTitle=Remaining useful life prediction of rolling bearings based on convolutional recurrent attention network, refAbstract=null), Reference(id=1203787164145397830, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2022, volume=55, issue=1/2, pageStart=79, pageEnd=93, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=Ding G, Wang W, Zhao J, journalName=Measurement and Control, refType=null, unstructuredReference=Ding G, Wang W, Zhao J. Prediction of remaining useful life of rolling bearing based on fractal dimension and convolutional neural network[J]. Measurement and Control, 2022, 55(1/2): 79-93., articleTitle=Prediction of remaining useful life of rolling bearing based on fractal dimension and convolutional neural network, refAbstract=null), Reference(id=1203787164271226958, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=Song X, Sun J, Li C, journalName=Proceedings of the Institution of Mecha-nical Engineers, Part E: Journal of Process Mechanical Engineering, refType=null, unstructuredReference=Song X, Sun J, Li C. An entire life-cycle rolling bearing remaining useful life prediction method using new degradation feature evaluation indicators[J]. Proceedings of the Institution of Mecha-nical Engineers, Part E: Journal of Process Mechanical Engineering, 2024: 09544089241228943., articleTitle=An entire life-cycle rolling bearing remaining useful life prediction method using new degradation feature evaluation indicators, refAbstract=null), Reference(id=1203787164459970653, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=5, pageStart=115, pageEnd=121, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=聂磊, 张吕凡, 徐诗奕, journalName=噪声与振动控制, refType=null, unstructuredReference=聂磊, 张吕凡, 徐诗奕, 等. 基于相似度特征融合和CNN的滚动轴承剩余寿命预测[J]. 噪声与振动控制, 2023, 43(5): 115-121., articleTitle=基于相似度特征融合和CNN的滚动轴承剩余寿命预测, refAbstract=null), Reference(id=1203787164581605477, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=5, pageStart=115, pageEnd=121, url=null, language=null, rfNumber=[12], rfOrder=14, authorNames=Nie Lei, Zhang Lüfan, Xu Shiyi, journalName=Noise and Vibration Control, refType=null, unstructuredReference=Nie Lei, Zhang Lüfan, Xu Shiyi, et al. Remaining life prediction of rolling bearings based on similarity feature fusion and convolutional neural network[J]. Noise and Vibration Control, 2023, 43(5): 115-121., articleTitle=Remaining life prediction of rolling bearings based on similarity feature fusion and convolutional neural network, refAbstract=null), Reference(id=1203787164770349166, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=31, pageStart=13328, pageEnd=13333, url=null, language=null, rfNumber=[13], rfOrder=15, authorNames=慎明俊, 高宏玉, 张守京, journalName=科学技术与工程, refType=null, unstructuredReference=慎明俊, 高宏玉, 张守京, 等. 基于DBN-LSTM的滚动轴承剩余寿命预测模型[J]. 科学技术与工程, 2021, 21(31): 13328-13333., articleTitle=基于DBN-LSTM的滚动轴承剩余寿命预测模型, refAbstract=null), Reference(id=1203787164942315638, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=31, pageStart=13328, pageEnd=13333, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=Shen Mingjun, Gao Hongyu, Zhang Shoujing, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Shen Mingjun, Gao Hongyu, Zhang Shoujing, et al. remaining useful life prediction model for rolling bearings based on DBN-LSTM[J]. Science Technology and Engineering, 2021, 21(31): 13328-13333., articleTitle=remaining useful life prediction model for rolling bearings based on DBN-LSTM, refAbstract=null), Reference(id=1203787165030396030, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=17, authorNames=刘路路, journalName=基于特征融合和LSTM的滚动轴承剩余寿命预测, refType=null, unstructuredReference=刘路路. 基于特征融合和LSTM的滚动轴承剩余寿命预测[D]. 成都: 电子科技大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1203787165114282117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=Liu Lulu, journalName=Remaining useful life prediction of rolling bearing based on feature fusion and LSTM, refType=null, unstructuredReference=Liu Lulu. Remaining useful life prediction of rolling bearing based on feature fusion and LSTM[D]. Chengdu: University of Electronic Science and Technology of China, 2022., articleTitle=null, refAbstract=null), Reference(id=1203787165198168204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2020, volume=151, issue=null, pageStart=107162, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=Chen C, Xu T, Wang G, journalName=Measurement, refType=null, unstructuredReference=Chen C, Xu T, Wang G, et al. Railway turnout system RUL prediction based on feature fusion and genetic programming[J]. Measurement, 2020, 151: 107162., articleTitle=Railway turnout system RUL prediction based on feature fusion and genetic programming, refAbstract=null), Reference(id=1203787165315608724, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2018, volume=102, issue=null, pageStart=382, pageEnd=400, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=Baraldi P, Bonfanti G, Zio E, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=Baraldi P, Bonfanti G, Zio E. Differential evolution-based multi-objective optimization for the definition of a health indicator for fault diagnostics and prognostics[J]. Mechanical Systems and Signal Processing, 2018, 102: 382-400., articleTitle=Differential evolution-based multi-objective optimization for the definition of a health indicator for fault diagnostics and prognostics, refAbstract=null), Reference(id=1203787165462409371, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=Nectoux P, Gouriveau R, Medjaher K, journalName=Proceedings of the IEEE International Conference on Prognostics and Health Management IEEE, refType=null, unstructuredReference=Nectoux P, Gouriveau