Article(id=1227591810156003816, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1227591806980915649, articleNumber=null, orderNo=null, doi=10.16385/j.cnki.issn.1004-4523.202309064, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1695312000000, receivedDateStr=2023-09-22, revisedDate=1699459200000, revisedDateStr=2023-11-09, acceptedDate=null, acceptedDateStr=null, onlineDate=1770610295094, onlineDateStr=2026-02-09, pubDate=1757433600000, pubDateStr=2025-09-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770610295094, onlineIssueDateStr=2026-02-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770610295094, creator=13701087609, updateTime=1770610295094, updator=13701087609, issue=Issue{id=1227591806980915649, tenantId=1146029695717560320, journalId=1225147924628267009, year='2025', volume='38', issue='9', pageStart='1935', pageEnd='2204', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1770610294337, creator=13701087609, updateTime=1770610356968, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1227592069754057532, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1227591806980915649, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1227592069754057533, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1227591806980915649, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=2182, endPage=2191, ext={EN=ArticleExt(id=1227591811552707062, articleId=1227591810156003816, tenantId=1146029695717560320, journalId=1225147924628267009, language=EN, title=Time-dependent reliability prediction of bridge components with the fusion of BO-LSTM and Copula theory, columnId=null, journalTitle=Journal of Vibration Engineering, columnName=null, runingTitle=null, highlight=null, articleAbstract=

There exists the nonlinear failure correlation among the multiple monitoring points of bridge components. Considering the influence of this factor on the reliability indices of the bridge, this paper adopts the Bayesian optimized long short-term memory (BO-LSTM) network model in machine learning to dynamically predict the monitoring data of the bridge, and establishes a three-dimensional Gaussian Copula model based on Copula theory to calculate the time-varying reliability indices and failure probability of the bridge construction. The rationality of the model and method is verified by applying the monitoring data of Fumin Bridge in Tianjin.

, 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=Qifan ZHAO, Yuefei LIU, Xueping FAN), CN=ArticleExt(id=1227591817139520211, articleId=1227591810156003816, tenantId=1146029695717560320, journalId=1225147924628267009, language=CN, title=BO-LSTM和Copula理论相融合的桥梁构件时变可靠性预测, columnId=0, journalTitle=振动工程学报, columnName=, runingTitle=null, highlight=null, articleAbstract=

桥梁构件的各个监测点之间存在着非线性失效动态相关性,为研究该因素对桥梁时变可靠指标的影响,建立了贝叶斯优化的长短期记忆(BO-LSTM)网络模型,对桥梁监测应力极值进行动态预测;建立考虑三个监测点失效非线性相关性的三元Gaussian Copula模型,对桥梁构件的时变可靠指标和时变失效概率进行预测,利用天津市富民桥的监测数据对模型与方法的合理性进行了验证分析。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
刘月飞(1982—),女,博士,副教授。 E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=M6hIv/AihXOtySRtKNaq6A==, magXml=KHhBKv/prTZNlAmUd5+xdw==, pdfUrl=null, pdf=Tc/YTGhmgGEHpA74frl32g==, pdfFileSize=1420287, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=neT5BcoLAYw5YnUFHj/qxw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=JyroluLBlRJcEi6vcprNIA==, mapNumber=null, authorCompany=null, fund=null, authors=

赵启凡(2000—),男,硕士研究生。E-mail:

, authorsList=赵启凡, 刘月飞, 樊学平)}, authors=[Author(id=1227653068506989012, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhaoqifan4396@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1227653068628623842, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, authorId=1227653068506989012, language=EN, stringName=Qifan ZHAO, firstName=Qifan, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Civil Engineering and Mechanics, Lanzhou University, Lanzhou 730000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1227653068750258665, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, authorId=1227653068506989012, language=CN, stringName=赵启凡, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.兰州大学土木工程与力学学院,甘肃 兰州 730000, bio={"content":"

赵启凡(2000—),男,硕士研究生。E-mail:

