Article(id=1228805366343987253, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, articleNumber=null, orderNo=null, doi=10.16385/j.cnki.issn.1004-4523.2025.06.010, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1714752000000, receivedDateStr=2024-05-04, revisedDate=1725206400000, revisedDateStr=2024-09-02, acceptedDate=null, acceptedDateStr=null, onlineDate=1770899629435, onlineDateStr=2026-02-12, pubDate=1749484800000, pubDateStr=2025-06-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770899629435, onlineIssueDateStr=2026-02-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770899629435, creator=13701087609, updateTime=1770899629435, updator=13701087609, issue=Issue{id=1228805359561802007, tenantId=1146029695717560320, journalId=1225147924628267009, year='2025', volume='38', issue='6', pageStart='1133', pageEnd='1362', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1770899627819, creator=13701087609, updateTime=1770901542852, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1228813391846896476, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1228813391846896477, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1221, endPage=1231, ext={EN=ArticleExt(id=1228805366675337284, articleId=1228805366343987253, tenantId=1146029695717560320, journalId=1225147924628267009, language=EN, title=A method for wheel tread damage identification using multi-sensor data fusion and improved convolutional neural networks, columnId=null, journalTitle=Journal of Vibration Engineering, columnName=null, runingTitle=null, highlight=null, articleAbstract=

To address the challenges of fully characterizing wheel information and accurately locating and quantifying wheel damage using trackside signals, this paper proposes a multi-sensor data fusion algorithm combined with an improved convolutional neural network (CNN) for wheel tread defect identification. A vehicle-track dynamics coupling model is established based on multi-body dynamics and finite element theory. By strategically arranging fewer sensors, multimodal features are extracted, and data fusion algorithms are optimized for parameters like wheel geometry and vehicle speed. An improved CNN model is then proposed, building upon both 1D-CNN and 2D-CNN architectures. Simutaneously, frequency domain features and image features are fused, leading to a new CNN algorithm model that incorporates these fusion features. Defect feature extraction is performed on the reconstructed signal, and the improved CNN, leveraging the fused data features, is used to achieve wheel damage identification. The effectiveness of the proposed method is validated using both simulation data and actual case studies, in conjunction with a proportional vehicle test rig. The damage identification performance of the proposed model is compared against CNN, BP neural network (BPNN), and support vector machine (SVM) under various signal test sets and data features. Results indicate that the proposed damage identification model can more effectively identify wheel tread defects, showing good consistency with measured results. Fusing data features from different dimensions can characterize defects under varying degrees of damage and significantly improve identification performance. This approach successfully addresses issues where trackside data alone cannot fully reconstruct wheel status, thereby providing crucial technical support for the online damage identification of wheel defects.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Bingrong MIAO, Songyuan XU, Xiaolin WU, Siming WANG, Zhe ZHANG), CN=ArticleExt(id=1228805369657487649, articleId=1228805366343987253, tenantId=1146029695717560320, journalId=1225147924628267009, language=CN, title=多传感器数据融合和改进卷积神经网络的车轮踏面损伤识别方法, columnId=0, journalTitle=振动工程学报, columnName=, runingTitle=null, highlight=null, articleAbstract=

