Article(id=1228634263294243389, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228634261138374834, articleNumber=null, orderNo=null, doi=10.16385/j.cnki.issn.1004-4523.2024.07.001, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1681056000000, receivedDateStr=2023-04-10, revisedDate=1693152000000, revisedDateStr=2023-08-28, acceptedDate=null, acceptedDateStr=null, onlineDate=1770858835290, onlineDateStr=2026-02-12, pubDate=1722096000000, pubDateStr=2024-07-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770858835290, onlineIssueDateStr=2026-02-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770858835290, creator=13701087609, updateTime=1770858835290, updator=13701087609, issue=Issue{id=1228634261138374834, tenantId=1146029695717560320, journalId=1225147924628267009, year='2024', volume='37', issue='7', pageStart='1089', pageEnd='1268', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1770858834775, creator=13701087609, updateTime=1770859016311, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1228635022622654927, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228634261138374834, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1228635022622654928, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228634261138374834, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1089, endPage=1097, ext={EN=ArticleExt(id=1228634263571067455, articleId=1228634263294243389, tenantId=1146029695717560320, journalId=1225147924628267009, language=EN, title=Vehicle-assisted bridge damage assessment by combining attention mechanism and Bi-LSTM network, columnId=null, journalTitle=Journal of Vibration Engineering, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Vehicle-assisted bridge damage identification has great application potential,but it is still difficult to extract damage-sensitive features from multi-source monitoring data and accurately evaluate the bridge damage status. To solve this problem,an Attention-LSTM-based Feature Fusion Model (ALFF-Net) is proposed. The model improves the perception ability of Bi-LSTM cells for multi-scale feature information in time series data through a preset data reconstruction layer. Furthermore,by employing attention mechanism and feature fusion strategy,the model reduces the prediction difficulty of downstream branches of deep neural networks and further improves the modeling ability for the important dependency relationships in the sequence data. A monitoring dataset under different road roughness and vehicle speeds is generated through a vehicle-bridge interaction system simulation,and the bridge damage identification performance of the ALFF-Net model is comprehensively tested. The results show that the ALFF-Net model improves the damage identification accuracy by up to 19.30% compared to the classical LSTM network while significantly reducing computational costs,and the identification errors under different road roughness levels are less than 3%. Moreover,by comparing the identification accuracy of the ALFF-Net model under different data-driven schemes,the robustness of the bridge damage detection results with synergistic multi-source monitoring data is verified.

, 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=Yan ZENG, Dong-ming FENG, Jian-an LI), CN=ArticleExt(id=1228634288271323696, articleId=1228634263294243389, tenantId=1146029695717560320, journalId=1225147924628267009, language=CN, title=融合注意力机制和Bi-LSTM网络的车辆辅助桥梁损伤评估, columnId=0, journalTitle=振动工程学报, columnName=, runingTitle=null, highlight=null, articleAbstract=

基于车辆辅助的桥梁损伤识别具有巨大应用潜力,但仍难以从多源监测数据中提取损伤敏感特征,进而准确评估桥梁损伤状态。为此,提出了基于长短时记忆网络的注意力加权特征融合模型(ALFF-Net)。该模型通过预置数据重构层,提高了Bi-LSTM单元对时间序列多尺度特征信息的感知能力。同时结合注意力机制和特征融合策略,降低了深度神经网络下游分支的预测难度,进一步提升了模型对序列数据重要依赖关系的建模能力。通过车-桥耦合仿真生成了不同路面不平整度和车速下的监测数据集,对ALFF-Net模型的桥梁损伤识别性能进行综合测试。结果表明:ALFF-Net模型较经典LSTM网络在显著降低计算成本的同时,损伤识别准确率最高可提升19.30%,且各级路面不平整度下的识别误差均小于3%。进一步地,通过对比ALFF-Net模型在不同监测数据驱动方案下的识别精度,验证了协同多源监测数据的桥梁结构损伤检测结果更为鲁棒。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
冯东明(1985―),男,博士,教授。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=xgfqFTVqtmpFK48RquPCww==, magXml=WOcczmuZMofVJyNiTN6UIg==, pdfUrl=null, pdf=4rQPOQ4sBj70PpJ8/6RMjQ==, pdfFileSize=2789940, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Ue1A1X7XYuSpmqSe2FytAQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Y5pwT9gg3gQg5VPxWuL+uw==, mapNumber=null, authorCompany=null, fund=null, authors=

曾 琰(1998—),男,硕士研究生。E-mail:

, authorsList=曾琰, 冯东明, 黎剑安)}, authors=[Author(id=1228634288816583251, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zengyan@seu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228634288892080729, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, authorId=1228634288816583251, language=EN, stringName=Yan ZENG, firstName=Yan, middleName=null, lastName=ZENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2School of Civil Engineering,Southeast University,Nanjing 211189,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228634289047269982, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, authorId=1228634288816583251, language=CN, stringName=曾琰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2东南大学土木工程学院, 江苏 南京 211189, bio={"content":"

曾 琰(1998—),男,硕士研究生。E-mail:

"}, bioImg=null, bioContent=

曾 琰(1998—),男,硕士研究生。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228634288590090823, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, xref=2, ext=[AuthorCompanyExt(id=1228634288598479430, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288590090823, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Civil Engineering,Southeast University,Nanjing 211189,China), AuthorCompanyExt(id=1228634288606868039, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288590090823, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2东南大学土木工程学院, 江苏 南京 211189)])]), Author(id=1228634289139544679, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dfeng@seu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228634289244402284, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, authorId=1228634289139544679, language=EN, stringName=Dong-ming FENG, firstName=Dong-ming, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1Key Laboratory of Concrete and Prestressed Concrete Structures of Ministry of Education,Southeast University, Nanjing 210096,China
2School of Civil Engineering,Southeast University,Nanjing 211189,China
3National and Local Joint Engineering Research Center for Intelligent Construction and Maintenance, Southeast University,Nanjing 211189,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228634289349259890, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, authorId=1228634289139544679, language=CN, stringName=冯东明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1东南大学混凝土与预应力混凝土结构教育部重点实验室,江苏 南京 210096
2东南大学土木工程学院, 江苏 南京 211189
3东南大学智慧建造与运维国家地方联合工程研究中心,江苏 南京 211189, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228634288493621821, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, xref=1, ext=[AuthorCompanyExt(id=1228634288502010431, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288493621821, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Key Laboratory of Concrete and Prestressed Concrete Structures of Ministry of Education,Southeast University, Nanjing 210096,China), AuthorCompanyExt(id=1228634288506204736, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288493621821, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学混凝土与预应力混凝土结构教育部重点实验室,江苏 南京 210096)]), AuthorCompany(id=1228634288590090823, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, xref=2, ext=[AuthorCompanyExt(id=1228634288598479430, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288590090823, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Civil Engineering,Southeast University,Nanjing 211189,China), AuthorCompanyExt(id=1228634288606868039, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288590090823, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2东南大学土木工程学院, 江苏 南京 211189)]), AuthorCompany(id=1228634288682365516, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, xref=3, ext=[AuthorCompanyExt(id=1228634288690754124, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288682365516, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3National and Local Joint Engineering Research Center for Intelligent Construction and Maintenance, Southeast University,Nanjing 211189,China), AuthorCompanyExt(id=1228634288694948429, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288682365516, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3东南大学智慧建造与运维国家地方联合工程研究中心,江苏 南京 211189)])]), Author(id=1228634289475089016, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, 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=1228634289609306750, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, authorId=1228634289475089016, language=EN, stringName=Jian-an LI, firstName=Jian-an, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2School of Civil Engineering,Southeast University,Nanjing 211189,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228634289751913091, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, authorId=1228634289475089016, language=CN, stringName=黎剑安, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2东南大学土木工程学院, 江苏 南京 211189, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228634288590090823, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, xref=2, ext=[AuthorCompanyExt(id=1228634288598479430, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288590090823, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Civil Engineering,Southeast University,Nanjing 211189,China), AuthorCompanyExt(id=1228634288606868039, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288590090823, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2东南大学土木工程学院, 江苏 南京 211189)])])], keywords=[Keyword(id=1228634289949045384, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, orderNo=1, keyword=bridge damage assessment), Keyword(id=1228634290049708686, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, orderNo=2, keyword=vehicle-bridge coupling vibration), Keyword(id=1228634290129400466, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, orderNo=3, keyword=LSTM network), Keyword(id=1228634290213286551, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, orderNo=4, keyword=attention mechanism), Keyword(id=1228634290292978332, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, orderNo=5, keyword=feature fusion), Keyword(id=1228634290360087200, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, orderNo=1, keyword=桥梁损伤评估), Keyword(id=1228634290456556196, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, orderNo=2, keyword=车-桥耦合振动), Keyword(id=1228634290586579625, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, orderNo=3, keyword=长短时记忆网络), Keyword(id=1228634290683048620, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, orderNo=4, keyword=注意力机制), Keyword(id=1228634290787906226, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, orderNo=5, keyword=特征融合)], refs=[Reference(id=1228634295166759710, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2021, volume=147, issue=null, pageStart=107077, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Avci O, Abdeljaber O, Kiranyaz S, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=Avci OAbdeljaber OKiranyaz 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 Processing2021147: 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=1228634295233868575, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=1996, volume=null, issue=null, pageStart=20, pageEnd=29, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=刘西拉, 杨国兴, journalName=工程力学, refType=null, unstructuredReference=刘西拉, 杨国兴. 桥梁健康监测系统的发展与趋势[J]. 工程力学1996(): 20-29., articleTitle=桥梁健康监测系统的发展与趋势, refAbstract=增刊), Reference(id=1228634295309366048, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2019, volume=32, issue=11, pageStart=1, pageEnd=20, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=孙利民, 尚志强, 夏烨, journalName=中国公路学报, refType=null, unstructuredReference=孙利民, 尚志强, 夏烨. 大数据背景下的桥梁结构健康监测研究现状与展望[J]. 中国公路学报201932(11): 1-20., articleTitle=大数据背景下的桥梁结构健康监测研究现状与展望, refAbstract=null), Reference(id=1228634295393252130, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2019, volume=32, issue=11, pageStart=1, pageEnd=20, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=SUN Limin, SHANG Zhiqiang, XIA Ye, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=SUN LiminSHANG ZhiqiangXIA Ye. Development and prospect of bridge structural health monitoring in the context of big data[J]. China Journal of Highway and Transport201932(11): 1-20., articleTitle=Development and prospect of bridge structural health monitoring in the context of big data, refAbstract=null), Reference(id=1228634296756400931, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2008, volume=22, issue=5, pageStart=1194, pageEnd=1215, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Bayissa W L, Haritos N, Thelandersson S, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=Bayissa W LHaritos NThelandersson S. Vibration-based structural damage identification using wavelet transform[J]. Mechanical Systems and Signal Processing200822(5): 1194-1215., articleTitle=Vibration-based structural damage identification using wavelet transform, refAbstract=null), Reference(id=1228634296865452836, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2016, volume=79, issue=null, pageStart=86, pageEnd=98, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=Lucena R L, Dos Santos J M C, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=Lucena R LDos Santos J M C. Structural health monitoring using time reversal and cracked rod spectral element[J]. Mechanical Systems and Signal Processing201679: 86-98., articleTitle=Structural health monitoring using time reversal and cracked rod spectral element, refAbstract=null), Reference(id=1228634296978699045, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2018, volume=19, issue=2, pageStart=552, pageEnd=586, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Wu R-T, Jahanshahi M R, journalName=Structural Health Monitoring, refType=null, unstructuredReference=Wu R-TJahanshahi M R. Data fusion approaches for structural health monitoring and system identification: past, present, and future[J]. Structural Health Monitoring201819(2): 552-586., articleTitle=Data fusion approaches for structural health monitoring and system identification: past, present, and future, refAbstract=null), Reference(id=1228634297070973733, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2019, volume=26, issue=10, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=An Y H, Chatzi E, Sim S-H, journalName=Structural Control & Health Monitoring, refType=null, unstructuredReference=An Y HChatzi ESim S-H, et al. Recent progress and future trends on damage identification methods for bridge structures[J]. Structural Control & Health Monitoring201926(10): e2416., articleTitle=Recent progress and future trends on damage identification methods for bridge structures, refAbstract=null), Reference(id=1228634297205191463, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=12, pageStart=3460, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=Shokravi H, Shokravi H, Bakhary N, journalName=Sensors, refType=null, unstructuredReference=Shokravi HShokravi