"}, bioImg=null, bioContent=

赵启凡(2000—),男,硕士研究生。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1227653068276302267, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, xref=1., ext=[AuthorCompanyExt(id=1227653068293079484, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068276302267, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil Engineering and Mechanics, Lanzhou University, Lanzhou 730000, China), AuthorCompanyExt(id=1227653068305662399, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068276302267, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.兰州大学土木工程与力学学院,甘肃 兰州 730000)])]), Author(id=1227653068850921967, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yfliu@lzu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1227653068947390969, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, authorId=1227653068850921967, language=EN, stringName=Yuefei LIU, firstName=Yuefei, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.School of Civil Engineering and Mechanics, Lanzhou University, Lanzhou 730000, China
2.Key Laboratory of Mechanics on Disaster and Environment in Western China of the Ministry of Education, Lanzhou University, Lanzhou 730000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1227653069098385919, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, authorId=1227653068850921967, language=CN, stringName=刘月飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.兰州大学土木工程与力学学院,甘肃 兰州 730000
2.兰州大学西部灾害与环境力学教育部重点实验室,甘肃 兰州 730000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1227653068276302267, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, xref=1., ext=[AuthorCompanyExt(id=1227653068293079484, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068276302267, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil Engineering and Mechanics, Lanzhou University, Lanzhou 730000, China), AuthorCompanyExt(id=1227653068305662399, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068276302267, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.兰州大学土木工程与力学学院,甘肃 兰州 730000)]), AuthorCompany(id=1227653068402131399, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, xref=2., ext=[AuthorCompanyExt(id=1227653068410520009, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068402131399, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory of Mechanics on Disaster and Environment in Western China of the Ministry of Education, Lanzhou University, Lanzhou 730000, China), AuthorCompanyExt(id=1227653068414714314, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068402131399, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.兰州大学西部灾害与环境力学教育部重点实验室,甘肃 兰州 730000)])]), Author(id=1227653069207437832, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, 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=1227653069333266960, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, authorId=1227653069207437832, language=EN, stringName=Xueping FAN, firstName=Xueping, middleName=null, lastName=FAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.School of Civil Engineering and Mechanics, Lanzhou University, Lanzhou 730000, China
2.Key Laboratory of Mechanics on Disaster and Environment in Western China of the Ministry of Education, Lanzhou University, Lanzhou 730000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1227653069459096092, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, authorId=1227653069207437832, language=CN, stringName=樊学平, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.兰州大学土木工程与力学学院,甘肃 兰州 730000
2.兰州大学西部灾害与环境力学教育部重点实验室,甘肃 兰州 730000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1227653068276302267, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, xref=1., ext=[AuthorCompanyExt(id=1227653068293079484, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068276302267, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil Engineering and Mechanics, Lanzhou University, Lanzhou 730000, China), AuthorCompanyExt(id=1227653068305662399, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068276302267, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.兰州大学土木工程与力学学院,甘肃 兰州 730000)]), AuthorCompany(id=1227653068402131399, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, xref=2., ext=[AuthorCompanyExt(id=1227653068410520009, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068402131399, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory of Mechanics on Disaster and Environment in Western China of the Ministry of Education, Lanzhou University, Lanzhou 730000, China), AuthorCompanyExt(id=1227653068414714314, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068402131399, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.兰州大学西部灾害与环境力学教育部重点实验室,甘肃 兰州 730000)])])], keywords=[Keyword(id=1227653069702365744, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, orderNo=1, keyword=structural engineering), Keyword(id=1227653069794640442, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, orderNo=2, keyword=Bayesian optimization), Keyword(id=1227653069882720835, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, orderNo=3, keyword=long short-term memory network), Keyword(id=1227653071287812683, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, orderNo=4, keyword=Copula theory), Keyword(id=1227653071409447511, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, orderNo=5, keyword=time-varying reliability prediction), Keyword(id=1227653071539470947, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, orderNo=1, keyword=结构工程), Keyword(id=1227653071669494384, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, orderNo=2, keyword=贝叶斯优化), Keyword(id=1227653071799517816, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, orderNo=3, keyword=长短期记忆网络), Keyword(id=1227653071933735551, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, orderNo=4, keyword=Copula理论), Keyword(id=1227653072038593160, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, orderNo=5, keyword=时变可靠性预测)], refs=[Reference(id=1227653082213975029, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2004, volume=130, issue=10, pageStart=1233, pageEnd=1244, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=CHING J, BECK J L, journalName=Journal of Engineering Mechanics, ASCE, refType=null, unstructuredReference=CHING J, BECK J L. Bayesian analysis of the phase II IASC-ASCE structural health monitoring experimental benchmark data[J]. Journal of Engineering Mechanics, ASCE, 2004, 130(10): 1233-1244., articleTitle=Bayesian analysis of the phase II IASC-ASCE structural health monitoring experimental benchmark data, refAbstract=null), Reference(id=1227653082335609849, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2008, volume=30, issue=12, pageStart=3644, pageEnd=3653, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=FRANGOPOL D M, STRAUSS A, KIM S, journalName=Engineering Structures, refType=null, unstructuredReference=FRANGOPOL D M, STRAUSS A, KIM S. Use of monitoring extreme data for the performance prediction of structures: general approach[J]. Engineering Structures, 2008, 30(12): 3644-3653., articleTitle=Use of monitoring extreme data for the performance prediction of structures: general approach, refAbstract=null), Reference(id=1227653082562101252, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2008, volume=30, issue=12, pageStart=3654, pageEnd=3666, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=STRAUSS A, FRANGOPOL D M, KIM S, journalName=Engineering Structures, refType=null, unstructuredReference=STRAUSS A, FRANGOPOL D M, KIM S. Use of monitoring extreme data for the performance prediction of structures: bayesian updating[J]. Engineering Structures, 2008, 30(12): 3654-3666., articleTitle=Use of monitoring extreme data for the performance prediction of structures: bayesian updating, refAbstract=null), Reference(id=1227653082658570249, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2006, volume=47, issue=2, pageStart=527, pageEnd=556, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=PATTON A J, journalName=International Economic Review, refType=null, unstructuredReference=PATTON A J. Modelling asymmetric exchange rate dependence[J]. International Economic Review, 2006, 47(2): 527-556., articleTitle=Modelling asymmetric exchange rate dependence, refAbstract=null), Reference(id=1227653082755039248, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2004, volume=3, issue=1, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=DIAS A, EMBRECHTS P, journalName=Working Papers, refType=null, unstructuredReference=DIAS A, EMBRECHTS P. Dynamic copula models for multivariate high-frequency data in finance[J]. Working Papers, 2004, 3(1): 1-14., articleTitle=Dynamic copula models for multivariate high-frequency data in finance, refAbstract=null), Reference(id=1227653082847313943, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2005, volume=37, issue=1, pageStart=101, pageEnd=114, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=VAN DEN GOORBERGH R W J, GENEST C, WERKER B J M, journalName=Insurance: Mathematics and Economics, refType=null, unstructuredReference=VAN DEN GOORBERGH R W J, GENEST C, WERKER B J M. Bivariate option pricing using dynamic copula models[J]. Insurance: Mathematics and Economics, 2005, 37(1): 101-114., articleTitle=Bivariate option pricing using dynamic copula models, refAbstract=null), Reference(id=1227653082939588636, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2002, volume=46, issue=1, pageStart=110, pageEnd=114, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=SHANMUGAM R, journalName=Journal of Mathematical Psychology, refType=null, unstructuredReference=SHANMUGAM R. Multivariate models and dependence concepts[J]. Journal of Mathematical Psychology, 2002, 46(1): 110-114., articleTitle=Multivariate models and dependence concepts, refAbstract=null), Reference(id=1227653083027669025, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=樊学平, journalName=null, refType=null, unstructuredReference=樊学平. 基于验证荷载和监测数据的桥梁可靠性修正与贝叶斯预测[D]. 哈尔滨: 哈尔滨工业大学, 2014., articleTitle=基于验证荷载和监测数据的桥梁可靠性修正与贝叶斯预测, refAbstract=null), Reference(id=1227653083115749414, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=FAN Xueping, journalName=null, refType=null, unstructuredReference=FAN Xueping. Reliability updating and Bayesian prediction of bridges based on proof loads and monitored data[D]. Harbin: Harbin Institute of Technology, 2014., articleTitle=Reliability updating and Bayesian prediction of bridges based on proof loads and monitored data, refAbstract=null), Reference(id=1227653083216412716, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2016, volume=44, issue=7, pageStart=1002, pageEnd=1009, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=樊学平, 刘月飞, 吕大刚, journalName=同济大学学报(自然科学版), refType=null, unstructuredReference=樊学平, 刘月飞, 吕大刚. 桥梁监测数据的动态线性建模与可靠性预测[J]. 同济大学学报(自然科学版), 2016, 44(7): 1002-1009., articleTitle=桥梁监测数据的动态线性建模与可靠性预测, refAbstract=null), Reference(id=1227653083300298799, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2016, volume=44, issue=7, pageStart=1002, pageEnd=1009, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=FAN Xueping, LIU Yuefei, LYU Dagang, journalName=Journal of Tongji University (Natural Science), refType=null, unstructuredReference=FAN Xueping, LIU Yuefei, LYU Dagang. Dynamic linear modeling of bridge monitored data and reliability prediction[J]. Journal of Tongji University (Natural Science), 2016, 44(7): 1002-1009., articleTitle=Dynamic linear modeling of bridge monitored data and reliability prediction, refAbstract=null), Reference(id=1227653083371601969, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=1875, pageEnd=1887, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=LIU Y F, FAN X P, LYU D G, journalName=null, refType=null, unstructuredReference=LIU Y F, FAN X P, LYU D G. Time-dependent uncertainty analysis of structures based on copula functions[C]// Proceedings of Vulnerability, Uncertainty, and Risk: Quantification, Mitigation, and Management. Reston, USA: American Society of Civil Engineers, 2014: 1875-1887., articleTitle=Time-dependent uncertainty analysis of structures based on copula functions, refAbstract=null), Reference(id=1227653084759916597, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2024, volume=54, issue=2, pageStart=485, pageEnd=493, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=樊学平, 周衡, 刘月飞, journalName=吉林大学学报(工学版), refType=null, unstructuredReference=樊学平, 周衡, 刘月飞. 基于Gaussian Copula-贝叶斯动态模型的桥梁构件时变可靠性分析[J]. 