R, Medjaher K, et al. An experimental platform for bearings accelerated degradation tests[C]// Proceedings of the IEEE International Conference on Prognostics and Health Management IEEE. New York: IEEE, 2012: 1-8., articleTitle=An experimental platform for bearings accelerated degradation tests, refAbstract=null)], funds=[Fund(id=1203787161238746073, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, awardId=ZR2021ME242, language=CN, fundingSource=山东省自然科学基金(ZR2021ME242), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1203787151658954986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, xref=null, ext=[AuthorCompanyExt(id=1203787151675732204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China), AuthorCompanyExt(id=1203787151679926510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, companyId=1203787151658954986, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=山东科技大学机械电子工程学院, 青岛 266590)])], figs=[ArticleFig(id=1203787156750840475, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.1, caption=Model structure diagram, figureFileSmall=kkUXIBvI3ryN+PfbvNl04g==, figureFileBig=CREEDvbY5mPGCtJFZLAZFA==, tableContent=null), ArticleFig(id=1203787156885058215, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图1, caption=模型结构图, figureFileSmall=kkUXIBvI3ryN+PfbvNl04g==, figureFileBig=CREEDvbY5mPGCtJFZLAZFA==, tableContent=null), ArticleFig(id=1203787157044441788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.2, caption=The process of constructing degradation indicators and life prediction methods based on ASSF-AAKR, figureFileSmall=sF4HR+8BCBXr28VTe70YQA==, figureFileBig=SL6BPcRfV3T4Y5V2e3Whow==, tableContent=null), ArticleFig(id=1203787157828776649, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图2, caption=基于ASSF-AAKR构建退化指标和寿命预测方法流程, figureFileSmall=sF4HR+8BCBXr28VTe70YQA==, figureFileBig=SL6BPcRfV3T4Y5V2e3Whow==, tableContent=null), ArticleFig(id=1203787157942022866, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.3, caption=PRONOSTIA platform, figureFileSmall=724cMAQHJtlceOw7tqxweg==, figureFileBig=eIWuMpuQu9orY+6wL19P5A==, tableContent=null), ArticleFig(id=1203787158013326043, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图3, caption=PRONOSTIA平台, figureFileSmall=724cMAQHJtlceOw7tqxweg==, figureFileBig=eIWuMpuQu9orY+6wL19P5A==, tableContent=null), ArticleFig(id=1203787158126572263, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.4, caption=Bearing1-1 and 1-3 trend and monotonicity indicators, figureFileSmall=tl1N7woZjPfBWKifKxJr0A==, figureFileBig=0MkLJVoCz6oo1TuF5/Mftw==, tableContent=null), ArticleFig(id=1203787158252401395, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图4, caption=Bearing1-1、1-3趋势性和单调性指标, figureFileSmall=tl1N7woZjPfBWKifKxJr0A==, figureFileBig=0MkLJVoCz6oo1TuF5/Mftw==, tableContent=null), ArticleFig(id=1203787158386619135, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.5, caption=Composite indicators, figureFileSmall=gJ5QxoE/uwOp6Me3VaZb7g==, figureFileBig=1YhNb545DBWj6OzNKtO/6A==, tableContent=null), ArticleFig(id=1203787158508253959, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图5, caption=综合指标, figureFileSmall=gJ5QxoE/uwOp6Me3VaZb7g==, figureFileBig=1YhNb545DBWj6OzNKtO/6A==, tableContent=null), ArticleFig(id=1203787158634083092, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.6, caption=Bearing1-1 degradation curve, figureFileSmall=ediFn5SqskSrNNzLaPbWaw==, figureFileBig=noABTmaDsOldoIXXUtGu6g==, tableContent=null), ArticleFig(id=1203787158755717920, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图6, caption=Bearing1-1退化曲线, figureFileSmall=ediFn5SqskSrNNzLaPbWaw==, figureFileBig=noABTmaDsOldoIXXUtGu6g==, tableContent=null), ArticleFig(id=1203787158965433135, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.7, caption=Bearing1-3 life prediction chart, figureFileSmall=SdgXqit5Jr1SiMgKWESzwQ==, figureFileBig=RG1EmuSQLTGtjG5VkM2CsQ==, tableContent=null), ArticleFig(id=1203787159091262267, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图7, caption=Bearing1-3寿命预测图, figureFileSmall=SdgXqit5Jr1SiMgKWESzwQ==, figureFileBig=RG1EmuSQLTGtjG5VkM2CsQ==, tableContent=null), ArticleFig(id=1203787159250645833, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.8, caption=Comparison of predictions of each model in Bearing1-3, figureFileSmall=HQag4frgMpCiHAXpadSCEQ==, figureFileBig=7pWYg0LzGVNvlCJKSM+ZDg==, tableContent=null), ArticleFig(id=1203787159321949007, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图8, caption=Bearing1-3各模型预测对比, figureFileSmall=HQag4frgMpCiHAXpadSCEQ==, figureFileBig=7pWYg0LzGVNvlCJKSM+ZDg==, tableContent=null), ArticleFig(id=1203787159431000921, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.9, caption=Comparison of predictions of each model in Bearing2-2, figureFileSmall=aflH92uNjxgeouFgP/ufTA==, figureFileBig=sS/Jp0w/S1jR39W6JZ5Whw==, tableContent=null), ArticleFig(id=1203787159561024354, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图9, caption=Bearing2-2各模型预测对比, figureFileSmall=aflH92uNjxgeouFgP/ufTA==, figureFileBig=sS/Jp0w/S1jR39W6JZ5Whw==, tableContent=null), ArticleFig(id=1203787159661687658, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Fig.10, caption=Comparison of predictions of each model in Bearing3-3, figureFileSmall=5uo81xXJ5aXRKrUj2fG8XA==, figureFileBig=+oHw1f1CtFpWs1jYpHG2iA==, tableContent=null), ArticleFig(id=1203787159783322487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=图10, caption=Bearing3-3各模型预测对比, figureFileSmall=5uo81xXJ5aXRKrUj2fG8XA==, figureFileBig=+oHw1f1CtFpWs1jYpHG2iA==, tableContent=null), ArticleFig(id=1203787159934317441, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Table 1, caption=

