Article(id=1149776905395725043, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149776900194791454, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2309051, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1700150400000, receivedDateStr=2023-11-17, revisedDate=1719158400000, revisedDateStr=2024-06-24, acceptedDate=null, acceptedDateStr=null, onlineDate=1752057776068, onlineDateStr=2025-07-09, pubDate=1744905600000, pubDateStr=2025-04-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752057776068, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752057776068, creator=13701087609, updateTime=1752057776068, updator=13701087609, issue=Issue{id=1149776900194791454, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='11', pageStart='4397', pageEnd='4826', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752057774827, creator=13701087609, updateTime=1768456666677, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218558837930512931, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149776900194791454, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218558837930512932, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149776900194791454, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=4551, endPage=4558, ext={EN=ArticleExt(id=1149776905815155444, articleId=1149776905395725043, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Fault Diagnosis of Yaw Damper Based on KPCA-SO-KELM, columnId=1156262732765717457, journalTitle=Science Technology and Engineering, columnName=Papers·Mechanical and Instrumental Industry, runingTitle=null, highlight=null, articleAbstract=

Aiming at the problem that the vibration signals in train operation are complex and nonlinear, and the information of single channel signal is incomplete, a fault diagnosis method of yaw damper based on multi-channel signal fusion on car body and bogie was proposed. Firstly, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was performed on the signals of multiple train channels, and the intrinsic mode function (IMF) was extracted to compose the feature set of refined composite multiscale dispersion entropy. Secondly, kernel principal component analysis (KPCA) was used to reduce the dimensionality of the extracted feature set. Finally, the optimal feature subset was inputted into the snake optimized kernel extreme learning machine (SO-KELM) to diagnose the yaw damper fault types. The experimental results show that the multi-channel fusion feature set optimized by kernel principal component analysis can accurately reflect the signal characteristics of different fault types of yaw damper, and realize the fault diagnosis of yaw damper. The superiority of this method is verified by comparing with other models.

, correspAuthors=Mao-ru CHI, 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=Chao-yu CEN, Liang-cheng DAI, Mao-ru CHI, Ming-hua ZHAO), CN=ArticleExt(id=1149776931412992328, articleId=1149776905395725043, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于KPCA-SO-KELM的抗蛇行减振器故障诊断, columnId=1156262732954461139, journalTitle=科学技术与工程, columnName=论文·机械、仪表工业, runingTitle=null, highlight=null, articleAbstract=

针对列车运行过程中的振动信号是复杂非线性的,并且单一通道的信号存在着信息不完全的问题,提出了一种车体和转向架上多个通道信号融合的抗蛇行减振器故障诊断的方法。首先,对列车多个通道的信号进行自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN),提取分解后的本征模态函数(intrinsic mode function, IMF)精细复合多尺度散布熵(refined composite multiscale dispersion entropy, RCMDE)组成特征集;其次,用核主成分分析法(kernel principal component analysis, KPCA)对提取出的特征集进行降维;最后,将最优特征子集输入到蛇优化的核极限学习机(snake optimized kernel extreme learning machine, SO-KELM)中来诊断抗蛇行减振器故障类型。试验结果表明,经过核主成分分析法优选过后的多通道融合特征集能够准确反映抗蛇行减振器不同故障类型信号特征,实现了抗蛇行减振器的故障诊断,并将蛇优化核极限学习机与其他模型对比验证了该方法的优越性。

, correspAuthors=池茂儒, authorNote=null, correspAuthorsNote=
* 池茂儒(1973—),男,汉族,四川通江人,博士,研究员。研究方向:车辆系统动力学。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=DXVWBRoj1lDGjpvzJHnhhg==, magXml=alaRgnI0YfU0sMi7pGNaCQ==, pdfUrl=null, pdf=TsRmvgYIclv+TH9hkyg0vQ==, pdfFileSize=5258413, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=4+WYclMvrJBI0QsRorI5mQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=dbzg8c5ocXueS9gWU9rN9A==, mapNumber=null, authorCompany=null, fund=null, authors=

岑潮宇(2000—),男,汉族,河北滦南人,硕士研究生。研究方向:车辆系统动力学。E-mail:

, authorsList=岑潮宇, 代亮成, 池茂儒, 赵明花)}, authors=[Author(id=1218843912039485641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cenchaoyuyyn@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1218843912156926167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, authorId=1218843912039485641, language=EN, stringName=Chao-yu CEN, firstName=Chao-yu, middleName=null, lastName=CEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218843912307921121, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, authorId=1218843912039485641, language=CN, stringName=岑潮宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西南交通大学轨道交通运载系统全国重点实验室, 成都610031, bio={"content":"

岑潮宇(2000—),男,汉族,河北滦南人,硕士研究生。研究方向:车辆系统动力学。E-mail:

"}, bioImg=null, bioContent=

岑潮宇(2000—),男,汉族,河北滦南人,硕士研究生。研究方向:车辆系统动力学。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218843911880102072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, xref=null, ext=[AuthorCompanyExt(id=1218843911888490682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China), AuthorCompanyExt(id=1218843911896879291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西南交通大学轨道交通运载系统全国重点实验室, 成都610031)])]), Author(id=1218843912416973033, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, orderNo=1, 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=1218843912546996472, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, authorId=1218843912416973033, language=EN, stringName=Liang-cheng DAI, firstName=Liang-cheng, middleName=null, lastName=DAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218843912660242692, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, authorId=1218843912416973033, language=CN, stringName=代亮成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西南交通大学轨道交通运载系统全国重点实验室, 成都610031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218843911880102072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, xref=null, ext=[AuthorCompanyExt(id=1218843911888490682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China), AuthorCompanyExt(id=1218843911896879291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西南交通大学轨道交通运载系统全国重点实验室, 成都610031)])]), Author(id=1218843912794460437, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cmr2000@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1218843912941261093, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, authorId=1218843912794460437, language=EN, stringName=Mao-ru CHI, firstName=Mao-ru, middleName=null, lastName=CHI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218843913100644657, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, authorId=1218843912794460437, language=CN, stringName=池茂儒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=西南交通大学轨道交通运载系统全国重点实验室, 成都610031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218843911880102072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, xref=null, ext=[AuthorCompanyExt(id=1218843911888490682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China), AuthorCompanyExt(id=1218843911896879291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西南交通大学轨道交通运载系统全国重点实验室, 成都610031)])]), Author(id=1218843913205502268, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, 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=1218843913360691529, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, authorId=1218843913205502268, language=EN, stringName=Ming-hua ZHAO, firstName=Ming-hua, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218843913436189008, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, authorId=1218843913205502268, language=CN, stringName=赵明花, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西南交通大学轨道交通运载系统全国重点实验室, 成都610031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218843911880102072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, xref=null, ext=[AuthorCompanyExt(id=1218843911888490682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China), AuthorCompanyExt(id=1218843911896879291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西南交通大学轨道交通运载系统全国重点实验室, 成都610031)])])], keywords=[Keyword(id=1218843913603961185, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, orderNo=1, keyword=yaw damper), Keyword(id=1218843913721401703, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, orderNo=2, keyword=refined composite multiscale dispersion entropy), Keyword(id=1218843913843036531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, orderNo=3, keyword=fault diagnosis), Keyword(id=1218843913943699835, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, orderNo=4, keyword=snake optimizer), Keyword(id=1218843914065334661, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, orderNo=5, keyword=kernel principal component analysis), Keyword(id=1218843914195358095, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, orderNo=1, keyword=抗蛇行减振器), Keyword(id=1218843914296021398, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, orderNo=2, keyword=精细复合多尺度散布熵), Keyword(id=1218843914388296091, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, orderNo=3, keyword=故障诊断), Keyword(id=1218843914501542308, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, orderNo=4, keyword=蛇优化), Keyword(id=1218843914648342956, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, orderNo=5, keyword=核主成分分析)], refs=[Reference(id=1218843917278171728, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=10, pageStart=210, pageEnd=215, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=蒋益平, 池茂儒, 朱海燕, journalName=科学技术与工程, refType=null, unstructuredReference=蒋益平, 池茂儒, 朱海燕. 不同位置横向减振器失效对地铁车辆动力学性能影响[J]. 科学技术与工程, 2019, 19(10): 210-215., articleTitle=不同位置横向减振器失效对地铁车辆动力学性能影响, refAbstract=null), Reference(id=1218843917399806552, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=10, pageStart=210, pageEnd=215, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Jiang Yiping, Chi Maoru, Zhu Haiyan, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Jiang Yiping, Chi Maoru, Zhu Haiyan. Effects of lateral damper invalid at different location on the dynamic performance of metro vehicle[J]. Science Technology and Engineering, 2019, 19(10): 210-215., articleTitle=Effects of lateral damper invalid at different location on the dynamic performance of metro vehicle, refAbstract=null), Reference(id=1218843917500469854, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2022, volume=35, issue=6, pageStart=1461, pageEnd=1470, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=姚远, 程俊, 张名扬, journalName=振动工程学报, refType=null, unstructuredReference=姚远, 程俊, 张名扬, 等. 高速列车抗蛇行减振器作用机制与频变刚度应用研究[J]. 振动工程学报, 2022, 35(6): 1461-1470., articleTitle=高速列车抗蛇行减振器作用机制与频变刚度应用研究, refAbstract=null), Reference(id=1218843917596938850, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2022, volume=35, issue=6, pageStart=1461, pageEnd=1470, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Yao Yuan, Cheng Jun, Zhang Mingyang, journalName=Journal of Vibration Engineering, refType=null, unstructuredReference=Yao Yuan, Cheng Jun, Zhang Mingyang, et al. Mechanism analysis of yaw damper in high-speed train and frequency-dependent stiffness application[J]. Journal of Vibration Engineering, 2022, 35(6): 1461-1470., articleTitle=Mechanism analysis of yaw damper in high-speed train and frequency-dependent stiffness application, refAbstract=null), Reference(id=1218843917664047720, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=6, pageStart=1155, pageEnd=1160, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=孙建锋, 池茂儒, 吴兴文, journalName=振动.测试与诊断, refType=null, unstructuredReference=孙建锋, 池茂儒, 吴兴文, 等. 抗蛇行减振器参数对车辆稳定性的影响分析[J]. 振动.测试与诊断, 2018, 38(6): 1155-1160, 1291., articleTitle=抗蛇行减振器参数对车辆稳定性的影响分析, refAbstract=null), Reference(id=1218843917773099633, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=6, pageStart=1155, pageEnd=1160, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Sun Jianfeng, Chi Maoru, Wu Xingwen, journalName=Journal of Vibration, Measurement & Diagnosis, refType=null, unstructuredReference=Sun Jianfeng, Chi Maoru, Wu Xingwen, et al. Analysis of the influences of the yaw damper parameters on the vehicle stability[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(6): 1155-1160, 1291., articleTitle=Analysis of the influences of the yaw damper parameters on the vehicle stability, refAbstract=null), Reference(id=1218843917865374328, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2021, volume=18, issue=3, pageStart=737, pageEnd=743, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=卢昌宏, 张利斌, 张恒志, journalName=铁道科学与工程学报, refType=null, unstructuredReference=卢昌宏, 张利斌, 张恒志, 等. 一种多通道信息融合的横向减振器性能退化阶段辨别方法[J]. 铁道科学与工程学报, 2021, 18(3): 737-743., articleTitle=一种多通道信息融合的横向减振器性能退化阶段辨别方法, refAbstract=null), Reference(id=1218843917991203455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2021, volume=18, issue=3, pageStart=737, pageEnd=743, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Lu Changhong, Zhang Libin, Zhang Hengzhi, journalName=Journal of Railway Science and Engineering, refType=null, unstructuredReference=Lu Changhong, Zhang Libin, Zhang Hengzhi, et al. A multi-channel information fusion lateral damper performance degradation stage identification method[J]. Journal of Railway Science and Engineering, 2021, 18(3): 737-743., articleTitle=A multi-channel information fusion lateral damper performance degradation stage identification method, refAbstract=null), Reference(id=1218843918104449668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2016, volume=33, issue=9, pageStart=2648, pageEnd=2651, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=李辉, 金炜东, journalName=计算机应用研究, refType=null, unstructuredReference=李辉, 金炜东. 