吉林大学学报(工学版), 2024, 54(2): 485-493., articleTitle=基于Gaussian Copula-贝叶斯动态模型的桥梁构件时变可靠性分析, refAbstract=null), Reference(id=1227653084885745721, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2024, volume=54, issue=2, pageStart=485, pageEnd=493, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=FAN Xueping, ZHOU Heng, LIU Yuefei, journalName=Journal of Jilin University (Engineering Edition), refType=null, unstructuredReference=FAN Xueping, ZHOU Heng, LIU Yuefei. Time-variant reliability analysis of bridge members based on Bayesian dynamic models and Copula theory[J]. Journal of Jilin University (Engineering Edition), 2024, 54(2): 485-493., articleTitle=Time-variant reliability analysis of bridge members based on Bayesian dynamic models and Copula theory, refAbstract=null), Reference(id=1227653084973826110, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2020, volume=34, issue=7, pageStart=4, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=14, authorNames=邱锡鹏, journalName=中文信息学报, refType=null, unstructuredReference=邱锡鹏. 神经网络与深度学习[J]. 中文信息学报, 2020, 34(7): 4., articleTitle=神经网络与深度学习, refAbstract=null), Reference(id=1227653085074489409, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2020, volume=34, issue=7, pageStart=4, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=QIU Xipeng, journalName=Journal of Chinese Information Processing, refType=null, unstructuredReference=QIU Xipeng. Neural network and deep learning[J]. Journal of Chinese Information Processing, 2020, 34(7): 4., articleTitle=Neural network and deep learning, refAbstract=null), Reference(id=1227653085191929925, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=1, pageStart=166, pageEnd=176, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=刘智, 李欣雨, 李震, journalName=中外公路, refType=null, unstructuredReference=刘智, 李欣雨, 李震, 等. 基于Bayes-LSTM的公路隧道围岩变形预测方法研究[J]. 中外公路, 2024, 44(1): 166-176., articleTitle=基于Bayes-LSTM的公路隧道围岩变形预测方法研究, refAbstract=null), Reference(id=1227653085330341959, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=1, pageStart=166, pageEnd=176, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=LIU Zhi, LI Xinyu, LI Zhen, journalName=Journal of China and Foreign Highway, refType=null, unstructuredReference=LIU Zhi, LI Xinyu, LI Zhen, et al. Study on deformation prediction method of surrounding rock of highway tunnel based on Bayes-LSTM[J]. Journal of China and Foreign Highway, 2024, 44(1): 166-176., articleTitle=Study on deformation prediction method of surrounding rock of highway tunnel based on Bayes-LSTM, refAbstract=null), Reference(id=1227653085418422346, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=1959, volume=8, issue=3, pageStart=229, pageEnd=231, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=SKLAR A, journalName=Annales de l'ISUP, refType=null, unstructuredReference=SKLAR A. Fonctions de repartition a n dimensions et leurs marges[J]. Annales de l'ISUP, 1959, 8(3): 229-231., articleTitle=Fonctions de repartition a n dimensions et leurs marges, refAbstract=null), Reference(id=1227653085519085646, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=刘月飞, journalName=null, refType=null, unstructuredReference=刘月飞. 考虑失效模式和验证模式相关性的桥梁结构体系可靠度分析[D]. 哈尔滨: 哈尔滨工业大学, 2015., articleTitle=考虑失效模式和验证模式相关性的桥梁结构体系可靠度分析, refAbstract=null), Reference(id=1227653085657497680, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=LIU Yuefei, journalName=null, refType=null, unstructuredReference=LIU Yuefei. System reliability analysis of bridge structures considering correlation of failure modes and proof modes[D]. Harbin: Harbin Institute of Technology, 2015., articleTitle=System reliability analysis of bridge structures considering correlation of failure modes and proof modes, refAbstract=null), Reference(id=1227653085829464147, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2021, volume=49, issue=5, pageStart=624, pageEnd=633, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=刘逸平, 肖青凯, 杨光红, journalName=同济大学学报(自然科学版), refType=null, unstructuredReference=刘逸平, 肖青凯, 杨光红, 等. 基于最优R-Vine Gaussian Copula模型的服役大跨桥梁主梁失效概率分析[J]. 同济大学学报(自然科学版), 2021, 49(5): 624-633., articleTitle=基于最优R-Vine Gaussian Copula模型的服役大跨桥梁主梁失效概率分析, refAbstract=null), Reference(id=1227653085930127443, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, doi=null, pmid=null, pmcid=null, year=2021, volume=49, issue=5, pageStart=624, pageEnd=633, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=LIU Yiping, XIAO Qingkai, YANG Guanghong, journalName=Journal of Tongji University (Natural Science Edition), refType=null, unstructuredReference=LIU Yiping, XIAO Qingkai, YANG Guanghong, et al. Failure probability analysis of service long-span bridge girder based on optimal R-Vine Gaussian Copula model[J]. Journal of Tongji University (Natural Science Edition), 2021, 49(5): 624-633., articleTitle=Failure probability analysis of service long-span bridge girder based on optimal R-Vine Gaussian Copula model, refAbstract=null)], funds=[Fund(id=1227653081693881302, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, awardId=20JR10RA625, language=CN, fundingSource=甘肃省自然科学基金资助项目(20JR10RA625), fundOrder=null, country=null), Fund(id=1227653081786155997, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, awardId=20JR10RA623, language=CN, fundingSource=甘肃省自然科学基金资助项目(20JR10RA623), fundOrder=null, country=null), Fund(id=1227653081907790822, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, awardId=51608243, language=CN, fundingSource=国家自然科学基金资助项目(51608243), fundOrder=null, country=null), Fund(id=1227653082000065512, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, awardId=lzujbky-2025-05, language=CN, fundingSource=兰州大学中央高校基本科研业务费专项资金资助项目(lzujbky-2025-05), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1227653068276302267, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, xref=1., ext=[AuthorCompanyExt(id=1227653068293079484, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068276302267, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil Engineering and Mechanics, Lanzhou University, Lanzhou 730000, China), AuthorCompanyExt(id=1227653068305662399, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068276302267, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.兰州大学土木工程与力学学院,甘肃 兰州 730000)]), AuthorCompany(id=1227653068402131399, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, xref=2., ext=[AuthorCompanyExt(id=1227653068410520009, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068402131399, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory of Mechanics on Disaster and Environment in Western China of the Ministry of Education, Lanzhou University, Lanzhou 730000, China), AuthorCompanyExt(id=1227653068414714314, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, companyId=1227653068402131399, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.兰州大学西部灾害与环境力学教育部重点实验室,甘肃 兰州 730000)])], figs=[ArticleFig(id=1227653072416080546, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 1, caption=Cyclic unit structure of LSTM network, figureFileSmall=8sN36unncbYtO5ofc73Y3g==, figureFileBig=Iz7IHIzwEnFw5qGNh/qv9A==, tableContent=null), ArticleFig(id=1227653072588047022, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图1, caption=LSTM网络的循环单元结构, figureFileSmall=8sN36unncbYtO5ofc73Y3g==, figureFileBig=Iz7IHIzwEnFw5qGNh/qv9A==, tableContent=null), ArticleFig(id=1227653072730653368, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 2, caption=Layout diagram of strain measuring points in section A, figureFileSmall=pZuXZ+QW8pAEEo4H9IGz3A==, figureFileBig=E+w26qGJArRi1GovWr+sVw==, tableContent=null), ArticleFig(id=1227653072827122370, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图2, caption=截面A应变测点布置图, figureFileSmall=pZuXZ+QW8pAEEo4H9IGz3A==, figureFileBig=E+w26qGJArRi1GovWr+sVw==, tableContent=null), ArticleFig(id=1227653072940368588, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 3, caption=Establishment process of BO-LSTM model, figureFileSmall=H95qmVF5QCia+Kz3YEUEIQ==, figureFileBig=xc9nElvevpf8oRc23lRpJQ==, tableContent=null), ArticleFig(id=1227653073196221143, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图3, caption=BO-LSTM模型建立流程, figureFileSmall=H95qmVF5QCia+Kz3YEUEIQ==, figureFileBig=xc9nElvevpf8oRc23lRpJQ==, tableContent=null), ArticleFig(id=1227653073322050267, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 4, caption=Prediction curve of FBG01074 monitoring stress, figureFileSmall=sEgSj52d65wuBbzrQA8hxw==, figureFileBig=d+S04ZBum86i60IF9Ut28w==, tableContent=null), ArticleFig(id=1227653073498211049, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图4, caption=FBG01074监测应力的预测曲线, figureFileSmall=sEgSj52d65wuBbzrQA8hxw==, figureFileBig=d+S04ZBum86i60IF9Ut28w==, tableContent=null), ArticleFig(id=1227653073607262961, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 5, caption=Prediction effect diagram of FBG01074 monitoring stress, figureFileSmall=stFF/H1JBpy1V9vayYUDvQ==, figureFileBig=9sVyNGaG0ypSsHTcNAKm6Q==, tableContent=null), ArticleFig(id=1227653073733092088, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图5, caption=FBG01074监测应力的预测效果图, figureFileSmall=stFF/H1JBpy1V9vayYUDvQ==, figureFileBig=9sVyNGaG0ypSsHTcNAKm6Q==, tableContent=null), ArticleFig(id=1227653073909252866, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 6, caption=Prediction curve of FBG01081 monitoring stress, figureFileSmall=iG5P8r9QNgmlMHKSbkysJw==, figureFileBig=DGExnDLBZMxkdvT6BSl3mA==, tableContent=null), ArticleFig(id=1227653074030887689, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图6, caption=FBG01081监测应力的预测曲线, figureFileSmall=iG5P8r9QNgmlMHKSbkysJw==, figureFileBig=DGExnDLBZMxkdvT6BSl3mA==, tableContent=null), ArticleFig(id=1227653074139939601, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 7, caption=Prediction effect diagram of FBG01081 monitoring stress, figureFileSmall=ZMeftzpgPV2XFzDfzGbJog==, figureFileBig=X5mJba94z4Dhz4C0gJ/0kg==, tableContent=null), ArticleFig(id=1227653074244797207, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图7, caption=FBG01081监测应力的预测效果图, figureFileSmall=ZMeftzpgPV2XFzDfzGbJog==, figureFileBig=X5mJba94z4Dhz4C0gJ/0kg==, tableContent=null), ArticleFig(id=1227653074362237727, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 8, caption=Prediction curve of FBG01078 monitoring stress, figureFileSmall=aGAapZv+MbCWSkNb62J9ww==, figureFileBig=lKH6VQgGi9765DwWv/Fl0Q==, tableContent=null), ArticleFig(id=1227653074450318119, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图8, caption=FBG01078监测应力的预测曲线, figureFileSmall=aGAapZv+MbCWSkNb62J9ww==, figureFileBig=lKH6VQgGi9765DwWv/Fl0Q==, tableContent=null), ArticleFig(id=1227653075842827054, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 9, caption=Prediction effect diagram of FBG01078 monitoring stress, figureFileSmall=66mfObcmgJ8rSUa5CI71Rw==, figureFileBig=Vd2+7mnfLPBc9gzYgN/jjw==, tableContent=null), ArticleFig(id=1227653077797372725, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图9, caption=FBG01078监测应力的预测效果图, figureFileSmall=66mfObcmgJ8rSUa5CI71Rw==, figureFileBig=Vd2+7mnfLPBc9gzYgN/jjw==, tableContent=null), ArticleFig(id=1227653077977727806, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 10, caption=Comparison curves between predicted value and measured value of FBG01081 monitoring stress extremum, figureFileSmall=7bnpB4WvGDppFN+qWWZQGw==, figureFileBig=TwTMTJmuCAbtUIsYpqPtzw==, tableContent=null), ArticleFig(id=1227653078141305665, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图10, caption=FBG01081监测应力极值预测值与实测值对比曲线, figureFileSmall=7bnpB4WvGDppFN+qWWZQGw==, figureFileBig=TwTMTJmuCAbtUIsYpqPtzw==, tableContent=null), ArticleFig(id=1227653078279717704, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 11, caption=Reliability indices at monitoring points, figureFileSmall=ZqIdWmAfbSiVUo0edyrqoA==, figureFileBig=qcR2EnEBhRyslbhtXDhA+g==, tableContent=null), ArticleFig(id=1227653078405546830, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图11, caption=监测点处的可靠指标, figureFileSmall=ZqIdWmAfbSiVUo0edyrqoA==, figureFileBig=qcR2EnEBhRyslbhtXDhA+g==, tableContent=null), ArticleFig(id=1227653078552347480, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 12, caption=Time-varying reliability indices of structural system, figureFileSmall=JCaCbX/mCaEhgjWRb8SHfA==, figureFileBig=Pb+y+FXJtB2a78c6VPMoMg==, tableContent=null), ArticleFig(id=1227653078720119653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图12, caption=结构体系的时变可靠指标, figureFileSmall=JCaCbX/mCaEhgjWRb8SHfA==, figureFileBig=Pb+y+FXJtB2a78c6VPMoMg==, tableContent=null), ArticleFig(id=1227653078829171562, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Fig. 13, caption=Time-varying failure probability of structural system, figureFileSmall=49mhPMIMATWuOwdvSz4yOQ==, figureFileBig=btUcn4TFpJhczN6kxRmQbQ==, tableContent=null), ArticleFig(id=1227653078950806382, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=图13, caption=结构体系的时变失效概率, figureFileSmall=49mhPMIMATWuOwdvSz4yOQ==, figureFileBig=btUcn4TFpJhczN6kxRmQbQ==, tableContent=null), ArticleFig(id=1227653080334926715, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Tab. 1, caption=

