Article(id=1245390007599477730, tenantId=1146029695717560320, journalId=1241701559352995854, issueId=1245390004252426256, articleNumber=null, orderNo=null, doi=10.13197/j.eeed.2024.0306, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1679673600000, receivedDateStr=2023-03-25, revisedDate=1686326400000, revisedDateStr=2023-06-10, acceptedDate=null, acceptedDateStr=null, onlineDate=1774853716038, onlineDateStr=2026-03-30, pubDate=null, pubDateStr=null, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774853716038, onlineIssueDateStr=2026-03-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774853716038, creator=13701087609, updateTime=1774853716038, updator=13701087609, issue=Issue{id=1245390004252426256, tenantId=1146029695717560320, journalId=1241701559352995854, year='2024', volume='44', issue='3', pageStart='1', pageEnd='230', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1774853715241, creator=13701087609, updateTime=1774854338522, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1245392618545332491, tenantId=1146029695717560320, journalId=1241701559352995854, issueId=1245390004252426256, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1245392618545332492, tenantId=1146029695717560320, journalId=1241701559352995854, issueId=1245390004252426256, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=61, endPage=72, ext={EN=ArticleExt(id=1245390007851135976, articleId=1245390007599477730, tenantId=1146029695717560320, journalId=1241701559352995854, language=EN, title=Structural damage detection by using densely connected convolutional neural network, columnId=null, journalTitle=Earthquake Engineering and Engineering Dynamics, columnName=null, runingTitle=null, highlight=null, articleAbstract=

A structure damage identification network model ( E-DenseNet) that combines empirical mode decomposition (EMD) and densely connected convolutional network ( DenseNet) is proposed. The collected acceleration signals undergo EMD to obtain multiple intrinsic mode function (IMF) components, and then the weakly correlated IMF components with small absolute values of Pearson correlation coefficients are removed. According to the organization of the input data, three types of E-DenseNet models are set. E-DenseNet1 reconstructs the signal using strongly correlated IMF components to establish one-dimensional single-channel input data. E-DenseNet2 treats each strongly correlated IMF component as a channel to establish one-dimensional multi-channel input data. E-DenseNet3 uses all strongly correlated IMF components to form a two-dimensional matrix to establish two-dimensional single-channel input data. The numerical analysis of a simply supported beam shows that: E-DenseNet1 runs quickly with poor damage detection accuracy. E-DenseNet2 is computationally efficient with high damage detection accuracy. E-DenseNet3 provides good damage detection results but is time-consuming. Compared with one-dimensional multi-channel residual convolutional neural network (ResNet) and standard convolutional neural network (CNN), E-DenseNet2 performs much better in damage detection accuracy. It is thus concluded that E-DenseNet2 ensures both the computational efficiency and the damage detection accuracy. The visualization analysis of E-DenseNet2 exhibits its damage detection process that for different samples of the same damage scenario, a deeper layer outputs more similar features until the fully connected layer provides the most similar output features.

, 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=Qiang YU, Xiaoli CAI, Cui LI, Xuekun ZHU, Xiaoshun WU, Chi ZHU), CN=ArticleExt(id=1245390015350550829, articleId=1245390007599477730, tenantId=1146029695717560320, journalId=1241701559352995854, language=CN, title=基于密集连接卷积神经网络的结构损伤识别, columnId=0, journalTitle=地震工程与工程振动, columnName=, runingTitle=null, highlight=null, articleAbstract=

提出一种经验模态分解(empirical mode decomposition,EMD)和密集连接卷积神经网络(densely connected convolutional network,DenseNet)相结合的结构损伤识别网络模型(E-DenseNet)。对采集的加速度信号进行EMD得到多个本征模态函数(intrinsic mode function,IMF)分量,接着剔除皮尔逊相关系数绝对值较小的弱相关IMF分量。根据输入数据的组织方式,设定3种E-DenseNet模型:E-DenseNet1利用强相关IMF分量重构信号建立一维单通道输入数据;E-DenseNet2将各强相关IMF分量分别视作一个通道来建立一维多通道输入数据;E-DenseNet3利用所有强相关IMF分量组成二维矩阵来建立二维单通道输入数据。某简支梁算例分析表明:E-DenseNet1计算速度快但识别精度低,E-DenseNet2计算速度快且识别精度高,E-DenseNet3识别精度高但计算速度慢;与一维多通道残差卷积神经网络(residual network,ResNet)及标准卷积神经网络(convolutional neural network,CNN)相比,E-DenseNet2的识别精度明显更优;E-DenseNet2因而具有兼顾计算效率和识别精度的优点。E-DenseNet2可视化分析表明了其识别过程,对于相同工况下的不同样本,输出层越深其输出特征越相似,直至全连接层给出极大相似输出特征。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
蔡晓丽(1985—),女,讲师,硕士,主要从事结构健康监测和BIM技术的研究。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=G4ElXCwK5/PDN45KFkSWfQ==, magXml=Eyafil+9w1nXlHZX4Avhxw==, pdfUrl=null, pdf=/AQ7NzeFovThl3+hGiXTfg==, pdfFileSize=29647547, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Y4/PgOMAJkmknIhSs0kzIQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=xkr7P3XwbPMUrMo0ZXOMBw==, mapNumber=null, authorCompany=null, fund=null, authors=

吁强(1997—),男,硕士研究生,主要从事结构健康监测研究。E-mail:

, authorsList=吁强, 蔡晓丽, 李翠, 朱学坤, 伍晓顺, 朱驰)}, authors=[Author(id=1245390015816118612, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yuq202204@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1245390015920976220, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390015816118612, language=EN, stringName=Qiang YU, firstName=Qiang, middleName=null, lastName=YU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1245390016021639525, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390015816118612, language=CN, stringName=吁强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013, bio={"content":"

吁强(1997—),男,硕士研究生,主要从事结构健康监测研究。E-mail:

"}, bioImg=null, bioContent=

吁强(1997—),男,硕士研究生,主要从事结构健康监测研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1245390015602209088, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, xref=1., ext=[AuthorCompanyExt(id=1245390015614792002, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China), AuthorCompanyExt(id=1245390015623180611, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013)])]), Author(id=1245390016143274350, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cxlgyx@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1245390016294269306, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390016143274350, language=EN, stringName=Xiaoli CAI, firstName=Xiaoli, middleName=null, lastName=CAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1245390016386543999, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390016143274350, language=CN, stringName=蔡晓丽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1245390015602209088, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, xref=1., ext=[AuthorCompanyExt(id=1245390015614792002, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China), AuthorCompanyExt(id=1245390015623180611, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013)])]), Author(id=1245390016478818694, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, 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=1245390016579481999, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390016478818694, language=EN, stringName=Cui LI, firstName=Cui, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Information Engineering, Jiangxi V&T College of Communication, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1245390016688533912, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390016478818694, language=CN, stringName=李翠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.江西交通职业技术学院 信息工程学院,江西 南昌 330013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1245390015719649611, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, xref=2., ext=[AuthorCompanyExt(id=1245390015723843916, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015719649611, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Information Engineering, Jiangxi V&T College of Communication, Nanchang 330013, China), AuthorCompanyExt(id=1245390015732232525, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015719649611, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.江西交通职业技术学院 信息工程学院,江西 南昌 330013)])]), Author(id=1245390016780808606, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1245390016885666220, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390016780808606, language=EN, stringName=Xuekun ZHU, firstName=Xuekun, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Information Engineering, Jiangxi V&T College of Communication, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1245390016982135220, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390016780808606, language=CN, stringName=朱学坤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.江西交通职业技术学院 信息工程学院,江西 南昌 330013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1245390015719649611, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, xref=2., ext=[AuthorCompanyExt(id=1245390015723843916, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015719649611, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Information Engineering, Jiangxi V&T College of Communication, Nanchang 330013, China), AuthorCompanyExt(id=1245390015732232525, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015719649611, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.江西交通职业技术学院 信息工程学院,江西 南昌 330013)])]), Author(id=1245390017057632700, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1245390017183461832, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390017057632700, language=EN, stringName=Xiaoshun WU, firstName=Xiaoshun, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1245390017330262480, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390017057632700, language=CN, stringName=伍晓顺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1245390015602209088, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, xref=1., ext=[AuthorCompanyExt(id=1245390015614792002, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China), AuthorCompanyExt(id=1245390015623180611, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013)])]), Author(id=1245390017418342872, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, orderNo=5, 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=1245390017523200480, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390017418342872, language=EN, stringName=Chi ZHU, firstName=Chi, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1245390017632252392, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, authorId=1245390017418342872, language=CN, stringName=朱驰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1245390015602209088, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, xref=1., ext=[AuthorCompanyExt(id=1245390015614792002, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China), AuthorCompanyExt(id=1245390015623180611, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013)])])], keywords=[Keyword(id=1245390017732915694, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, orderNo=1, keyword=damage detection), Keyword(id=1245390017812607480, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, orderNo=2, keyword=neural network), Keyword(id=1245390017930047998, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, orderNo=3, keyword=dynamic test), Keyword(id=1245390018051682818, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, orderNo=4, keyword=sensitivity analysis), Keyword(id=1245390018160734730, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, orderNo=5, keyword=empirical mode decomposition), Keyword(id=1245390018248815118, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, orderNo=1, keyword=损伤识别), Keyword(id=1245390018353672721, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, orderNo=2, keyword=神经网络), Keyword(id=1245390018458530328, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, orderNo=3, keyword=动力测试), Keyword(id=1245390018596942362, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, orderNo=4, keyword=灵敏度分析), Keyword(id=1245390018697605665, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, orderNo=5, keyword=经验模态分解)], refs=[Reference(id=1245390023630107396, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2002, volume=22, issue=3, pageStart=82, pageEnd=90, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=李宏男, 李东升, journalName=地震工程与工程振动, refType=null, unstructuredReference=李宏男,李东升. 土木工程结构安全性评估、健康监测及诊断述评[J]. 地震工程与工程振动200222(3):82-90., articleTitle=土木工程结构安全性评估、健康监测及诊断述评, refAbstract=null), Reference(id=1245390023739159305, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2002, volume=22, issue=3, pageStart=82, pageEnd=90, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=LI Hongnan, LI Dongsheng, journalName=Earthquake Engineering and Engineering Dynamics, refType=null, unstructuredReference=LI Hongnan, LI Dongsheng. Safety assessment, health monitoring and damage diagnosis for structures in civil engineering[J]. Earthquake Engineering and Engineering Dynamics, 2002, 22(3): 82-90. (in Chinese), articleTitle=Safety assessment, health monitoring and damage diagnosis for structures in civil engineering, refAbstract=null), Reference(id=1245390023856599822, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=3, pageStart=486, pageEnd=493, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=张家滨, 唐催, 王磊, journalName=振动. 测试与诊断, refType=null, unstructuredReference=张家滨,唐催,王磊,. 基于频率变化率的结构刚度非均匀退化识别[J]. 振动. 测试与诊断201838(3):486-493., articleTitle=基于频率变化率的结构刚度非均匀退化识别, refAbstract=null), Reference(id=1245390023986623252, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=3, pageStart=486, pageEnd=493, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=ZHANG Jiabin, TANG Cui, WANG Lei, journalName=Journal of Vibration, Measurement & Diagnosis, refType=null, unstructuredReference=ZHANG Jiabin, TANG Cui, WANG Lei, et al. Identification of non-uniform stiffness degradation in structure based on the change rate of frequency[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(3): 486-493. (in Chinese), articleTitle=Identification of non-uniform stiffness degradation in structure based on the change rate of frequency, refAbstract=null), Reference(id=1245390024087286552, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2011, volume=28, issue=2, pageStart=1, pageEnd=11, 17, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=朱宏平, 余璟, 张俊兵, journalName=工程力学, refType=null, unstructuredReference=朱宏平,余璟,张俊兵. 