针对轨旁信号难以完全表征车轮信息和车轮损伤难以定位与量化的问题,提出一种多传感器数据融合算法和改进卷积神经网络(CNN)的车轮踏面缺陷识别方法。基于多体动力学和有限元理论构建车辆-轨道动力学耦合模型。通过布置较少的传感器,进行多模态特征的提取,对车轮几何特征、车速等参数进行了数据融合的算法优化。基于1D-CNN和2D-CNN提出改进的CNN模型。同时,将频域特征和图像特征进行数据融合,并提出考虑融合特征的CNN算法模型。对重构信号进行缺陷特征提取,并利用改进的CNN融合数据特征实现车轮损伤识别。结合比例车辆试验平台,并利用仿真数据和实际算例验证提出方法的有效性。在不同信号测试集和数据特征下,对CNN、BP神经网络(BPNN)和支持向量机(SVM)的损伤识别效果进行对比分析。结果表明:所提损伤识别模型可以更好地识别车轮踏面缺陷,识别结果与实测结果有很好的一致性;将不同维度的数据特征进行融合,可以表征不同损伤程度下的缺陷并提高识别效果;能够解决轨旁数据不能完整重构车轮状态等问题,为车轮缺陷的在线损伤识别提供技术支撑。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
缪炳荣(1970—),男,博士,副研究员。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=p+7ioBdEBMYCiRha3a9fJw==, magXml=UDd3wUM9tWgBFNoicXzq9A==, pdfUrl=null, pdf=fSglCn/GfsHCqAW7xPfhQg==, pdfFileSize=2972460, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=FmTOAq/zS+8stu/nEYGHMA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=kXuTgkmoeNaSZx72NuMVDg==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=缪炳荣, 徐松源, 吴啸林, 王思明, 张哲)}, authors=[Author(id=1228805369993032001, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=brmiao@home.swjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228805370085306697, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805369993032001, language=EN, stringName=Bingrong MIAO, firstName=Bingrong, middleName=null, lastName=MIAO, 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=1228805370177581397, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805369993032001, language=CN, stringName=缪炳荣, 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,四川 成都 610031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369904951607, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, xref=null, ext=[AuthorCompanyExt(id=1228805369909145912, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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=1228805369917534521, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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,四川 成都 610031)])]), Author(id=1228805370274050395, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, 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=1228805370370519394, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805370274050395, language=EN, stringName=Songyuan XU, firstName=Songyuan, middleName=null, lastName=XU, 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=1228805370466988398, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805370274050395, language=CN, stringName=徐松源, 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,四川 成都 610031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369904951607, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, xref=null, ext=[AuthorCompanyExt(id=1228805369909145912, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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=1228805369917534521, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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,四川 成都 610031)])]), Author(id=1228805370555068796, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, 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=1228805370672509319, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805370555068796, language=EN, stringName=Xiaolin WU, firstName=Xiaolin, middleName=null, lastName=WU, 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=1228805370752201101, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805370555068796, language=CN, stringName=吴啸林, 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,四川 成都 610031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369904951607, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, xref=null, ext=[AuthorCompanyExt(id=1228805369909145912, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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=1228805369917534521, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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,四川 成都 610031)])]), Author(id=1228805370831892884, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, 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=1228805370907390364, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805370831892884, language=EN, stringName=Siming WANG, firstName=Siming, middleName=null, lastName=WANG, 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=1228805370987082148, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805370831892884, language=CN, stringName=王思明, 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,四川 成都 610031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369904951607, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, xref=null, ext=[AuthorCompanyExt(id=1228805369909145912, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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=1228805369917534521, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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,四川 成都 610031)])]), Author(id=1228805371100328366, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, 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=1228805371196797365, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805371100328366, language=EN, stringName=Zhe ZHANG, firstName=Zhe, middleName=null, lastName=ZHANG, 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=1228805371305849280, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, authorId=1228805371100328366, language=CN, stringName=张哲, 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,四川 成都 610031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369904951607, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, xref=null, ext=[AuthorCompanyExt(id=1228805369909145912, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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=1228805369917534521, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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,四川 成都 610031)])])], keywords=[Keyword(id=1228805371431678411, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, orderNo=1, keyword=damage recognition), Keyword(id=1228805371553313236, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, orderNo=2, keyword=data fusion), Keyword(id=1228805371645587930, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, orderNo=3, keyword=machine learning), Keyword(id=1228805371737862627, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, orderNo=4, keyword=optimization algorithm), Keyword(id=1228805371825943019, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, orderNo=5, keyword=wheel defects), Keyword(id=1228805371934994927, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, orderNo=1, keyword=损伤识别), Keyword(id=1228805372044046843, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, orderNo=2, keyword=数据融合), Keyword(id=1228805372132127234, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, orderNo=3, keyword=机器学习), Keyword(id=1228805372245373447, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, orderNo=4, keyword=优化算法), Keyword(id=1228805372367008268, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, orderNo=5, keyword=车轮缺陷)], refs=[Reference(id=1228805376204796593, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=1, pageStart=1, pageEnd=35, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=赵鑫, 温泽峰, 王衡禹, journalName=交通运输工程学报, refType=null, unstructuredReference=赵鑫,温泽峰, 王衡禹,等.中国轨道交通轮轨滚动接触疲劳研究进展[J]. 交通运输工程学报, 2021, 21(1):1-35., articleTitle=中国轨道交通轮轨滚动接触疲劳研究进展, refAbstract=null), Reference(id=1228805376280294069, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=1, pageStart=1, pageEnd=35, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=ZHAO Xin, WEN Zefeng, WANG Hengyu, journalName=Journal of Traffic and Transportation Engineering, refType=null, unstructuredReference=ZHAO Xin, WEN Zefeng, WANG Hengyu, et al.Research progress on wheel/rail rolling contact fatigue of rail transit in China[J]. Journal of Traffic and Transportation Engineering, 2021, 21(1): 1-35., articleTitle=Research progress on wheel/rail rolling contact fatigue of rail transit in China, refAbstract=null), Reference(id=1228805376359985849, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=1, pageStart=285, pageEnd=315, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=敬霖, 刘凯, journalName=交通运输工程学报, refType=null, unstructuredReference=敬霖, 刘凯. 车轮踏面缺陷引起的轮轨动态响应综述[J]. 交通运输工程学报, 2021, 21(1):285-315., articleTitle=车轮踏面缺陷引起的轮轨动态响应综述, refAbstract=null), Reference(id=1228805376460649150, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=1, pageStart=285, pageEnd=315, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=JING Lin, LIU Kai, journalName=Journal of Traffic and Transportation Engineering, refType=null, unstructuredReference=JING Lin, LIU Kai. Review on wheel-rail dynamic responses caused by wheel tread defects[J]. Journal of Traffic and Transportation Engineering, 2021, 21(1): 285-315., articleTitle=Review on wheel-rail dynamic responses caused by wheel tread defects, refAbstract=null), Reference(id=1228805376552923844, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=4, pageStart=151, pageEnd=165, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=王金能, 郭鑫, 敬霖, journalName=爆炸与冲击, refType=null, unstructuredReference=王金能,郭鑫, 敬霖,等.高速列车车轮踏面剥离引起的轮轨冲击力学响应有限元模拟[J]. 爆炸与冲击, 2022, 42(4):151-165., articleTitle=高速列车车轮踏面剥离引起的轮轨冲击力学响应有限元模拟, refAbstract=null), Reference(id=1228805376661975752, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=4, pageStart=151, pageEnd=165, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=WANG Jinneng, GUO Xin, JING Lin, journalName=Explosion and Shock Waves, refType=null, unstructuredReference=WANG Jinneng, GUO Xin, JING Lin, et al.Finite element simulations of wheel-rail impact response induced by wheel tread spalling of high-speed trains[J]. Explosion and Shock Waves, 2022, 42(4): 151-165., articleTitle=Finite element simulations of wheel-rail impact response induced by wheel tread spalling of high-speed trains, refAbstract=null), Reference(id=1228805376754250445, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=翟婉明, journalName=车辆-轨道耦合动力学上册, refType=null, unstructuredReference=翟婉明. 车辆-轨道耦合动力学上册[M]. 4版. 北京:科学出版社,2015., articleTitle=null, refAbstract=null), Reference(id=1228805376846525136, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=ZHAI Wanming, journalName=Vehicle-Track Coupled Dynamics-Volume 1, refType=null, unstructuredReference=ZHAI Wanming. Vehicle-Track Coupled Dynamics-Volume 1[M]. 4th ed. Beijing:Science Press,2015., articleTitle=null, refAbstract=null), Reference(id=1228805376934605524, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2015, volume=37, issue=7, pageStart=32, pageEnd=39, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=凌亮, 曹亚博, 肖新标, journalName=铁道学报, refType=null, unstructuredReference=凌亮,曹亚博, 肖新标,等.车轮擦伤对高速轮轨接触行为的影响[J]. 铁道学报, 2015, 37(7):32-39., articleTitle=车轮擦伤对高速轮轨接触行为的影响, refAbstract=null), Reference(id=1228805377047851736, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2015, volume=37, issue=7, pageStart=32, pageEnd=39, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=LING Liang, CAO Yabo, XIAO Xinbiao, journalName=Journal of the China Railway Society, refType=null, unstructuredReference=LING Liang, CAO Yabo, XIAO Xinbiao, et al.Effect of wheel flats on the high-speed wheel-rail contact behavior[J]. Journal of the China Railway Society, 2015, 37(7): 32-39., articleTitle=Effect of wheel flats on the high-speed wheel-rail contact behavior, refAbstract=null), Reference(id=1228805377135932123, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2020, volume=28, issue=4, pageStart=317, pageEnd=345, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=TAO G Q, WEN Z F, JIN X S, journalName=Railway Engineering Science, refType=null, unstructuredReference=TAO G Q, WEN Z F, JIN X S, et al.Polygonisation of railway wheels: a critical review[J]. Railway Engineering Science, 2020, 28(4): 317-345., articleTitle=Polygonisation of railway wheels: a critical review, refAbstract=null), Reference(id=1228805377232401119, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2022, volume=236, issue=3, pageStart=247, pageEnd=261, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=TAO G Q, LIU M Q, XIE Q L, journalName=Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, refType=null, unstructuredReference=TAO G Q, LIU M Q, XIE Q L, et al.Wheel–rail dynamic interaction caused by wheel out-of-roundness and its transmission between wheelsets[J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2022, 236(3): 247-261., articleTitle=Wheel–rail dynamic interaction caused by wheel out-of-roundness and its transmission between wheelsets, refAbstract=null), Reference(id=1228805377303704291, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=1, pageStart=338, pageEnd=357, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=缪炳荣, 刘俊利, 张盈, journalName=交通运输工程学报, refType=null, unstructuredReference=缪炳荣,刘俊利, 张盈,等.轨道车辆结构振动损伤识别技术综述[J]. 交通运输工程学报, 2021, 21(1):338-357., articleTitle=轨道车辆结构振动损伤识别技术综述, refAbstract=null), Reference(id=1228805377387590375, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=1, pageStart=338, pageEnd=357, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=MIAO Bingrong, LIU Junli, ZHANG Ying, journalName=Journal of Traffic and Transportation Engineering, refType=null, unstructuredReference=MIAO Bingrong, LIU Junli, ZHANG Ying, et al.Review on structural vibration damage identification technology for railway vehicles[J]. Journal of Traffic and Transportation Engineering, 2021, 21(1): 338-357., articleTitle=Review on structural vibration damage identification technology for railway vehicles, refAbstract=null), Reference(id=1228805377517613803, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=ALIREZA A, journalName=null, refType=null, unstructuredReference=ALIREZA A. Railway wheel defect identification[D]. Delft: Delft University of Technology, 2019., articleTitle=Railway wheel defect identification, refAbstract=null), Reference(id=1228805377605694194, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2016, volume=2016, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=LI Y F, LIU J X, WANG Y, journalName=Shock and Vibration, refType=null, unstructuredReference=LI Y F, LIU J X, WANG Y. Railway wheel flat detection based on improved empirical mode decomposition[J]. Shock and Vibration, 2016, 2016: 4879283., articleTitle=Railway wheel flat detection based on improved empirical mode decomposition, refAbstract=null), Reference(id=1228805377714746102, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=8, pageStart=182, pageEnd=189, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=刘国云, 曾京, 邬平波, journalName=机械工程学报, refType=null, unstructuredReference=刘国云,曾京, 邬平波,等.车轮扁疤所引起的车辆系统振动特性分析[J]. 机械工程学报, 2020, 56(8):182-189., articleTitle=车轮扁疤所引起的车辆系统振动特性分析, refAbstract=null), Reference(id=1228805377807020795, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=8, pageStart=182, pageEnd=189, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=LIU Guoyun, ZENG Jing, WU Pingbo, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=LIU Guoyun, ZENG Jing, WU Pingbo, et al.Vibration characteristic analysis of vehicle systems due to wheel flat[J]. Journal of Mechanical Engineering, 2020, 56(8): 182-189., articleTitle=Vibration characteristic analysis of vehicle systems due to wheel flat, refAbstract=null), Reference(id=1228805377895101185, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2014, volume=49, issue=4, pageStart=700, pageEnd=705, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=王忆佳, 曾京, 高浩, journalName=西南交通大学学报, refType=null, unstructuredReference=王忆佳,曾京, 高浩,等.车轮扁疤引起的轮轨冲击分析[J]. 