基于白噪声统计特性与EEMD的高速列车横向减振器故障诊断[J]. 计算机应用研究, 2016, 33(9): 2648-2651., articleTitle=基于白噪声统计特性与EEMD的高速列车横向减振器故障诊断, refAbstract=null), Reference(id=1218843918247056011, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2016, volume=33, issue=9, pageStart=2648, pageEnd=2651, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Li Hui, Jin Weidong, journalName=Application Research of Computer, refType=null, unstructuredReference=Li Hui, Jin Weidong. Lateral damper fault diagnosis of high-speed train based on statistical characteristics of white noise and EEMD[J]. Application Research of Computer, 2016, 33(9): 2648-2651., articleTitle=Lateral damper fault diagnosis of high-speed train based on statistical characteristics of white noise and EEMD, refAbstract=null), Reference(id=1218843918356107920, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2016, volume=52, issue=14, pageStart=226, pageEnd=231, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=王卫朝, 石国良, 李晓, journalName=计算机工程与应用, refType=null, unstructuredReference=王卫朝, 石国良, 李晓, 等. 应用EMD熵和Relief分析高铁横向减振器故障[J]. 计算机工程与应用, 2016, 52(14): 226-231, 236., articleTitle=应用EMD熵和Relief分析高铁横向减振器故障, refAbstract=null), Reference(id=1218843918448382612, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2016, volume=52, issue=14, pageStart=226, pageEnd=231, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Wang Weizhao, Shi Guoliang, Li Xiao, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=Wang Weizhao, Shi Guoliang, Li Xiao, et al. Application of EMD entropy and Relief in fault analysis of high-speed train lateral damper failure[J]. Computer Engineering and Applications, 2016, 52(14): 226-231, 236., articleTitle=Application of EMD entropy and Relief in fault analysis of high-speed train lateral damper failure, refAbstract=null), Reference(id=1218843918603571872, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=6, pageStart=34, pageEnd=41, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=郑航, 李刚, 李德仓, journalName=电力机车与城轨车辆, refType=null, unstructuredReference=郑航, 李刚, 李德仓. 基于PELCD样本熵的抗蛇行减振器故障诊断[J]. 电力机车与城轨车辆, 2023, 46(6): 34-41., articleTitle=基于PELCD样本熵的抗蛇行减振器故障诊断, refAbstract=null), Reference(id=1218843918687457960, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=6, pageStart=34, pageEnd=41, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Zheng Hang, Li Gang, Li Decang, journalName=Electric Locomotives & Mass Transit Vehicles, refType=null, unstructuredReference=Zheng Hang, Li Gang, Li Decang. Fault diagnosis of anti-yaw damper based on PELCD sample entropy[J]. Electric Locomotives & Mass Transit Vehicles, 2023, 46(6): 34-41., articleTitle=Fault diagnosis of anti-yaw damper based on PELCD sample entropy, refAbstract=null), Reference(id=1218843918796509871, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2009, volume=29, issue=1, pageStart=101, pageEnd=104, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=王小亮, 李立, 张卫华, journalName=振动、测试与诊断, refType=null, unstructuredReference=王小亮, 李立, 张卫华. 高速列车垂向振动的模拟器再现方法研究[J]. 振动、测试与诊断, 2009, 29(1): 101-104., articleTitle=高速列车垂向振动的模拟器再现方法研究, refAbstract=null), Reference(id=1218843918872007347, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2009, volume=29, issue=1, pageStart=101, pageEnd=104, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Wang Xiaoliang, Li Li, Zhang Weihua, journalName=Journal of Vibration, Measurement & Diagnosis, refType=null, unstructuredReference=Wang Xiaoliang, Li Li, Zhang Weihua. Fuzzy self-tuning based washout algorithm for simulator of high speed locomotive vertical vibration[J]. Journal of Vibration, Measurement & Diagnosis, 2009, 29(1): 101-104., articleTitle=Fuzzy self-tuning based washout algorithm for simulator of high speed locomotive vertical vibration, refAbstract=null), Reference(id=1218843918989447862, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=4144, pageEnd=4147, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=Torres M E, Colominas M A, Schlotthauer G, journalName=IEEE International Conference on Acoustics, Speech and Signal Processing, refType=null, unstructuredReference=Torres M E, Colominas M A, Schlotthauer G, et al. A complete ensemble empirical mode decomposition with adaptive noise[C]// IEEE International Conference on Acoustics, Speech and Signal Processing. New York: IEEE, 2011: 4144-4147., articleTitle=A complete ensemble empirical mode decomposition with adaptive noise, refAbstract=null), Reference(id=1218843919132054204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=28, pageStart=11980, pageEnd=11989, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=顾春生, 唐鑫, 朱常坤, journalName=科学技术与工程, refType=null, unstructuredReference=顾春生, 唐鑫, 朱常坤, 等. 基于主成分分析法优化神经网络的滆湖组黏性土抗剪强度预测[J]. 科学技术与工程, 2023, 23(28): 11980-11989., articleTitle=基于主成分分析法优化神经网络的滆湖组黏性土抗剪强度预测, refAbstract=null), Reference(id=1218843919224328896, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=28, pageStart=11980, pageEnd=11989, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=Gu Chunsheng, Tang Xin, Zhu Changkun, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Gu Chunsheng, Tang Xin, Zhu Changkun, et al. Prediction of shear strength of cohesive soil in gehu formation based on back propagation neural network optimized by principal component analysis[J]. Science Technology and Engineering, 2023, 23(28): 11980-11989., articleTitle=Prediction of shear strength of cohesive soil in gehu formation based on back propagation neural network optimized by principal component analysis, refAbstract=null), Reference(id=1218843919362740935, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2013, volume=13, issue=25, pageStart=7371, pageEnd=7376, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=杨雪梅, journalName=科学技术与工程, refType=null, unstructuredReference=杨雪梅. 基于KPCA及SVM的蛋白质O-糖基化位点的预测[J]. 科学技术与工程, 2013, 13(25): 7371-7376., articleTitle=基于KPCA及SVM的蛋白质O-糖基化位点的预测, refAbstract=null), Reference(id=1218843919475987149, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2013, volume=13, issue=25, pageStart=7371, pageEnd=7376, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=Yang Xuemei, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Yang Xuemei. Prediction of the protein oglycosylation by kernel principal component analysis and support vector machines[J]. Science Technology and Engineering, 2013, 13(25): 7371-7376., articleTitle=Prediction of the protein oglycosylation by kernel principal component analysis and support vector machines, refAbstract=null), Reference(id=1218843919606010576, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=7, pageStart=1180, pageEnd=1189, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=王利福, 魏玉琪, 刘屹江泽, journalName=控制工程, refType=null, unstructuredReference=王利福, 魏玉琪, 刘屹江泽. 基于KPCA与IPFA-KELM的变压器故障识别方法[J]. 控制工程, 2023, 30(7): 1180-1189., articleTitle=基于KPCA与IPFA-KELM的变压器故障识别方法, refAbstract=null), Reference(id=1218843919719256791, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=7, pageStart=1180, pageEnd=1189, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=Wang Lifu, Wei Yuqi, Liu Yijiangze, journalName=Control Engineering of China, refType=null, unstructuredReference=Wang Lifu, Wei Yuqi, Liu Yijiangze. Transformer fault identification method based on KPCA and IPFA-KELM[J]. Control Engineering of China, 2023, 30(7): 1180-1189., articleTitle=Transformer fault identification method based on KPCA and IPFA-KELM, refAbstract=null), Reference(id=1218843919832503003, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=5, pageStart=1459, pageEnd=1464, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=闫鹏程, 张超银, 孙全胜, journalName=光谱学与光谱分析, refType=null, unstructuredReference=闫鹏程, 张超银, 孙全胜, 等. LIF技术与ELM算法的电力变压器故障诊断研究[J]. 