HBakhary N, et al. Vehicle-assisted techniques for health monitoring of bridges[J]. Sensors202020(12): 3460., articleTitle=Vehicle-assisted techniques for health monitoring of bridges, refAbstract=null), Reference(id=1228634297318437673, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2004, volume=272, issue=3-5, pageStart=471, pageEnd=493, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=Yang Y B, Lin C W, Yau J D, journalName=Journal of Sound and Vibration, refType=null, unstructuredReference=Yang Y BLin C WYau J D. Extracting bridge frequencies from the dynamic response of a passing vehicle[J]. Journal of Sound and Vibration2004272(3-5): 471-493., articleTitle=Extracting bridge frequencies from the dynamic response of a passing vehicle, refAbstract=null), Reference(id=1228634297393935147, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2016, volume=23, issue=8, pageStart=1088, pageEnd=1107, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=Feng D M, Feng M Q, journalName=Structural Control & Health Monitoring, refType=null, unstructuredReference=Feng D MFeng M Q. Output-only damage detection using vehicle‐induced displacement response and mode shape curvature index[J]. Structural Control & Health Monitoring201623(8): 1088-1107., articleTitle=Output-only damage detection using vehicle‐induced displacement response and mode shape curvature index, refAbstract=null), Reference(id=1228634297482015532, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2014, volume=13, issue=5, pageStart=731, pageEnd=753, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=Oshima Y, Yamamoto K, Sugiura K, journalName=Smart Structures and Systems, refType=null, unstructuredReference=Oshima YYamamoto KSugiura K. Damage assessment of a bridge based on mode shapes estimated by responses of passing vehicles[J]. Smart Structures and Systems201413(5): 731-753., articleTitle=Damage assessment of a bridge based on mode shapes estimated by responses of passing vehicles, refAbstract=null), Reference(id=1228634297565901614, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2009, volume=319, issue=1-2, pageStart=355, pageEnd=365, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=Sieniawska R, Śniady P, Żukowski S, journalName=Journal of Sound and Vibration, refType=null, unstructuredReference=Sieniawska RŚniady PŻukowski S. Identification of the structure parameters applying a moving load[J]. Journal of Sound and Vibration2009319(1-2): 355-365., articleTitle=Identification of the structure parameters applying a moving load, refAbstract=null), Reference(id=1228634297653982000, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2018, volume=29, issue=5, pageStart=1331, pageEnd=1341, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=Xiong C B, Lu H L, Zhu J S, journalName=Neural Computing & Applications, refType=null, unstructuredReference=Xiong C BLu H LZhu J S. Reality of virtual damage identification based on neural networks and vibration analysis of a damaged bridge under a moving vehicle[J]. Neural Computing & Applications201829(5): 1331-1341., articleTitle=Reality of virtual damage identification based on neural networks and vibration analysis of a damaged bridge under a moving vehicle, refAbstract=null), Reference(id=1228634297729479474, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=1, pageStart=20, pageEnd=23, url=null, language=null, rfNumber=[14], rfOrder=14, authorNames=何兴文, 王宝, 石磊, journalName=天津建设科技, refType=null, unstructuredReference=何兴文, 王宝, 石磊, 等. 基于车桥耦合分析与神经网络的桥梁损伤识别[J]. 天津建设科技202333(1): 20-23., articleTitle=基于车桥耦合分析与神经网络的桥梁损伤识别, refAbstract=null), Reference(id=1228634297809171251, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=1, pageStart=20, pageEnd=23, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=HE Xingwen, WANG Bao, SHI Lei, journalName=Tianjin Construction Science & Technology, refType=null, unstructuredReference=HE XingwenWANG BaoSHI Lei, et al. Bridge damage identification based on vehicle bridge coupling analysis and neural network[J]. Tianjin Construction Science & Technology202333(1): 20-23., articleTitle=Bridge damage identification based on vehicle bridge coupling analysis and neural network, refAbstract=null), Reference(id=1228634297880474421, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2020, volume=468, issue=null, pageStart=115088, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=Locke W, Sybrandt J, Redmond L, journalName=Journal of Sound and Vibration, refType=null, unstructuredReference=Locke WSybrandt JRedmond L, et al. Using drive-by health monitoring to detect bridge damage considering environmental and operational effects[J]. Journal of Sound and Vibration2020468: 115088., articleTitle=Using drive-by health monitoring to detect bridge damage considering environmental and operational effects, refAbstract=null), Reference(id=1228634297955971895, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2023, volume=22, issue=2, pageStart=897, pageEnd=912, url=null, language=null, rfNumber=[16], rfOrder=17, authorNames=Hajializadeh D, journalName=Structural Health Monitoring, refType=null, unstructuredReference=Hajializadeh D. Deep learning-based indirect bridge damage identification system[J]. Structural Health Monitoring202322(2): 897-912., articleTitle=Deep learning-based indirect bridge damage identification system, refAbstract=null), Reference(id=1228634298044052279, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2023, volume=206, issue=null, pageStart=112216, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=18, authorNames=Sarwar M Z, Cantero D, journalName=Measurement, refType=null, unstructuredReference=Sarwar M ZCantero D. Vehicle assisted bridge damage assessment using probabilistic deep learning[J]. Measurement2023206: 112216., articleTitle=Vehicle assisted bridge damage assessment using probabilistic deep learning, refAbstract=null), Reference(id=1228634298136326969, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2011, volume=44, issue=10, pageStart=81, pageEnd=90, url=null, language=null, rfNumber=[18], rfOrder=19, authorNames=韩万水, 马麟, 院素静, journalName=土木工程学报, refType=null, unstructuredReference=韩万水, 马麟, 院素静, 等. 路面粗糙度非一致激励对车桥耦合振动系统响应影响分析[J]. 土木工程学报201144(10): 81-90., articleTitle=路面粗糙度非一致激励对车桥耦合振动系统响应影响分析, refAbstract=null), Reference(id=1228634298199241531, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2011, volume=44, issue=10, pageStart=81, pageEnd=90, url=null, language=null, rfNumber=[18], rfOrder=20, authorNames=HAN Wanshui, MA Lin, YUAN Sujing, journalName=China Civil Engineering Journal, refType=null, unstructuredReference=HAN WanshuiMA LinYUAN Sujing, et al. Analysis of the effect of inconsistent stimulus of surface roughness on vehicle-bridge coupling vibrations[J].China Civil Engineering Journal201144(10): 81-90., articleTitle=Analysis of the effect of inconsistent stimulus of surface roughness on vehicle-bridge coupling vibrations, refAbstract=null), Reference(id=1228634298283127613, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=21, authorNames=BSI, journalName=null, refType=null, unstructuredReference=BSI. Mechanical vibration-road surface profiles-reporting of measured data: ISO 8608—2016[S]. London: BSI Standards Publication, 2016., articleTitle=null, refAbstract=null), Reference(id=1228634298346042175, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=1959, volume=85, issue=3, pageStart=67, pageEnd=94, url=null, language=null, rfNumber=[20], rfOrder=22, authorNames=Newmark N M, journalName=Journal of the Engineering Mechanics Divison, refType=null, unstructuredReference=Newmark N M. A method of computation for structural dynamics[J]. Journal of the Engineering Mechanics Divison195985(3): 67-94., articleTitle=A method of computation for structural dynamics, refAbstract=null), Reference(id=1228634298413151041, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=1310, pageEnd=1318, url=null, language=null, rfNumber=[21], rfOrder=23, authorNames=Pascanu R, Mikolov T, Bengio Y, journalName=null, refType=null, unstructuredReference=Pascanu RMikolov TBengio Y. On the difficulty of training recurrent neural networks[C]//Proceedings of the 30th International Conference on Machine Learning. Atlanta, 2013: 1310-1318., articleTitle=On the difficulty of training recurrent neural networks, refAbstract=null), Reference(id=1228634298476065603, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=1997, volume=9, issue=8, pageStart=1735, pageEnd=1780, url=null, language=null, rfNumber=[22], rfOrder=24, authorNames=Hochreiter S, Schmidhuber J, journalName=Neural Computation, refType=null, unstructuredReference=Hochreiter SSchmidhuber J. Long Short-Term Memory[J]. Neural Computation19979(8): 1735-1780., articleTitle=Long Short-Term Memory, refAbstract=null), Reference(id=1228634298555757380, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=25, authorNames=Bahdanau D, Cho K, Bengio Y, journalName=null, refType=null, unstructuredReference=Bahdanau DCho KBengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint, 2014:, articleTitle=Neural machine translation by jointly learning to align and translate, refAbstract=null), Reference(id=1228634298639643462, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=5998, pageEnd=6008, url=null, language=null, rfNumber=[24], rfOrder=26, authorNames=Vaswani A, Shazeer N, Parmar N, journalName=null, refType=null, unstructuredReference=Vaswani AShazeer NParmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York, 2017: 5998-6008., articleTitle=Attention is all you need, refAbstract=null)], funds=[Fund(id=1228634294915101464, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, awardId=2242024K40013, language=CN, fundingSource=中央高校基本科研业务费专项资金资助项目(2242024K40013), fundOrder=null, country=null), Fund(id=1228634295007376154, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, awardId=RF1028623149, language=CN, fundingSource=东南大学新进教师科研启动经费资助项目(RF1028623149), fundOrder=null, country=null), Fund(id=1228634295070290716, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, awardId=P2022G054, language=CN, fundingSource=中国国家铁路集团有限公司科技研究开发计划资助项目(P2022G054), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1228634288493621821, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, xref=1, ext=[AuthorCompanyExt(id=1228634288502010431, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288493621821, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Key