西南交通大学学报, 2014, 49(4):700-705., articleTitle=车轮扁疤引起的轮轨冲击分析, refAbstract=null), Reference(id=1228805377970598660, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2014, volume=49, issue=4, pageStart=700, pageEnd=705, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=WANG Yijia, ZENG Jing, GAO Hao, journalName=Journal of Southwest Jiaotong University, refType=null, unstructuredReference=WANG Yijia, ZENG Jing, GAO Hao, et al.Analysis of wheel/rail impact induced by wheel flats[J]. Journal of Southwest Jiaotong University, 2014, 49(4): 700-705., articleTitle=Analysis of wheel/rail impact induced by wheel flats, refAbstract=null), Reference(id=1228805378058679046, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2008, volume=265, issue=9-10, pageStart=1518, pageEnd=1525, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=MATSUMOTO A, SATO Y, OHNO H, journalName=Wear, refType=null, unstructuredReference=MATSUMOTO A, SATO Y, OHNO H, et al.A new measuring method of wheel-rail contact forces and related considerations[J]. Wear, 2008, 265(9-10): 1518-1525., articleTitle=A new measuring method of wheel-rail contact forces and related considerations, refAbstract=null), Reference(id=1228805378167730955, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=46, pageEnd=55, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=FRANKENSTEIN B, HENTSCHEL D, PRIDOEHL E, journalName=null, refType=null, unstructuredReference=FRANKENSTEIN B, HENTSCHEL D, PRIDOEHL E, et al.Hollow shaft integrated health monitoring system for railroad wheels[C]//Proceedings of Advanced Sensor Technologies for Nondestructive Evaluation and Structural Health Monitoring. Washington, D. C., USA: SPIE, 2005: 46-55., articleTitle=Hollow shaft integrated health monitoring system for railroad wheels, refAbstract=null), Reference(id=1228805378255811344, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=1993, volume=100, issue=4, pageStart=243, pageEnd=245, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=PARTINGTON W, journalName=Proceedings of the Institution of Civil Engineers-Transport, refType=null, unstructuredReference=PARTINGTON W. Wheel impact load monitoring[J]. Proceedings of the Institution of Civil Engineers-Transport,1993,100(4): 243-245., articleTitle=Wheel impact load monitoring, refAbstract=null), Reference(id=1228805378360668950, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2019, volume=432-433, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=FRÖHLING R, SPANGENBERG U, REITMANN E, journalName=Wear, refType=null, unstructuredReference=FRÖHLING R, SPANGENBERG U, REITMANN E. Root cause analysis of locomotive wheel tread polygonisation[J]. Wear, 2019, 432-433: 102911., articleTitle=Root cause analysis of locomotive wheel tread polygonisation, refAbstract=null), Reference(id=1228805378448749334, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2022, volume=193, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=PENG X, ZENG J, WANG J, journalName=Measurement, refType=null, unstructuredReference=PENG X, ZENG J, WANG J, et al.Wayside wheel-rail vertical contact force continuous detecting method and its application[J]. Measurement, 2022, 193: 110975., articleTitle=Wayside wheel-rail vertical contact force continuous detecting method and its application, refAbstract=null), Reference(id=1228805378536829723, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=PENG B, journalName=null, refType=null, unstructuredReference=PENG B. Mechanisms of railway wheel polygonization[D]. Huddersfield: University of Huddersfield, 2020., articleTitle=Mechanisms of railway wheel polygonization, refAbstract=null), Reference(id=1228805378629104415, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2018, volume=19, issue=4, pageStart=1176, pageEnd=1187, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=KRUMMENACHER G, ONG C S, KOLLER S, journalName=IEEE Transactions on Intelligent Transportation Systems, refType=null, unstructuredReference=KRUMMENACHER G, ONG C S, KOLLER S, et al.Wheel defect detection with machine learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(4): 1176-1187., articleTitle=Wheel defect detection with machine learning, refAbstract=null), Reference(id=1228805378721379108, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2021, volume=147, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=27, authorNames=AVCI O, ABDELJABER O, KIRANYAZ S, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=AVCI O, ABDELJABER O, KIRANYAZ S, et al.A review of vibration-based damage detection in civil structures: from traditional methods to Machine Learning and Deep Learning applications[J]. Mechanical Systems and Signal Processing,2021,147: 107077., articleTitle=A review of vibration-based damage detection in civil structures: from traditional methods to Machine Learning and Deep Learning applications, refAbstract=null), Reference(id=1228805378813653798, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2018, volume=21, issue=5, pageStart=687, pageEnd=694, url=null, language=null, rfNumber=[21], rfOrder=28, authorNames=LIU X Z, NI Y Q, journalName=Smart Structure System, refType=null, unstructuredReference=LIU X Z, NI Y Q. Wheel tread defect detection for high-speed trains using FBG-based online monitoring techniques[J]. Smart Structure System, 2018, 21(5): 687-694., articleTitle=Wheel tread defect detection for high-speed trains using FBG-based online monitoring techniques, refAbstract=null), Reference(id=1228805378905928490, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=1, pageStart=211, pageEnd=235, url=null, language=null, rfNumber=[22], rfOrder=29, authorNames=YANG Y F, LING L, WANG C, journalName=Vehicle System Dynamics, refType=null, unstructuredReference=YANG Y F, LING L, WANG C, et al.Wheel/rail dynamic interaction induced by polygonal wear of locomotive wheels[J]. Vehicle System Dynamics, 2022, 60(1): 211-235., articleTitle=Wheel/rail dynamic interaction induced by polygonal wear of locomotive wheels, refAbstract=null), Reference(id=1228805378985620271, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2021, volume=11, issue=9, pageStart=4002, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=30, authorNames=MOSLEH A, MONTENEGRO P A, COSTA P A, journalName=Applied Sciences, refType=null, unstructuredReference=MOSLEH A, MONTENEGRO P A, COSTA P A, et al.Railway vehicle wheel flat detection with multiple records using spectral kurtosis analysis[J]. Applied Sciences, 2021, 11(9): 4002., articleTitle=Railway vehicle wheel flat detection with multiple records using spectral kurtosis analysis, refAbstract=null), Reference(id=1228805379090477872, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=4, pageStart=1910, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=31, authorNames=MOHAMMADI M, MOSLEH A, VALE C, journalName=Sensors, refType=null, unstructuredReference=MOHAMMADI M, MOSLEH A, VALE C, et al.An unsupervised learning approach for wayside train wheel flat detection[J]. Sensors, 2023, 23(4): 1910., articleTitle=An unsupervised learning approach for wayside train wheel flat detection, refAbstract=null), Reference(id=1228805379170169653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2020, volume=139, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=32, authorNames=WANG Y W, NI Y Q, WANG X, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=WANG Y W, NI Y Q, WANG X. Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model[J]. Mechanical Systems and Signal Processing, 2020, 139: 106654., articleTitle=Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model, refAbstract=null), Reference(id=1228805379262444341, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2022, volume=203, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=33, authorNames=XING Z Y, ZHANG Z Y, YAO X W, journalName=Measurement, refType=null, unstructuredReference=XING Z Y, ZHANG Z Y, YAO X W, et al.Rail wheel tread defect detection using improved YOLOv3[J]. Measurement, 2022, 203: 111959., articleTitle=Rail wheel tread defect detection using improved YOLOv3, refAbstract=null), Reference(id=1228805379325358902, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2018, volume=19, issue=4, pageStart=1176, pageEnd=1187, url=null, language=null, rfNumber=[27], rfOrder=34, authorNames=Gabriel K, Cheng S O, Stefan K, journalName=IEEE Transactions on Intelligent Transportation Systems, refType=null, unstructuredReference=Gabriel K, Cheng S O, Stefan K,et al.Wheel defect detection with machine learning[J].IEEE Transactions on Intelligent Transportation Systems, 2018,19(4): 1176-1187., articleTitle=Wheel defect detection with machine learning, refAbstract=null), Reference(id=1228805379384079161, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2020, volume=10, issue=14, pageStart=4720, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=35, authorNames=TENG Z Q, TENG S, ZHANG J Q, journalName=Applied Sciences, refType=null, unstructuredReference=TENG Z Q, TENG S, ZHANG J Q, et al.Structural damage detection based on real-time vibration signal and convolutional neural network[J]. Applied Sciences., 2020, 10(14): 4720., articleTitle=Structural damage detection based on real-time vibration signal and convolutional neural network, refAbstract=null), Reference(id=1228805379438605116, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2020, volume=303, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=36, authorNames=DU C, DUTTA S, KURUP P, journalName=Sensors and Actuators A: Physical, refType=null, unstructuredReference=DU C, DUTTA S, KURUP P, et al.A review of railway infrastructure monitoring using fiber optic sensors[J]. Sensors and Actuators A: Physical, 2020, 303: 111728., articleTitle=A review of railway infrastructure monitoring using fiber optic sensors, refAbstract=null), Reference(id=1228805379501519679, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[30], rfOrder=37, authorNames=AMINI A, journalName=null, refType=null, unstructuredReference=AMINI A. Online condition monitoring of railway wheelsets[D]. Birmingham: University of Birmingham, 2016., articleTitle=Online condition monitoring of railway wheelsets, refAbstract=null)], funds=[Fund(id=1228805375898612386, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, awardId=2024YFB4303200, language=CN, fundingSource=国家重点研发项目(2024YFB4303200), fundOrder=null, country=null), Fund(id=1228805375990887077, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, awardId=2023YFG0197, language=CN, fundingSource=四川省重点研发项目(2023YFG0197), fundOrder=null, country=null), Fund(id=1228805376083161769, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, awardId=2023TPL_T08, language=CN, fundingSource=轨道交通运载系统全国重点实验室自主项目(2023TPL_T08), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1228805369904951607, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, xref=null, ext=[AuthorCompanyExt(id=1228805369909145912, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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=1228805369917534521, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, companyId=1228805369904951607, 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,四川 成都 610031)])], figs=[ArticleFig(id=1228805372480254487, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 1, caption=Schematic diagram of the effective area of the sensor in relation to the tread surface, figureFileSmall=zbdZo/UXFYh/bBzTh1D/GQ==, figureFileBig=FmTOAq/zS+8stu/nEYGHMA==, tableContent=null), ArticleFig(id=1228805372572529181, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图1, caption=传感器有效区与踏面对应位置示意图, figureFileSmall=zbdZo/UXFYh/bBzTh1D/GQ==, figureFileBig=FmTOAq/zS+8stu/nEYGHMA==, tableContent=null), ArticleFig(id=1228805372807410219, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 2, caption=Schematic diagram of convolutional neural network structure, figureFileSmall=yuQUUGxDjQ8MfT0qXEa63w==, figureFileBig=/z+FyVZ6Uz4cmdMnaPjmkA==, tableContent=null), ArticleFig(id=1228805372941627955, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图2, caption=卷积神经网络结构示意图, figureFileSmall=yuQUUGxDjQ8MfT0qXEa63w==, figureFileBig=/z+FyVZ6Uz4cmdMnaPjmkA==, tableContent=null), ArticleFig(id=1228805373017125428, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 3, caption=Schematic diagram of ResNet50 network structure, figureFileSmall=8pMQ7cIfLqBNGNErMMErKg==, figureFileBig=jr/AloN4pE0APOXvdpAjNA==, tableContent=null), ArticleFig(id=1228805373126177338, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图3, caption=ResNet50网络结构示意图, figureFileSmall=8pMQ7cIfLqBNGNErMMErKg==, figureFileBig=jr/AloN4pE0APOXvdpAjNA==, tableContent=null), ArticleFig(id=1228805373205869117, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 4, caption=Schematic diagram of the improved CNN structure, figureFileSmall=+zHc7I/k+0yZZwjb6ZDORA==, figureFileBig=n+AD8Ex7SnS6BUQ8QJaCuQ==, tableContent=null), ArticleFig(id=1228805373293949504, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图4, caption=改进的CNN结构示意图, figureFileSmall=+zHc7I/k+0yZZwjb6ZDORA==, figureFileBig=n+AD8Ex7SnS6BUQ8QJaCuQ==, tableContent=null), ArticleFig(id=1228805373394612802, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 5, caption=Wheel damage identification model based on improved CNN, figureFileSmall=fZzTTEOtEflx5EadZioIJQ==, figureFileBig=nlCpW4t2wR6/REO0KV/1Eg==, tableContent=null), ArticleFig(id=1228805373482693192, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图5, caption=基于改进CNN的车轮损伤识别模型, figureFileSmall=fZzTTEOtEflx5EadZioIJQ==, figureFileBig=nlCpW4t2wR6/REO0KV/1Eg==, tableContent=null), ArticleFig(id=1228805373604328012, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 6, caption=Vehicle-track multibody dynamics model and elastic wheelset modeling, figureFileSmall=8dn96WWfCJMLfya8CqXYSw==, figureFileBig=E3rvB9h4d9DivzSR7rFunA==, tableContent=null), ArticleFig(id=1228805373725962832, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图6, caption=车辆-轨道多体动力学模型和弹性轮对模型, figureFileSmall=8dn96WWfCJMLfya8CqXYSw==, figureFileBig=E3rvB9h4d9DivzSR7rFunA==, tableContent=null), ArticleFig(id=1228805373843403347, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 7, caption=Reconstructed signal shapes for wheels with different lengths of flat scars, figureFileSmall=1W2SBOdpFNGOaaQYnBWtXw==, figureFileBig=f4uDvsROT/L14nUzd2stRA==, tableContent=null), ArticleFig(id=1228805373939872345, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图7, caption=不同长度扁疤车轮重构信号形状, figureFileSmall=1W2SBOdpFNGOaaQYnBWtXw==, figureFileBig=f4uDvsROT/L14nUzd2stRA==, tableContent=null), ArticleFig(id=1228805374011175514, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 8, caption=Schematic diagram of the recognition effect of different wheel damages under the simulation dataset, figureFileSmall=VIC+GQXTBC7QsUPT3ulGsw==, figureFileBig=6ODCV2J6Fkks7ll7/mV6ew==, tableContent=null), ArticleFig(id=1228805374090867297, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图8, caption=仿真数据集下不同车轮损伤的识别效果示意图, figureFileSmall=VIC+GQXTBC7QsUPT3ulGsw==, figureFileBig=6ODCV2J6Fkks7ll7/mV6ew==, tableContent=null), ArticleFig(id=1228805374178947685, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 9, caption=Wheel damage experiment platform, figureFileSmall=zaYT7fhbiNIdi4v4buztqg==, figureFileBig=+S7C3TFUpwX6Zcrf4uhXMA==, tableContent=null), ArticleFig(id=1228805374250250853, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图9, caption=车轮损伤试验平台, figureFileSmall=zaYT7fhbiNIdi4v4buztqg==, figureFileBig=+S7C3TFUpwX6Zcrf4uhXMA==, tableContent=null), ArticleFig(id=1228805374329942634, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 10, caption=Three measurements and corresponding ranges, figureFileSmall=QS4VQDSGT70UKDUxUEwzeQ==, figureFileBig=FZKlSLHrrhQaXInbGScgBQ==, tableContent=null), ArticleFig(id=1228805374501909104, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图10, caption=3次测量及对应范围, figureFileSmall=QS4VQDSGT70UKDUxUEwzeQ==, figureFileBig=FZKlSLHrrhQaXInbGScgBQ==, tableContent=null), ArticleFig(id=1228805374585795187, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 11, caption=Schematic of reconstructed signals from test data, figureFileSmall=35X2bG15XVufagqUqLfetA==, figureFileBig=oX42Cp9/+SnK4P9KpZfwLA==, tableContent=null), ArticleFig(id=1228805374665486965, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图11, caption=试验数据的重构信号示意图, figureFileSmall=35X2bG15XVufagqUqLfetA==, figureFileBig=oX42Cp9/+SnK4P9KpZfwLA==, tableContent=null), ArticleFig(id=1228805374749373049, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 12, caption=Energy distribution of reconstructed signals under different damage conditions, figureFileSmall=NApZcIsCxbk0Gzw/bN8+EQ==, figureFileBig=mItav3FaUmDAIIbtUfZFFQ==, tableContent=null), ArticleFig(id=1228805374837453435, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图12, caption=不同损伤条件下重构信号能量分布图, figureFileSmall=NApZcIsCxbk0Gzw/bN8+EQ==, figureFileBig=mItav3FaUmDAIIbtUfZFFQ==, tableContent=null), ArticleFig(id=1228805374921339521, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 13, caption=Improved CNN confusion matrix based on reconstructed signal test set, figureFileSmall=YoQ9BcYBat/Juw0QCTRNgQ==, figureFileBig=ZPItKda7yB70shHQeJrQqg==, tableContent=null), ArticleFig(id=1228805375022002819, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图13, caption=基于重构信号测试集的改进CNN混淆矩阵, figureFileSmall=YoQ9BcYBat/Juw0QCTRNgQ==, figureFileBig=ZPItKda7yB70shHQeJrQqg==, tableContent=null), ArticleFig(id=1228805375122666119, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Fig. 14, caption=Accuracy of each model for classification in different signal data, figureFileSmall=yDh5D7Lxnz9Scup3b0rrCQ==, figureFileBig=NIhZmgiwJii357E3/kzPxQ==, tableContent=null), ArticleFig(id=1228805375202357898, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=图14, caption=各模型在不同信号数据中分类的准确率, figureFileSmall=yDh5D7Lxnz9Scup3b0rrCQ==, figureFileBig=NIhZmgiwJii357E3/kzPxQ==, tableContent=null), ArticleFig(id=1228805375294632590, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Tab.1, caption=