Main contents of Bayesian optimization

, figureFileSmall=null, figureFileBig=null, tableContent=
主要部分解释
目标函数模型想要最小化的函数,本文中为LSTM模型中使用该组超参数在验证集上的损失大小
域空间需要调优的超参数的取值范围,本文中为LSTM单元内隐藏层的尺寸大小,初始学习率和正则化参数
优化算法构造代理函数并选择下一个超参数的方法,即采集函数
结果历史记录目标函数评估的存储结果
), ArticleFig(id=1227653080460755838, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=表1, caption=

贝叶斯优化的主要内容

, figureFileSmall=null, figureFileBig=null, tableContent=
主要部分解释
目标函数模型想要最小化的函数,本文中为LSTM模型中使用该组超参数在验证集上的损失大小
域空间需要调优的超参数的取值范围,本文中为LSTM单元内隐藏层的尺寸大小,初始学习率和正则化参数
优化算法构造代理函数并选择下一个超参数的方法,即采集函数
结果历史记录目标函数评估的存储结果
), ArticleFig(id=1227653080557224839, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Tab. 2, caption=

Unidirectional stress obtained by monitoring

, figureFileSmall=null, figureFileBig=null, tableContent=
时间单向应力/MPa
监测点FBG01074监测点FBG01081监测点FBG01078
8/19 22:05−82.30232089−82.30232089−58.01665251
8/19 22:10−82.1034107−82.1034107−58.32982158
8/19 22:15−82.12141271−82.12141271−58.42480884
8/19 22:20−82.00086781−82.00086781−58.00050977
8/19 22:25−82.34377397−82.34377397−58.25301614
8/19 22:30−82.66322906−82.66322906−58.06762957
8/19 22:35−82.28304743−82.28304743−57.88581138
8/19 22:40−82.0634107−82.0634107−58.19898046
8/19 22:45−82.04141271−82.04141271−58.19745115
8/19 22:50−82.40304743−82.40304743−58.0671198
8/19 22:55−82.3845005−82.3845005−58.2353441
8/19 23:00−82.72522704−82.72522704−58.1039932
8/29 10:20−81.77184662−81.77184662−59.16618522
8/29 10:25−81.67039354−81.67039354−59.29957519
8/29 10:30−81.2843996−81.2843996−59.37841971
8/29 10:35−81.5643996−81.5643996−59.27187766
8/29 10:40−81.1007669−81.1007669−58.90773152
8/29 10:45−81.13786075−81.13786075−58.93305013
8/29 11:25−79.63061554−79.63061554−58.13338997
8/29 11:30−79.20607467−79.20607467−58.16227698
8/29 11:35−78.88207871−78.88207871−58.16890399
8/29 11:40−78.99953582−78.99953582−57.88258284
8/29 11:45−78.51535822−78.51535822−57.542226
8/29 11:50−78.43172553−78.43172553−57.7271028
8/29 11:55−78.16500505−78.16500505−57.59643161
), ArticleFig(id=1227653080653693842, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=表2, caption=

监测得到的单向应力

, figureFileSmall=null, figureFileBig=null, tableContent=
时间单向应力/MPa
监测点FBG01074监测点FBG01081监测点FBG01078
8/19 22:05−82.30232089−82.30232089−58.01665251
8/19 22:10−82.1034107−82.1034107−58.32982158
8/19 22:15−82.12141271−82.12141271−58.42480884
8/19 22:20−82.00086781−82.00086781−58.00050977
8/19 22:25−82.34377397−82.34377397−58.25301614
8/19 22:30−82.66322906−82.66322906−58.06762957
8/19 22:35−82.28304743−82.28304743−57.88581138
8/19 22:40−82.0634107−82.0634107−58.19898046
8/19 22:45−82.04141271−82.04141271−58.19745115
8/19 22:50−82.40304743−82.40304743−58.0671198
8/19 22:55−82.3845005−82.3845005−58.2353441
8/19 23:00−82.72522704−82.72522704−58.1039932
8/29 10:20−81.77184662−81.77184662−59.16618522
8/29 10:25−81.67039354−81.67039354−59.29957519
8/29 10:30−81.2843996−81.2843996−59.37841971
8/29 10:35−81.5643996−81.5643996−59.27187766
8/29 10:40−81.1007669−81.1007669−58.90773152
8/29 10:45−81.13786075−81.13786075−58.93305013
8/29 11:25−79.63061554−79.63061554−58.13338997
8/29 11:30−79.20607467−79.20607467−58.16227698
8/29 11:35−78.88207871−78.88207871−58.16890399
8/29 11:40−78.99953582−78.99953582−57.88258284
8/29 11:45−78.51535822−78.51535822−57.542226
8/29 11:50−78.43172553−78.43172553−57.7271028
8/29 11:55−78.16500505−78.16500505−57.59643161
), ArticleFig(id=1227653080758551451, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Tab. 3, caption=

Optimal parameters of BO-LSTM model

, figureFileSmall=null, figureFileBig=null, tableContent=
模型参数名称初始参数最优参数
贝叶斯优化优化时间(MaxTime)Inf
最大迭代次数(MaxObjectiveEvaluations)40
LSTM模型隐藏层节点(NumOfUnits)10优化所得
优化算法adamadam
最大训练次数(MaxEpochs)800800
梯度阈值(GradientThreshold)11
初始学习率(InitialLearnRate)0.001优化所得
学习率调整轮次(LearnRateDropPeriod)700700
学习率调整因子(LearnRateDropFactor)0.20.2
正则化参数L2(L2Regularization)2×10−10优化所得
), ArticleFig(id=1227653080863409059, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=表3, caption=

BO-LSTM模型的最优参数

, figureFileSmall=null, figureFileBig=null, tableContent=
模型参数名称初始参数最优参数
贝叶斯优化优化时间(MaxTime)Inf
最大迭代次数(MaxObjectiveEvaluations)40
LSTM模型隐藏层节点(NumOfUnits)10优化所得
优化算法adamadam
最大训练次数(MaxEpochs)800800
梯度阈值(GradientThreshold)11
初始学习率(InitialLearnRate)0.001优化所得
学习率调整轮次(LearnRateDropPeriod)700700
学习率调整因子(LearnRateDropFactor)0.20.2
正则化参数L2(L2Regularization)2×10−10优化所得
), ArticleFig(id=1227653080964072362, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Tab. 4, caption=

Variation of each optimal parameter of BO-LSTM model with Bayesian optimization iteration number

, figureFileSmall=null, figureFileBig=null, tableContent=
监测点迭代次数隐藏层节点初始学习率正则化参数L2RMSE/MPaMAE/MPa
FBG0107410500.08976.0120×10−90.954160.77642
15460.04212.2246×10−80.842170.62543
20420.03221.0494×10−80.765780.55339
25450.03431.3457×10−100.520740.43104
30490.03596.9529×10−100.355860.35820
40460.03615.5924×10−100.355780.34872
FBG0108110370.09881.6448×10−100.869410.38627
15430.05971.7559×10−100.743520.21359
20400.02561.0732×10−80.307950.19957
25440.05643.4598×10−90.423450.20354
30350.09892.3356×10−100.294390.19847
40320.19874.9260×10−100.284440.19662
FBG0107810500.00191.1305×10−100.315950.20412
15420.01341.1427×10−100.306460.20089
20290.02911.1197×10−90.434570.33493
25460.01598.4465×10−90.300240.19824
30410.02341.1082×10−100.298040.18227
40440.01111.0764×10−100.296720.17622
), ArticleFig(id=1227653081098290097, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=表4, caption=