Laboratory of Concrete and Prestressed Concrete Structures of Ministry of Education,Southeast University, Nanjing 210096,China), AuthorCompanyExt(id=1228634288506204736, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288493621821, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学混凝土与预应力混凝土结构教育部重点实验室,江苏 南京 210096)]), AuthorCompany(id=1228634288590090823, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, xref=2, ext=[AuthorCompanyExt(id=1228634288598479430, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288590090823, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Civil Engineering,Southeast University,Nanjing 211189,China), AuthorCompanyExt(id=1228634288606868039, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288590090823, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2东南大学土木工程学院, 江苏 南京 211189)]), AuthorCompany(id=1228634288682365516, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, xref=3, ext=[AuthorCompanyExt(id=1228634288690754124, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288682365516, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3National and Local Joint Engineering Research Center for Intelligent Construction and Maintenance, Southeast University,Nanjing 211189,China), AuthorCompanyExt(id=1228634288694948429, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, companyId=1228634288682365516, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3东南大学智慧建造与运维国家地方联合工程研究中心,江苏 南京 211189)])], figs=[ArticleFig(id=1228634290896958134, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.1, caption=Vehicle-bridge coupling vibration system, figureFileSmall=bt3tXhDI3R/GUddzc6Hkpw==, figureFileBig=Ue1A1X7XYuSpmqSe2FytAQ==, tableContent=null), ArticleFig(id=1228634291010204346, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图1, caption=车-桥耦合振动系统, figureFileSmall=bt3tXhDI3R/GUddzc6Hkpw==, figureFileBig=Ue1A1X7XYuSpmqSe2FytAQ==, tableContent=null), ArticleFig(id=1228634291312194243, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.2, caption=The basic structure of ALFF-Net model, figureFileSmall=qrLlw1YAjfoDEwc1lE2lqQ==, figureFileBig=1EUogScrRNt67bQVr0QM9w==, tableContent=null), ArticleFig(id=1228634291375108807, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图2, caption=ALFF-Net模型基本结构, figureFileSmall=qrLlw1YAjfoDEwc1lE2lqQ==, figureFileBig=1EUogScrRNt67bQVr0QM9w==, tableContent=null), ArticleFig(id=1228634291454800587, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.3, caption=The basic structure of LSTM cell, figureFileSmall=xfN2qVwGQPUGx3NCmvyKzQ==, figureFileBig=seR7s71V4DXW33dHt8ajYA==, tableContent=null), ArticleFig(id=1228634291547075277, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图3, caption=LSTM单元基本结构, figureFileSmall=xfN2qVwGQPUGx3NCmvyKzQ==, figureFileBig=seR7s71V4DXW33dHt8ajYA==, tableContent=null), ArticleFig(id=1228634291635155662, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.4, caption=The basic structure of Bi-LSTM network, figureFileSmall=f1Kzz9ci8nDjrr55zQ/WJQ==, figureFileBig=WuQtg+83JhO6gPeEBQalrQ==, tableContent=null), ArticleFig(id=1228634291723236048, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图4, caption=Bi-LSTM网络基本结构, figureFileSmall=f1Kzz9ci8nDjrr55zQ/WJQ==, figureFileBig=WuQtg+83JhO6gPeEBQalrQ==, tableContent=null), ArticleFig(id=1228634291811316433, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.5, caption=The structure of attention mechanism, figureFileSmall=NG7+UTWsFVzB6AChYywmzA==, figureFileBig=nSNyX6d/VUT5aRygysDk4g==, tableContent=null), ArticleFig(id=1228634291903591125, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图5, caption=注意力机制结构, figureFileSmall=NG7+UTWsFVzB6AChYywmzA==, figureFileBig=nSNyX6d/VUT5aRygysDk4g==, tableContent=null), ArticleFig(id=1228634291983282904, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.6, caption=The numerical verification process, figureFileSmall=armV/3v9Z2R1yaMppylr0w==, figureFileBig=ql3H/x1olP1LeASsA7Xipg==, tableContent=null), ArticleFig(id=1228634292104917721, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图6, caption=数值验证流程, figureFileSmall=armV/3v9Z2R1yaMppylr0w==, figureFileBig=ql3H/x1olP1LeASsA7Xipg==, tableContent=null), ArticleFig(id=1228634292251718362, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.7, caption=Sensor layout for vehicle and bridge, figureFileSmall=Teb28nJI8tl0epdfxV/B3A==, figureFileBig=JnHMA6Ajfe3ah1F2rmr7Rw==, tableContent=null), ArticleFig(id=1228634292331410143, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图7, caption=车辆和桥梁的传感器布置, figureFileSmall=Teb28nJI8tl0epdfxV/B3A==, figureFileBig=JnHMA6Ajfe3ah1F2rmr7Rw==, tableContent=null), ArticleFig(id=1228634292415296226, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.8, caption=The distribution of vehicle speed and bridge flexural stiffness in damage sample set, figureFileSmall=pEn6cxPjjYIsg22ZkWIjSw==, figureFileBig=/fyITFFLCwyhdL7gkL6jeA==, tableContent=null), ArticleFig(id=1228634292494988003, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图8, caption=损伤样本的车速和桥梁抗弯刚度分布, figureFileSmall=pEn6cxPjjYIsg22ZkWIjSw==, figureFileBig=/fyITFFLCwyhdL7gkL6jeA==, tableContent=null), ArticleFig(id=1228634292574679781, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.9, caption=The displacement response signal of the bridge, figureFileSmall=rf4MxEjKKrN8d9Ot6b+2oQ==, figureFileBig=IKOBvdasa5grKwe/BhakYA==, tableContent=null), ArticleFig(id=1228634292666954471, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图9, caption=桥梁位移响应信号, figureFileSmall=rf4MxEjKKrN8d9Ot6b+2oQ==, figureFileBig=IKOBvdasa5grKwe/BhakYA==, tableContent=null), ArticleFig(id=1228634292763423463, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.10, caption=The time-history of vehicle dynamic action, figureFileSmall=SmZsl7OyjTaip0qKDzeYzw==, figureFileBig=8QxBaev82OQLmTZgWttETQ==, tableContent=null), ArticleFig(id=1228634292847309545, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图10, caption=车辆动态作用时程, figureFileSmall=SmZsl7OyjTaip0qKDzeYzw==, figureFileBig=8QxBaev82OQLmTZgWttETQ==, tableContent=null), ArticleFig(id=1228634292943778539, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.11, caption=The curve of learning rate with a piecewise constant decay strategy, figureFileSmall=oPubZ92IHky843rmfIKVDA==, figureFileBig=uVNUpL2DKKOZxxnel2oIHA==, tableContent=null), ArticleFig(id=1228634293027664620, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图11, caption=学习率分段常数衰减曲线, figureFileSmall=oPubZ92IHky843rmfIKVDA==, figureFileBig=uVNUpL2DKKOZxxnel2oIHA==, tableContent=null), ArticleFig(id=1228634293119939311, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.12, caption=The descent curve of the loss function, figureFileSmall=bD/ISEQh3TQX6/pqoSVQgA==, figureFileBig=a+PpwhfWc+PDAsNE2x3K3A==, tableContent=null), ArticleFig(id=1228634293191242481, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图12, caption=损失函数下降曲线, figureFileSmall=bD/ISEQh3TQX6/pqoSVQgA==, figureFileBig=a+PpwhfWc+PDAsNE2x3K3A==, tableContent=null), ArticleFig(id=1228634293262545651, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.13, caption=The accuracy of the validation set of the models, figureFileSmall=TaIiI6LhnYUpHMWpqtn0HQ==, figureFileBig=lAJrRz2QVXDrcqefFz06qA==, tableContent=null), ArticleFig(id=1228634293342237428, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图13, caption=模型的验证集准确率, figureFileSmall=TaIiI6LhnYUpHMWpqtn0HQ==, figureFileBig=lAJrRz2QVXDrcqefFz06qA==, tableContent=null), ArticleFig(id=1228634293421929207, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.14, caption=The optimum number of parameters of the models, figureFileSmall=r2PrQS1gri5zdVVrsv9NYw==, figureFileBig=HdbRteaTqYQdIpfm9yuYUQ==, tableContent=null), ArticleFig(id=1228634293484843770, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图14, caption=模型最佳参数量, figureFileSmall=r2PrQS1gri5zdVVrsv9NYw==, figureFileBig=HdbRteaTqYQdIpfm9yuYUQ==, tableContent=null), ArticleFig(id=1228634293556146939, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.15, caption=Training time of the models, figureFileSmall=ll7Oxkp2L+W2ybRirqKpHQ==, figureFileBig=bqFZotDpLz/izEptS8UIaQ==, tableContent=null), ArticleFig(id=1228634293631644412, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图15, caption=模型训练时长, figureFileSmall=ll7Oxkp2L+W2ybRirqKpHQ==, figureFileBig=bqFZotDpLz/izEptS8UIaQ==, tableContent=null), ArticleFig(id=1228634293711336189, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.16, caption=Damage identification results of ALFF-Net model, figureFileSmall=5dw3beBPVy1Kb+VbTwnMgA==, figureFileBig=AeiIcAgqyXoT9vceScYLDg==, tableContent=null), ArticleFig(id=1228634293803610878, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图16, caption=ALFF-Net模型损伤识别结果, figureFileSmall=5dw3beBPVy1Kb+VbTwnMgA==, figureFileBig=AeiIcAgqyXoT9vceScYLDg==, tableContent=null), ArticleFig(id=1228634293908468480, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.17, caption=Damage identification results of LSTM network, figureFileSmall=XUNjq1O4ONjYG7WU4aOlLw==, figureFileBig=E7qgHozkjSSG2XsCH+gEPA==, tableContent=null), ArticleFig(id=1228634294025908994, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图17, caption=LSTM网络损伤识别结果, figureFileSmall=XUNjq1O4ONjYG7WU4aOlLw==, figureFileBig=E7qgHozkjSSG2XsCH+gEPA==, tableContent=null), ArticleFig(id=1228634294113989380, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Fig.18, caption=Comparison of damage identification accuracy of different monitoring data-driven schemes, figureFileSmall=1LFmd1leG8+JwLISXRaZ2g==, figureFileBig=9pGAlU0DvsH5QecN60f0KQ==, tableContent=null), ArticleFig(id=1228634294181098246, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=图18, caption=不同监测数据驱动方案下的损伤识别准确率对比, figureFileSmall=1LFmd1leG8+JwLISXRaZ2g==, figureFileBig=9pGAlU0DvsH5QecN60f0KQ==, tableContent=null), ArticleFig(id=1228634294244012808, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Tab.1, caption=