Feature names and abbreviations

, figureFileSmall=null, figureFileBig=null, tableContent=
特征类型 特征名称
时域特征 方差Var
均值Mean
标准差Std
峰峰值P2P
均方根RMS
绝对均值AbsMean
偏度Skew
峭度Kur
裕度因子MF
脉冲因子IF
峰值因子CF
波形因子WF
频域特征 频率均值FMean
频率均方根FRMS
时频域特征 小波节点能量(NE1-NE8)
), ArticleFig(id=1203787160089506701, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=表1, caption=

特征名称及简称

, figureFileSmall=null, figureFileBig=null, tableContent=
特征类型 特征名称
时域特征 方差Var
均值Mean
标准差Std
峰峰值P2P
均方根RMS
绝对均值AbsMean
偏度Skew
峭度Kur
裕度因子MF
脉冲因子IF
峰值因子CF
波形因子WF
频域特征 频率均值FMean
频率均方根FRMS
时频域特征 小波节点能量(NE1-NE8)
), ArticleFig(id=1203787160232113047, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Table 2, caption=

Data sets

, figureFileSmall=null, figureFileBig=null, tableContent=
工况 转速/
(r·min-1 )
负载/
N
训练数据 测试数据
工况1 1 800 4 000 Bearing1-1、1-2 Bearing1-3、1-4、1-5、
1-6、1-7
工况2 1 650 4 200 Bearing2-1、2-2 Bearing2-3、2-4、2-5、
2-6、2-7
工况3 1 500 5 000 Bearing3-1、3-2 Beaing3-3
), ArticleFig(id=1203787160425051046, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=表2, caption=

数据集情况

, figureFileSmall=null, figureFileBig=null, tableContent=
工况 转速/
(r·min-1 )
负载/
N
训练数据 测试数据
工况1 1 800 4 000 Bearing1-1、1-2 Bearing1-3、1-4、1-5、
1-6、1-7
工况2 1 650 4 200 Bearing2-1、2-2 Bearing2-3、2-4、2-5、
2-6、2-7
工况3 1 500 5 000 Bearing3-1、3-2 Beaing3-3
), ArticleFig(id=1203787160597017514, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Table 3, caption=