BO-LSTM模型各优化参数随贝叶斯优化迭代次数的变化

, figureFileSmall=null, figureFileBig=null, tableContent=
监测点迭代次数隐藏层节点初始学习率正则化参数L2RMSE/MPaMAE/MPa
FBG0107410500.08976.0120×10−90.954160.77642
15460.04212.2246×10−80.842170.62543
20420.03221.0494×10−80.765780.55339
25450.03431.3457×10−100.520740.43104
30490.03596.9529×10−100.355860.35820
40460.03615.5924×10−100.355780.34872
FBG0108110370.09881.6448×10−100.869410.38627
15430.05971.7559×10−100.743520.21359
20400.02561.0732×10−80.307950.19957
25440.05643.4598×10−90.423450.20354
30350.09892.3356×10−100.294390.19847
40320.19874.9260×10−100.284440.19662
FBG0107810500.00191.1305×10−100.315950.20412
15420.01341.1427×10−100.306460.20089
20290.02911.1197×10−90.434570.33493
25460.01598.4465×10−90.300240.19824
30410.02341.1082×10−100.298040.18227
40440.01111.0764×10−100.296720.17622
), ArticleFig(id=1227653081236702138, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Tab. 5, caption=

Hyperparameters of RNN model and LSTM model

, figureFileSmall=null, figureFileBig=null, tableContent=
参数名称RNN模型LSTM模型
隐藏层节点(NumOfUnits)4040
优化算法adamadam
最大训练次数(MaxEpochs)800800
梯度阈值(GradientThreshold)11
初始学习率(InitialLearnRate)0.1980.198
学习率调整轮次(LearnRateDropPeriod)700700
学习率调整因子(LearnRateDropFactor)0.20.2
正则化参数L2(L2Regularization)4.92×10−104.92×10−10
), ArticleFig(id=1227653081341559746, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=表5, caption=

RNN模型与LSTM模型的超参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数名称RNN模型LSTM模型
隐藏层节点(NumOfUnits)4040
优化算法adamadam
最大训练次数(MaxEpochs)800800
梯度阈值(GradientThreshold)11
初始学习率(InitialLearnRate)0.1980.198
学习率调整轮次(LearnRateDropPeriod)700700
学习率调整因子(LearnRateDropFactor)0.20.2
正则化参数L2(L2Regularization)4.92×10−104.92×10−10
), ArticleFig(id=1227653081442223048, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=EN, label=Tab. 6, caption=

Monitoring stress extremum of monitoring points

, figureFileSmall=null, figureFileBig=null, tableContent=
时间/d应力极值/MPa
监测点FBG01074监测点FBG01081监测点FBG01078
279.6933−13.5776−55.9488
388.469−13.2206−62.9587
488.9938−17.5406−63.7411
582.3743−14.0977−57.7986
682.8216−13.8898−58.0185
783.5275−12.0826−58.8782
885.7818−15.3158−60.8729
985.7943−18.9939−60.4010
), ArticleFig(id=1227653081517720526, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1227591810156003816, language=CN, label=表6, caption=

监测点的监测应力极值

, figureFileSmall=null, figureFileBig=null, tableContent=
时间/d应力极值/MPa
监测点FBG01074监测点FBG01081监测点FBG01078
279.6933−13.5776−55.9488
388.469−13.2206−62.9587
488.9938−17.5406−63.7411
582.3743−14.0977−57.7986
682.8216−13.8898−58.0185
783.5275−12.0826−58.8782
885.7818−15.3158−60.8729
985.7943−18.9939−60.4010
)], 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.1004-4523.202309064, detailUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/10.16385/j.cnki.issn.1004-4523.202309064, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/PDF/10.16385/j.cnki.issn.1004-4523.202309064, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/PDF/10.16385/j.cnki.issn.1004-4523.202309064, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
BO-LSTM和Copula理论相融合的桥梁构件时变可靠性预测
收藏切换
PDF下载
赵启凡 1 , 刘月飞 1, 2 , 樊学平 1, 2
振动工程学报 | 2025,38(9): 2182-2191
收起
收藏切换
振动工程学报 | 2025, 38(9): 2182-2191
BO-LSTM和Copula理论相融合的桥梁构件时变可靠性预测
全屏
赵启凡1 , 刘月飞1, 2 , 樊学平1, 2
作者信息
  • 1.兰州大学土木工程与力学学院,甘肃 兰州 730000
  • 2.兰州大学西部灾害与环境力学教育部重点实验室,甘肃 兰州 730000
  • 赵启凡(2000—),男,硕士研究生。E-mail:

通讯作者:

刘月飞(1982—),女,博士,副教授。 E-mail:
Time-dependent reliability prediction of bridge components with the fusion of BO-LSTM and Copula theory
Qifan ZHAO1 , Yuefei LIU1, 2 , Xueping FAN1, 2
Affiliations
  • 1.School of Civil Engineering and Mechanics, Lanzhou University, Lanzhou 730000, China
  • 2.Key Laboratory of Mechanics on Disaster and Environment in Western China of the Ministry of Education, Lanzhou University, Lanzhou 730000, China
出版时间: 2025-09-10 doi: 10.16385/j.cnki.issn.1004-4523.202309064
文章导航
收藏切换

桥梁构件的各个监测点之间存在着非线性失效动态相关性,为研究该因素对桥梁时变可靠指标的影响,建立了贝叶斯优化的长短期记忆(BO-LSTM)网络模型,对桥梁监测应力极值进行动态预测;建立考虑三个监测点失效非线性相关性的三元Gaussian Copula模型,对桥梁构件的时变可靠指标和时变失效概率进行预测,利用天津市富民桥的监测数据对模型与方法的合理性进行了验证分析。

结构工程  /  贝叶斯优化  /  长短期记忆网络  /  Copula理论  /  时变可靠性预测

There exists the nonlinear failure correlation among the multiple monitoring points of bridge components. Considering the influence of this factor on the reliability indices of the bridge, this paper adopts the Bayesian optimized long short-term memory (BO-LSTM) network model in machine learning to dynamically predict the monitoring data of the bridge, and establishes a three-dimensional Gaussian Copula model based on Copula theory to calculate the time-varying reliability indices and failure probability of the bridge construction. The rationality of the model and method is verified by applying the monitoring data of Fumin Bridge in Tianjin.