光谱学与光谱分析, 2022, 42(5): 1459-1464., articleTitle=LIF技术与ELM算法的电力变压器故障诊断研究, refAbstract=null), Reference(id=1218843919933166304, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=5, pageStart=1459, pageEnd=1464, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=Yan Pengcheng, Zhang Chaoyin, Sun Quansheng, journalName=Spectroscopy and Spectral Analysis, refType=null, unstructuredReference=Yan Pengcheng, Zhang Chaoyin, Sun Quansheng, et al. LIF technology and ELM algorithm power transformer fault diagnosis research[J]. Spectroscopy and Spectral Analysis, 2022, 42(5): 1459-1464., articleTitle=LIF technology and ELM algorithm power transformer fault diagnosis research, refAbstract=null), Reference(id=1218843920046412517, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2017, volume=64, issue=12, pageStart=2872, pageEnd=2879, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=Azami H, Rostaghi M, Abasolo D, journalName=IEEE Transactions on Biomedical Engineering, refType=null, unstructuredReference=Azami H, Rostaghi M, Abasolo D, et al. Refined composite multiscale dispersion entropy and its application to bio medical signals[J]. IEEE Transactions on Biomedical Engineering, 2017, 64(12): 2872-2879., articleTitle=Refined composite multiscale dispersion entropy and its application to bio medical signals, refAbstract=null), Reference(id=1218843920142881513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2022, volume=242, issue=null, pageStart=108320, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=26, authorNames=Hashim F A, Hussien A G, journalName=Knowledge-Based Systems, refType=null, unstructuredReference=Hashim F A, Hussien A G. Snake optimizer: a novel meta-heuristic optimization algorithm[J]. Knowledge-Based Systems, 2022, 242: 108320., articleTitle=Snake optimizer: a novel meta-heuristic optimization algorithm, refAbstract=null), Reference(id=1218843920247739116, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2014, volume=6, issue=3, pageStart=376, pageEnd=390, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=Huang G B, journalName=Cognitive Computation, refType=null, unstructuredReference=Huang G B. An insight into extreme learning machines: random neurons, random features and kernels[J]. Cognitive Computation, 2014, 6(3): 376-390., articleTitle=An insight into extreme learning machines: random neurons, random features and kernels, refAbstract=null), Reference(id=1218843920373568242, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2012, volume=42, issue=2, pageStart=513, pageEnd=529, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=Huang G B, Zhou H M, Ding X J, journalName=IEEE Transactions Systems, Man and Cybernetics, Part B: Cybernetics, refType=null, unstructuredReference=Huang G B, Zhou H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions Systems, Man and Cybernetics, Part B: Cybernetics, 2012, 42(2): 513-529., articleTitle=Extreme learning machine for regression and multiclass classification, refAbstract=null), Reference(id=1218843920478425843, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2021, volume=15, issue=6, pageStart=1155, pageEnd=1164, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=毛清华, 张强, journalName=计算机科学与探索, refType=null, unstructuredReference=毛清华, 张强. 融合柯西变异和反向学习的改进麻雀算法[J]. 计算机科学与探索, 2021, 15(6): 1155-1164., articleTitle=融合柯西变异和反向学习的改进麻雀算法, refAbstract=null), Reference(id=1218843920566506229, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, doi=null, pmid=null, pmcid=null, year=2021, volume=15, issue=6, pageStart=1155, pageEnd=1164, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=Mao Qinghua, Zhang Qiang, journalName=Journal of Frontiers of Computer Science and Technology, refType=null, unstructuredReference=Mao Qinghua, Zhang Qiang. Improved sparrow algorithm combining cauchy mutation and opposition-based learning[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(6): 1155-1164., articleTitle=Improved sparrow algorithm combining cauchy mutation and opposition-based learning, refAbstract=null)], funds=[Fund(id=1218843916971987522, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, awardId=2022YFB4301303, language=CN, fundingSource=国家重点研发计划(2022YFB4301303), fundOrder=null, country=null), Fund(id=1218843917081039432, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, awardId=K2022J004, language=CN, fundingSource=中国国家铁路集团有限公司科技研究开发计划(K2022J004), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1218843911880102072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, xref=null, ext=[AuthorCompanyExt(id=1218843911888490682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China), AuthorCompanyExt(id=1218843911896879291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, companyId=1218843911880102072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西南交通大学轨道交通运载系统全国重点实验室, 成都610031)])], figs=[ArticleFig(id=1218843914883224004, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, label=Fig.1, caption=Fault diagnosis flow chart, figureFileSmall=4u5n5jjub6RihObpWTnVxw==, figureFileBig=Ra8sI7kYI0rDAwF0XclQ/g==, tableContent=null), ArticleFig(id=1218843915000664522, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, label=图1, caption=故障诊断流程图, figureFileSmall=4u5n5jjub6RihObpWTnVxw==, figureFileBig=Ra8sI7kYI0rDAwF0XclQ/g==, tableContent=null), ArticleFig(id=1218843915143270870, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, label=Fig.2, caption=Vibration signal, figureFileSmall=DrkZVuI4Bxn1cSSEkpe5uA==, figureFileBig=Z31XyJXrvHKZMf4K/3DNJQ==, tableContent=null), ArticleFig(id=1218843915260711390, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, label=图2, caption=振动信号, figureFileSmall=DrkZVuI4Bxn1cSSEkpe5uA==, figureFileBig=Z31XyJXrvHKZMf4K/3DNJQ==, tableContent=null), ArticleFig(id=1218843915445260772, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, label=Fig.3, caption=Principal component contribution rate, figureFileSmall=YK9CZ/+U4oFJf2Q+E1eQ2A==, figureFileBig=YPNVxs56D1Mg2+q8GIAcpg==, tableContent=null), ArticleFig(id=1218843915562701294, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, label=图3, caption=主成分贡献率, figureFileSmall=YK9CZ/+U4oFJf2Q+E1eQ2A==, figureFileBig=YPNVxs56D1Mg2+q8GIAcpg==, tableContent=null), ArticleFig(id=1218843915705307639, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, label=Fig.4, caption=Accuracy of test sets with different feature dimensions, figureFileSmall=dCmfIjdBbKd//AoA3+qJNA==, figureFileBig=fXHe2tWZ+/fD7tVfvqZBeg==, tableContent=null), ArticleFig(id=1218843915835331070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, label=图4, caption=不同特征维数测试集正确率, figureFileSmall=dCmfIjdBbKd//AoA3+qJNA==, figureFileBig=fXHe2tWZ+/fD7tVfvqZBeg==, tableContent=null), ArticleFig(id=1218843915956965892, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, label=Fig.5, caption=Diagnostic results after KPCA downscaling, figureFileSmall=le9BYFD3yUz8t0jGrU+Ygw==, figureFileBig=5Lf9LJTbvf0uiD4WMfAXXw==, tableContent=null), ArticleFig(id=1218843916082795019, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, label=图5, caption=KPCA降维后的诊断结果, figureFileSmall=le9BYFD3yUz8t0jGrU+Ygw==, figureFileBig=5Lf9LJTbvf0uiD4WMfAXXw==, tableContent=null), ArticleFig(id=1218843916179264016, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, label=Fig.6, caption=Fitness value change curve, figureFileSmall=b/6Gu/ZQdaOphEFoDuweHw==, figureFileBig=/zJhcuhgFEPRVuzrSOtVmg==, tableContent=null), ArticleFig(id=1218843916279927318, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, label=图6, caption=适应度值变化曲线, figureFileSmall=b/6Gu/ZQdaOphEFoDuweHw==, figureFileBig=/zJhcuhgFEPRVuzrSOtVmg==, tableContent=null), ArticleFig(id=1218843916405756445, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, label=Fig.7, caption=Fault identification results of three models, figureFileSmall=7pwPmcrDpLbkM1FUoimW+g==, figureFileBig=xW1vYCPV9A4LKLeZEUi0Tw==, tableContent=null), ArticleFig(id=1218843916523196962, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, label=图7, caption=3种模型故障预测结果, figureFileSmall=7pwPmcrDpLbkM1FUoimW+g==, figureFileBig=xW1vYCPV9A4LKLeZEUi0Tw==, tableContent=null), ArticleFig(id=1218843916649026088, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=EN, label=Fig.8, caption=Diagnostic accuracy of different training sets, figureFileSmall=omBrjOwL7Avu/FYUR35BNQ==, figureFileBig=cuLu+HxeX2o48lckePnjtw==, tableContent=null), ArticleFig(id=1218843916753883696, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149776905395725043, language=CN, label=图8, caption=不同训练集诊断正确率, figureFileSmall=omBrjOwL7Avu/FYUR35BNQ==, figureFileBig=cuLu+HxeX2o48lckePnjtw==, tableContent=null)], 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.1671-1815.2309051, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2309051, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2309051, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2309051, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于KPCA-SO-KELM的抗蛇行减振器故障诊断
收藏切换
PDF下载
岑潮宇 , 代亮成 , 池茂儒 * , 赵明花
科学技术与工程 | 论文·机械、仪表工业 2025,25(11): 4551-4558
收起
收藏切换
科学技术与工程 | 论文·机械、仪表工业 2025, 25(11): 4551-4558
基于KPCA-SO-KELM的抗蛇行减振器故障诊断
全屏
岑潮宇 , 代亮成, 池茂儒* , 赵明花
作者信息
  • 西南交通大学轨道交通运载系统全国重点实验室, 成都610031
  • 岑潮宇(2000—),男,汉族,河北滦南人,硕士研究生。研究方向:车辆系统动力学。E-mail:

通讯作者:

* 池茂儒(1973—),男,汉族,四川通江人,博士,研究员。研究方向:车辆系统动力学。E-mail:
Fault Diagnosis of Yaw Damper Based on KPCA-SO-KELM
Chao-yu CEN , Liang-cheng DAI, Mao-ru CHI* , Ming-hua ZHAO
Affiliations
  • State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu 610031, China
出版时间: 2025-04-18 doi: 10.12404/j.issn.1671-1815.2309051
文章导航
收藏切换

针对列车运行过程中的振动信号是复杂非线性的,并且单一通道的信号存在着信息不完全的问题,提出了一种车体和转向架上多个通道信号融合的抗蛇行减振器故障诊断的方法。首先,对列车多个通道的信号进行自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN),提取分解后的本征模态函数(intrinsic mode function, IMF)精细复合多尺度散布熵(refined composite multiscale dispersion entropy, RCMDE)组成特征集;其次,用核主成分分析法(kernel principal component analysis, KPCA)对提取出的特征集进行降维;最后,将最优特征子集输入到蛇优化的核极限学习机(snake optimized kernel extreme learning machine, SO-KELM)中来诊断抗蛇行减振器故障类型。试验结果表明,经过核主成分分析法优选过后的多通道融合特征集能够准确反映抗蛇行减振器不同故障类型信号特征,实现了抗蛇行减振器的故障诊断,并将蛇优化核极限学习机与其他模型对比验证了该方法的优越性。

抗蛇行减振器  /  精细复合多尺度散布熵  /  故障诊断  /  蛇优化  /  核主成分分析

Aiming at the problem that the vibration signals in train operation are complex and nonlinear, and the information of single channel signal is incomplete, a fault diagnosis method of yaw damper based on multi-channel signal fusion on car body and bogie was proposed. Firstly, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was performed on the signals of multiple train channels, and the intrinsic mode function (IMF) was extracted to compose the feature set of refined composite multiscale dispersion entropy. Secondly, kernel principal component analysis (KPCA) was used to reduce the dimensionality of the extracted feature set. Finally, the optimal feature subset was inputted into the snake optimized kernel extreme learning machine (SO-KELM) to diagnose the yaw damper fault types. The experimental results show that the multi-channel fusion feature set optimized by kernel principal component analysis can accurately reflect the signal characteristics of different fault types of yaw damper, and realize the fault diagnosis of yaw damper. The superiority of this method is verified by comparing with other models.