Different sensor combinations schemes

, figureFileSmall=null, figureFileBig=null, tableContent=
传感器组合方案信号数量传感器类型和位置
协同驱动方案3DS-1/DS-2/(AS-1, AS-2)*
非协同驱动方案3DS-1/DS-2/DS-3
), ArticleFig(id=1228634294336287498, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=表1, caption=

不同传感器组合方案

, figureFileSmall=null, figureFileBig=null, tableContent=
传感器组合方案信号数量传感器类型和位置
协同驱动方案3DS-1/DS-2/(AS-1, AS-2)*
非协同驱动方案3DS-1/DS-2/DS-3
), ArticleFig(id=1228634294399202060, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Tab. 2, caption=

Classification of bridge damage state

, figureFileSmall=null, figureFileBig=null, tableContent=
评估分类标签桥梁抗弯刚度
State Ⅰ整体刚度折减小于5%
State Ⅱ整体刚度折减5%~10%
State Ⅲ整体刚度折减10%~15%
State Ⅳ整体刚度折减大于15%
), ArticleFig(id=1228634294470505230, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=表2, caption=

桥梁损伤状态分类

, figureFileSmall=null, figureFileBig=null, tableContent=
评估分类标签桥梁抗弯刚度
State Ⅰ整体刚度折减小于5%
State Ⅱ整体刚度折减5%~10%
State Ⅲ整体刚度折减10%~15%
State Ⅳ整体刚度折减大于15%
), ArticleFig(id=1228634294546002704, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Tab.3, caption=

Relevant parameters of vehicle-bridge coupling vibration system

, figureFileSmall=null, figureFileBig=null, tableContent=
车辆参数取值桥梁参数取值
m1/kg1425L/m40
m2/kg32025EI/(N⋅m-2)1.275×1011
k1/(N⋅m-1)2.85×105ρ/(kg⋅m-1)1.2×104
k2/(N⋅m-1)6.5×105ξ0
c1/(N⋅s⋅m-1)0
c2/(N⋅s⋅m-1)2.1×104
), ArticleFig(id=1228634294621500178, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=表3, caption=

车-桥耦合振动系统相关参数

, figureFileSmall=null, figureFileBig=null, tableContent=
车辆参数取值桥梁参数取值
m1/kg1425L/m40
m2/kg32025EI/(N⋅m-2)1.275×1011
k1/(N⋅m-1)2.85×105ρ/(kg⋅m-1)1.2×104
k2/(N⋅m-1)6.5×105ξ0
c1/(N⋅s⋅m-1)0
c2/(N⋅s⋅m-1)2.1×104
), ArticleFig(id=1228634294717969172, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=EN, label=Tab.4, caption=

The calculation results of the classification index of the models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型路面不平整度等级Accuracy/%Pmacro/%Rmacro/%Fmacro/%
ALFF-NetClass A97.6097.5497.5697.55
Class B97.7097.7197.6497.67
Class C97.1097.1397.1497.14
Class D97.0097.0197.1097.05
LSTMClass A93.4093.4193.4293.42
Class B90.4090.5290.2290.37
Class C87.9087.9987.7787.88
Class D77.7078.1577.8878.01
), ArticleFig(id=1228634294806049558, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228634263294243389, language=CN, label=表4, caption=

模型分类指标计算结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型路面不平整度等级Accuracy/%Pmacro/%Rmacro/%Fmacro/%
ALFF-NetClass A97.6097.5497.5697.55
Class B97.7097.7197.6497.67
Class C97.1097.1397.1497.14
Class D97.0097.0197.1097.05
LSTMClass A93.4093.4193.4293.42
Class B90.4090.5290.2290.37
Class C87.9087.9987.7787.88
Class D77.7078.1577.8878.01
)], 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.1004-4523.2024.07.001, detailUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/10.16385/j.cnki.issn.1004-4523.2024.07.001, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/PDF/10.16385/j.cnki.issn.1004-4523.2024.07.001, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/PDF/10.16385/j.cnki.issn.1004-4523.2024.07.001, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
融合注意力机制和Bi-LSTM网络的车辆辅助桥梁损伤评估
收藏切换
PDF下载
曾琰 2 , 冯东明 1, 2, 3 , 黎剑安 2
振动工程学报 | 2024,37(7): 1089-1097
收起
收藏切换
振动工程学报 | 2024, 37(7): 1089-1097
融合注意力机制和Bi-LSTM网络的车辆辅助桥梁损伤评估
全屏
曾琰2 , 冯东明1, 2, 3 , 黎剑安2
作者信息
  • 1东南大学混凝土与预应力混凝土结构教育部重点实验室,江苏 南京 210096
  • 2东南大学土木工程学院, 江苏 南京 211189
  • 3东南大学智慧建造与运维国家地方联合工程研究中心,江苏 南京 211189
  • 曾 琰(1998—),男,硕士研究生。E-mail:

通讯作者:

冯东明(1985―),男,博士,教授。E-mail:
Vehicle-assisted bridge damage assessment by combining attention mechanism and Bi-LSTM network
Yan ZENG2 , Dong-ming FENG1, 2, 3 , Jian-an LI2
Affiliations
  • 1Key Laboratory of Concrete and Prestressed Concrete Structures of Ministry of Education,Southeast University, Nanjing 210096,China
  • 2School of Civil Engineering,Southeast University,Nanjing 211189,China
  • 3National and Local Joint Engineering Research Center for Intelligent Construction and Maintenance, Southeast University,Nanjing 211189,China
出版时间: 2024-07-28 doi: 10.16385/j.cnki.issn.1004-4523.2024.07.001
文章导航
收藏切换

基于车辆辅助的桥梁损伤识别具有巨大应用潜力,但仍难以从多源监测数据中提取损伤敏感特征,进而准确评估桥梁损伤状态。为此,提出了基于长短时记忆网络的注意力加权特征融合模型(ALFF-Net)。该模型通过预置数据重构层,提高了Bi-LSTM单元对时间序列多尺度特征信息的感知能力。同时结合注意力机制和特征融合策略,降低了深度神经网络下游分支的预测难度,进一步提升了模型对序列数据重要依赖关系的建模能力。通过车-桥耦合仿真生成了不同路面不平整度和车速下的监测数据集,对ALFF-Net模型的桥梁损伤识别性能进行综合测试。结果表明:ALFF-Net模型较经典LSTM网络在显著降低计算成本的同时,损伤识别准确率最高可提升19.30%,且各级路面不平整度下的识别误差均小于3%。进一步地,通过对比ALFF-Net模型在不同监测数据驱动方案下的识别精度,验证了协同多源监测数据的桥梁结构损伤检测结果更为鲁棒。

桥梁损伤评估  /  车-桥耦合振动  /  长短时记忆网络  /  注意力机制  /  特征融合

Vehicle-assisted bridge damage identification has great application potential,but it is still difficult to extract damage-sensitive features from multi-source monitoring data and accurately evaluate the bridge damage status. To solve this problem,an Attention-LSTM-based Feature Fusion Model (ALFF-Net) is proposed. The model improves the perception ability of Bi-LSTM cells for multi-scale feature information in time series data through a preset data reconstruction layer. Furthermore,by employing attention mechanism and feature fusion strategy,the model reduces the prediction difficulty of downstream branches of deep neural networks and further improves the modeling ability for the important dependency relationships in the sequence data. A monitoring dataset under different road roughness and vehicle speeds is generated through a vehicle-bridge interaction system simulation,and the bridge damage identification performance of the ALFF-Net model is comprehensively tested. The results show that the ALFF-Net model improves the damage identification accuracy by up to 19.30% compared to the classical LSTM network while significantly reducing computational costs,and the identification errors under different road roughness levels are less than 3%. Moreover,by comparing the identification accuracy of the ALFF-Net model under different data-driven schemes,the robustness of the bridge damage detection results with synergistic multi-source monitoring data is verified.