结构损伤动力检测与健康监测研究现状与展望[J]. 工程力学201128(2):1-11, 17., articleTitle=结构损伤动力检测与健康监测研究现状与展望, refAbstract=null), Reference(id=1245390024225698587, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2011, volume=28, issue=2, pageStart=1, pageEnd=11, 17, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=ZHU Hongping, YU Jing, ZHANG Junbing, journalName=Engineering Mechanics, refType=null, unstructuredReference=ZHU Hongping, YU Jing, ZHANG Junbing. A summary review and advantages of vibration-based damage identification methods in structural health monitoring[J]. Engineering Mechanics, 2011, 28(2): 1-11, 17. (in Chinese), articleTitle=A summary review and advantages of vibration-based damage identification methods in structural health monitoring, refAbstract=null), Reference(id=1245390024322167585, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2015, volume=521, issue=null, pageStart=436, pageEnd=444, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=LECUN Y, BENGIO Y, HINTON G, journalName=Nature, refType=null, unstructuredReference=LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521: 436-444., articleTitle=Deep learning, refAbstract=null), Reference(id=1245390024427025190, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=139, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=FLAH M, RAGAB M, LAZHARI M, journalName=Automation in Construction, refType=null, unstructuredReference=FLAH M, RAGAB M, LAZHARI M, et al. Localization and classification of structural damage using deep learning single-channel signal-based measurement[J]. Automation in Construction, 2022, 139: 104271., articleTitle=Localization and classification of structural damage using deep learning single-channel signal-based measurement, refAbstract=null), Reference(id=1245390024594797354, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=张伟, journalName=null, refType=null, unstructuredReference=张伟. 基于卷积神经网络的轴承故障诊断算法研究[D]. 哈尔滨:哈尔滨工业大学,2017., articleTitle=基于卷积神经网络的轴承故障诊断算法研究, refAbstract=null), Reference(id=1245390024678683437, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=ZHANG Wei, journalName=null, refType=null, unstructuredReference=ZHANG Wei. Study on bearing fault diagnosis algorithm based on convolutional neural network[D]. Harbin: Harbin Institute of Technology, 2017. (in Chinese), articleTitle=Study on bearing fault diagnosis algorithm based on convolutional neural network, refAbstract=null), Reference(id=1245390024758375216, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=12, pageStart=3228, pageEnd=3239, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=李泽东, 李志农, 陶俊勇, journalName=兵工学报, refType=null, unstructuredReference=李泽东,李志农,陶俊勇,. 基于特征融合的注意力增强卷积神经网络的航空发动机滚动轴承故障诊断方法[J]. 兵工学报202243(12):3228-3239., articleTitle=基于特征融合的注意力增强卷积神经网络的航空发动机滚动轴承故障诊断方法, refAbstract=null), Reference(id=1245390024892592947, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=12, pageStart=3228, pageEnd=3239, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=LI Zedong, LI Zhinong, TAO Junyong, journalName=Acta Armamentarii, refType=null, unstructuredReference=LI Zedong, LI Zhinong, TAO Junyong, et al. Fault diagnosis for aero-engine rolling bearings based on an attention augmented convolutional neural network with feature fusion[J]. Acta Armamentarii, 2022, 43(12): 3228-3239. (in Chinese), articleTitle=Fault diagnosis for aero-engine rolling bearings based on an attention augmented convolutional neural network with feature fusion, refAbstract=null), Reference(id=1245390024963896120, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=1, pageStart=159, pageEnd=167, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=李雪松, 马宏伟, 林逸洲, journalName=振动与冲击, refType=null, unstructuredReference=李雪松,马宏伟,林逸洲. 基于卷积神经网络的结构损伤识别[J]. 振动与冲击201938(1):159-167., articleTitle=基于卷积神经网络的结构损伤识别, refAbstract=null), Reference(id=1245390025068753723, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=1, pageStart=159, pageEnd=167, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=LI Xuesong, MA Hongwei, LIN Yizhou, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=LI Xuesong, MA Hongwei, LIN Yizhou. Structural damage identification based on convolution neural network[J]. Journal of Vibration and Shock, 2019, 38(1): 159-167. (in Chinese), articleTitle=Structural damage identification based on convolution neural network, refAbstract=null), Reference(id=1245390025156834110, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=3, pageStart=155, pageEnd=161, 173, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=罗雨舟, 向天宇, 郝柳青, journalName=土木工程与管理学报, refType=null, unstructuredReference=罗雨舟,向天宇,郝柳青. 卷积神经网络在结构损伤检测中的应用[J]. 土木工程与管理学报202037(3):155-161, 173., articleTitle=卷积神经网络在结构损伤检测中的应用, refAbstract=null), Reference(id=1245390025278468929, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=3, pageStart=155, pageEnd=161, 173, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=LUO Yuzhou, XIANG Tianyu, HAO Liuqing, journalName=Journal of Civil Engineering and Management, refType=null, unstructuredReference=LUO Yuzhou, XIANG Tianyu, HAO Liuqing. Application of convolutional neural network in structural damage diagnosis[J]. Journal of Civil Engineering and Management, 2020, 37(3): 155-161, 173. (in Chinese), articleTitle=Application of convolutional neural network in structural damage diagnosis, refAbstract=null), Reference(id=1245390025362355013, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=6, pageStart=29, pageEnd=37, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=李书进, 赵源, 孔凡, journalName=建筑科学与工程学报, refType=null, unstructuredReference=李书进,赵源,孔凡,. 卷积神经网络在结构损伤诊断中的应用[J]. 建筑科学与工程学报202037(6):29-37., articleTitle=卷积神经网络在结构损伤诊断中的应用, refAbstract=null), Reference(id=1245390025463018312, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=6, pageStart=29, pageEnd=37, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=LI Shujin, ZHAO Yuan, KONG Fan, journalName=Journal of Architecture and Civil Engineering, refType=null, unstructuredReference=LI Shujin, ZHAO Yuan, KONG Fan, et al. Application of convolutional neural network in structural damage identification[J]. Journal of Architecture and Civil Engineering, 2020, 37(6): 29-37. (in Chinese), articleTitle=Application of convolutional neural network in structural damage identification, refAbstract=null), Reference(id=1245390025546904396, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=1, pageStart=169, pageEnd=176, 202, 203, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=骆勇鹏, 王林堃, 郭旭, journalName=振动.测试与诊断, refType=null, unstructuredReference=骆勇鹏,王林堃,郭旭,. 利用单传感器数据基于GAF-CNN的结构损伤识别[J]. 振动.测试与诊断202242(1):169-176, 202, 203., articleTitle=利用单传感器数据基于GAF-CNN的结构损伤识别, refAbstract=null), Reference(id=1245390025634984785, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=1, pageStart=169, pageEnd=176, 202, 203, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=LUO Yongpeng, WANG Linkun, GUO Xu, journalName=Journal of Vibration, Measurement & Diagnosis, refType=null, unstructuredReference=LUO Yongpeng, WANG Linkun, GUO Xu, et al. Structural damage identification using single sensor data based on GAF-CNN[J]. Journal of Vibration, Measurement & Diagnosis, 2022, 42(1): 169-176, 202, 203. (in Chinese), articleTitle=Structural damage identification using single sensor data based on GAF-CNN, refAbstract=null), Reference(id=1245390025752425301, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=1994, volume=5, issue=2, pageStart=157, pageEnd=166, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=BENGIO Y, SIMARD P, FRASCONI P, journalName=IEEE Transactions on Neural Networks, refType=null, unstructuredReference=BENGIO Y, SIMARD P, FRASCONI P. Learning long-term dependencies with gradient descent is difficult[J]. IEEE Transactions on Neural Networks, 1994, 5(2): 157-166., articleTitle=Learning long-term dependencies with gradient descent is difficult, refAbstract=null), Reference(id=1245390025827922776, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=2261, pageEnd=2269, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=HUANG G, LIU Z, VAN DER MAATEN L, journalName=null, refType=null, unstructuredReference=HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA. Piscataway, NJ, USA: IEEE, 2017: 2261-2269., articleTitle=Densely connected convolutional networks, refAbstract=null), Reference(id=1245390025916003162, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=770, pageEnd=778, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=HE K M, ZHANG X Y, REN S Q, journalName=null, refType=null, unstructuredReference=HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. Piscataway, NJ, USA: IEEE, 2016: 770-778., articleTitle=Deep residual learning for image recognition, refAbstract=null), Reference(id=1245390026020860765, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2021, volume=245, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=WANG R H, LI J, Chen cho, journalName=Engineering Structures, refType=null, unstructuredReference=WANG R H, LI J, Chen cho, et al. Densely connected convolutional networks for vibration based structural damage identification[J]. Engineering Structures, 2021, 245: 112871., articleTitle=Densely connected convolutional networks for vibration based structural damage identification, refAbstract=null), Reference(id=1245390026108941153, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=4, pageStart=145, pageEnd=156, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=骆勇鹏, 王林堃, 廖飞宇, journalName=地震工程与工程振动, refType=null, unstructuredReference=骆勇鹏,王林堃,廖飞宇,. 基于一维卷积神经网络的结构损伤识别[J]. 地震工程与工程振动202141(4):145-156., articleTitle=基于一维卷积神经网络的结构损伤识别, refAbstract=null), Reference(id=1245390026217993061, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=4, pageStart=145, pageEnd=156, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=LUO Yongpeng, WANG Linkun, LIAO Feiyu, journalName=Earthquake Engineering and Engineering Dynamics, refType=null, unstructuredReference=LUO Yongpeng, WANG Linkun, LIAO Feiyu, et al. Vibration-based structural damage identification by 1-dimensional convolutional neural network[J]. Earthquake Engineering and Engineering Dynamics, 2021, 41(4): 145-156. (in Chinese), articleTitle=Vibration-based structural damage identification by 1-dimensional convolutional neural network, refAbstract=null), Reference(id=1245390026327044968, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=4, pageStart=546, pageEnd=552, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=骆剑彬, 刘越生, 姜绍飞, journalName=福州大学学报(自然科学版), refType=null, unstructuredReference=骆剑彬,刘越生,姜绍飞,. 基于卷积神经网络和迁移学习的结构损伤识别[J]. 福州大学学报(自然科学版)202250(4):546-552., articleTitle=基于卷积神经网络和迁移学习的结构损伤识别, refAbstract=null), Reference(id=1245390026423513963, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=4, pageStart=546, pageEnd=552, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=LUO Jianbin, LIU Yuesheng, JIANG Shaofei, journalName=Journal of Fuzhou University (Natural Science Edition), refType=null, unstructuredReference=LUO Jianbin, LIU Yuesheng, JIANG Shaofei, et al. Structural damage detection based on convolutional neural networks and transfer learning[J].Journal of Fuzhou University (Natural Science Edition), 2022, 50(4): 546-552. (in Chinese), articleTitle=Structural damage detection based on convolutional neural networks and transfer learning, refAbstract=null), Reference(id=1245390026511594349, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=20, pageStart=55, pageEnd=66, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=叶壮, 余建波, journalName=振动与冲击, refType=null, unstructuredReference=叶壮,余建波. 基于多通道一维卷积神经网络特征学习的齿轮箱故障诊断方法[J]. 振动与冲击202039(20):55-66., articleTitle=基于多通道一维卷积神经网络特征学习的齿轮箱故障诊断方法, refAbstract=null), Reference(id=1245390026591286129, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=20, pageStart=55, pageEnd=66, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=YE Zhuang, YU Jianbo, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=YE Zhuang, YU Jianbo. Gearbox fault diagnosis based on feature learning of multi-channel one-dimensional convolutional neural network[J]. Journal of Vibration and Shock, 2020, 39(20): 55-66. (in Chinese), articleTitle=Gearbox fault diagnosis based on feature learning of multi-channel one-dimensional convolutional neural network, refAbstract=null), Reference(id=1245390026704532341, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=1, pageStart=132, pageEnd=142, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=张健飞, 蔡东成, journalName=地震工程与工程振动, refType=null, unstructuredReference=张健飞,蔡东成. 基于多尺度卷积神经网络的结构损伤识别研究[J]. 地震工程与工程振动202242(1):132-142., articleTitle=基于多尺度卷积神经网络的结构损伤识别研究, refAbstract=null), Reference(id=1245390026784224120, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=1, pageStart=132, pageEnd=142, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=ZHANG Jianfei, CAI Dongcheng, journalName=Earthquake Engineering and Engineering Dynamics, refType=null, unstructuredReference=ZHANG Jianfei, CAI Dongcheng. Research on structural damage identification based on multi-scale convolutional neural networks[J]. Earthquake Engineering and Engineering Dynamics, 2022, 42(1): 132-142. (in Chinese), articleTitle=Research on structural damage identification based on multi-scale convolutional neural networks, refAbstract=null), Reference(id=1245390026901664636, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=4, pageStart=188, pageEnd=195, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=戴伦, 张文达, 田石柱, journalName=地震工程与工程振动, refType=null, unstructuredReference=戴伦,张文达,田石柱. 桥梁线弹性地震反应的卷积神经网络估计[J]. 地震工程与工程振动202141(4):188-195., articleTitle=桥梁线弹性地震反应的卷积神经网络估计, refAbstract=null), Reference(id=1245390027006522239, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=4, pageStart=188, pageEnd=195, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=DAI Lun, ZHANG Wenda, TIAN Shizhu, journalName=Earthquake Engineering and Engineering Dynamics, refType=null, unstructuredReference=DAI Lun, ZHANG Wenda, TIAN Shizhu. Convolutional neural network estimation of bridge linear elastic seismic response[J]. Earthquake Engineering and Engineering Dynamics, 2021, 41(4): 188-195. (in Chinese), articleTitle=Convolutional neural network estimation of bridge linear elastic seismic response, refAbstract=null), Reference(id=1245390027086214017, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=1998, volume=454, issue=1971, pageStart=903, pageEnd=995, url=null, language=null, rfNumber=[21], rfOrder=34, authorNames=HUANG N E, SHEN Z, LONG S R, journalName=Proceedings of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences, refType=null, unstructuredReference=HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995., articleTitle=The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, refAbstract=null), Reference(id=1245390027182683011, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=5, pageStart=1075, pageEnd=1080, url=null, language=null, rfNumber=[22], rfOrder=35, authorNames=陶洋, 祝小钧, 杨柳, journalName=小型微型计算机系统, refType=null, unstructuredReference=陶洋,祝小钧,杨柳. 基于皮尔逊相关系数和信息熵的多传感器数据融合[J]. 小型微型计算机系统202344(5):1075-1080., articleTitle=基于皮尔逊相关系数和信息熵的多传感器数据融合, refAbstract=null), Reference(id=1245390027283346309, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=5, pageStart=1075, pageEnd=1080, url=null, language=null, rfNumber=[22], rfOrder=36, authorNames=TAO Yang, ZHU Xiaojun, YANG Liu, journalName=Journal of Chinese Computer Systems, refType=null, unstructuredReference=TAO Yang, ZHU Xiaojun, YANG Liu. Multi-sensor data fusion based on pearson coefficient and information entropy[J]. Journal of Chinese Computer Systems, 2023, 44(5): 1075-1080. (in Chinese), articleTitle=Multi-sensor data fusion based on pearson coefficient and information entropy, refAbstract=null), Reference(id=1245390027388203913, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=17, pageStart=213, pageEnd=220, 261, url=null, language=null, rfNumber=[23], rfOrder=37, authorNames=伍晓顺, 程润辉, journalName=振动与冲击, refType=null, unstructuredReference=伍晓顺,程润辉. 阶跃激励下网架结构的动力响应扩展及其误差分析[J]. 