1D-CNN network basic structure

, figureFileSmall=null, figureFileBig=null, tableContent=
网络结构特征尺度网络结构特征尺度
输入层13×1×1归一化层210×1×128
卷积层112×1×64激活层210×1×128
归一化层112×1×64最大池化层25×1×128
激活层112×1×64Flatten1×640
最大池化层111×1×64全连接层1×128
卷积层210×1×128
), ArticleFig(id=1228805375416267411, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=表1, caption=

1D-CNN网络基本结构

, figureFileSmall=null, figureFileBig=null, tableContent=
网络结构特征尺度网络结构特征尺度
输入层13×1×1归一化层210×1×128
卷积层112×1×64激活层210×1×128
归一化层112×1×64最大池化层25×1×128
激活层112×1×64Flatten1×640
最大池化层111×1×64全连接层1×128
卷积层210×1×128
), ArticleFig(id=1228805375533707925, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Tab.2, caption=

Parameters for simulating wheel defect characteristics

, figureFileSmall=null, figureFileBig=null, tableContent=
参数数值
车轮直径/mm840
损伤类型20~60 mm扁疤
传感器数量40
车速/(km·h−1)40~120
有效区长度/mm80
噪声/%5~20
), ArticleFig(id=1228805375617594008, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=表2, caption=

车轮缺陷特征模拟的参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数数值
车轮直径/mm840
损伤类型20~60 mm扁疤
传感器数量40
车速/(km·h−1)40~120
有效区长度/mm80
噪声/%5~20
), ArticleFig(id=1228805375718257307, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=EN, label=Tab.3, caption=

Accuracy of machine learning models for classification in test sets

, figureFileSmall=null, figureFileBig=null, tableContent=
特征分类器重构信号分类准确率/%
融合特征改进CNN97.6
二维图像CNN95.2
一维时域特征BPNN88.8
SVM96.8
一维频域特征BPNN79.2
SVM80.0
), ArticleFig(id=1228805375789560478, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366343987253, language=CN, label=表3, caption=