bridge damage assessment  /  vehicle-bridge coupling vibration  /  LSTM network  /  attention mechanism  /  feature fusion
曾琰, 冯东明, 黎剑安. 融合注意力机制和Bi-LSTM网络的车辆辅助桥梁损伤评估. 振动工程学报, 2024 , 37 (7) : 1089 -1097 . DOI: 10.16385/j.cnki.issn.1004-4523.2024.07.001
Yan ZENG, Dong-ming FENG, Jian-an LI. Vehicle-assisted bridge damage assessment by combining attention mechanism and Bi-LSTM network[J]. Journal of Vibration Engineering, 2024 , 37 (7) : 1089 -1097 . DOI: 10.16385/j.cnki.issn.1004-4523.2024.07.001
由于过载、疲劳和环境腐蚀等1多种因素作用,桥梁的老化问题对其安全服役产生重大威胁。自20世纪末开始,为保障桥梁结构的安全可靠运营,旨在为桥梁检测和养护提供科学决策依据的结构健康监测系统逐渐发展起来2。近三十年来,中国在多座桥梁特别是大跨度桥梁上广泛应用具备大规模传感器的结构健康监测系统,如何快速和准确地通过监测到的大量传感器数据进行结构状态评估成为结构健康监测的核心内容3
结构损伤检测最初依靠人工目视检测方法,随着结构健康监测领域的不断突破,涌现了大量用于检测、定位和量化结构损伤的识别技术4-6。与此同时,现阶段传感技术和数据采集系统的不断进步,使得基于振动的结构健康监测方案有望成为有效和准确识别结构整体损伤的“银弹方案”7。其中,基于车-桥耦合振动理论的车辆辅助桥梁损伤检测方法通过分析移动车辆对桥梁的激励作用,从桥梁的动力特征中提取和量化桥梁损伤敏感特征,被广泛认为是一种贴近实际的桥梁损伤识别方法8-9。Feng等10提出了一种无需输入交通激励和路面不平整度的桥梁损伤检测方法,通过测量车致桥梁位移响应提取一阶模态振型曲率指数,进而完成对桥梁损伤的定位和量化;Oshima等11采用重载卡车放大桥梁振动响应,基于估算的桥梁模态振型对桥梁损伤状态进行评估,并探讨了路面不平整度和环境噪声等因素对评估结果的影响;Sieniawska等12通过集成移动短期荷载作用和桥梁结构位移响应,将动态问题转换为静态问题,建立起允许考虑路面不平整度的桥梁结构抗弯刚度识别方法。
深度学习算法作为机器学习领域的重要突破,近年来凭借其强大的非线性映射能力和无需手动特征工程的特性,已在众多工程实践中取得了瞩目成就。与此同时,随着数据计算平台和传感技术的不断发展,长期监测累积的大规模传感数据对结构健康监测系统的数字解析能力提出了更高的要求。因此,基于深度学习算法开发新型且高效的桥梁损伤检测技术势在必行。Xiong等13利用四自由度平面双轴车辆的耦合系统生成考虑路面不平整度下的桥梁损伤样本,将桥梁受损后的频率变化信息输入至BP神经网络,模拟了桥梁损伤的定位、定量识别;何兴文等14通过对二自由度车辆-桥梁相互作用模型的桥梁抗弯刚度进行折减来模拟结构损伤,利用BP神经网络建立桥梁加速度响应和损伤状态之间的映射关系;Locke等15采用基于1/4车辆模型的车-桥耦合振动数值算例,在时域内通过一维卷积神经网络对桥梁不同损伤程度下捕获的车辆加速度信号进行处理,测试了神经网络模型在包含多种真实环境噪声干扰下桥梁损伤识别的预测精度和抗噪能力;Hajializadeh16结合缩尺试验采集的测试列车加速度信号及相应信号处理技术,采用配置迁移学习等训练策略的二维卷积神经网络进行桥梁损伤识别,从概念上验证了仅输入测试车辆传感器数据进行桥梁损伤识别的可行性。Sarwar等17基于铰接式五轴卡车激励桥梁的仿真案例,提出了一种利用车辆与桥梁传感器信息融合的概率神经网络方法,该方法能够实现桥梁损伤状态的鲁棒评估。目前,结合深度神经网络与车-桥耦合振动理论的结构损伤识别方法建模仍然比较少见,且相关研究在复杂环境工况和多传感器协同下仍然存在模型识别效率不足等问题。
本研究结合注意力机制和Bi-LSTM模型的优势,提出一种数据驱动的基于长短时记忆神经网络的注意力加权特征融合模型(Attention- LSTM-based Feature Fusion Model,ALFF-Net),显著优化了经典LSTM网络的计算成本和预测精度,并首次应用在基于车-桥耦合振动理论的桥梁损伤识别研究上。具体而言,通过建立路面不平整度未知的简支梁桥和激励车辆在随机车速下的车-桥耦合振动系统,基于深度神经网络进行不同桥面路况等级和不同监测数据驱动下的桥梁损伤识别研究。
路面在空间上介于桥梁和车辆之间,路面不平整度通常作为主要激励直接影响到车-桥耦合振动的动力响应18。本文采用文献[19]定义的功率谱密度函数生成路面不平整度数据,假定粗糙程度在整个路面属于相同的统计分类,且被划分为A级(最好)~H级(最差)共8个等级。鉴于桥梁表面的路面不平整度一般相对较好,本文仅采用文献[19]中的前4个路况等级。路面不平整度的计算公式为:
式中  为路面不平整度信号;为用以生成路面不平整度的谐波数量;为空间频率的间距,,一般取x为桥梁的位置坐标;为均匀分布于[0,2π]的随机相位角;为位移功率谱密度函数;为第k个谐波的空间频率;为参考空间频率,一般取为0.1 m-1为参考空间频率对应的位移功率谱密度值,按路面不平整度的等级取值。
本文采用基于1/4车辆模型的车-桥耦合振动系统,模型计算简图如图1所示。其中,桥梁模型为线弹性欧拉-伯努利简支梁桥,车辆选用以恒定速度v通过桥面的单轴双自由度车辆简化模型。如图1所示,车体质量为,悬架与轮胎质量之和为,悬架的弹簧刚度和阻尼系数分别为,轮胎的弹簧刚度和阻尼系数分别为
忽略桥梁由于结构自重引起的静挠度,基于达朗贝尔原理可以得到欧拉-伯努利弯曲振动梁在上述车辆模型激励下的动力平衡方程:
式中  为桥梁结构的竖向位移;EI为桥梁的抗弯刚度;为桥梁每延米的质量;c为桥梁的阻尼系数;为狄克拉函数;为车辆对桥梁产生的动态激励作用,其大小为:
基于车辆的动态平衡条件可以建立两个附加动力平衡方程:
式中  分别表示悬架与轮胎质量的竖向位移和车体质量的竖向位移,且均以车辆模型在自重作用下的静力平衡位置为原点。
采用振型叠加法近似表示梁体竖向位移响应,可得:
式中 对于简支梁模型,第i阶振型函数,第i阶模态频率为对应的模态位移响应;m为模态截断阶数。
将式(6)代入式(3),两侧同乘并沿梁长L积分可得:
式中 振型函数为第i阶的模态阻尼比。
联立式(5)和(7),可得上述车-桥耦合振动模型的动力学方程:
式中 质量矩阵、阻尼矩阵和刚度矩阵均为时变矩阵,分别表示为:
利用Newmark-β方法20对式(8)进行迭代求解,可得车-桥耦合振动系统的动态响应。本文通过上述模型仿真生成桥梁损伤样本,进而基于深度神经网络完成对桥梁损伤评估方法的建模。
本文提出的ALFF-Net模型由数据重构层、特征融合模块和输出层构成,基本结构如图2所示。其中,特征融合模块设置了注意力机制对LSTM层提取的隐藏特征进行自适应加权,通过突出关键因素的影响提高预测精度。该模型可以利用车-桥相互作用产生的监测信号作为输入序列,输出对桥梁损伤状态的评估分类。
循环神经网络是一种串行计算序列化数据时域特征的方法,通过基本单元的循环迭代挖掘数据中的上下文信息,实现对序列关键依赖关系的建模。然而,循环神经网络存在长期依赖问题,在分析和处理过长的序列数据时可能会产生梯度消失和梯度爆炸的现象21。Hochreiter等22提出的长短时记忆(Long Short Term Memory,LSTM)神经网络是一种改进的循环神经网络,一定程度上改善了循环神经网络的长期依赖问题。
LSTM网络一般包含多个相互连接的LSTM单元,用以模拟信息流在网络中的动态传播,其基本结构如图3所示。
每个LSTM单元均包含输入门、遗忘门和输出门三个门控单元,通过门机制可以控制特征的流通和损失,相关的计算流程如下式所示:
式中  表示Sigmoid激活函数;表示双曲正切函数;分别表示遗忘门、输入门、内部状态和输出门的权重矩阵;分别表示遗忘门、输入门、内部状态和输出门的偏置向量;分别表示LSTM单元在时刻t对应的隐藏、输入和记忆状态;表示矩阵逐元素相乘。
时间序列在单个时间尺度上仅保留了标量信息,其关键特征通常隐藏在序列数据的变化中。为此,ALFF-Net模型将Bi-LSTM单元和预置输入重构层相结合,以提升LSTM单元对输入信号的时域特征感知能力,确保模型在隐层输出中能够充分表征输入序列数据的重要隐藏特征。
图4所示的Bi-LSTM网络由两个方向相反的LSTM单元组成,分别沿正向和反向的时间步处理时序数据,充分利用了序列数据的未来语境信息,对不同方向上生成的隐层进行综合输出,进而实现对整体序列信息的特征抽取。
模型中的数据重构方法如下式所示:
式中  n为原始序列向量的长度;h为输入神经网络的序列变量数;为第i个原始序列重构后的升维形式;为多个重构序列数据的拼接格式。
假定输入神经网络的多变量时间序列数目为h,则第i个原始时间序列在完成重构后的维度会发生改变,重构后的输入数据在时刻t将包含其临近时间步的信息组成观测结果。通过输入序列样本的重构数据,LSTM单元能够在每个时间步的迭代计算中感知到邻近时间步的时序信息,从而扩大特征提取的感受野。