振动与冲击202241(17):213-220, 261., articleTitle=阶跃激励下网架结构的动力响应扩展及其误差分析, refAbstract=null), Reference(id=1245390027472089994, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=17, pageStart=213, pageEnd=220, 261, url=null, language=null, rfNumber=[23], rfOrder=38, authorNames=WU Xiaoshun, CHENG Runhui, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=WU Xiaoshun, CHENG Runhui. Dynamic response expansion and its error analysis of space truss structures under step excitation[J]. Journal of Vibration and Shock, 2022, 41(17): 213-220, 261. (in Chinese), articleTitle=Dynamic response expansion and its error analysis of space truss structures under step excitation, refAbstract=null)], funds=[Fund(id=1245390023281980151, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, awardId=51868026, language=CN, fundingSource=国家自然科学基金项目(51868026), fundOrder=null, country=null), Fund(id=1245390023399420667, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, awardId=20202BAB204028, language=CN, fundingSource=江西省自然科学基金项目(20202BAB204028), fundOrder=null, country=null), Fund(id=1245390023516861183, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, awardId=YC2022-S695, language=CN, fundingSource=江西省研究生创新专项资金项目(YC2022-S695), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1245390015602209088, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, xref=1., ext=[AuthorCompanyExt(id=1245390015614792002, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China), AuthorCompanyExt(id=1245390015623180611, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015602209088, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013)]), AuthorCompany(id=1245390015719649611, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, xref=2., ext=[AuthorCompanyExt(id=1245390015723843916, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015719649611, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Information Engineering, Jiangxi V&T College of Communication, Nanchang 330013, China), AuthorCompanyExt(id=1245390015732232525, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, companyId=1245390015719649611, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.江西交通职业技术学院 信息工程学院,江西 南昌 330013)])], figs=[ArticleFig(id=1245390018877960748, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 1, caption=Diagram of a four-layer densely connected block (k = 3), figureFileSmall=C4qov9v8RNYM2G9jjLxaqg==, figureFileBig=Y4/PgOMAJkmknIhSs0kzIQ==, tableContent=null), ArticleFig(id=1245390018961846836, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图1, caption=某4层密集连接块示意图(k = 3), figureFileSmall=C4qov9v8RNYM2G9jjLxaqg==, figureFileBig=Y4/PgOMAJkmknIhSs0kzIQ==, tableContent=null), ArticleFig(id=1245390019196727873, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 2, caption=Diagram of DenseNet, figureFileSmall=VgZbAGdYDEKMoO9gUwU1JQ==, figureFileBig=8FsUruJr/rTa8ZlZkt9G5w==, tableContent=null), ArticleFig(id=1245390019301585479, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图2, caption=DenseNet示意图, figureFileSmall=VgZbAGdYDEKMoO9gUwU1JQ==, figureFileBig=8FsUruJr/rTa8ZlZkt9G5w==, tableContent=null), ArticleFig(id=1245390019410637390, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 3, caption=Illustration of the E-DensNet model architecture, figureFileSmall=EzekOP1H9CbTiblnhKNcbA==, figureFileBig=FwHI287gyHgjh/5ll0gMIQ==, tableContent=null), ArticleFig(id=1245390019498717778, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图3, caption=E-DensNet模型架构示意图, figureFileSmall=EzekOP1H9CbTiblnhKNcbA==, figureFileBig=FwHI287gyHgjh/5ll0gMIQ==, tableContent=null), ArticleFig(id=1245390019616158294, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 4, caption=A simply supported I-beam, figureFileSmall=D1Lm8S1Z3evZpTSUWK5Jug==, figureFileBig=sFQAZu+O86vgXI86ZL92Zw==, tableContent=null), ArticleFig(id=1245390019750376031, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图4, caption=某简支工字梁, figureFileSmall=D1Lm8S1Z3evZpTSUWK5Jug==, figureFileBig=sFQAZu+O86vgXI86ZL92Zw==, tableContent=null), ArticleFig(id=1245390019855233638, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 5, caption=Slide window resampling schematic diagram, figureFileSmall=7YKyzwFB22VPlUO7BOgbdQ==, figureFileBig=bp7dlPssD+WNusWoHApwEg==, tableContent=null), ArticleFig(id=1245390019968479852, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图5, caption=滑窗重采样, figureFileSmall=7YKyzwFB22VPlUO7BOgbdQ==, figureFileBig=bp7dlPssD+WNusWoHApwEg==, tableContent=null), ArticleFig(id=1245390020073337456, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 6, caption=Damage detection results of DenseNet and E-Densenet1, E-DenseNet2, E-DenseNet3 (Case 15), figureFileSmall=DF13uh5PlDpxPjW2IqnK5Q==, figureFileBig=2mIWb33VtjmNmLiffbpR4Q==, tableContent=null), ArticleFig(id=1245390020283052667, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图6, caption=DenseNet,E-DenseNet1,E-DenseNet2,E-DenseNet3的损伤识别结果(工况15), figureFileSmall=DF13uh5PlDpxPjW2IqnK5Q==, figureFileBig=2mIWb33VtjmNmLiffbpR4Q==, tableContent=null), ArticleFig(id=1245390020379521663, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 7, caption=Changing trend of MSE in training set and test set, figureFileSmall=73YN5M2X5sbaN8VDqRNXFQ==, figureFileBig=RSYPxGrFtYz+lVCPUefj8g==, tableContent=null), ArticleFig(id=1245390020467602052, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图7, caption=训练集和测试集的MSE变化趋势, figureFileSmall=73YN5M2X5sbaN8VDqRNXFQ==, figureFileBig=RSYPxGrFtYz+lVCPUefj8g==, tableContent=null), ArticleFig(id=1245390020572459660, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 8, caption=Damage detection results of DenseNet2, ResNet and CNN (Case 5), figureFileSmall=NTuDAwLqnUC78u72qNR/gQ==, figureFileBig=fnTQ1QxnQR+uOpzUVX6EXQ==, tableContent=null), ArticleFig(id=1245390020664734352, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图8, caption=DenseNet2、ResNet和CNN的损伤识别结果(工况5), figureFileSmall=NTuDAwLqnUC78u72qNR/gQ==, figureFileBig=fnTQ1QxnQR+uOpzUVX6EXQ==, tableContent=null), ArticleFig(id=1245390020769591957, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 9, caption=Randomly selected 1D multi-channel input data (IMFs), figureFileSmall=1Hz7FRT5M7AE7oiYDnI7LA==, figureFileBig=qwtPLLR58FL18pYINRT9Vw==, tableContent=null), ArticleFig(id=1245390020861866651, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图9, caption=随机选取的一维多通道输入数据(IMFs), figureFileSmall=1Hz7FRT5M7AE7oiYDnI7LA==, figureFileBig=qwtPLLR58FL18pYINRT9Vw==, tableContent=null), ArticleFig(id=1245390020962529955, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 10, caption=The last convolutional layer features output of the first densely connected block, figureFileSmall=yBM0RwpfpTNXc4oR0oXg1A==, figureFileBig=ymP3xmzCJd5Z+foa1wjhAg==, tableContent=null), ArticleFig(id=1245390021063193252, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图10, caption=第一个密集连接块最后一层卷积层特征输出, figureFileSmall=yBM0RwpfpTNXc4oR0oXg1A==, figureFileBig=ymP3xmzCJd5Z+foa1wjhAg==, tableContent=null), ArticleFig(id=1245390021176439464, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 11, caption=The last convolutional layer features output of the second densely connected block, figureFileSmall=nIBeP7DCiIlA42P3ePd2IQ==, figureFileBig=JicdC6Mj4/eu5sOR7kI5TQ==, tableContent=null), ArticleFig(id=1245390021298074284, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图11, caption=第二个密集连接块最后一层卷积层特征输出, figureFileSmall=nIBeP7DCiIlA42P3ePd2IQ==, figureFileBig=JicdC6Mj4/eu5sOR7kI5TQ==, tableContent=null), ArticleFig(id=1245390021440680624, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 12, caption=The last convolutional layer features output of the third densely connected block, figureFileSmall=6LxX8nTHmyjIW1rTXQ6XhA==, figureFileBig=sdosLjheJXeha+Xo5T8UBw==, tableContent=null), ArticleFig(id=1245390021583286967, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图12, caption=第三个密集连接块最后一层卷积层特征输出, figureFileSmall=6LxX8nTHmyjIW1rTXQ6XhA==, figureFileBig=sdosLjheJXeha+Xo5T8UBw==, tableContent=null), ArticleFig(id=1245390021709116092, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 13, caption=Global average pooling output, figureFileSmall=y8J8i0/nYdf3VZDh5ydcBw==, figureFileBig=qmO4AowFezLkyRiLtV9nGQ==, tableContent=null), ArticleFig(id=1245390021834945217, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图13, caption=全局平均池化输出, figureFileSmall=y8J8i0/nYdf3VZDh5ydcBw==, figureFileBig=qmO4AowFezLkyRiLtV9nGQ==, tableContent=null), ArticleFig(id=1245390021964968647, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Fig. 14, caption=Fully connected layer output, figureFileSmall=h6+WjJblST5NNKyUShbwSA==, figureFileBig=lo/qKpw+o8bGT60VkyTKXQ==, tableContent=null), ArticleFig(id=1245390022090797770, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=图14, caption=全连接层输出, figureFileSmall=h6+WjJblST5NNKyUShbwSA==, figureFileBig=lo/qKpw+o8bGT60VkyTKXQ==, tableContent=null), ArticleFig(id=1245390022204043980, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Table 1, caption=