structural engineering  /  Bayesian optimization  /  long short-term memory network  /  Copula theory  /  time-varying reliability prediction
赵启凡, 刘月飞, 樊学平. BO-LSTM和Copula理论相融合的桥梁构件时变可靠性预测. 振动工程学报, 2025 , 38 (9) : 2182 -2191 . DOI: 10.16385/j.cnki.issn.1004-4523.202309064
Qifan ZHAO, Yuefei LIU, Xueping FAN. Time-dependent reliability prediction of bridge components with the fusion of BO-LSTM and Copula theory[J]. Journal of Vibration Engineering, 2025 , 38 (9) : 2182 -2191 . DOI: 10.16385/j.cnki.issn.1004-4523.202309064
国内外学者在结构可靠度预测领域进行了大量研究。国外方面,CHING等[1] 运用贝叶斯分析对IASC-ASCE结构健康监测第二阶段的Benchmark模型进行了分析;FRANGOPOL等[2]提出了基于监测应力极值的桥梁性能可靠度评估及预测方法,并引入基于贝叶斯更新的桥梁可靠度预测方法[3];PATTON[4]、DIAS等[5]和VAN DEN GOORBERGH等[6]研究了双变量时间序列的动态时变Copula模型;SHANMUGAM[7]使用常数参数的Copulas函数研究了马尔可夫时间序列。国内方面,樊学平[8]利用桥梁健康监测数据,运用贝叶斯动态模型,对美国I-39北桥和长春伊通河桥的构件可靠度进行了预测分析;樊学平等[9]进行了在役桥梁的动力响应数据动态线性建模和可靠性修正分析;LIU等[10]利用动态时变Copula模型考虑了失效模式对串联结构体系的影响,对长春伊通河桥进行了可靠性分析;樊学平等[11]采用Copula理论建立了三元的Gaussian Copula-BDMs模型,计算桥梁构件的时变可靠性,并对天津富民桥进行了可靠度分析与预测。
在桥梁构件可靠度预测方面,国内多采用以贝叶斯动态模型为基础的预测方法。该类方法多采用时间序列分析方法、移动平均法以及五点三次平滑法等方法将采集的健康监测信息进行降噪处理,再基于健康监测数据的分布特性,建立多过程贝叶斯动态线性模型(如R-Vine Copula模型),实现了多个模型对监测应力极值信号的实时预测和分析,最后结合健康监测信息和可靠度计算方法对桥梁构件的时变可靠性进行预测和分析[11-16]
神经网络算法不仅可以反映序列数据发展和变化的趋势,而且可以考虑数据序列中随机波动的影响,拟合并进行高精度预测。而针对时序数据的预测,采用较多的是内侧节点递归连接的循环神经网络(recurrent neural network,RNN)模型[12],该模型可以实现多个隐藏层的相互连接,获得更好的网络状态反馈。在RNN模型的基础上,长短期记忆(long short-term memory,LSTM)网络解决了RNN模型无法处理的长距离依赖问题,对时序数据能够进行更好的处理。
贝叶斯优化是一种通过近似逼近来估计最优解的优化方法,多适用于黑箱优化。贝叶斯优化的LSTM模型可以给出最好的超参数组合。在面对不同的桥梁数据时,只需对贝叶斯优化的两个参数进行调整,而不需要额外对LSTM模型进行超参数确定,大大提高了优化的效率[13]
基于以上研究,本文采用LSTM模型,并引入贝叶斯优化方法对LSTM模型中的初始超参数进行优化,构建贝叶斯优化下的长短期记忆(BO-LSTM)网络模型,利用BO-LSTM模型对桥梁监测应力极值进行预测。并以天津富民桥为例,基于二元Copula[14-15]理论,将二元Gaussian Copula推广至三元,建立三元的Gaussian Copula模型,对桥梁可靠性进行计算分析,验证模型与方法的合理性。
在一般的循环神经网络中,其参数往往可以通过梯度下降的方法来进行较为高效的学习,进而进行神经网络的构建[12]。由于在一般循环神经网络中,非线性激活函数经常使用导数小于1的Logistic函数或Tanh函数,其权重矩阵均较小,因此往往会出现梯度消失的问题。
一般循环网络尽管在理论上可建立长时间间隔数据状态之间的关系,但由于存在梯度爆炸或消失的问题,在实际操作中只能学习到短期的依赖关系,这种问题称为长程依赖问题。
为了解决一般循环神经网络的长程依赖问题,本文采用引入门控机制的方法来控制信息的积累速度,对输入神经网络的信息进行一定程度的筛选,有选择地加入新信息或遗忘之前的信息。长短期记忆网络就是基于门控的循环神经网络的变体,可以有效解决梯度爆炸或消失的问题[12]
LSTM网络中的重复模块包含四个交互的层:3个Sigmoid层和1个Tanh层,并以图1所示的方式进行交互。
图1中:
it=σ(Wixt+Uiht1+bi)
ft=σ(Wfxt+Ufht1+bf)
ot=σ(Woxt+Uoht1+bo)
c~t=tanh(Wcxt+Ucht1+bc)
ct=ftct1+itc~t
ht=ottanh(ct)
式中,itftotctc~t分别为输入门、遗忘门、输出门、细胞状态和细胞状态候选值;σ()为Logistic函数,输出函数区间为(0,1);WiWfWoWc分别为输入门、遗忘门、输出门和细胞状态候选值的权重矩阵;UiUfUoUc分别为为输入门、遗忘门、输出门和细胞状态上一时刻外部状态的权重;bibfbobc分别为输入门、遗忘门、输出门和细胞状态候选值的偏置矩阵;xt为当前时刻的输入;ht−1为上一时刻的外部状态。
在LSTM网络中,记忆单元c可以在某个时刻捕捉到某个关键信息,并有能力将此关键信息保存一定的时间间隔。记忆单元c中保存信息的生命周期要长于短期记忆h,但又远远短于长期记忆。
机器学习模型中一般有两类参数:第一类参数通常称为模型参数(parameter),需要从数据中学习和估计得到,例如线性回归中的斜率与截距等;第二类参数通常称为超参数(hyperparameter),是机器学习算法中的调优参数(tuning parameter),需要提前设定,例如神经网络的初始学习率等。在本文中,使用贝叶斯优化对LSTM网络的超参数进行优化。
贝叶斯优化[13]是一种通过近似逼近来估计最优解的优化方法,多适用于黑箱优化,采用高斯过程、随机森林等各种概率代理模型拟合超参数与评价模型之间的关系,得出效果最好的超参数组合。贝叶斯优化会考虑之前的参数信息,更新目标函数的后验分布,直到后验分布基本贴合真实分布。相较于传统的LSTM模型对于时序数据的预测,引入贝叶斯优化的LSTM模型可以通过对各种概率代理模型拟合超参数与模型之间的关系进行评价,得出最好的超参数组合,而不需要额外进行超参数模拟与组合,大大提高了优化的效率。后验概率的更新公式为:
p(f|D)=p(D|f)p(f)p(D)
式中,D={(x1,f1),(x2,f2),,(xn,fn)}为已经采集到的样本点,其中,xnfn分别为样本和其对应的概率;p(f)为先验分布,能够通过上述贝叶斯公式算出f的后验分布;p(D|f)为似然函数;p(f|D)为后验分布函数。
贝叶斯优化中的概率代理模型指的是通过某种概率模型替代目标函数,主要分为以下三类:TPE(树形Parzen评估器,tree parzen estimator)、SMAC(随机森林回归)和GP(高斯过程)。本文采用高斯过程回归对贝叶斯优化模型进行建模,有:
yn=fn(xn)+εn
式中,εn为高斯白噪声且服从正态分布N(0,σn2),其中σn为标准差。
f(x)GP[m(x),k(x,x)]
式中,m(x)为均值;k(x,x')为指数协方差,称为核函数,可表示为:
k(x,x)=σf2exp[(x,x)TΛ1(x,x)]
式中,σf2为核函数信号差;Λ为超参数对称矩阵。
根据贝叶斯理论,基于样本数据集D由高斯过程建立的先验函数在给定测试样本x*的条件下将变化为后验分布,因此样本数据集的观察目标值和预测值的联合分布为:
[yf(x)]N(0,[K(X,X)+σn2IK(X,x)K(x,X)K(x,x)])
式中,K(X,x*)=KT(x*,X),且该项为测试样本x*与训练集样本X之间的N×1阶协方差核矩阵;I为单位矩阵。
由此可得测试样本x*模型预测值f(x*)满足的后验分布:
p(f(x*)|X,Y,x)N(μ,Σ)
其中:
μ=K(x,X)[K(X,X)+σn2I]1Y
Σ*=K(x,x)K(x,X)[K(X,X)+σn2IN]1K(X,x)
式中,Y为样本数据集的观测目标值;μ*为均值;Σ*为方差;INN维单位矩阵;K(X,X)为协方差矩阵,是一个实对称阵。
综上,θ={σf2,σn2,Λ}为超参数集合,一般而言,高斯过程回归通过极大似然估计求解优化超参数,其对数似然函数为:
L(θ)=lg[p(Y|X,θ)]=12YTM1Y+12lg|M|+n2lg2π
式中,M=K(X,X)+σn2I。通过求解极大似然函数的极值可以确定优化后的超参数组合。
贝叶斯优化问题包括目标函数、域空间、优化算法、结果历史记录4个主要部分,如表1所示。
由于本文所采用的桥例(天津富民桥)在横梁底板横桥向布置了内侧、中部和外侧3个监测点,因此将二元Gaussian Copula模型推广至三元Gaussian Copula,对监测点进行整体可靠指标预测与分析。
对于X=(X1, X2,,Xn),本文假设Fn元联合概率概率分布函数,其边缘分布函数为FX1,FX2,,FXn,有Copula函数C1,使得对于任意的x=(x1, x2,, xn)∈Rn,都有下式成立[14]
F(x1,x2,,x3)=C1(Fx1(x1),Fx2(x2),,Fxn(xn))
若边缘分布函数Fxi(i=1,2,,n)连续,则Copula函数唯一。由式(16)可得随机向量X=(X1,X2,, Xn)的联合概率密度函数为:
p(x1,x2,,xn)=c(FX1(x1),FX2(x2),,FXn(xn))i=1npXi(xi)
式中,pXi(xi)为边缘密度函数;c(u)为Copula函数的联合概率密度函数:
c(u1,u2,,un)=2Cu1u2un(u1,u2,,un)
FXi1FXi(i=1,2,,n)的广义逆函数,式(17)还可写为:
F(FX11(u1)FX21(u2)FXn1(un))=C(u1u2un)
式中,ui=FXi(i=1,2,,n);(u1,u2,,un)=u
式(19)表示在边缘分布已知的条件下构造Copula函数的方法。由概率积分变换可知,随机变量UiFXi(Xi)(i=1,2,,n)服从(0,1)均匀分布且Xi=FXi1(Ui)(i=1,2,,n),U=(U1,U2,,Un),因此式(19)可以进一步表示为:
P(X1x1X2x2Xnxn)=P(X1FX11(u1)X2FX21(u2)XnFXn1(un))=P(U1u1U2u2Unun)=C(u1u2un)
由式(20)可知,Copula函数可以将多元随机变量的联合概率密度与各变量的边缘概率密度函数有效地连接起来,考虑随机变量之间的相关性,简化了多元随机变量的概率建模过程。
Gaussian Copula是椭圆Copula函数的一种[11],根据椭圆Copula函数的构造方法,由多元正态分布函数推导可得到Gaussian Copula。以三元Copula函数为例,相对应的概率分布函数C为:
C(u1,u2,u3;ρ12,ρ13,ρ23)=ΦG(Φ1(u1),Φ1(u2),Φ1(u3);ρ)=Φ1(u1)Φ1(u2)Φ1(u3)1(2π)32A12×exp(B2A)drdsdt
其中:
A=1ρ122ρ132ρ232+2ρ12ρ13ρ23
B=(1ρ232)r2+(1ρ132)s2+(1ρ122)t22K
K=(ρ12ρ13ρ23)rs+(ρ13ρ12ρ23)rt+(ρ23ρ12ρ13)st
式中,ui=Fi(xi),其中Fi(xi)为xii=1,2,3)的边缘概率分布函数;Ф为标准正态分布函数;ρρ12ρ13ρ23为Copula函数的分布参数,取值均为[−1,1];rst为极坐标变换后的积分变量。
Pearson线性相关系数是度量随机变量间线性相关性强弱的指标,本文采用Pearson线性相关系数法来确定Gaussian Copula函数的相关参数ρ。
假设随机变量x1x2的Pearson线性相关系数表示为ρ(1,2),结合Copula函数的概念可以得到Gaussian Copula函数相关参数ρ的关系式[14],如下式所示:
ρ=ρ(Φ1(u1),Φ1(u2))=ρ(Φ1(F1(x1)),Φ1(F2(x2)))=ρ(x1,x2)=ρ(1,2)
由式(22)可得,t+1时刻基与Pearson线性相关系数的Gaussian Copula函数的相关参数为:
ρt+1=ρt+1(1,2)
基于随机变量之间的Pearson线性相关系数,通过推导可得到三元的Gaussian Copula模型:y1,t+1的分布函数为N(μ1,t+1,σ1,t+12),y2,t+1的分布函数为N(μ2,t+1,σ2,t+12),y3,t+1的分布函数为N(μ3,t+1,σ3,t+12),即
F1(y1,t+1)=N(μ1,t+1,σ1,t+12)=Φ(y1,t+1μ1,t+1σ1,t+1)
F2(y2,t+1)=N(μ2,t+1,σ2,t+12)=Φ(y2,t+1μ2,t+1σ2,t+1)
F3(y3,t+1)=N(μ3,t+1,σ3,t+12)=Φ(y3,t+1μ3,t+1σ3,t+1)
式中,μσ分别表示平均值和标准差。
u1=F1(y1,t+1),u2=F2(y2,t+1),u3=F3(y3,t+1),可得三元Gaussian Copula模型函数为:
(y1,t+1y2,t+1y3,t+1)C(F1(y1,t+1)F2(y2,t+1)F3(y3,t+1))=C(u1u2u3)
C(u1u2u3)=ΦG(F1(y1,t+1)F2(y2,t+1)F3(y3,t+1)ρ12,t+1ρ13,t+1ρ23,t+1)
式中,ФG()为Gaussian Copula函数;ρ12,t+1ρ13,t+1ρ23,t+1为基于BO-LSTM得到的Gaussian Copula函数的时变相关参数。
结构体系三个失效模式所对应的功能函数为:
gi,t+1(X1,X2,,Xn)=[σ]yi,t+1i=1,2,3
三个失效模式同时发生的概率为:
P(g1,t+1(X)0g2,t+1(X)0g3,t+1(X)0)=P(F1(g1,t+1(X))F1(0)F2(g2,t+1(X))F2(0)F3(g3,t+1(X))F3(0))=P(U1,t+1F1(0)U2,t+1F2(0)U3,t+1F3(0))=C(F1(0)F2(0)F3(0)ρ12,t+1ρ13,t+1ρ23,t+1)
其中:
Ui,t+1=Φ([σ]yi,t+1μi,t+1σi,t+1)
Fi(0)=Φ(μi,t+1σi,t+1)i=1,2,3
根据Sklar定理,由式(30)可以得到三元串联体系的失效概率为:
P(A1,t+1A2,t+1A3,t+1)=P(A1,t+1)+P(A2,t+1)+P(A3,t+1)P(A1,t+1A2,t+1)P(A1,t+1A3,t+1)P(A2,t+1A3,t+1)+P(A1,t+1A2,t+1A3,t+1)=pf1,t+1+pf2,t+1+pf3,t+1C(pf1,t+1pf2,t+1)C(pf1,t+1pf3,t+1)C(pf2,t+1pf3,t+1)+C(pf1,t+1pf2,t+1pf3,t+1)=pf1,t+1+pf2,t+1+pf3,t+1ΦG(pf1,t+1pf2,t+1)ΦG(pf1,t+1pf3,t+1)ΦG(pf2,t+1pf3,t+1)+ΦG(pf1,t+1pf2,t+1pf3,t+1)
式中,Ai,t+1表示gi,t+1(X) ≤ 0(i=1,2,3);pf1,t+1pf2,t+1pf3,t+1为三个失效模式的概率;C为Copula函数。
天津市富民桥是横跨在海河上的单塔空间索面自锚悬索桥,该桥主跨主缆被锚定在主梁两侧,边跨主缆被锚定在重力式锚碇,通过这种锚定形式,构成了一个稳定结构体系。主跨主缆采用三维空间线性,在立面及平面皆为抛物线,边跨主缆采用一组(两根并排)缆索、不加竖向吊索形式。本文主要对主跨部分横梁的时序监测应力极值作出预测,并对时变可靠性进行分析。
考虑到桥梁监测应力极值的时序数据的特征,采用MATLAB建立贝叶斯优化的长短期记忆网络模型。
串联结构体系是指结构中一个元件失效则结构失效的结构体系,是无冗余度的体系,也称为最弱链体系,其安全可靠度要求所有组成元件不得失效。而并联结构体系是指只有在结构中全部元件都失效时结构才失效的结构体系。并联结构的体系是有冗余度的体系,只要有任何元件不失效则结构体系依然可靠。对于本桥来说,当横梁底板横桥向的内侧、中部和外侧3个测点之中,任意一点发生失效,则整体结构发生失效,因此认为该三点存在串联关系。采用天津富民桥主梁截面A横桥向底板内侧、中部和外侧3个存在着串联关系的控制监测点FBG01074、FBG01081和FBG01078的单向应力,对该横梁构件可靠度进行计算分析。截面A的应变测点布置图如图2所示。图2中,测点1、3和5分别表示FBG01074、FBG01078和FBG01081;测点2、4和6均为温度补偿测点。
BO-LSTM模型的训练过程分为三个阶段:
(1)使用传统的LSTM模型进行预训练,得到初始模型参数;
(2)使用贝叶斯优化模型,通过采样和优化算法来估计LSTM模型的超参数的后验分布,计算出指定数据集和任务中LSTM模型的最优超参数;
(3)将贝叶斯优化下的最优超参数引入LSTM模型,对LSTM模型重新进行训练。
综上,BO-LSTM模型就可以通过贝叶斯优化模型的迭代获得更准确的模型参数,更好地对桥梁时序监测应力极值作出预测。为提高模型的泛化能力,防止过拟合现象,将前70%的数据作为训练集,用作寻找贝叶斯优化最优模型的参数;后30%作为测试集,对模型预测能力进行评估。
对天津富民桥某横梁底板横桥向的3个控制监测点FBG01074、FBG01081和FBG01078从2009年8月19日22时5分开始以5 min为时间间隔采集数据,至2009年8月29日11时55分,每个监测点获得2691个单向应力,所测数据不包括桥梁恒载效应,如表2所示。
在构建过程中,使用均方根误差RMSE作为损失函数,通过计算RMSE是否在合理范围内,不断训练调节超参数,直到参数精度满足要求:
RMSE=1nt=1n(yty^t)2
并通过计算最终预测值与实测值之间的平均绝对误差MAE,反映实际预测的误差大小,对模型整体的预测精度进行评估:
MAE=1n1t=1n1|yty^t|
式中,n1为训练数据的个数;yt为第t个训练数据;ŷt为模型对训练集第t个数据的预测值。
BO-LSTM模型的建立流程如图3所示。
MATLAB中选取的使用贝叶斯优化的初始参数与得到的各个最优参数如表3所示。
表3中,初始参数为在预训练中获得的参数;除隐藏层节点、初始学习率、正则化参数外的最优参数,均为在先前研究中确定的通用参数。本文仅对在不同模型中变化较大的参数进行贝叶斯优化。
图4~9为BO-LSTM对监测点FBG01074、FBG01081和FBG01078的预测曲线与预测效果图。
由桥梁监测应力的测试集样本计算可得:
MAEFBG01074=0.34872MPa
MAEFBG01081=0.36742MPa
MAEFBG01078=0.17622MPa
由平均绝对误差MAE值可知,本文所建立的BO-LSTM模型能够对监测点FBG01074、FBG01081和FBG01078的监测应力极值进行有效地预测和分析,预测的结果能够合理地解释检测结果的变化范围和趋势。
BO-LSTM模型各优化参数随贝叶斯优化迭代次数的变化如表4所示。由表4可知,测试集的均方根误差RMSE和平均绝对误差MAE总体上随着贝叶斯优化网络的迭代次数增加而降低。说明BO-LSTM模型的计算精度在一定范围内总体上随着贝叶斯优化的迭代次数的增加而增加。
为验证BO-LSTM模型的有效性,分别采用内侧节点递归连接的循环神经网络模型、长短期记忆网络模型,并以桥梁底板中部的监测点FBG01081为例,对桥梁监测应力极值进行预测,以均方根误差RMSE为评价指标,与BO-LSTM模型预测值进行比较,其中RNN模型与LSTM模型的超参数如表5所示。
桥梁监测应力极值预测对比分析结果如图10所示。由图10可知,利用BO-LSTM模型可以较好地预测监测应力的变化特征。RNN模型、LSTM模型和BO-LSTM模型的均方根误差RMSE分别为:
RMSERNN=0.90485
RMSELSTM=0.44572
RMSEBOLSTM=0.28444
由均方根误差RMSE可得:BO-LSTM模型的预测效果总体上要优于RNN模型与LSTM模型。
底板控制监测点FBG01074、FBG01081和FBG01078对应的功能函数为[11]
Zyi,t=[σ]yi,ti=1,2,3
式中,[σ]~N(96.44,12.042),单位为MPa。
监测点FBG01074、FBG01081和FBG01078为串联关系,由3个监测点组成的结构时变失效概率为:
pf,t+1=pZy1,t+1+pZy2,t+1+pZy3,t+1ΦG(pZy1,t+1pZy2,t+1)ΦG(pZy1,t+1pZy3,t+1)ΦG(pZy2,t+1pZy3,t+1)+ΦG(pZy1,t+1pZy2,t+1pZy3,t+1)
提取出BO-LSTM模型预测第2~9天不包含恒载效应的监测应力极值,如表6所示。
根据功能函数,采用一次二阶矩方法(FOSM)计算结构的可靠指标,则监测点FBG01074、FBG01081和FBG0107处的可靠指标如图11所示。