不同模型在重构信号测试集中分类的准确率

, figureFileSmall=null, figureFileBig=null, tableContent=
特征分类器重构信号分类准确率/%
融合特征改进CNN97.6
二维图像CNN95.2
一维时域特征BPNN88.8
SVM96.8
一维频域特征BPNN79.2
SVM80.0
)], attaches=null, journal=Journal(id=1225147830491308032, delFlag=0, nameCn=振动工程学报, nameEn=Journal of Vibration Engineering, nameHistory1=null, nameHistory2=null, issn=1004-4523, eissn=null, cn=32-1349/TB, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=null, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Vibration Engineering, journalRemark=null, publicationField=null, createdTime=1770027604939, updatedTime=1770169610881, createdBy=18614031015, updatedBy=18614031015, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=null, picEn=null, jcr=null, cjcr=null, exts=[JournalExt(id=1225743346702925905, language=CN, name=振动工程学报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国振动工程学会, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770169587064, updatedTime=1770169587064, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionEditorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionReviewUrl=https://www.manuscripts.com.cn/zdgcxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1225743346765840466, language=EN, name=Journal of Vibration Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770169587079, updatedTime=1770169587079, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionEditorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionReviewUrl=https://www.manuscripts.com.cn/zdgcxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1225147924628267009, websiteList=[Website(id=1225150618881404985, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225147924628267009, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zdgcxb/CN, language=CN, createTime=1770028269739, createBy=18614031015, updateTime=1770028293069, updateBy=18614031015, name=振动工程学报-中文, tplId=1146099689490845704, title=振动工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225151164178673750, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=articleTextType, value=kx, createTime=1770028399748, updateTime=1770028399748, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164157702227, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=banner, value=null, createTime=1770028399743, updateTime=1770028399743, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164203839577, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=grayFlag, value=0, createTime=1770028399754, updateTime=1770028399754, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164145119314, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=logo, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic?fileId=L7mSU8YPwm66NWFMoTG4aQ==, createTime=1770028399740, updateTime=1770028399740, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164212228187, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=minRunFlag, value=0, createTime=1770028399756, updateTime=1770028399756, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164170285141, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/file/pic, createTime=1770028399746, updateTime=1770028399746, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164208033882, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=silenceFlag, value=0, createTime=1770028399755, updateTime=1770028399755, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164166090836, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770028399745, updateTime=1770028399745, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164187062359, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=themeColor, value=null, createTime=1770028399750, updateTime=1770028399750, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164195450968, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=themeStyle, value=null, createTime=1770028399752, updateTime=1770028399752, creator=18614031015, updator=18614031015)]), Website(id=1225150619003039804, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225147924628267009, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zdgcxb/EN, language=EN, createTime=1770028269768, createBy=18614031015, updateTime=1770028309190, updateBy=18614031015, name=振动工程学报-英文, tplId=1146101810881728533, title=Journal of Vibration Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225151193366835296, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=articleTextType, value=kx, createTime=1770028406707, updateTime=1770028406707, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193350058077, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=banner, value=null, createTime=1770028406703, updateTime=1770028406703, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193387806819, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=grayFlag, value=0, createTime=1770028406712, updateTime=1770028406712, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193341669468, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=logo, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic?fileId=L7mSU8YPwm66NWFMoTG4aQ==, createTime=1770028406701, updateTime=1770028406701, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193400389733, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=minRunFlag, value=0, createTime=1770028406715, updateTime=1770028406715, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193362640991, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic, createTime=1770028406706, updateTime=1770028406706, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193392001124, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=silenceFlag, value=0, createTime=1770028406713, updateTime=1770028406713, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193354252382, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770028406704, updateTime=1770028406704, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193371029601, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=themeColor, value=null, createTime=1770028406708, updateTime=1770028406708, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193379418210, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=themeStyle, value=null, createTime=1770028406710, updateTime=1770028406710, creator=18614031015, updator=18614031015)])], journalTitle=振动工程学报, weixinUrl=null, journalUrl=http://zdgcxb.csve.org.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Vibration Engineering, journalPhotoCn=null, journalPhotoEn=null, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2025.06.010, detailUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/10.16385/j.cnki.issn.1004-4523.2025.06.010, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/PDF/10.16385/j.cnki.issn.1004-4523.2025.06.010, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/PDF/10.16385/j.cnki.issn.1004-4523.2025.06.010, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
多传感器数据融合和改进卷积神经网络的车轮踏面损伤识别方法
收藏切换
PDF下载
缪炳荣 , 徐松源 , 吴啸林 , 王思明 , 张哲
振动工程学报 | 2025,38(6): 1221-1231
收起
收藏切换
振动工程学报 | 2025, 38(6): 1221-1231
多传感器数据融合和改进卷积神经网络的车轮踏面损伤识别方法
全屏
缪炳荣 , 徐松源, 吴啸林, 王思明, 张哲
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,四川 成都 610031

通讯作者:

缪炳荣(1970—),男,博士,副研究员。E-mail:
A method for wheel tread damage identification using multi-sensor data fusion and improved convolutional neural networks
Bingrong MIAO , Songyuan XU, Xiaolin WU, Siming WANG, Zhe ZHANG
Affiliations
  • State Key Laboratory of Rail Transit Vehicle System,Southwest Jiaotong University,Chengdu 610031,China
出版时间: 2025-06-10 doi: 10.16385/j.cnki.issn.1004-4523.2025.06.010
文章导航
收藏切换

针对轨旁信号难以完全表征车轮信息和车轮损伤难以定位与量化的问题,提出一种多传感器数据融合算法和改进卷积神经网络(CNN)的车轮踏面缺陷识别方法。基于多体动力学和有限元理论构建车辆-轨道动力学耦合模型。通过布置较少的传感器,进行多模态特征的提取,对车轮几何特征、车速等参数进行了数据融合的算法优化。基于1D-CNN和2D-CNN提出改进的CNN模型。同时,将频域特征和图像特征进行数据融合,并提出考虑融合特征的CNN算法模型。对重构信号进行缺陷特征提取,并利用改进的CNN融合数据特征实现车轮损伤识别。结合比例车辆试验平台,并利用仿真数据和实际算例验证提出方法的有效性。在不同信号测试集和数据特征下,对CNN、BP神经网络(BPNN)和支持向量机(SVM)的损伤识别效果进行对比分析。结果表明:所提损伤识别模型可以更好地识别车轮踏面缺陷,识别结果与实测结果有很好的一致性;将不同维度的数据特征进行融合,可以表征不同损伤程度下的缺陷并提高识别效果;能够解决轨旁数据不能完整重构车轮状态等问题,为车轮缺陷的在线损伤识别提供技术支撑。

损伤识别  /  数据融合  /  机器学习  /  优化算法  /  车轮缺陷

To address the challenges of fully characterizing wheel information and accurately locating and quantifying wheel damage using trackside signals, this paper proposes a multi-sensor data fusion algorithm combined with an improved convolutional neural network (CNN) for wheel tread defect identification. A vehicle-track dynamics coupling model is established based on multi-body dynamics and finite element theory. By strategically arranging fewer sensors, multimodal features are extracted, and data fusion algorithms are optimized for parameters like wheel geometry and vehicle speed. An improved CNN model is then proposed, building upon both 1D-CNN and 2D-CNN architectures. Simutaneously, frequency domain features and image features are fused, leading to a new CNN algorithm model that incorporates these fusion features. Defect feature extraction is performed on the reconstructed signal, and the improved CNN, leveraging the fused data features, is used to achieve wheel damage identification. The effectiveness of the proposed method is validated using both simulation data and actual case studies, in conjunction with a proportional vehicle test rig. The damage identification performance of the proposed model is compared against CNN, BP neural network (BPNN), and support vector machine (SVM) under various signal test sets and data features. Results indicate that the proposed damage identification model can more effectively identify wheel tread defects, showing good consistency with measured results. Fusing data features from different dimensions can characterize defects under varying degrees of damage and significantly improve identification performance. This approach successfully addresses issues where trackside data alone cannot fully reconstruct wheel status, thereby providing crucial technical support for the online damage identification of wheel defects.