yaw damper  /  refined composite multiscale dispersion entropy  /  fault diagnosis  /  snake optimizer  /  kernel principal component analysis
岑潮宇, 代亮成, 池茂儒, 赵明花. 基于KPCA-SO-KELM的抗蛇行减振器故障诊断. 科学技术与工程, 2025 , 25 (11) : 4551 -4558 . DOI: 10.12404/j.issn.1671-1815.2309051
Chao-yu CEN, Liang-cheng DAI, Mao-ru CHI, Ming-hua ZHAO. Fault Diagnosis of Yaw Damper Based on KPCA-SO-KELM[J]. Science Technology and Engineering, 2025 , 25 (11) : 4551 -4558 . DOI: 10.12404/j.issn.1671-1815.2309051
高速列车在运行过程中可能会受到轨道随机不平顺,车轮扁疤冲击和外界因素的影响,为了减少列车运行过程中的振动,必须在车辆转向架中装备悬挂元件。转向架的悬挂元件能够衰减高频和低频振动,主要分为空气弹簧、各种类型的减振器和钢弹簧等等,其中二系横向减振器能够抑制车体的横摆和摇头[1],一系垂向减振器和钢弹簧用于减小轴箱与转向架之间的振动,抗蛇行减振器用来抑制转向架蛇行运动,提高临界速度,确保列车安全运行[2-3],而空气弹簧则衰减转向架传到车体的振动。但在实际运行过程中,减振器的寿命会随着运行里程的增加而不断减小,不仅会降低旅客乘坐的舒适度,而且危机列车运行的安全性,因此,有必要开展对减振器的故障诊断,及时发现问题所在,保证列车的正常行驶。
高速列车在运行过程中是一个复杂的紧密结合的整体系统,减振器发生故障往往可以反映到列车运行中的信号中,因此如何从非线性信号中提取能够准确反应减振器的故障信号并提取出有效特征是实现减振器故障诊断的重要步骤。由于抗蛇行减振器故障会对列车和转向架运行状态产生影响,因此只是通过单个传感器进行信号监测来进行抗蛇行减振器故障诊断是不准确的,需要在车体和转向架上添加多个传感器监测列车运行信号变化来更加全面具体的反应抗蛇行减振器故障类型。为实现对减振器的故障诊断,卢昌宏等[4]通过卷积神经网络结合多通道信息融合的方法实现了减振器的故障诊断;李辉等[5]通过选取最能反映振动信号的IMF(intrinsic mode function),通过计算排列组合熵组成的特征集准确识别了高速列车横向减振器的故障工况;王卫朝等[6] 通过Relief F特征分析方法对提取出的熵值组成的特征向量进行降维,证明了该方法在减振器故障诊断中的有效性;郑航等[7]通过提取振动信号样本熵特征,输入到支持向量机进行故障诊断。列车故障信号特征的有效提取很难依靠于传统方法[8],本文中采用了自适应噪声完备集合模态分解方法[9],该方法克服了经验模态分解(empirical mode decomposition, EMD)在分解过程中模态混淆的问题,解决了集合经验模态分解(ensemble empirical mode decomposition, EEMD)分解过程中的重构误差问题,实现了对信号更加准确的分解。主成分分析法(principal component analysis, PCA)[10]主要用于去除冗余信息,同时能够减小计算成本,但是PCA对于非线性数据效果不佳,容易丢失非线性的数据特征,因此该方法用于列车振动非线性信号不够精准。核主成分分析法是主成分分析法的一种扩展,可以处理非线性数据,杨雪梅[11]通过核主成分分析法提取了样本特征,结果表明核主成分分析法(kernel principal component analysis, KPCA)方法预测得到的效果要优于PCA方法的预测效果;王利福等[12]通过核主成分析法对变压器样本数据降维提升了模型的收敛速度;闫鹏程等[13]用核主成分分析法使数据处理时间更短,快速精准完成了对电力变压器的快速故障类型诊断。
以抗蛇行减振器为研究对象,通过自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)对列车振动信号进行分解,提取各分量的精细复合多尺度散布熵[14],将提取出的特征组成特征集,然后使用核主成分分析法进行降维,最后将降维过后的特征集输入到经过蛇优化算法[15]的核极限学习机(snake optimized kernel extreme learning machine, SO-KELM)模型中。在经过训练集训练后,通过对比不同模型对测试集的识别正确率,验证该方法针对抗蛇行减振器故障诊断的有效性和可行性。
CEEMDAN通过引入自适应高斯白噪声,旨在降低分解中的重构误差,并提高分解的准确性。该方法在分解信号时有效地抑制了模态混叠,同时也能提高分解的效率,使得整个过程更加的稳定和可靠。CEEMDAN方法与EEMD方法相比分解效率高消除了虚假本征模态函数,保持了分解的稳定性和准确性。CEEMDAN信号分解步骤如下:
(1)对原始振动信号x(t)添加高斯白噪声wf(t)得
xf(t)=x(t)+ε0wf(t), f=1,2,…,T
式(1)中:ε0为噪声标准差;T为添加噪声的次数。
(2) 利用EMD对xf(t)进行分解得到第一个模态分量IMF1
IMF1= 1 T i = 1 T I M F 1 i
(3) 在第一个阶段j=1时,计算第一阶的残差余量为
q1(t)=x(t)-IMF1
(4)Ep(·)为EMD分解后的第p阶IMF分量,通过EMD分解每个q1(t)+ε1E1[wf(t)],得到IMF2
I M F 2 = 1 T i = 1 TE1{q1(t)+ε1E1[wf(t)]}
(5) 当j=2,3,…,N时,第j个余量为
qj(t)=qj-1(t)-IMFj
(6)通过EMD分解每个qj(t)+εjEj[wf(t)],得到第j+1个CEEMDAN的模态分量为
IMFj+1= 1 T i = 1 TE1{qj(t)+εjEj[wf(t)]}
(7) 不断重复上述步骤直到余量不能再被分解,最后的余量和信号可以表达为
qN(t)=x(t)- j = 1 NIMFj
x(t)= j = 1 NIMFj+qN(t)
多尺度散布熵在时间序列较短的情况下可能导致未定义的熵值,进而影响最终结果的准确性。相比之下,精细复合多尺度散布熵(refined composite multiscale dispersion entropy, RCMDE)采用了求平均值的方法,减少了MDE在粗粒化过程中可能出现的数据丢失问题,保证了计算精度,使得RCMDE方法更加有效和精确。
计算步骤如下:
(1)对于原始数据a,长度为L的信号a={ a 1, a 2,…,aL}。将原信号aa1开始平均分割β小段,计算每小段的平均值,再将每段的平均值组成粗粒化序列。第h个粗粒化序列为
x h , j β= 1 β b = h + β ( j - 1 ) h + j β - 1ab, 1≤j≤ L β,1≤h≤β
(2)下面开始计算每个粗粒化散布模式Φ的概率并求其平均值。利用正态分布函数将x={ x j,j=1,2,…,N}映射到y={yj,j=1,2,…,N},其中yj∈(0,1),yj的计算公式为
yj= 1 δ 2 π - x j e - ( t - λ ) 2 2 δ 2dt
式(10)中:λ为均值;δ为标准差。
(3)通过线性算法将yj映射到[1,2,…,c]的范围内,即
g j c=Z(cyj+0.5)
式(11)中: g j c表示时间序列的类数;c为类别个数;Z(·)为取整运算。
(4)计算嵌入维数m和时间延迟d组成的时间序列为
g i m , c={ g i c, g i + d c,…, g i + ( m - 1 ) d c},i={1,2,…,N-(m-1)d}
(5) 如果各个时间序列 g i m , c的散布模式 Φ l 0 l 1 l m - 1符合 g i c=l0, g i + d c=l1,…, g i + ( m - 1 ) d c=lm-1, g i m , c散布模式为 Φ l 0 l 1 l m - 1,散布模式 Φ l 0 l 1 l m - 1的概率P( Φ l 0 l 1 , l m - 1)为
P( Φ l 0 l 1 , , l m - 1 )= n u m ( Φ l 0 l 1 , , l m - 1 ) N - ( M - 1 ) d
(6)对于每个尺度下的β,RCMDE定义为
RCMDE(X,m,c,d,β)=- Φ = 1 c m P ¯( Φ l 0 l 1 l m - 1)×ln[ P ¯( Φ l 0 l 1 l m - 1)]
式(14)中: P ¯( Φ l 0 l 1 l m - 1)= 1 β h = 1 β P h β,为粗粒化序列 x h β的散布模式Φ概率的平均值。
蛇优化算法是根据蛇的交配行为得到的启发,该算法根据温度低和食物足够的条件下会进行交配,否则蛇会搜索食物或者吃现有的食物,根据这些特性,将算法主要分为探索和开发两个阶段,探索阶段下蛇会寻找食物,开发阶段中当温度高时,会吃现有的食物;当温度低时,过渡为交配阶段或者战斗阶段。首先初始化随机种群,并将种群划分为雌性和雄性种群,两个种群数量各占一半。
首先定义食物量为
Q=0.5 e t k M m a x - 1
式(15)中:tk为当前迭代次数;Mmax为最大迭代次数。
当食物量低于阈值Zr=0.25,即Q<0.25时,种群会进行搜索,此时雄性和雌性的位置会更新为
X q , n ( t + 1 ) = X g , n ( t ) ± 0.05 e - f g , n f q , n [ ( a 1 - a 0 ) r a n d + a 0 ] X q , h ( t + 1 ) = X g , h ( t ) ± 0.05 e - f g , h f q , h [ ( a 1 - a 0 ) r a n d + a 0 ]
式(16)中:Xq,nXq,h为第q个雄性和雌性蛇的位置;Xg,nXg,h分别为雄性和雌性蛇群中随机个体的位置;fg,nfg,h分别为Xg,nXg,h相应的适应度值;fq,nfq,h分别为第q个雄性和雌性蛇对应的适应度值;a1a0分别为上限和下限;rand为(0,1)之间的随机数。
当食物比阈值Zr大的时候,到开发阶段,蛇群主要受到环境温度T影响,即
T= e - t k M m a x
当温度高于阈值0.6时,即T>0.6并且Q>0.25,蛇群只会吃已有的食物,此时雄性和雌性蛇的个体位置为