基于上文中建立的Gaussian Copula函数,将考虑失效模式相关性和不考虑失效模式相关性计算所得的结构体系的时变可靠指标和时变失效概率进行对比,分别如图1213所示。
图1213可知,考虑失效相关性的三元串联结构体系的可靠指标明显高于不考虑相关性的可靠指标,考虑失效相关性的失效概率明显低于不考虑相关性的失效概率。因此,在多元体系的可靠度分析中,考虑失效模式的相关性有一定必要性与合理性。
本文提出了BO-LSTM神经网络预测时间序列下桥梁应力的模型,利用贝叶斯优化中的高斯过程对超参数进行优化并得到预测值,结合Gaussian Copula模型对结构体系的时变可靠性进行预测分析,得出结论如下:
(1)贝叶斯优化下的长短期神经网络模型考虑了数据序列中随机噪声的影响,不需要通过时间序列分析方法、移动平均法以及五点三次平滑法等方法将采集的健康监测信息进行降噪处理,对于不同的桥梁有更好的泛化能力。
(2)随着贝叶斯优化的迭代次数在一定范围内增加,对贝叶斯优化下的神经网络中的超参数进行不断修正,LSTM模型的预测精度越来越高。
(3)贝叶斯优化下的长短期神经网络模型能够对三元结构体的实时监测信息进行较高精度的预测,并在后续进行对结构可靠度进行预测和分析,预测的结果能够对结构进行多元结构的可靠性分析。
(4)在分析多元结构体系的可靠性时,由于考虑结构相关性的失效概率比不考虑结构相关性的失效概率小,所以应当考虑结构体系失效模式相关性。
  • 甘肃省自然科学基金资助项目(20JR10RA625)
  • 甘肃省自然科学基金资助项目(20JR10RA623)
  • 国家自然科学基金资助项目(51608243)
  • 兰州大学中央高校基本科研业务费专项资金资助项目(lzujbky-2025-05)
参考文献 引证文献
排序方式:
[1]
CHING J, BECK J L. Bayesian analysis of the phase II IASC-ASCE structural health monitoring experimental benchmark data[J]. Journal of Engineering Mechanics, ASCE, 2004, 130(10): 1233-1244.
[2]
FRANGOPOL D M, STRAUSS A, KIM S. Use of monitoring extreme data for the performance prediction of structures: general approach[J]. Engineering Structures, 2008, 30(12): 3644-3653.
[3]
STRAUSS A, FRANGOPOL D M, KIM S. Use of monitoring extreme data for the performance prediction of structures: bayesian updating[J]. Engineering Structures, 2008, 30(12): 3654-3666.
[4]
PATTON A J. Modelling asymmetric exchange rate dependence[J]. International Economic Review, 2006, 47(2): 527-556.
[5]
DIAS A, EMBRECHTS P. Dynamic copula models for multivariate high-frequency data in finance[J]. Working Papers, 2004, 3(1): 1-14.
[6]
VAN DEN GOORBERGH R W J, GENEST C, WERKER B J M. Bivariate option pricing using dynamic copula models[J]. Insurance: Mathematics and Economics, 2005, 37(1): 101-114.
[7]
SHANMUGAM R. Multivariate models and dependence concepts[J]. Journal of Mathematical Psychology, 2002, 46(1): 110-114.
[8]
樊学平. 基于验证荷载和监测数据的桥梁可靠性修正与贝叶斯预测[D]. 哈尔滨: 哈尔滨工业大学, 2014.
FAN Xueping. Reliability updating and Bayesian prediction of bridges based on proof loads and monitored data[D]. Harbin: Harbin Institute of Technology, 2014.
[9]
樊学平, 刘月飞, 吕大刚. 桥梁监测数据的动态线性建模与可靠性预测[J]. 同济大学学报(自然科学版), 2016, 44(7): 1002-1009.
FAN Xueping, LIU Yuefei, LYU Dagang. Dynamic linear modeling of bridge monitored data and reliability prediction[J]. Journal of Tongji University (Natural Science), 2016, 44(7): 1002-1009.
[10]
LIU Y F, FAN X P, LYU D G. Time-dependent uncertainty analysis of structures based on copula functions[C]// Proceedings of Vulnerability, Uncertainty, and Risk: Quantification, Mitigation, and Management. Reston, USA: American Society of Civil Engineers, 2014: 1875-1887.
[11]
樊学平, 周衡, 刘月飞. 基于Gaussian Copula-贝叶斯动态模型的桥梁构件时变可靠性分析[J]. 吉林大学学报(工学版), 2024, 54(2): 485-493.
FAN Xueping, ZHOU Heng, LIU Yuefei. Time-variant reliability analysis of bridge members based on Bayesian dynamic models and Copula theory[J]. Journal of Jilin University (Engineering Edition), 2024, 54(2): 485-493.
[12]
邱锡鹏. 神经网络与深度学习[J]. 中文信息学报, 2020, 34(7): 4.
QIU Xipeng. Neural network and deep learning[J]. Journal of Chinese Information Processing, 2020, 34(7): 4.
[13]
刘智, 李欣雨, 李震, 等. 基于Bayes-LSTM的公路隧道围岩变形预测方法研究[J]. 中外公路, 2024, 44(1): 166-176.
LIU Zhi, LI Xinyu, LI Zhen, et al. Study on deformation prediction method of surrounding rock of highway tunnel based on Bayes-LSTM[J]. Journal of China and Foreign Highway, 2024, 44(1): 166-176.
[14]
SKLAR A. Fonctions de repartition a n dimensions et leurs marges[J]. Annales de l'ISUP, 1959, 8(3): 229-231.
[15]
刘月飞. 考虑失效模式和验证模式相关性的桥梁结构体系可靠度分析[D]. 哈尔滨: 哈尔滨工业大学, 2015.
LIU Yuefei. System reliability analysis of bridge structures considering correlation of failure modes and proof modes[D]. Harbin: Harbin Institute of Technology, 2015.
[16]
刘逸平, 肖青凯, 杨光红, 等. 基于最优R-Vine Gaussian Copula模型的服役大跨桥梁主梁失效概率分析[J]. 同济大学学报(自然科学版), 2021, 49(5): 624-633.
LIU Yiping, XIAO Qingkai, YANG Guanghong, et al. Failure probability analysis of service long-span bridge girder based on optimal R-Vine Gaussian Copula model[J]. Journal of Tongji University (Natural Science Edition), 2021, 49(5): 624-633.
2025年第38卷第9期
PDF下载
90
43
引用本文
BibTeX
文章信息
doi: 10.16385/j.cnki.issn.1004-4523.202309064
  • 接收时间:2023-09-22
  • 首发时间:2026-02-09
  • 出版时间:2025-09-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-09-22
  • 修回日期:2023-11-09
基金
甘肃省自然科学基金资助项目(20JR10RA625)
甘肃省自然科学基金资助项目(20JR10RA623)
国家自然科学基金资助项目(51608243)
兰州大学中央高校基本科研业务费专项资金资助项目(lzujbky-2025-05)
作者信息
    1.兰州大学土木工程与力学学院,甘肃 兰州 730000
    2.兰州大学西部灾害与环境力学教育部重点实验室,甘肃 兰州 730000

通讯作者:

刘月飞(1982—),女,博士,副教授。 E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.202309064
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