Model structure parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 网络层 关键参数
1 卷积层 核大小:7×1,数目:32,步长:1
2 池化层 核大小:2×1,步长:2
3 BILSTM层 LSTM单元数:128,dropout:0.1
4 BILSTM层 LSTM单元数:128,dropout:0.1
5 Liner层 激活函数:ReLU
6 Liner层 激活函数:ReLU
), ArticleFig(id=1203787160710263730, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=表3, caption=

模型结构参数

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 网络层 关键参数
1 卷积层 核大小:7×1,数目:32,步长:1
2 池化层 核大小:2×1,步长:2
3 BILSTM层 LSTM单元数:128,dropout:0.1
4 BILSTM层 LSTM单元数:128,dropout:0.1
5 Liner层 激活函数:ReLU
6 Liner层 激活函数:ReLU
), ArticleFig(id=1203787160810927036, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=EN, label=Table 4, caption=

Comparison of errors of each model

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 Bearing1-3 Bearing2-2 Bearing3-3
MAE RMSE R2 MAE RMSE R2 MAE RMSE R2
LSTM 0.061 8 0.093 8 0.894 4 0.110 8 0.124 9 0.812 9 0.095 6 0.120 4 0.826 0
CNN 0.075 1 0.110 7 0.852 7 0.077 3 0.094 7 0.892 3 0.191 9 0.247 3 0.266 1
CNN-BILSTM-ATT 0.075 7 0.095 6 0.890 3 0.055 6 0.066 4 0.947 1 0.097 9 0.124 5 0.814 1
CNN-BILSTM 0.047 4 0.060 4 0.956 1 0.054 0 0.063 3 0.951 9 0.087 4 0.103 6 0.871 3
), ArticleFig(id=1203787160966116290, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1203753461679628367, language=CN, label=表4, caption=

各模型误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 Bearing1-3 Bearing2-2 Bearing3-3
MAE RMSE R2 MAE RMSE R2 MAE RMSE R2
LSTM 0.061 8 0.093 8 0.894 4 0.110 8 0.124 9 0.812 9 0.095 6 0.120 4 0.826 0
CNN 0.075 1 0.110 7 0.852 7 0.077 3 0.094 7 0.892 3 0.191 9 0.247 3 0.266 1
CNN-BILSTM-ATT 0.075 7 0.095 6 0.890 3 0.055 6 0.066 4 0.947 1 0.097 9 0.124 5 0.814 1
CNN-BILSTM 0.047 4 0.060 4 0.956 1 0.054 0 0.063 3 0.951 9 0.087 4 0.103 6 0.871 3
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402488, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2402488, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2402488, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2402488, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于ASFF-AAKR和CNN-BILSTM滚动轴承寿命预测
收藏切换
PDF下载
张永超 , 刘嵩寿 * , 陈昱锡 , 杨海昆 , 陈庆光
科学技术与工程 | 论文·机械、仪表工业 2025,25(2): 567-573
收起
收藏切换
科学技术与工程 | 论文·机械、仪表工业 2025, 25(2): 567-573
基于ASFF-AAKR和CNN-BILSTM滚动轴承寿命预测
全屏
张永超 , 刘嵩寿* , 陈昱锡, 杨海昆, 陈庆光
作者信息
  • 山东科技大学机械电子工程学院, 青岛 266590
  • 张永超(1977—),男,汉族,山东青岛人,硕士,副教授。研究方向:机电智能控制、流体机械。E-mail:

通讯作者:

* 刘嵩寿(1998—),男,汉族,山东潍坊人,硕士研究生。研究方向:机电装备状态评估与寿命预测。E-mail:
Life Prediction Based on ASFF-AAKR and CNN-BILSTM Rolling Bearings
Yong-chao ZHANG , Song-shou LIU* , Yu-xi CHEN, Hai-kun YANG, Qing-guang CHEN
Affiliations
  • College of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Qingdao 266590, China
出版时间: 2025-01-18 doi: 10.12404/j.issn.1671-1815.2402488
文章导航
收藏切换

针对滚动轴承寿命预测精度低,构建健康指标困难的问题。提出了一种基于自适应特征融合(adaptively spatial feature fusion,ASFF)和自联想核回归模型(auto associative kernel regression, AAKR)与卷积神经网络(convolutional neural networks, CNN)和双向长短期记忆网络(bi-directional long-short term memory,BILSTM)的轴承剩余寿命预测模型。首先,在时域、频域和时频域提取多维特征,利用单调性和趋势性筛选敏感特征;其次利用ASFF-AAKR对敏感特征进行特征融合构建健康指标;最后,将健康指标输入到CNN和BILSTM中,实现对滚动轴承的寿命预测。结果表明:所构建的寿命预测模型优于其他模型,该方法具有更低的误差、寿命预测精度更高。