在每一次迭代计算中配置输入重构层的Bi-LSTM单元,不仅能够感知原始时间序列在当前时刻的标量信息,同时也能够结合局部观测向量和整体序列特征,输出时序依赖关系在多尺度综合下的特征提取结果。
LSTM网络仍然缺乏对长期依赖关系的有效建模能力,而注意力机制对长期依赖关系的建模具有天然优势23。ALFF-Net模型结合Bi-LSTM单元与注意力机制进行特征提取,引入注意力可以赋予重要信息向量更高的权重值,同时增加模型非线性映射的表现能力,进一步提升对多变量时间序列关键特征的学习效率。模型中的注意力机制结构如图5所示。
本文采用缩放点积注意力机制24,通过对输入向量的匹配打分进行特征选择,其计算公式如下式所示:
式中  分别为查询和键对应的权重矩阵;d为LSTM单元输出的隐层数目;s为隐藏状态的数目;为时刻i的隐藏状态向量;为时刻i的加权隐藏状态向量。
ALFF-Net模型采用浅层特征和深层特征进行拼接的特征融合策略,一方面通过充分利用隐藏特征减少模型的待训练参数以提升参数优化效率;另一方面加强特征传播使得下游的预测分支更容易完成任务。同时,为保证注意力层的所有隐藏特征均能被后续预测分支充分利用,本文还通过特征加和的方式对注意力机制层提取的加权特征进行融合。其中,特征加和策略无需增加模型的参数量,通过整合规格相同的隐藏状态向量信息保证注意力机制用于特征提取的泛化性能。
基于上述车-桥耦合模型和神经网络模型,建立如图6所示的数值验证流程,对ALFF-Net模型在桥梁损伤评估任务上的识别性能进行综合测试。
通过求解上述车-桥耦合振动模型获得的车-桥振动响应,可以近似模拟实际运营环境中的桥梁和车辆通过传感器获得的车-桥耦合振动信号,本文模拟的传感器布置方案如图7所示。其中,待检测桥梁分别在处安装3个位移计,以记录测试车辆通过桥面时的桥梁位移响应时程。测试车辆分别在车体质量和悬架质量上布置相应的加速度计,按式(4)对车辆加速度响应进行换算,可得车辆对桥梁的动态荷载效应。对上述监测信号进行组合,以设置不同的数据驱动方案,对神经网络模型进行训练和测试。传感器具体组合方案如表1所示。
对桥梁的抗弯刚度进行折减以模拟结构整体损伤,其损伤程度的评估分类标签如表2所示。
为建立用于深度神经网络训练的损失样本集,基于车-桥耦合数值模型分别在各个路面不平整度等级下生成500个桥梁损伤数据样本,按4∶1划分训练集和验证集。实验时设置采样频率为50 Hz,测试车辆和待检测桥梁的相关参数如表3所示。
为模拟桥梁在相对复杂环境下的实际运营工况,在不同桥面路况等级下均采用随机路面不平整度数据来建立桥梁损伤样本,且车辆行驶速度和桥梁刚度折减比例分别服从[10,15] m/s和[0.75,1.0]上的均匀分布。以D级路面不平整度下的损伤样本集为例,生成样本数据的车速和桥梁抗弯刚度分布如图8所示,用以集成损伤样本的桥梁和车辆传感信号分别如图910所示。需要指出,当路面不平整度等级升高时,不同损伤样本的振动信号差异也会加大,对神经网络模型的特征提取能力提出更高要求。
上述两类用于输入神经网络的车-桥耦合振动信号在桥梁抗弯刚度、测试车速和路面不平整度数据均随机取值的情况下生成。其中,桥梁的抗弯刚度不仅是耦合系统的基础参数,也是神经网络输出的分类标签。由图8可知,聚集于类别边缘处的样本点的抗弯刚度取值较为接近,会造成该桥梁损伤评估任务具有一定的复杂性,也更接近实际运营下的结构损伤检测场景。
通过基于Python环境的Pytorch框架对深度神经网络进行搭建,计算机配置为12核20线程i7-12700 CPU和NIVIDIA RTX-3060Ti GPU。利用优化框架Optuna实现随机搜索方法并对学习率(0.0001~0.005)、批尺度大小(16~128)和LSTM隐层节点数(50~750)进行自动最优化调试。在模型训练之前,对输入数据采取标准差归一化方法,以消除量纲差异并加快参数优化的收敛速度。在训练过程中,模型接近收敛时其梯度变化通常较小,本文采用多步长分段常数衰减的学习率动态调整策略,以保证神经网络能够稳定地收敛到最优点。学习率逐步衰减的过程如图11所示。
上述桥梁损伤评估任务属于多分类问题,采用准确率、宏查准率、宏查全率和宏F1分数作为分类评价指标对神经网络模型的识别结果进行性能测试。其中,准确率定义为正确预测的样本占总损伤样本集的百分比,其他指标的计算方式分别如下式所示:
式中  TP为正样本正确预测的数量;FP为负样本错误预测的数量;FN为正样本错误预测的数量;n为分类任务的类别数目。
上述指标用于全面衡量该多分类问题中各类别识别结果的准确率和覆盖能力。
本文首先对ALFF-Net模型和经典LSTM网络在多源监测数据协同驱动方案下的综合性能进行测试。将不同路面不平整度等级下建立的桥梁损伤样本数据集分别用于模型训练,两类模型训练过程的损失函数下降曲线和验证集准确率分别如图1213所示。由图可知,两类模型的权重误差随着迭代最后趋于平稳,ALFF-Net模型较经典LSTM网络在训练过程中表现出更好的拟合能力和验证精度,其优势随着路面不平整度等级的提高更加明显。
图1415分别对应两类模型在不同路面不平整度等级的损伤样本集上的最佳参数量和训练时长。综合训练过程的表现可以发现,ALFF-Net模型在预测能力和计算成本上较经典LSTM网络具有明显改进。
为进一步测试两类模型对桥梁损伤的分类评估性能,本文通过在各级路面不平整度下分别设置具有1000个损伤样本的独立测试集,以统计ALFF-Net模型和经典LSTM网络对桥梁损伤状态的识别表现。图1617分别为两类模型在四个路面不平整度等级下桥梁损伤识别结果的混淆矩阵,其元素表示含有不同损伤状态的测试集样本被识别预测为各损伤状态类别的样本总数。由此可知,两类模型在低等级路面不平整度下的损伤评估分类的准确率普遍较高,经典LSTM网络在路况较差时的评估分类误差主要来自对临近损伤状态的误判。
基于混淆矩阵分别计算ALFF-Net模型和经典LSTM网络的分类性能评价指标,计算结果如表4所示。结果表明,在四个不同路面不平整度等级的独立测试集中,ALFF-Net模型的准确率、宏查准率、宏查全率和宏F1分数均高于经典LSTM网络,且ALFF-Net模型在各级桥面路况下的识别误差均小于3%。
在协同输入桥梁和车辆传感数据下的桥梁损伤评估任务中,ALFF-Net模型表现出优越的识别性能。进一步地,本文进行消融实验验证了融合注意力机制的有效性,同时通过屏蔽车辆监测信号设置了仅有桥梁响应输入下的非协同驱动方案作为对照。不同监测数据驱动方案下ALFF-Net模型的损伤识别准确率如图18所示。
消融实验结果表明,融合注意力机制可有效提高模型识别结果的准确性和鲁棒性。另外,不同监测数据驱动方案会对深度神经网络的识别准确率产生影响,随着路面等级的提高,协同输入车-桥监测数据较仅输入桥梁传感器数据的预测结果更加可靠。其原因在于,较差路况下的车辆响应主要来源于路面不平整度激励,补充输入车辆振动信号能为神经网络对桥梁损伤状态的准确评估提供更多关键辅助信息。
本研究结合了注意力机制对关键隐藏特征的高效建模优势,提出了一种基于长短时记忆网络的注意力加权特征融合模型(ALFF-Net)。通过设置相对复杂运营工况下的车-桥耦合振动数值案例,对比了ALFF-Net模型和经典LSTM网络在协同输入车辆和桥梁的传感器信息下的桥梁损伤评估性能,研究了ALFF-Net模型在不同传感器数据驱动方案下的桥梁损伤评估精度。主要结论如下:
(1) ALFF-Net模型对桥梁损伤状态的评估具有高度准确性,其识别性能在所有实验指标上优于经典LSTM网络,表现出低计算成本和高预测精度的优越性能。
(2) 通过多源监测数据协同驱动的ALFF-Net模型能够准确提取振动信号的关键损伤敏感特征,在路况较差时的识别表现仍保持相对稳定,且各级路面不平整度下的识别误差均低于3%。
(3) ALFF-Net模型在协同车-桥振动信号进行数据驱动下的损伤识别的准确率较仅输入桥梁响应时更高。由此表明,在桥面路况较差的情况下,结合车辆监测数据进行桥梁损伤识别具有重要辅助意义。
  • 中央高校基本科研业务费专项资金资助项目(2242024K40013)
  • 东南大学新进教师科研启动经费资助项目(RF1028623149)
  • 中国国家铁路集团有限公司科技研究开发计划资助项目(P2022G054)
参考文献 引证文献
排序方式:
[1]
Avci OAbdeljaber OKiranyaz 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 Processing2021147: 107077.
[2]
刘西拉, 杨国兴. 桥梁健康监测系统的发展与趋势[J]. 工程力学1996(): 20-29.
[3]
孙利民, 尚志强, 夏烨. 大数据背景下的桥梁结构健康监测研究现状与展望[J]. 中国公路学报201932(11): 1-20.
SUN LiminSHANG ZhiqiangXIA Ye. Development and prospect of bridge structural health monitoring in the context of big data[J]. China Journal of Highway and Transport201932(11): 1-20.
[4]