damage recognition  /  data fusion  /  machine learning  /  optimization algorithm  /  wheel defects
缪炳荣, 徐松源, 吴啸林, 王思明, 张哲. 多传感器数据融合和改进卷积神经网络的车轮踏面损伤识别方法. 振动工程学报, 2025 , 38 (6) : 1221 -1231 . DOI: 10.16385/j.cnki.issn.1004-4523.2025.06.010
Bingrong MIAO, Songyuan XU, Xiaolin WU, Siming WANG, Zhe ZHANG. A method for wheel tread damage identification using multi-sensor data fusion and improved convolutional neural networks[J]. Journal of Vibration Engineering, 2025 , 38 (6) : 1221 -1231 . DOI: 10.16385/j.cnki.issn.1004-4523.2025.06.010
轨道车辆在高速运营过程中容易产生各种车轮缺陷,如滚动接触疲劳[1]、扁疤[2-3]、剥离[4]、擦伤[5]、多边形和不圆度[6-7]等。这些典型的踏面缺陷不仅会导致列车运行时的轮轨接触力和材料特性的异常变化,更容易产生异常的冲击载荷与结构损伤问题。车轮踏面缺陷的监测研究是轨道车辆故障诊断及在线评估的热点问题之一[8]。但由于运行环境恶劣等原因,车轮的故障诊断技术还不能真正实现车轮缺陷类型和程度的在线识别。为了保障列车的运行安全并提高车辆的运营维修质量,降低维修成本并延长检测周期,开展车轮踏面缺陷的精准识别和在线评估具有重要的意义。
常见的车轮踏面缺陷的检测方法主要包括两种:根据车载响应和轨旁响应监测车轮损伤[9]。对于车载检测技术,按其检测原理不同可以分为振动检测、声学检测、轮轨力检测等技术。振动检测通常将加速度传感器安装于车轮轴箱或构架端部,以实时监测车轮的振动情况。LI等[10]提出了一种用于识别车轮扁疤的改进经验模态分解方法,并通过仿真与滚动试验台验证了其有效性。轮轨力检测可直观反映车轮踏面的状态并分析其对钢轨的冲击[11-12]。MATSUMOTO等[13]通过非接触式的间隙传感器测量轮轨横向力,并进行车轮损伤的识别。车轮踏面损伤还会导致规律的冲击噪声,FRANKENSTEIN等[14]将麦克风安装于空心车轴的轴端,并通过噪声对损伤进行识别;该方法能够对小损伤进行检测,但抗干扰的能力较弱。车载检测方法存在的共同问题是需要在每节车厢上安装设备,并要对车辆进行改造,这将提高检测成本,还可能造成二次安全隐患[15]
目前,利用轨旁加速度识别车轮缺陷是一种常见的检测方法,该方法能够适应不同车速和环境,具有成本低、维护简单等优点[16]。基本原理是通过应变与力的关系计算作用在钢轨上的轮轨力的异常,采用剪应变法检测轮轨力和识别车轮扁疤。缺点是只能测量每跨轨枕间的部分区域内的轮轨力。为了能够监测整个车轮踏面,需要在一段较长的轨道布置多个应变片,测量多跨轨道的轮轨力。通过轨旁多传感器采集的数据计算得到的轮轨力一般可以识别90%的车轮踏面缺陷,但是依然存在一些踏面缺陷无法被有效识别的问题。也有学者对不同车速、轴重和损伤程度下轨道应变和加速度的峰值进行研究,发现轮轨力的峰值受轮轨结构和动力学参数的影响较大,该方法难以获得稳定的计算结果[17]
为了克服传统轨旁响应识别方法的缺点,国内外一直在探索利用轨旁应变数据实现对轮轨力连续测量的方法。比如在轨枕下方安装力传感器,实现对剪力测试区间外的盲区识别。PENG等[18]采用拼接离散轮轨力的方法,在应变测量有效区段的前后位置安装控制开关,识别车轮经过或离开的时间点,在车轮踏面的不同位置测试轮轨力信号,进行数据组合后获得车轮圆周上连续的轮轨力。也有学者通过机器学习方法对车轮损伤进行识别,如KRUMMENACHER等[19]使用机器学习方法,将离散轮轨力小波分解信号的中心距作为SVM的输入特征,并将轮轨力信号转换为二维图像作为CNN的输入,进而对车轮损伤进行有效的识别与分类。
众多学者[19-24]利用轨旁的响应数据对车轮缺陷损伤检测的问题进行了大量研究。但是,基于轨旁应变数据的在线检测方法中依然存在一些迫切需要解决的技术难题[25-28],包括:
(1)信号测量范围较短。较少的加速度或应变传感器无法完整实现对车轮整个圆周踏面的检测,使用多个传感器依然只能获得部分离散信号,不能保证全面检测车轮踏面,需要改进识别算法获得整个车轮圆周的应变信号。
(2)轮轨力峰值更容易受到外界因素干扰。常规的时频检测方法多数只能检测到车轮损伤的存在性,却难以全面和准确表征车轮踏面的完整状态,包括损伤的定位、类型和量化分析。仅使用轮轨力的峰值或频率异常作为车轮损伤存在性的判断标准存在局限性,容易导致误判,且难以有效识别踏面的损伤类型和程度。
因此,针对车轮踏面扁疤缺陷的检测难题[19-29],本文提出一种基于多传感器数据融合和改进CNN的车轮损伤识别模型。该方法首先考虑较少的传感器布置、有效的检测区域、车轮几何特征和车速等因素,对轨旁有限传感器的应变信号进行轮轨力数据的特征提取、特征融合与信号重构。其次,结合1D-CNN和2D-CNN对CNN模型进行多传感器融合算法优化,并提出改进CNN模型。最后,建立车轮损伤识别模型;将重构信号作为数据输入,融合一维频域特征和二维图像特征进行车轮损伤识别。
本文通过动力学仿真和比例车辆-轨道试验平台的实测数据,验证了多传感器数据融合和改进卷积神经网络的车轮踏面损伤识别方法的效果。
在轨旁振动应变和加速度的测试中,获得的信号里包含大量车轮踏面的损伤信息。但其受传感器数量和位置的限制,采集的信号测量范围较短,难以完全表征车轮的信息。考虑到轮轨力的周期性,可将多个传感器的数据进行融合,并重构出一个包含车轮踏面状态信息的信号,称为重构信号[9, 27]。各传感器输出的有效区和对应的踏面位置如图1所示,相同的颜色表示各传感器有效区对应的踏面位置。
xm为第m个传感器有效区中第一个样本在轨道上的对应位置,sm,1为第m个传感器有效区内的第一个样本。车轮圆周坐标如下式所示:
ym,1=xm(C×xm/C)
ym,n=ym,1+λ(n1)
式中,ym,n表示第m个传感器有效区内第n个样本对应的圆周坐标,y(0,C),其中C为车轮周长;表示向上取整;λ表示输出中两样本间的空间间隔,取决于车速v和采样频率fs,即λ=v/fs
若共有M个传感器,有效区长度内有N个样本,sij表示第i个传感器在j时刻有效区的输出。将各传感器的输出样本与踏面位置对应,其重构信号ψ为:
ψ=[y1,1y1,Ny2,1y2,Ny3,1yM,Ns1,1s1,Ns2,1s1,Ns3,1sM,N]
卷积神经网络(CNN)是一种为处理二维输入数据而特殊设计的多层人工神经网络,广泛应用于图像处理领域中。CNN由卷积层、激活层和池化层三种基本结构组成。该网络可用于自动提取图像特征,并生成每幅图像的特定特征空间输出结果。对图像进行分类时,常将CNN的输出作为全连接层的输入,通过全连接层实现对图像的分类,其结构如图2所示。
一般而言,较少的传感器很难完整地实现对车轮的整个圆周踏面缺陷的检测,即使在测量范围内能够布置较多的传感器,也只能获得部分包含扁疤信息的响应数据。这些数据并不能保证车轮踏面缺陷都能获得全面的检测。这就需要改进损伤识别算法获得反映整个车轮圆周的应变信号特征[30]
本文考虑传感器间隔、车轮直径等因素,设计多传感器数据融合算法。通过组合多传感器的有效区域数据,与车轮踏面标定的位置一一对应,获得表征车轮圆周踏面状态的完整重构信号。以设计的多传感器数据融合算法作为数据处理方法,并通过重构信号提高CNN的识别精度。
(1)根据单个传感器获得的信号矩阵和信号的延迟,结合低通滤波组合计算获得多传感器矩阵。
{z1(i)=w(i)+g1(i)+n1(i)g1(i)=w(i)×g(i)z2(i)=w(iδ)+g2(i)+n2(i)g2(i)=w(iδ)×g(i)
Z=[z1,1z1,2z1,I1z1,Iz2,1z2,2z2,I1z1,IzM1,1zM1,2zM1,I1zM1,IzM,1zM,2zM,I1zM,I]
式中,z1(i)z2(i)为传感器在样本域i的测量信号;w(i)为车轮经过产生的信号;g(i)为车轮损伤产生的冲击信号;n1(i)n2(i)为噪声信号的样本域表示;δ表示样本延迟,即两传感器间相差的样本数量。Z表示传感器信号矩阵;M表示传感器数量;I为信号样本总数;zm,i表示第m个传感器在i时刻下的样本,且1mM,1iI
(2)根据滤波后的多传感器信号数据和样本延迟δ,计算车轮对应的有效区域位置和列车速度。
Rz1,z2(γ)=i=1Iγ[z1(i+γ)z2(i)]2
δ=argminγ(Rz1,z2(γ))
式中,Rz1,z2表示信号平移后的计算平方误差,属于平移量z1z2的函数;γ表示信号之间的滞后;argmin()表示括号值取得最小值时对应的变量值。通过传感器的样本延迟δ确定车轮在每个传感器输出中对应的有效区位置,计算相邻传感器的车轮有效区位置的样本差;再选择样本差与δ最接近的两个样本。
sop=argminsn|snsn1δ|
式中,sop为误差最小时对应的车轮样本号;snsn1分别为第nn−1个传感器中车轮位置对应的样本。同时,通过各传感器的空间延迟ρ和样本延迟δ计算得到车速:
v=ρδmean×fs
式中,v为车速(单位为m/s);δmean为样本延迟的平均值;fs为采样频率(单位为Hz)。
(3)结合车轮位置信息、车速信息形成传感器信号矩阵Z,确定信号有效区域,进行数据样本提取,计算获得有效区样本矩阵S。当考虑车速和采样频率均不发生变化时,任意两传感器的输出关系表示为za,bzm,b+(ma)×δ。以此为基础,对传感器输出信号的有效区间进行样本提取,并构建样本长度为N的有效区样本矩阵,表示为:
S=(s1,1s1,2s1,N1s1,Ns2,1s2,2s2,N1s1,NsM1,1sM1,2sM1,N1sM1,NsM,1sM,2sM,N1sM,N)
式中,si,j表示第i个传感器在j时刻有效区的输出。
(4)基于样本矩阵S,计算车轮直径。
确定车轮扁疤损伤区域对应的样本数据的轨道坐标,如下所示:
smout={sm|sm<μscf×σs,sm>μs+cf×σs}
式中,smout为有效区间的样本矩阵Sm行中损伤区域内的样本集合;smS中第m行向量组成的集合;cf为滤波系数;μsσs分别为样本的均值和标准差。smout对应的轨道坐标集合定义为xmout
假设车轮真实的直径d在一定范围内,通过下式可以得到车轮直径的估计值de
de=argmaxd(u>v|(pupv)%(πd)πd/2|)
式中,de为车轮直径的估计值(m);pu则表示M个传感器中所包含的p个损伤区域内对应的第u个轨道坐标值,其差值应均为车轮周长的整数倍;%表示两者之间的余数运算。
(5)将车轮位置信息、车速和有效区位置代入式(1)~(3)进行计算,并得到初始重构信号ψ
(6)对初始的重构信号进行插值、滤波处理,得到多传感器数据融合的重构信号。本文采用Savitzky-Golay滤波器(S-G)方法对重构信号进行数据处理。
CNN在处理和分析具有网格结构的数据上具有优势,但仅使用二维图像数据难以定位并量化车轮损伤。为提高损伤识别的准确性,本文通过重构的信号可以获得更完整的车轮损伤信息,同时考虑一维特征和二维特征的差异性,设计并构建了改进的CNN模型。改进的CNN模型主要包含:1D-CNN、2D-CNN和二者之间的特征融合神经网络(feature fusion neural network,FF-NN)。