滚动轴承  /  自适应特征融合  /  自联想核回归  /  卷积神经网络  /  双向长短期记忆网络  /  剩余寿命预测

To address the issues of low accuracy in rolling bearing life prediction and the difficulty of constructing health indicators, a bearing remaining life prediction model based on ASFF (adaptively spatial feature fusion) and AAKR (auto associative kernel regression) combined with CNN (convolutional neural networks) and BILSTM (bi-directional long-short term memory networks) was proposed. Firstly, the multidimensional features were extracted in the time domain, frequency domain, and time-frequency domain, and the sensitive features were screened using monotonicity and trend. Secondly, the sensitive features were feature fused using ASFF-AAKR to construct the health indicators. Finally, the health indicators were inputted into CNN and BILSTM to realize the life prediction of rolling bearings. The results show that the constructed life prediction model is better than other models, and the method has lower error and higher life prediction accuracy.

rolling bearing  /  adaptive feature fusion  /  auto associative kernel regression  /  convolutional neural network  /  bidirectional long short-term memory network  /  remaining life prediction
张永超, 刘嵩寿, 陈昱锡, 杨海昆, 陈庆光. 基于ASFF-AAKR和CNN-BILSTM滚动轴承寿命预测. 科学技术与工程, 2025 , 25 (2) : 567 -573 . DOI: 10.12404/j.issn.1671-1815.2402488
Yong-chao ZHANG, Song-shou LIU, Yu-xi CHEN, Hai-kun YANG, Qing-guang CHEN. Life Prediction Based on ASFF-AAKR and CNN-BILSTM Rolling Bearings[J]. Science Technology and Engineering, 2025 , 25 (2) : 567 -573 . DOI: 10.12404/j.issn.1671-1815.2402488
随着现代工业的高速发展,旋转机械趋于高度化、集成化、智能化的方向发展,而滚动轴承作为旋转机械的关键部位[1],其寿命直接影响旋转机械是否正常运行。因此,对滚动轴承剩余寿命预测(remaining useful fife,RUL)研究对于设备维护、机械系统正常运行具有重要意义[2-3]
目前,对滚动轴承寿命预测大致可以分为两类:基于物理模型预测的方法、基于数据驱动预测的方法[4];基于物理模型预测是通过建立数学退化现象和物理模型来对关键部位的RUL[5],Qian等[5]建立用来描述裂纹扩展的Paris公式;Deng等[6]构建了滚动轴承的五自由度(five-degree-of-freedom,5-DOF)动力学模型,综合考虑退化过程中的裂纹和剥落行为,实现对轴承RUL预测,随着旋转机械结构越来越复杂难以构建物理模型,因此基于物理模型RUL预测难度较高;而基于数据驱动预测的方法逐渐成为主流研究方法[7]。剩余寿命预测一般包括数据采集、构建退化指标和寿命预测3个步骤。Wang等[8]对原始振动信号进行自适应分频,然后根据峰度指数选择最优分量,将最优分量输入CNN网络中实现RUL预测。Zhang等[9]提出了一种卷积循环注意力网络(convolutional recurrent attention networks, CRAN),并通过试验验证了该网络的有效性。Ding等[10]在时域、频域、小波域和熵域等提取多个特征,引入分形维数来衡量滚动轴承的退化,最后用CNN来拟合退化指标与多维特征之间的隐藏关系。Song等[11]通过高斯混合模型(gaussian mixture model, GMM)和支持向量机(support vector machines, SVM)模型对轴承整个寿命周期划分为正常阶段、早期退化阶段和退化阶段3个阶段,引入长短期记忆网络(long short-term memory, LSTM)对轴承退化阶段实现RUL预测。聂磊等[12]首先提取多维特征,用主成分分析法(principal component analysis,PCA)构建健康指标(health indicators,HI),然后输入到CNN提取空间信息特征实现对轴承的寿命预测。慎明俊等[13]首先利用深度置信神经网络(deep belief neural,DBN)提取特征,接着利用长短期记忆网络(long-short term memory,LSTM)能记忆时间序列前后信息实现对轴承的寿命预测。上述方法只采用单一模型,往往忽略了时间序列空间特征或者时间前后关联信息。
因此,现结合CNN和BILSTM建立轴承寿命预测模型,一方面发挥CNN在空间提取特征的优势;另一方面利用BILSTM处理长时间序列优势,使模型同时具有提取空间特征能力和记忆前后信息的能力,同时用ASFF-AAKR模型构建的健康指标能有效反映轴承的退化程度,从而实现更精确的轴承寿命预测。