Damage condition setting

, figureFileSmall=null, figureFileBig=null, tableContent=
工况号损伤单元损伤程度工况号损伤单元损伤程度工况号损伤单元损伤程度
11050.0451990.285
210.0751150.30020100.120
310.211260.15021100.195
420.1351360.165223,60.150,0.165
520.271470.060235,70.30,0.06
630.0151570.255241,3,50.075,0.180,0.300
730.181680.090253,6,90.180,0.150,0.285
840.1051780.225
940.2401890.030
), ArticleFig(id=1245390022317290193, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=表1, caption=

损伤工况设置

, figureFileSmall=null, figureFileBig=null, tableContent=
工况号损伤单元损伤程度工况号损伤单元损伤程度工况号损伤单元损伤程度
11050.0451990.285
210.0751150.30020100.120
310.211260.15021100.195
420.1351360.165223,60.150,0.165
520.271470.060235,70.30,0.06
630.0151570.255241,3,50.075,0.180,0.300
730.181680.090253,6,90.180,0.150,0.285
840.1051780.225
940.2401890.030
), ArticleFig(id=1245390022443119317, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Table 2, caption=

Hyperparameter settings for E-DenseNet

, figureFileSmall=null, figureFileBig=null, tableContent=
结构层次E-DenseNet1、E-DenseNet2E-DenseNet3
超参数输出尺寸超参数输出尺寸
1#卷积层50×1Conv1D,strides =(20,1)100×2450×1Conv2D,strides =(20,1)100×8×24
1#密集连接块100×96100×8×96
1#过渡层1×1Conv1D100×481×1Conv2D100×8×48
5×1Maxpooling,strides =(5,1)20×485×1Maxpooling,strides =(5,2)20×4×48
2#密集连接块20×12020×4×120
2#过渡层1×1Conv1D20×601×1Conv2D20×4×60
5×1Maxpooling,strides =(5,1)4×605×1Maxpooling,strides =(5,2)4×1×60
3#密集连接块4×1324×1×132
目标层4×1Globalavepooling1×1324×1Globalavepooling1×1×132
10×1fullyconnected,tan h1010×1fullyconnected,tan h10
), ArticleFig(id=1245390022581531356, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=表2, caption=

E-DenseNet超参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
结构层次E-DenseNet1、E-DenseNet2E-DenseNet3
超参数输出尺寸超参数输出尺寸
1#卷积层50×1Conv1D,strides =(20,1)100×2450×1Conv2D,strides =(20,1)100×8×24
1#密集连接块100×96100×8×96
1#过渡层1×1Conv1D100×481×1Conv2D100×8×48
5×1Maxpooling,strides =(5,1)20×485×1Maxpooling,strides =(5,2)20×4×48
2#密集连接块20×12020×4×120
2#过渡层1×1Conv1D20×601×1Conv2D20×4×60
5×1Maxpooling,strides =(5,1)4×605×1Maxpooling,strides =(5,2)4×1×60
3#密集连接块4×1324×1×132
目标层4×1Globalavepooling1×1324×1Globalavepooling1×1×132
10×1fullyconnected,tan h1010×1fullyconnected,tan h10
), ArticleFig(id=1245390022728332000, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Table 3, caption=