(1)1D-CNN具有多尺度特征提取能力,可用于对重构信号的一维特征进行分析。频域特征对车轮状态的时间性变化更为敏感,使用频域分析方法可更好地揭示数据特征。本文对重构信号进行离散小波分解,并将归一化后的能量作为重构信号的频域特征向量输入到1D-CNN进行分析。1D-CNN的基本结构参数如表1所示。
(2)2D-CNN用于二维特征的分析。本文将重构信号数据转化为二维图像,并输入到2D-CNN。基于ResNet构建2D-CNN,其结构如图3所示。
(3)FF-NN通过将1D-CNN和2D-CNN提取的特征进行融合,实现跨维度的信息交互。FF-NN可将汇聚层的合并特征向量x转换为一个耦合特征向量y。其中每个特征值都包含不同维度特征值的耦合信息。表达式如下:
yi=ReLU(j=1P+Qwi,jxj+bi)
式中,yi为耦合特征向量y中的第i个特征值,1iNNy的长度;xj为合并向量x中的第j个特征值;PQ分别表示1D-CNN、2D-CNN单元输入向量的长度;wi,j表示与耦合特征向量中第i个特征值相连的归并向量中第j个特征值的权值;bi表示第i个特征值在耦合特征向量中的偏置;ReLU(x)=max(0,x)表示激活函数。
(4)基于FF-NN将1D-CNN和2D-CNN的特征进行融合,并搭建了一种能够融合不同尺寸特征的改进CNN模型。改进CNN由1D-CNN和2D-CNN并联,再与FF-NN串联组成。其中,1D-CNN单元处理频域特征,2D-CNN处理二维特征,FF-NN单元融合特征并进行处理。改进CNN采用Adam优化器,其学习率为0.001,并使用ReLU作为激活函数。整体结构如图4所示。
针对车轮踏面损伤识别过程中存在的技术问题,结合布置在轨旁的多传感器采集的应变信号数据,改进了多传感器数据融合算法,可以完整表征车轮踏面的数据特征。同时,结合重构信号特征和改进的CNN构建了车轮踏面损伤的识别模型。该识别模型主要包括:轨道响应数据的采集与分析、多传感器信号的信号重构和车轮损伤识别,主要流程如图5所示。
改进卷积神经网络的车轮损伤识别方法主要包括以下步骤:
步骤1:基于车辆-轨道多体动力学模型和典型工况,通过多个传感器收集车轮损伤特征的数据。
步骤2:结合2.1节理论提出多传感器数据融合算法,对车轮损伤的轨旁信号进行处理和重构。
步骤3:利用2.2节中提出的改进CNN模型,对重构信号进行数据特征提取和分析。将重构信号的一维特征和二维特征进行融合,并作为改进CNN的输入层。基于融合特征在改进CNN模型内进行训练、迭代并识别车轮损伤。
步骤4:构建试验平台并通过多个传感器采集轨旁数据。以试验数据为基础,通过步骤2和3对模型进行验证和分析。
为了分析所提出算法和改进模型的可行性,先从理论建模的角度,分析含缺陷的车轮的轨旁响应数据,通过改进的多传感器数据融合后,再利用改进CNN进行数据驱动的车轮损伤识别数值仿真研究。本文采用车辆-轨道耦合多体动力学仿真的FASTSIM算法,计算轮轨接触点处的横纵向蠕滑力和自旋蠕滑力矩,并利用Hertz非线性弹性接触理论求解轮轨接触点处的法向力。考虑柔性车轮的踏面典型缺陷和柔性轨道的车辆-轨道耦合多体动力学模型如图6所示。
为了能够对车轮踏面缺陷进行定性与定量的识别,仿真模拟生成了多种不同的车轮损伤状态。具体数据如表2所示。
通过提出的多传感器数据融合算法,对仿真的车轮损伤数据进行信号重构,其结果如图7所示。根据重构信号数据,对提出的改进CNN模型进行验证与分析,其结果如图8所示。
图8(a)反映了改进后的CNN的训练误差和分类准确率的变化,随着迭代次数的增加,误差明显降低,准确率显著提高。同时,改进后的混淆矩阵中,类别1表示无损车轮、类别2~6分别表示20~60 mm的车轮扁疤损伤,也说明预测的类别和目标类别一致性较好,识别精度可以达到98.9%,分类的误差最大为2.5%,表明所提出的多传感器数据融合算法适用于车轮损伤数据的信号重构并能高效表征相应的数据特征,而改进的CNN模型也能有效识别不同类型的车轮损伤。
为了对车轮扁疤的识别效果进行试验验证,通过搭建的1∶5比例车辆-轨道试验平台,对提出的算法效果进行分析。该试验平台是课题组设计、建立,用于车轮/轨道的载荷识别和损伤识别的实时状态检测平台。在试验平台中分别设计了4、8、12和16 mm的金属薄垫片,模拟车轮四种不同程度的损伤情况。采样频率2 kHz,采样点2048个,主要测试仪器设备采用DH 5922N动态信号测试分析系统、IEPE型加速度传感器、应变传感器、笔记本电脑、各种数据线及连接线。主要功能包括:(1)对实测的轨旁响应的数据进行采集与处理;(2)多传感器数据融合和信号重构;(3)损伤特征提取;(4)损伤识别和量化分析。核心是对布置在轨旁的多个传感器实测的信号数据进行融合分析后,再根据建立的车轮损伤识别模型进行损伤识别。1∶5比例车辆-轨道的试验布置和现场试验的示意图如图9所示。
由于轨道长度的限制,将一组数据分为3次采集:(1)让车轮圆周坐标0位置与轨道的起始点对齐采集第1次数据;(2)在340 mm位置处对齐采集第2次数据;(3)在140 mm位置处对齐采集第3次数据。每次测量对应的测量范围如图10所示。
为验证车轮损伤识别模型的有效性,利用试验平台上采集到的轨道应变信号对模型进行实测数据的训练和验证。其中,4类车轮损伤数据各125组、无损车轮数据125组,共计625组轨旁数据。
基于轨旁应变测试获得的多传感器信号,利用融合算法对试验数据进行有效处理,并得到重构信号数据特征。通过Savitzky-Golay滤波获得车轮完整圆周中含车轮典型损伤对应的重构信号,并作为车轮损伤识别模型的数据基础。车轮损伤对应的有效区样本点和重构信号,如图11所示。
由试验结果的重构信号可以发现,4 mm损伤(限于篇幅,8、12、16 mm的样本点数没有表述)车轮对应有效区域的样本点的应变范围主要集中在30με~60με。在不同扁疤长度下的重构信号中均可以观察到冲击导致的高频成分;随着扁疤长度增大,其对应冲击信号的变化幅度也增大。
同时,以实测数据的重构信号为基础提取一维特征和二维特征,并作为改进CNN的特征输入。基于离散小波提取重构信号的频域特征,经归一化处理后作为一维特征。离散信号xk,h(μ)的长度为N,其能量可表示为En[xk,h(μ)]=1Ni=1N[xk,h(μ)]2k为分解次数,h为分解频带的位置序号。对第h频带分解信号的能量做归一化处理:En(h)=En[xk,h(μ)]En[x(t)];其中h=02k1En(h)=1。不同损伤条件下的重构信号的能量分布如图12所示。
图12可知,当车轮存在扁疤损伤时,信号中的低频成分的占比降低,高频成分的占比增大。同时对于长度较小的扁疤,虽然其引起的重构信号冲击的幅度较小,但其在不同频段中能量的占比与无损车轮有明显的差异。因此,使用频域特征作为一维特征进行分析。
为了比较提出的车轮损伤识别模型效果,以实测数据的重构信号为基础,使用改进的CNN、CNN、BPNN和SVM等方法进行损伤识别。其中,CNN和BPNN的模型参数较多,会影响其在不同数据集上的性能。而SVM的分类能力较强且具有较少的模型参数,这有助于提升泛化能力。为降低过拟合的影响,在625组轨旁重构信号数据中,分层抽取375组数据作为训练集进行模型训练,并抽取125组数据作为验证集,剩余的125组数据作为测试集。
在不同模型下,考虑融合特征、二维图像、一维频域特征和时域特征(方差、峭度、偏度、峰值因子、脉冲因子和裕度因子)等不同输入特征下的识别效果,其比较结果如表3图13所示。
根据实测数据的分类结果可以发现,以重构信号为基础的识别模型均有良好的效果,其准确率均在79.2%以上。在一维特征下,SVM的准确率和泛化能力均高于BPNN。而在交叉验证下,本文提出的改进CNN分类准确率最优,为97.6%。这表明融合一维和二维特征的识别效果要优于单一维度。
同时,为验证重构信号对车轮损伤模型的性能影响,在相同参数下对原始应变信号数据和重构信号进行分析,其结果如图14所示。
由图中结果可知,根据实测数据的重构信号相较于应变信号的分类准确率更高;而频域特征下BPNN的分类准确率提升最高,为47.8%。同时也说明了本文基于多传感器数据融合算法提出的车轮损伤识别模型具有可行性。
本文基于多传感器数据融合算法,提出了一种改进的CNN模型对车轮踏面扁疤损伤进行特征提取和识别方法研究。且通过比例车辆-轨道试验台架进行测试,验证了提出的车轮损伤识别模型的有效性以及重构信号在车轮损伤识别模型中所具有的可行性和结果一致性。同时,将改进方法与CNN、SVM和BPNN等算法进行效果对比分析。本文提出的多传感器数据融合方法可实现对车轮踏面圆周的完整缺陷检测;考虑一维和二维特征改进的CNN算法模型,可解决较少的轨旁应变信号测量范围较小、无法连续检测和识别损伤等关键技术问题,提高了损伤识别的准确性。这说明本文提出的方法可以有效构建车轮损伤识别模型,对于研究高速铁路智能运维具有重要的意义。主要结论如下:
(1)结合多体动力学仿真模型,通过理论建模的方法考虑传感器布置、车轮、车速等因素,设计了多传感器数据融合算法,并验证了识别方法的可行性。
(2)利用多传感器融合算法和特征融合方法,设计并提出的改进CNN模型可以更加有效地构建车轮损伤识别的模型。该模型可以准确反映原始信号特征的重构信号,从不同维度对数据特征进行分析。
(3)使用仿真数据和实测数据对车轮损伤识别模型进行本文方法的结果验证与分析。以重构的轮轨力信号为基础,分析融合一维和二维特征的改进CNN方法的损伤识别效果,发现改进CNN方法对车轮踏面损伤具有更好的识别效果。
(4)在相同的模型参数下,相较于原始应变信号的其他几种方法,基于重构信号驱动的改进CNN方法分类准确率更高;在频域特征下,重构信号对BPNN和SVM的准确率提升也较为明显。
  • 国家重点研发项目(2024YFB4303200)
  • 四川省重点研发项目(2023YFG0197)
  • 轨道交通运载系统全国重点实验室自主项目(2023TPL_T08)
参考文献 引证文献
排序方式:
[1]
赵鑫,温泽峰, 王衡禹,等.中国轨道交通轮轨滚动接触疲劳研究进展[J]. 交通运输工程学报, 2021, 21(1):1-35.
ZHAO Xin, WEN Zefeng, WANG Hengyu, et al.Research progress on wheel/rail rolling contact fatigue of rail transit in China[J]. Journal of Traffic and Transportation Engineering, 2021, 21(1): 1-35.
[2]
敬霖, 刘凯. 车轮踏面缺陷引起的轮轨动态响应综述[J]. 交通运输工程学报, 2021, 21(1):285-315.
JING Lin, LIU Kai. Review on wheel-rail dynamic responses caused by wheel tread defects[J]. Journal of Traffic and Transportation Engineering, 2021, 21(1): 285-315.
[3]
王金能,郭鑫, 敬霖,等.高速列车车轮踏面剥离引起的轮轨冲击力学响应有限元模拟[J]. 爆炸与冲击, 2022, 42(4):151-165.
WANG Jinneng, GUO Xin, JING Lin, et al.Finite element simulations of wheel-rail impact response induced by wheel tread spalling of high-speed trains[J]. Explosion and Shock Waves, 2022, 42(4): 151-165.
[4]
翟婉明. 车辆-轨道耦合动力学上册[M]. 4版. 北京:科学出版社,2015.
ZHAI Wanming. Vehicle-Track Coupled Dynamics-Volume 1[M]. 4th ed. Beijing:Science Press,2015.