时域特征能方便看出随时间变换趋势的信息;频域特征是先将时域信号经过快速傅里叶变换(fast fourier transform,FFT)变为频域信号,从频谱信息中可以得到不同频率下频谱的信息,进而可以判断轴承随频率变换的健康状态;时频域分析可以同时从时域和频域来描述非平稳信号随时间的变化,本文研究采用haar小波进行3次小波包分解,选取最后一层8个节点能量特征作为时频域特征。而本文研究从时域、频域、时频域共提取22种特征[14],如表1所示。
原始特征因包含大量冗余信息,不能很好地反映轴承退化信息,固对其做敏感特征的筛选,对每个特征做趋势性和单调性的定量分析。通过趋势性Corr可以了解到原始特征与被测时间的关联程度,趋势性越大,原始特征与真实值越相关。单调性Mon可以衡量信号随时间的波动情况,单调性越大,原始特征更好地反映轴承的退化情况。两者定义为
C o r r i ( f i , T i ) = c o v ( f i , T i ) σ f i σ T i
式(1)中: c o v ( f i , T i )为第 i个特征向量f与时间向量T之间的协方差; σ f i σ T i分别为特征向量fT的标准差。
M o n i = d d f i > 0 - d d f i < 0 N - 1
式(2)中:d/dfi>0和d/dfi<0分别表示导数为正、负的个数; N为特征向量 f的长度。
综合指标Cor是将上述两个评价指标取平均,第 i个特征向量的综合指标计算式为
C o r i = C o r r i + M o n i 2
式(3)中:Corri、Moni分别为第i个特征的趋势性和单调性数值。
得到敏感特征后,生成的特征矩阵是多维的,不能够直接反映轴承在某一时刻的健康状态。针对上述问题,本文研究中采用ASFF和AAKR的方法将多维数据融合为一维数据,以此作为滚动轴承的健康指标。ASFF原理为
d i ( x i t ) = 1 k - 1 i j , i = 1 k ( x i t - x j t ) 2
ω i t = e x p [ - 1 × d i ( x i t ) ]
F ( t ) = i = 1 k ω i t x i t i = 1 k ω i t
式中: d i ( x i t )t时刻第i特征与其他不同特征平均距离; x i t x j t为第ij个特征向量在 t时刻的值; ω i tt时刻第 i特征的权重; F (t) t时刻的HI值。
该算法只是在空间纵轴上对不同特征向量的压缩,而忽略了水平时间轴,本文研究中在此基础上加入AAKF算法[15-16]。首先用ASFF方法得到一维向量 D N o b s,即
F (t) = D N o b s = [ F 1 o b s , F 2 o b s , , F N o b s ]
D N o b s中取 h个样本作健康向量 H h
H h = [ F 1 , F 2 , , F h ]
在向量 D N o b s中,对于任意时刻的特征值 F t o b s与健康向量中第 k个健康值 H (k) 之间的距离为
d k [ F t o b s , H (k) ] = F t o b s - H (k)
F t o b s与健康空间 H k个健康值的权重 ω k
ω k = K h ( d k ) = 1 2 π h 2 e - d k 2 / 2 h 2
健康向量 H (k) 加权平均为
F ^ t o b s = k = 1 h [ ω k H (k) ] k = 1 h ω k
F t o b s F ^ t o b s绝对距离HI为
H I ( t ) = F t o b s - F ^ t o b s
CNN是一种由多层结构构成的前馈神经网络,该网络主要由卷积层、池化层和全连接层构成,其中卷积层和池化层主要用来特征提取,全连接层用来回归或者分类任务。LSTM是循环神经网络(recurrent neural network,RNN)的一种变体,其克服了RNN中梯度消失和梯度爆炸的问题,其主要包括遗忘门、输入门、输出门。BILSTM是LSTM的改进,由前向和后向LSTM共同组成,可以综合提取时间序列前后的信息特征。本文研究提出了一种CNN和BILSTM结合模型,其结构如图1所示。
本文研究的主要方法,如图2所示。从原始水平振动信号中提取时域、频域、时频域多个特征;对每个特征进行单调性和趋势性的定量分析来计算综合指标,大于特定阈值的被认为敏感特征;筛选的敏感特征通过ASFF-AAKR模型进行特征融合构建健康指标;将构建的健康指标输入CNN-BILSTM模型中,预测不同时刻轴承的寿命,并对不同模型预测结果进行误差分析。
为验证本文方法的可靠性,试验数据采用PHM 2012。试验数据在PRONOSTIA(图3)试验台上采集,该试验台上有水平和垂直两个方向加速度计,每次采样时间为0.1 s,每10 s采集一次数据,数据采样频率为25.6 kHz,每个样本有2 560个数据点。数据采集和试验台详细描述参见文献[17]。该数据集共包含3种运行状态下17个滚动轴承加速度振动信号,如表2所示。
以Bearing1-1和Bearing1-3为例,对水平振动信号提取的22个特征进行窗口为50的平滑平均处理(moving average,MA),然后进行归一化处理。通过式(1)和式(2)计算2个轴承的趋势性和单调性,如图4所示。
利用式(3)计算所有工况下17个轴承的平均综合指标,并对综合指标进行归一化处理,通过设定阈值0.5来筛选特征,大于0.5被认为敏感特征,如图5所示。
通过3.2.1节对特征筛选得到的敏感特征,首先利用式(4)~式(6)将多维数据进行自适应特征融合为一维数据 F (t) ,而自联想核回归模型需要健康向量 H h,将一维数据 F (t) 的前 1 / 10长度每隔两个特征值取一个作为健康向量 H h;再根据式(9)计算一维向量与每个健康值的距离,然后再利用式(10)求出每一个健康值的权重,式中 h = 1,最后利用式(11)和式(12)得到每个时刻的HI。
基于ASFF-AAKR模型融合敏感特征,得到Bearing1-1的HI,如图6所示。从图6可以看出前中期退化缓慢,后期退化加剧,能有效反映轴承的退化程度。
对每个样本 ( X i , Y i ), X i是作为模型的输入, Y i是轴承寿命标签,当 t=0时, Y i为1,表示轴承刚开始退化; Y i=0时,表示轴承完全失效。公式为