X q , n ( t + 1 ) = X f d ( t ) ± 2 T [ X f d - X q , n ( t ) ] r a n d X q , h ( t + 1 ) = X f d ( t ) ± 2 T [ X f d - X q , h ( t ) ] r a n d
式(18)中:Xfd为最好的个体位置。
T<0.6且Q>0.25时,蛇群会进入到战斗或交配模式,进入交配模式后的雄性和雌性个体更新为
X q , n ( t + 1 ) = X q , n ( t ) ± 2 e - f q , h f q , n [ Q X q , h ( t ) - X q , n ( t ) ] r a n d X q , h ( t + 1 ) = X q , h ( t ) ± 2 e - f q , n f q , h [ Q X q , n ( t ) - X q , h ( t ) ] r a n d
如果蛇卵孵化,选择适应度最差的雄性和雌性蛇个体并替换它们。
进入战斗模式后的雄性和雌性蛇的位置更新为
X q , n ( t + 1 ) = X q , n ( t ) ± 2 e - f b , h f q , n [ Q X b , h ( t ) - X q , n ( t ) ] r a n d X q , h ( t + 1 ) = X q , h ( t ) ± 2 e - f b , n f q , h [ Q X b , n ( t ) - X q , h ( t ) ] r a n d
式(20)中: f b , n f b , h分别为雄性和雌性蛇群的最好适应度值;Xb,nXb,h分别为雄性和雌性蛇群当前最好的位置。
核极限学习机由于不仅不用对映射函数进行定义,并且针对隐藏神经元个数也无需设置,节省了时间,提高了运算效率。核极限学习机[16]是在极限学习机[17]基础上引入了核函数,通过核函数代替了极限学习机(extreme learning machine,ELM)的随机映射,具有更高的稳定性,本文中采用高斯函数
k(xi,xj)=exp - x i - x j 2 2 σ 2 )
式(21)中:σ为核函数参数,当其过大时,会导致无法准确识别出现欠拟合现象;当其过小时,会导致在未知样本上分类效果差而出现过拟合现象。参数的取值会影响到模型的泛化能力,为了使其拥有最优性能,通常采用优化算法对参数进行寻优,提升模型分类准确性。
抗蛇行减振器故障信号是非线性不平稳的,通过CEEMDAN分解信号得到的IMF得精细复合多尺度散布熵值作为故障特征,以SO-KELM模型对抗蛇行减振器进行故障诊断。本文中对抗蛇行减振器故障诊断的主要流程如图1所示,具体步骤如下。
(1)对不同工况列车多个通道信号采集分割并用CEEMDAN进行分解。
(2)对分解得到的每个IMF提取RCMDE,重构融合得到特征集。
(3)用核主成分分析法对重构得到的特征集进行降维,选取贡献率累计超90%的主成分,组成新的特征集并划分训练集和测试集。
(4)用蛇优化算法对核极限学习的核参数和惩罚因子进行优化,利用得到的最优参数构建KELM进行抗蛇行减振器的故障诊断。
本文中选用某动车参数建模的Simpack模型,设置采样频率243 Hz,仿真时间216 s,在列车上添加多个传感器,记录不同工况下的信号变化。每个通道下包括横向、垂向、纵向的信号信息,但抗蛇行减振器主要抑制车体和转向架的横移和摇头,所以选择横向的振动信号,并且横向振动加速度信号的敏感度比横向位移和角加速度更明显,因此主要选取车体和转向架的横向振加速度信号。每个列车有两个转向架,前后转向架各有两个抗蛇行减振器,沿列车纵向中心线对称分布,抗蛇行减振器一端节点连接车体,另一端节点连接构架,在前转向架上添加的传感器记为前构架1位和2位,后转向架的记为后构架1位和2位,车体前端的记为车体1位后端的记为车体2位,将每个传感器记为通道,每个通道得到的信号按3 s一个进行拆分,分成 72个样本,一共设置了5种工况包括正常、一个抗蛇行减振器失效、两个抗蛇行减振器失效、3个抗蛇行减振器失效、全部失效4种工况,记为工况1~工况5。采集不同工况不同通道的信号拆分作为样本。
图2为不同工况下单个通道的振动加速度时域图,可以看出不同故障类型之间的振动加速度信号区别不大,想仅仅依靠时域图来区分不同工况是不太可能的,需要提取信号中的关键特征信息进行分析,并需要构建模型来进行分类,实现精确的故障诊断。
精细复合多尺度散布熵能够更好地检测信号的不规则性与复杂的局部变化,适应不同类型的信号和数据,精细复合多尺度熵的取值通常与嵌入尺寸、类数、时间延迟、尺度因子的个数有关系,在本文中时间延迟取1,嵌入维数选4,而类数一般在研究中选6,尺度因子选6。尺度因子在实际选取中通常不宜过小或过大,过小会导致不能完整的反应信号,过多会导致计算效率低下提取不到关键信息。通过CEEMDAN对列车不同工况下的各个通道信号进行分解,对每个样本分解得到的IMF提取RCMDE,将提取出的特征进行重构并组成特征集。
列车在运行过程中由于复杂的线路环境往往会掺杂冗余和无效的信号,这些信号会干扰抗蛇行减振器故障诊断的精确性和有效性,并且会增加计算时间,因此有必要对重构组成的特征集进行降维,选择更能反应信号关键信息的特征,从而实现抗蛇行减振器的故障诊断。采用核主成分分析法对组成的特征集进行降维,根据贡献度选出贡献度最大的主成分作为降维后的特征集,先对每个通道下提取出的RCMDE进行降维,主成分累计贡献率如图3所示。
通过核函数将抗蛇行减振器单通道下的9个特征值映射到高维空间,使得数据更容易被区分开,提升了计算效率,然后在高维空间下进行降维。核函数仍然选取高斯函数,由图3可以看出,每个通道前6个特征值的贡献率已经能达到90%,已经基本能够反映该通道下信号的特征,因此选择每个通道下的前6个特征值组成36维特征向量进行后续的故障诊断。
用2.3节降维之后得到的特征集,随机选取0.7比例样本训练模型,0.3比例样本测试模型分类性能,通过对训练集的训练,经过蛇优化的核极限学习机表现出对测试集的准确判别能力。蛇优化算法的参数设置为:种群数量20,最大迭代次数50。通过SO-KELM测试集诊断正确率来判断各个通道经过主成分分析法降维过后组成的特征集在不同维度下的优劣,对比不同维度特征集的正确率,结果如图4所示。由图4可以看出,随着维度的增加虽然正确率在上下波动,但整体诊断正确率不断提高,表明多个通道下的特征融合比单个通道的正确率更高,这是因为抗蛇行减振器影响的是列车整体的运动状态,相对于单个通道的信号多个通道能更加全面的反应故障问题所在,并且在维度为24时正确率最高,诊断结果如图5所示,测试集诊断错误个数为一个,正确率可高达99%。
为验证不同优化方法对核极限学习机参数优化的优劣,采用麻雀优化算法、融合柯西变异和反向学习的改进麻雀算法[18]、灰狼优化算法与蛇优化算法核极限学习机进行比较,核函数都选择高斯函数,并且各个算法的迭代次数和种群等各个参数保持一致。在寻找最优解的过程中采用误差值作为适应度指标,所以适应度值越低证明寻优的精度越高。用降维得到的特征集作为不同模型的输入,得到不同模型的适应度值变化曲线。由图6可知,每个算法的适应度值均随迭代次数增加不断下降并趋于稳定,蛇优化算法能在很少的迭代次数下达到最优的适应度值,并且适应度值最低,改进麻雀算法(improved sparrow search algorithm, ISSA)算法相对于麻雀算法(sparrow search algorithm,SSA)寻优速度更快,适应度值也较低。其中蛇算法迭代第5次就可以达到最小适应度值为0.009,改进麻雀算法迭代第9次达到适应度值0.045 4并趋于稳定,灰狼算法迭代第13次时就可以达到最小适应度,而麻雀算法则需要迭代16次才可以达到最小适应度,适应度值也相比其他算法最大为0.082。因此对于抗蛇行减振器故障诊断蛇优化算法优于麻雀算法、改进麻雀算法和灰狼优化算法。
将KPCA降维过后的特征组成的特征集输入到SSA-KELM、ISSA-KELM、GWO-KELM模型中,每个模型抗蛇行减振器故障诊断各个诊断结果如图7所示。
图7可知,SSA-KELM、ISSA-KELM、GWO-KELM模型对抗蛇行减振器故障诊断的识别率为91.82%、95.45%、94.54%。4种模型均能较为准确的诊断抗蛇行减振器故障,但相比之下,SO-KELM的诊断正确率要高于其他模型,这与蛇优化算法能够更快更准的寻找最优参数息息相关。其中麻雀算法针对工况4和工况5的诊断结果有混淆,识别率最低,诊断错误个数为9个,改进麻雀算法诊断错误个数为5个,灰狼优化算法诊断错误个数为6个,并且前3个工况主要误判为工况4。以上结果表明,针对抗蛇行减振器的故障识别,蛇优化算法的核极限学习机模型识别率最高,相对于其他算法具有优越性。
为分析不同训练样本数据对抗蛇行故障诊断结果的影响,从抗蛇行减振器5种工况中随机选取75、110、145、180、215、250个数据作为训练样本,其余的样本作为测试集数据,每个工况下样本均分。抗蛇行减振器不同诊断模型在不同的训练样本下的诊断结果如图8所示,可以看出测试集的正确率随着训练样本的增加不断增加,不同模型的故障诊断正确率都在提升,其中蛇优化算法相比其他算法的诊断正确率最高,证明了该方法在不同训练集下针对抗蛇行减振器故障诊断的有效性。
针对抗蛇行减振器的故障诊断对保证列车安全运行具有重要意义,本文提出一种CEEMDAN分量精细复合多尺度散布熵表征抗蛇行减振器运行状态的信号特征提取方法,反映出了振动信号的不确定性,精准捕捉了列车振动信号的非线性特征。考虑到列车是多自由度的系统,减振器影响的是列车整体的振动信号,因此仅仅通过某一通道的信号来反应抗蛇行减振器的故障是片面的,往往需要通过融合多个通道信号特征提高故障诊断的准确性。
本文采用了蛇优化算法优化了核极限学习机参数,提升了模型性能,与麻雀优化算法、灰狼优化算法等相比,SO-KELM的故障诊断正确率最高,证明了该方法针对抗蛇行减振器故障诊断的可行性。
  • 国家重点研发计划(2022YFB4301303)
  • 中国国家铁路集团有限公司科技研究开发计划(K2022J004)
参考文献 引证文献
排序方式:
[1]
蒋益平, 池茂儒, 朱海燕. 不同位置横向减振器失效对地铁车辆动力学性能影响[J]. 科学技术与工程, 2019, 19(10): 210-215.
Jiang Yiping, Chi Maoru, Zhu Haiyan. Effects of lateral damper invalid at different location on the dynamic performance of metro vehicle[J]. Science Technology and Engineering, 2019, 19(10): 210-215.
[2]
姚远, 程俊, 张名扬, 等. 高速列车抗蛇行减振器作用机制与频变刚度应用研究[J]. 振动工程学报, 2022, 35(6): 1461-1470.