[5]
凌亮,曹亚博, 肖新标,等.车轮擦伤对高速轮轨接触行为的影响[J]. 铁道学报, 2015, 37(7):32-39.
LING Liang, CAO Yabo, XIAO Xinbiao, et al.Effect of wheel flats on the high-speed wheel-rail contact behavior[J]. Journal of the China Railway Society, 2015, 37(7): 32-39.
[6]
TAO G Q, WEN Z F, JIN X S, et al.Polygonisation of railway wheels: a critical review[J]. Railway Engineering Science, 2020, 28(4): 317-345.
[7]
TAO G Q, LIU M Q, XIE Q L, et al.Wheel–rail dynamic interaction caused by wheel out-of-roundness and its transmission between wheelsets[J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2022, 236(3): 247-261.
[8]
缪炳荣,刘俊利, 张盈,等.轨道车辆结构振动损伤识别技术综述[J]. 交通运输工程学报, 2021, 21(1):338-357.
MIAO Bingrong, LIU Junli, ZHANG Ying, et al.Review on structural vibration damage identification technology for railway vehicles[J]. Journal of Traffic and Transportation Engineering, 2021, 21(1): 338-357.
[9]
ALIREZA A. Railway wheel defect identification[D]. Delft: Delft University of Technology, 2019.
[10]
LI Y F, LIU J X, WANG Y. Railway wheel flat detection based on improved empirical mode decomposition[J]. Shock and Vibration, 2016, 2016: 4879283.
[11]
刘国云,曾京, 邬平波,等.车轮扁疤所引起的车辆系统振动特性分析[J]. 机械工程学报, 2020, 56(8):182-189.
LIU Guoyun, ZENG Jing, WU Pingbo, et al.Vibration characteristic analysis of vehicle systems due to wheel flat[J]. Journal of Mechanical Engineering, 2020, 56(8): 182-189.
[12]
王忆佳,曾京, 高浩,等.车轮扁疤引起的轮轨冲击分析[J]. 西南交通大学学报, 2014, 49(4):700-705.
WANG Yijia, ZENG Jing, GAO Hao, et al.Analysis of wheel/rail impact induced by wheel flats[J]. Journal of Southwest Jiaotong University, 2014, 49(4): 700-705.
[13]
MATSUMOTO A, SATO Y, OHNO H, et al.A new measuring method of wheel-rail contact forces and related considerations[J]. Wear, 2008, 265(9-10): 1518-1525.
[14]
FRANKENSTEIN B, HENTSCHEL D, PRIDOEHL E, et al.Hollow shaft integrated health monitoring system for railroad wheels[C]//Proceedings of Advanced Sensor Technologies for Nondestructive Evaluation and Structural Health Monitoring. Washington, D. C., USA: SPIE, 2005: 46-55.
[15]
PARTINGTON W. Wheel impact load monitoring[J]. Proceedings of the Institution of Civil Engineers-Transport,1993,100(4): 243-245.
[16]
FRÖHLING R, SPANGENBERG U, REITMANN E. Root cause analysis of locomotive wheel tread polygonisation[J]. Wear, 2019, 432-433: 102911.
[17]
PENG X, ZENG J, WANG J, et al.Wayside wheel-rail vertical contact force continuous detecting method and its application[J]. Measurement, 2022, 193: 110975.
[18]
PENG B. Mechanisms of railway wheel polygonization[D]. Huddersfield: University of Huddersfield, 2020.
[19]
KRUMMENACHER G, ONG C S, KOLLER S, et al.Wheel defect detection with machine learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(4): 1176-1187.
[20]
AVCI O, ABDELJABER O, KIRANYAZ S, et al.A review of vibration-based damage detection in civil structures: from traditional methods to Machine Learning and Deep Learning applications[J]. Mechanical Systems and Signal Processing,2021,147: 107077.
[21]
LIU X Z, NI Y Q. Wheel tread defect detection for high-speed trains using FBG-based online monitoring techniques[J]. Smart Structure System, 2018, 21(5): 687-694.
[22]
YANG Y F, LING L, WANG C, et al.Wheel/rail dynamic interaction induced by polygonal wear of locomotive wheels[J]. Vehicle System Dynamics, 2022, 60(1): 211-235.
[23]
MOSLEH A, MONTENEGRO P A, COSTA P A, et al.Railway vehicle wheel flat detection with multiple records using spectral kurtosis analysis[J]. Applied Sciences, 2021, 11(9): 4002.
[24]
MOHAMMADI M, MOSLEH A, VALE C, et al.An unsupervised learning approach for wayside train wheel flat detection[J]. Sensors, 2023, 23(4): 1910.
[25]
WANG Y W, NI Y Q, WANG X. Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model[J]. Mechanical Systems and Signal Processing, 2020, 139: 106654.
[26]
XING Z Y, ZHANG Z Y, YAO X W, et al.Rail wheel tread defect detection using improved YOLOv3[J]. Measurement, 2022, 203: 111959.
[27]
Gabriel K, Cheng S O, Stefan K,et al.Wheel defect detection with machine learning[J].IEEE Transactions on Intelligent Transportation Systems, 2018,19(4): 1176-1187.
[28]
TENG Z Q, TENG S, ZHANG J Q, et al.Structural damage detection based on real-time vibration signal and convolutional neural network[J]. Applied Sciences., 2020, 10(14): 4720.
[29]
DU C, DUTTA S, KURUP P, et al.A review of railway infrastructure monitoring using fiber optic sensors[J]. Sensors and Actuators A: Physical, 2020, 303: 111728.
[30]
AMINI A. Online condition monitoring of railway wheelsets[D]. Birmingham: University of Birmingham, 2016.
2025年第38卷第6期
PDF下载
87
41
引用本文
BibTeX
文章信息
doi: 10.16385/j.cnki.issn.1004-4523.2025.06.010
  • 接收时间:2024-05-04
  • 首发时间:2026-02-12
  • 出版时间:2025-06-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-05-04
  • 修回日期:2024-09-02
基金
国家重点研发项目(2024YFB4303200)
四川省重点研发项目(2023YFG0197)
轨道交通运载系统全国重点实验室自主项目(2023TPL_T08)
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,四川 成都 610031

通讯作者:

缪炳荣(1970—),男,博士,副研究员。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2025.06.010
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