Y t = N - N t N
式(13)中: N为样本点; N t为当前监测点。
模型的输入将对RUL产生直接的影响,因此给模型输入有效的特征至关重要。本文研究将构建的HI采用时间窗口为6的处理,网络模型采用均方误差(mean square error, MSE)作为损失函数,采用Adam优化器,学习率为0.001,批次为64,迭代次数250。本文模型参数如表3所示。
在工况1下,以Bearing1-1全寿命数据作为训练数据集,Bearing1-3作为测试集;对于工况2下,以Bearing2-1全寿命数据作为训练数据集, Bearing2-2作为测试集;对于工况3下,以Bearing3-1全寿命数据作为训练数据集, Bearing3-3作为测试集。Bearing1-3预测结果如图7所示,从图7可以看出,前期预测较差,中后期预测的趋势和真实趋势非常接近。
为了验证CNN-BILSTM模型的有效性,该模型预测结果与CNN、LSTM和CNN-BILSTM-ATT模型预测结果进行了对比,其结果如图8~图10所示,使用平均绝对误差(mean absolute error,MAE)、均方根误差(root mean square error,RMSE)和决定系数(R-square,R2)对模型进行评价,如式(14)~式(16)所示。MAE、RMAE越小模型越好,R2越大模型越好。
M A E = i = 1 n p i - y i n
R M S E = i = 1 n ( p i - y i ) 2 n
R 2 = 1 - i = 1 n ( p i - y i ) 2 i = 1 n ( p i ¯ - y i ) 2
式中: p i为真实值; y i为预测值; n为样本点; p i ¯为真实值的平均值。
表4可以看出,在3种不同工况下的轴承RUL,采用CNN-BILSTM模型预测的MAE比LSTM模型平均降低了27.7%,比CNN模型和CNN-BILSTM-ATT模型分别平均降低了40.8%、17.1%;RMSE对比LSTM、CNN、CNN-BILSTM-ATT模型分别平均降低了32.9%、45.5%、19.4%;R2对比LSTM、CNN、CNN-BILSTM-ATT模型分别平均提升了9.8%、13.8%、4.97%。由此可见,本文模型预测精度更高。
针对滚动轴承寿命预测精度低,构建健康指标的困难问题,提出了一种ASFF-AAKR和CNN-BILSTM模型对滚动轴承寿命预测方法,经过试验验证得出以下结论。
(1)首先在时域、频域、时频域提取多维特征,然后通过趋势性和单调性计算综合指标来筛选敏感特征,筛选的敏感特征有效剔除了冗余信息。
(2)将得到的敏感特征通过ASFF-AAKR模型进行特征融合得到健康指标,健康指标能有效反映轴承退化信息。
(3)构建的退化模型CNN-BILSTM相比LSTM、CNN、CNN-BILSTM-ATT误差更低,该模型更能精确地预测滚动轴承的寿命。
  • 山东省自然科学基金(ZR2021ME242)
参考文献 引证文献
排序方式:
[1]
Zhang X, Yang J, Yang X. Residual life prediction of rolling bearings based on a CEEMDAN algorithm fused with CNN-attention-based bidirectional LSTM modeling[J]. Processes, 2023, 12(1): 1-8.
[2]
Deutsch J, He D. Using deep learning-based approach to predict remaining useful life of rotating components[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017, 48(1): 11-20.
[3]
Yang C, Ma J, Wang X, et al. A novel based-performance degradation indicator RUL prediction model and its application in rolling bearing[J]. ISA Transactions, 2022, 121: 349-364.
[4]
张金豹, 邹天刚, 王敏, 等. 滚动轴承剩余使用寿命预测综述[J]. 机械科学与技术, 2023, 42(1): 1-23.
Zhang Jinbao, Zou Tiangang, Wang Min, et al. Review on remaining useful life prediction of rolling bearing[J]. Mechanical Science and Technology for Aerospace Engineering, 2023, 42(1): 1-23.
[5]
Qian Y, Yan R, Gao R X. A multi-time scale approach to remaining useful life prediction in rolling bearing[J]. Mechanical Systems and Signal Processing, 2017, 83(3): 549-567.
[6]
Deng Y, Du S, Wang D, et al. A calibration-based hybrid transfer learning framework for RUL prediction of rolling bearing across different machines[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-15.
[7]
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.
Si Xiaosheng, Hu Changhua. Data-driven remaining useful life prediction theory and applications for equipment[M]. Beijing: Natio-nal Defense Industry Press, 2016.
[8]