Bayissa W LHaritos NThelandersson S. Vibration-based structural damage identification using wavelet transform[J]. Mechanical Systems and Signal Processing200822(5): 1194-1215.
[5]
Lucena R LDos Santos J M C. Structural health monitoring using time reversal and cracked rod spectral element[J]. Mechanical Systems and Signal Processing201679: 86-98.
[6]
Wu R-TJahanshahi M R. Data fusion approaches for structural health monitoring and system identification: past, present, and future[J]. Structural Health Monitoring201819(2): 552-586.
[7]
An Y HChatzi ESim S-H, et al. Recent progress and future trends on damage identification methods for bridge structures[J]. Structural Control & Health Monitoring201926(10): e2416.
[8]
Shokravi HShokravi HBakhary N, et al. Vehicle-assisted techniques for health monitoring of bridges[J]. Sensors202020(12): 3460.
[9]
Yang Y BLin C WYau J D. Extracting bridge frequencies from the dynamic response of a passing vehicle[J]. Journal of Sound and Vibration2004272(3-5): 471-493.
[10]
Feng D MFeng M Q. Output-only damage detection using vehicle‐induced displacement response and mode shape curvature index[J]. Structural Control & Health Monitoring201623(8): 1088-1107.
[11]
Oshima YYamamoto KSugiura K. Damage assessment of a bridge based on mode shapes estimated by responses of passing vehicles[J]. Smart Structures and Systems201413(5): 731-753.
[12]
Sieniawska RŚniady PŻukowski S. Identification of the structure parameters applying a moving load[J]. Journal of Sound and Vibration2009319(1-2): 355-365.
[13]
Xiong C BLu H LZhu J S. Reality of virtual damage identification based on neural networks and vibration analysis of a damaged bridge under a moving vehicle[J]. Neural Computing & Applications201829(5): 1331-1341.
[14]
何兴文, 王宝, 石磊, 等. 基于车桥耦合分析与神经网络的桥梁损伤识别[J]. 天津建设科技202333(1): 20-23.
HE XingwenWANG BaoSHI Lei, et al. Bridge damage identification based on vehicle bridge coupling analysis and neural network[J]. Tianjin Construction Science & Technology202333(1): 20-23.
[15]
Locke WSybrandt JRedmond L, et al. Using drive-by health monitoring to detect bridge damage considering environmental and operational effects[J]. Journal of Sound and Vibration2020468: 115088.
[16]
Hajializadeh D. Deep learning-based indirect bridge damage identification system[J]. Structural Health Monitoring202322(2): 897-912.
[17]
Sarwar M ZCantero D. Vehicle assisted bridge damage assessment using probabilistic deep learning[J]. Measurement2023206: 112216.
[18]
韩万水, 马麟, 院素静, 等. 路面粗糙度非一致激励对车桥耦合振动系统响应影响分析[J]. 土木工程学报201144(10): 81-90.
HAN WanshuiMA LinYUAN Sujing, et al. Analysis of the effect of inconsistent stimulus of surface roughness on vehicle-bridge coupling vibrations[J].China Civil Engineering Journal201144(10): 81-90.
[19]
BSI. Mechanical vibration-road surface profiles-reporting of measured data: ISO 8608—2016[S]. London: BSI Standards Publication, 2016.
[20]
Newmark N M. A method of computation for structural dynamics[J]. Journal of the Engineering Mechanics Divison195985(3): 67-94.
[21]
Pascanu RMikolov TBengio Y. On the difficulty of training recurrent neural networks[C]//Proceedings of the 30th International Conference on Machine Learning. Atlanta, 2013: 1310-1318.
[22]
Hochreiter SSchmidhuber J. Long Short-Term Memory[J]. Neural Computation19979(8): 1735-1780.
[23]
Bahdanau DCho KBengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint, 2014
[24]
Vaswani AShazeer NParmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York, 2017: 5998-6008.
2024年第37卷第7期
PDF下载
50
24
引用本文
BibTeX
文章信息
doi: 10.16385/j.cnki.issn.1004-4523.2024.07.001
  • 接收时间:2023-04-10
  • 首发时间:2026-02-12
  • 出版时间:2024-07-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-04-10
  • 修回日期:2023-08-28
基金
中央高校基本科研业务费专项资金资助项目(2242024K40013)
东南大学新进教师科研启动经费资助项目(RF1028623149)
中国国家铁路集团有限公司科技研究开发计划资助项目(P2022G054)
作者信息
    1东南大学混凝土与预应力混凝土结构教育部重点实验室,江苏 南京 210096
    2东南大学土木工程学院, 江苏 南京 211189
    3东南大学智慧建造与运维国家地方联合工程研究中心,江苏 南京 211189

通讯作者:

冯东明(1985―),男,博士,教授。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2024.07.001
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