Yao Yuan, Cheng Jun, Zhang Mingyang, et al. Mechanism analysis of yaw damper in high-speed train and frequency-dependent stiffness application[J]. Journal of Vibration Engineering, 2022, 35(6): 1461-1470.
[3]
孙建锋, 池茂儒, 吴兴文, 等. 抗蛇行减振器参数对车辆稳定性的影响分析[J]. 振动.测试与诊断, 2018, 38(6): 1155-1160, 1291.
Sun Jianfeng, Chi Maoru, Wu Xingwen, et al. Analysis of the influences of the yaw damper parameters on the vehicle stability[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(6): 1155-1160, 1291.
[4]
卢昌宏, 张利斌, 张恒志, 等. 一种多通道信息融合的横向减振器性能退化阶段辨别方法[J]. 铁道科学与工程学报, 2021, 18(3): 737-743.
Lu Changhong, Zhang Libin, Zhang Hengzhi, et al. A multi-channel information fusion lateral damper performance degradation stage identification method[J]. Journal of Railway Science and Engineering, 2021, 18(3): 737-743.
[5]
李辉, 金炜东. 基于白噪声统计特性与EEMD的高速列车横向减振器故障诊断[J]. 计算机应用研究, 2016, 33(9): 2648-2651.
Li Hui, Jin Weidong. Lateral damper fault diagnosis of high-speed train based on statistical characteristics of white noise and EEMD[J]. Application Research of Computer, 2016, 33(9): 2648-2651.
[6]
王卫朝, 石国良, 李晓, 等. 应用EMD熵和Relief分析高铁横向减振器故障[J]. 计算机工程与应用, 2016, 52(14): 226-231, 236.
Wang Weizhao, Shi Guoliang, Li Xiao, et al. Application of EMD entropy and Relief in fault analysis of high-speed train lateral damper failure[J]. Computer Engineering and Applications, 2016, 52(14): 226-231, 236.
[7]
郑航, 李刚, 李德仓. 基于PELCD样本熵的抗蛇行减振器故障诊断[J]. 电力机车与城轨车辆, 2023, 46(6): 34-41.
Zheng Hang, Li Gang, Li Decang. Fault diagnosis of anti-yaw damper based on PELCD sample entropy[J]. Electric Locomotives & Mass Transit Vehicles, 2023, 46(6): 34-41.
[8]
王小亮, 李立, 张卫华. 高速列车垂向振动的模拟器再现方法研究[J]. 振动、测试与诊断, 2009, 29(1): 101-104.
Wang Xiaoliang, Li Li, Zhang Weihua. Fuzzy self-tuning based washout algorithm for simulator of high speed locomotive vertical vibration[J]. Journal of Vibration, Measurement & Diagnosis, 2009, 29(1): 101-104.
[9]
Torres M E, Colominas M A, Schlotthauer G, et al. A complete ensemble empirical mode decomposition with adaptive noise[C]// IEEE International Conference on Acoustics, Speech and Signal Processing. New York: IEEE, 2011: 4144-4147.
[10]
顾春生, 唐鑫, 朱常坤, 等. 基于主成分分析法优化神经网络的滆湖组黏性土抗剪强度预测[J]. 科学技术与工程, 2023, 23(28): 11980-11989.
Gu Chunsheng, Tang Xin, Zhu Changkun, et al. Prediction of shear strength of cohesive soil in gehu formation based on back propagation neural network optimized by principal component analysis[J]. Science Technology and Engineering, 2023, 23(28): 11980-11989.
[11]
杨雪梅. 基于KPCA及SVM的蛋白质O-糖基化位点的预测[J]. 科学技术与工程, 2013, 13(25): 7371-7376.
Yang Xuemei. Prediction of the protein oglycosylation by kernel principal component analysis and support vector machines[J]. Science Technology and Engineering, 2013, 13(25): 7371-7376.
[12]
王利福, 魏玉琪, 刘屹江泽. 基于KPCA与IPFA-KELM的变压器故障识别方法[J]. 控制工程, 2023, 30(7): 1180-1189.
Wang Lifu, Wei Yuqi, Liu Yijiangze. Transformer fault identification method based on KPCA and IPFA-KELM[J]. Control Engineering of China, 2023, 30(7): 1180-1189.
[13]
闫鹏程, 张超银, 孙全胜, 等. LIF技术与ELM算法的电力变压器故障诊断研究[J]. 光谱学与光谱分析, 2022, 42(5): 1459-1464.
Yan Pengcheng, Zhang Chaoyin, Sun Quansheng, et al. LIF technology and ELM algorithm power transformer fault diagnosis research[J]. Spectroscopy and Spectral Analysis, 2022, 42(5): 1459-1464.
[14]
Azami H, Rostaghi M, Abasolo D, et al. Refined composite multiscale dispersion entropy and its application to bio medical signals[J]. IEEE Transactions on Biomedical Engineering, 2017, 64(12): 2872-2879.
[15]
Hashim F A, Hussien A G. Snake optimizer: a novel meta-heuristic optimization algorithm[J]. Knowledge-Based Systems, 2022, 242: 108320.
[16]
Huang G B. An insight into extreme learning machines: random neurons, random features and kernels[J]. Cognitive Computation, 2014, 6(3): 376-390.
[17]
Huang G B, Zhou H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions Systems, Man and Cybernetics, Part B: Cybernetics, 2012, 42(2): 513-529.
[18]
毛清华, 张强. 融合柯西变异和反向学习的改进麻雀算法[J]. 计算机科学与探索, 2021, 15(6): 1155-1164.
Mao Qinghua, Zhang Qiang. Improved sparrow algorithm combining cauchy mutation and opposition-based learning[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(6): 1155-1164.
2025年第25卷第11期
PDF下载
326
130
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2309051
  • 接收时间:2023-11-17
  • 首发时间:2025-07-09
  • 出版时间:2025-04-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-11-17
  • 修回日期:2024-06-24
基金
国家重点研发计划(2022YFB4301303)
中国国家铁路集团有限公司科技研究开发计划(K2022J004)
作者信息
    西南交通大学轨道交通运载系统全国重点实验室, 成都610031

通讯作者:

* 池茂儒(1973—),男,汉族,四川通江人,博士,研究员。研究方向:车辆系统动力学。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2309051
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