Wang W, Zhao J, Ding G. RUL prediction of rolling bearings based on improved empirical wavelet transform and convolutional neural network[J]. Advances in Mechanical Engineering, 2022, 14(6): 16878132221106609.
[9]
Zhang Q, Ye Z, Shao S, et al. Remaining useful life prediction of rolling bearings based on convolutional recurrent attention network[J]. Assembly Automation, 2022, 42(3): 372-387.
[10]
Ding G, Wang W, Zhao J. Prediction of remaining useful life of rolling bearing based on fractal dimension and convolutional neural network[J]. Measurement and Control, 2022, 55(1/2): 79-93.
[11]
Song X, Sun J, Li C. An entire life-cycle rolling bearing remaining useful life prediction method using new degradation feature evaluation indicators[J]. Proceedings of the Institution of Mecha-nical Engineers, Part E: Journal of Process Mechanical Engineering, 2024: 09544089241228943.
[12]
聂磊, 张吕凡, 徐诗奕, 等. 基于相似度特征融合和CNN的滚动轴承剩余寿命预测[J]. 噪声与振动控制, 2023, 43(5): 115-121.
Nie Lei, Zhang Lüfan, Xu Shiyi, et al. Remaining life prediction of rolling bearings based on similarity feature fusion and convolutional neural network[J]. Noise and Vibration Control, 2023, 43(5): 115-121.
[13]
慎明俊, 高宏玉, 张守京, 等. 基于DBN-LSTM的滚动轴承剩余寿命预测模型[J]. 科学技术与工程, 2021, 21(31): 13328-13333.
Shen Mingjun, Gao Hongyu, Zhang Shoujing, et al. remaining useful life prediction model for rolling bearings based on DBN-LSTM[J]. Science Technology and Engineering, 2021, 21(31): 13328-13333.
[14]
刘路路. 基于特征融合和LSTM的滚动轴承剩余寿命预测[D]. 成都: 电子科技大学, 2022.
Liu Lulu. Remaining useful life prediction of rolling bearing based on feature fusion and LSTM[D]. Chengdu: University of Electronic Science and Technology of China, 2022.
[15]
Chen C, Xu T, Wang G, et al. Railway turnout system RUL prediction based on feature fusion and genetic programming[J]. Measurement, 2020, 151: 107162.
[16]
Baraldi P, Bonfanti G, Zio E. Differential evolution-based multi-objective optimization for the definition of a health indicator for fault diagnostics and prognostics[J]. Mechanical Systems and Signal Processing, 2018, 102: 382-400.
[17]
Nectoux P, Gouriveau R, Medjaher K, et al. An experimental platform for bearings accelerated degradation tests[C]// Proceedings of the IEEE International Conference on Prognostics and Health Management IEEE. New York: IEEE, 2012: 1-8.
2025年第25卷第2期
PDF下载
258
108
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2402488
  • 接收时间:2024-04-07
  • 首发时间:2025-12-05
  • 出版时间:2025-01-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-04-07
  • 修回日期:2024-11-06
基金
山东省自然科学基金(ZR2021ME242)
作者信息
    山东科技大学机械电子工程学院, 青岛 266590

通讯作者:

* 刘嵩寿(1998—),男,汉族,山东潍坊人,硕士研究生。研究方向:机电装备状态评估与寿命预测。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402488
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