Evaluation results of E-DenseNet and DenseNet

, figureFileSmall=null, figureFileBig=null, tableContent=
模型类型数据类型RMSE单条样本用时/ms
DenseNet无噪声0.49442.00×10–31.0
SNR=10 dB0.49642.00×10–3
SNR=5 dB0.46202.20×10–3
E-DenseNet1无噪声0.94511.48×10–41.0
SNR=10 dB0.90092.98×10–4
SNR=5 dB0.86314.02×10–4
E-DenseNet2无噪声0.99865.32×10–61.3
SNR=10 dB0.99232.51×10–5
SNR=5 dB0.98962.96×10–5
E-DenseNet3无噪声0.99898.84×10–612
SNR=10 dB0.98813.05×10–5
SNR=5 dB0.97636.51×10–5
), ArticleFig(id=1245390022845772520, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=表3, caption=

E-DenseNet,DenseNet评估结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型类型数据类型RMSE单条样本用时/ms
DenseNet无噪声0.49442.00×10–31.0
SNR=10 dB0.49642.00×10–3
SNR=5 dB0.46202.20×10–3
E-DenseNet1无噪声0.94511.48×10–41.0
SNR=10 dB0.90092.98×10–4
SNR=5 dB0.86314.02×10–4
E-DenseNet2无噪声0.99865.32×10–61.3
SNR=10 dB0.99232.51×10–5
SNR=5 dB0.98962.96×10–5
E-DenseNet3无噪声0.99898.84×10–612
SNR=10 dB0.98813.05×10–5
SNR=5 dB0.97636.51×10–5
), ArticleFig(id=1245390023021933292, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=EN, label=Table 4, caption=

Evaluation results of the three models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型类型数据类型RMSE单条样本用时/ ms
E-DenseNet2无噪声0.998605.32×10-61.3
SNR=10 dB0.992302.51×10-5
SNR=5 dB0.989602.96×10-5
ResNet无噪声0.914203.31×10-41.0
SNR=10 dB0.892703.46×10-4
SNR=5 dB0.853204.03×10-4
CNN无噪声0.444802.20×10-32.0
SNR=10 dB0.045742.10×10-3
SNR=5 dB0.412402.32×10-3
), ArticleFig(id=1245390023143568114, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1245390007599477730, language=CN, label=表4, caption=

3种模型的评估结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型类型数据类型RMSE单条样本用时/ ms
E-DenseNet2无噪声0.998605.32×10-61.3
SNR=10 dB0.992302.51×10-5
SNR=5 dB0.989602.96×10-5
ResNet无噪声0.914203.31×10-41.0
SNR=10 dB0.892703.46×10-4
SNR=5 dB0.853204.03×10-4
CNN无噪声0.444802.20×10-32.0
SNR=10 dB0.045742.10×10-3
SNR=5 dB0.412402.32×10-3
)], attaches=null, journal=Journal(id=1241699397025705997, delFlag=0, nameCn=地震工程与工程振动, nameEn=Earthquake Engineering and Engineering Dynamics, nameHistory1=null, nameHistory2=null, issn=1000-1301, eissn=null, cn=23-1157/P, coden=null, periodic=1, 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=/vhigrb0Ie5dk9EvytPyQg==, journalPrice=null, startedYear=null, abbrevIsoEn=Earthquake Engineering and Engineering Dynamics, journalRemark=null, publicationField=null, createdTime=1773973805912, updatedTime=1773974475511, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=E, firstLetterEn=E, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=/vhigrb0Ie5dk9EvytPyQg==, picEn=mP4JjBszibypE3yTy4J1ag==, jcr=null, cjcr=null, exts=[JournalExt(id=1241702205619753886, language=CN, name=地震工程与工程振动, 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=1773974475531, updatedTime=1773974475531, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://dzgc.paperonce.org/#/Login, submissionEditorUrl=https://dzgc.paperonce.org/#/Login, submissionReviewUrl=https://dzgc.paperonce.org/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1241702205665891231, language=EN, name=Earthquake Engineering and Engineering Dynamics, 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=1773974475542, updatedTime=1773974475542, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://dzgc.paperonce.org/#/Login, submissionEditorUrl=https://dzgc.paperonce.org/#/Login, submissionReviewUrl=https://dzgc.paperonce.org/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1241701559352995854, websiteList=[Website(id=1241702575498646432, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1241701559352995854, 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/dzgcygczd/CN, language=CN, createTime=1773974563717, createBy=18614031015, updateTime=1773974590635, updateBy=18614031015, name=地震工程与工程振动-中文, tplId=1146099689490845704, title=地震工程与工程振动, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1241703043805270973, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=articleTextType, value=kx, createTime=1773974675370, updateTime=1773974675370, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043771716538, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=banner, value=null, createTime=1773974675362, updateTime=1773974675362, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043830436800, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=grayFlag, value=0, createTime=1773974675376, updateTime=1773974675376, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043759133625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=logo, value=https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/file/pic?fileId=C6sfoMWhaI5iihfhixVjYQ==, createTime=1773974675359, updateTime=1773974675359, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043843019714, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=minRunFlag, value=0, createTime=1773974675379, updateTime=1773974675379, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043801076668, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/file/pic, createTime=1773974675369, updateTime=1773974675369, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043838825409, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=silenceFlag, value=0, createTime=1773974675378, updateTime=1773974675378, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043780105147, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1773974675364, updateTime=1773974675364, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043813659582, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=themeColor, value=null, createTime=1773974675372, updateTime=1773974675372, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043822048191, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=themeStyle, value=null, createTime=1773974675374, updateTime=1773974675374, creator=18614031015, updator=18614031015)]), Website(id=1241702575569949602, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1241701559352995854, 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/dzgcygczd/EN, language=EN, createTime=1773974563735, createBy=18614031015, updateTime=1773974605208, updateBy=18614031015, name=地震工程与工程振动-英文, tplId=1146101810881728533, title=Earthquake Engineering and Engineering Dynamics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1241703068497138631, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=articleTextType, value=kx, createTime=1773974681257, updateTime=1773974681257, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068480361412, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=banner, value=null, createTime=1773974681253, updateTime=1773974681253, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068513915850, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=grayFlag, value=0, createTime=1773974681261, updateTime=1773974681261, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068471972803, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=logo, value=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/file/pic?fileId=C6sfoMWhaI5iihfhixVjYQ==, createTime=1773974681251, updateTime=1773974681251, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068530693068, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=minRunFlag, value=0, createTime=1773974681265, updateTime=1773974681265, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068492944326, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/file/pic, createTime=1773974681256, updateTime=1773974681256, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068522304459, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=silenceFlag, value=0, createTime=1773974681263, updateTime=1773974681263, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068484555717, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1773974681254, updateTime=1773974681254, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068505527240, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=themeColor, value=null, createTime=1773974681259, updateTime=1773974681259, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068509721545, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=themeStyle, value=null, createTime=1773974681260, updateTime=1773974681260, creator=18614031015, updator=18614031015)])], journalTitle=地震工程与工程振动, weixinUrl=null, journalUrl=https://dzgc.paperonce.org/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Earthquake Engineering and Engineering Dynamics, journalPhotoCn=/vhigrb0Ie5dk9EvytPyQg==, journalPhotoEn=mP4JjBszibypE3yTy4J1ag==, journalFirstLetter=E, 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/dzgcygczd/CN/10.13197/j.eeed.2024.0306, detailUrlEn=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/10.13197/j.eeed.2024.0306, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/PDF/10.13197/j.eeed.2024.0306, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/PDF/10.13197/j.eeed.2024.0306, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于密集连接卷积神经网络的结构损伤识别
收藏切换
PDF下载
吁强 1 , 蔡晓丽 1 , 李翠 2 , 朱学坤 2 , 伍晓顺 1 , 朱驰 1
地震工程与工程振动 | 2024,44(3): 61-72
收起
收藏切换
地震工程与工程振动 | 2024, 44(3): 61-72
基于密集连接卷积神经网络的结构损伤识别
全屏
吁强1 , 蔡晓丽1 , 李翠2, 朱学坤2, 伍晓顺1, 朱驰1
作者信息
  • 1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013
  • 2.江西交通职业技术学院 信息工程学院,江西 南昌 330013
  • 吁强(1997—),男,硕士研究生,主要从事结构健康监测研究。E-mail:

通讯作者:

蔡晓丽(1985—),女,讲师,硕士,主要从事结构健康监测和BIM技术的研究。E-mail:
Structural damage detection by using densely connected convolutional neural network
Qiang YU1 , Xiaoli CAI1 , Cui LI2, Xuekun ZHU2, Xiaoshun WU1, Chi ZHU1
Affiliations
  • 1.School of Civil and Surveying and Mapping Engineering (Nanchang), Jiangxi University of Science and Technology, Nanchang 330013, China
  • 2.College of Information Engineering, Jiangxi V&T College of Communication, Nanchang 330013, China
doi: 10.13197/j.eeed.2024.0306
文章导航
收藏切换

提出一种经验模态分解(empirical mode decomposition,EMD)和密集连接卷积神经网络(densely connected convolutional network,DenseNet)相结合的结构损伤识别网络模型(E-DenseNet)。对采集的加速度信号进行EMD得到多个本征模态函数(intrinsic mode function,IMF)分量,接着剔除皮尔逊相关系数绝对值较小的弱相关IMF分量。根据输入数据的组织方式,设定3种E-DenseNet模型:E-DenseNet1利用强相关IMF分量重构信号建立一维单通道输入数据;E-DenseNet2将各强相关IMF分量分别视作一个通道来建立一维多通道输入数据;E-DenseNet3利用所有强相关IMF分量组成二维矩阵来建立二维单通道输入数据。某简支梁算例分析表明:E-DenseNet1计算速度快但识别精度低,E-DenseNet2计算速度快且识别精度高,E-DenseNet3识别精度高但计算速度慢;与一维多通道残差卷积神经网络(residual network,ResNet)及标准卷积神经网络(convolutional neural network,CNN)相比,E-DenseNet2的识别精度明显更优;E-DenseNet2因而具有兼顾计算效率和识别精度的优点。E-DenseNet2可视化分析表明了其识别过程,对于相同工况下的不同样本,输出层越深其输出特征越相似,直至全连接层给出极大相似输出特征。

损伤识别  /  神经网络  /  动力测试  /  灵敏度分析  /  经验模态分解

A structure damage identification network model ( E-DenseNet) that combines empirical mode decomposition (EMD) and densely connected convolutional network ( DenseNet) is proposed. The collected acceleration signals undergo EMD to obtain multiple intrinsic mode function (IMF) components, and then the weakly correlated IMF components with small absolute values of Pearson correlation coefficients are removed. According to the organization of the input data, three types of E-DenseNet models are set. E-DenseNet1 reconstructs the signal using strongly correlated IMF components to establish one-dimensional single-channel input data. E-DenseNet2 treats each strongly correlated IMF component as a channel to establish one-dimensional multi-channel input data. E-DenseNet3 uses all strongly correlated IMF components to form a two-dimensional matrix to establish two-dimensional single-channel input data. The numerical analysis of a simply supported beam shows that: E-DenseNet1 runs quickly with poor damage detection accuracy. E-DenseNet2 is computationally efficient with high damage detection accuracy. E-DenseNet3 provides good damage detection results but is time-consuming. Compared with one-dimensional multi-channel residual convolutional neural network (ResNet) and standard convolutional neural network (CNN), E-DenseNet2 performs much better in damage detection accuracy. It is thus concluded that E-DenseNet2 ensures both the computational efficiency and the damage detection accuracy. The visualization analysis of E-DenseNet2 exhibits its damage detection process that for different samples of the same damage scenario, a deeper layer outputs more similar features until the fully connected layer provides the most similar output features.

damage detection  /  neural network  /  dynamic test  /  sensitivity analysis  /  empirical mode decomposition
吁强, 蔡晓丽, 李翠, 朱学坤, 伍晓顺, 朱驰. 基于密集连接卷积神经网络的结构损伤识别. 地震工程与工程振动, 2024 , 44 (3) : 61 -72 . DOI: 10.13197/j.eeed.2024.0306
Qiang YU, Xiaoli CAI, Cui LI, Xuekun ZHU, Xiaoshun WU, Chi ZHU. Structural damage detection by using densely connected convolutional neural network[J]. Earthquake Engineering and Engineering Dynamics, 2024 , 44 (3) : 61 -72 . DOI: 10.13197/j.eeed.2024.0306
工程结构在服役过程中不断累积的损伤对结构的安全性和耐久性构成严重威胁,甚至引发工程事故造成财产损失和人员伤亡。为避免工程事故的发生,有必要对在役结构进行结构健康监测[1]。作为结构健康监测的核心内容,损伤识别一直备受研究人员关注。其中,基于结构动力特性的损伤识别方法成为研究热点[2-3]
近年来,随着深度学习[4]的快速发展,卷积神经网络(convolutional neural network,CNN)凭借其强大的特征提取及特征映射能力,在智能诊断领域有着不俗的表现[5-7]。其中,基于结构动力特性和CNN相结合的结构损伤识别方法也取得了很多成果[8-11]为了保证神经网络的学习能力,往往需要大幅增加网络深度。但是,网络深度的增加容易导致梯度消失和梯度爆炸[12]。为了解决这个问题,HUANG等[13]在残差结构(ResNet)[14]基础上开发了一种称为密集连接卷积网络(densely connected convolutional neural network,DenseNet)的新架构,并在2017年获得CVPR最佳论文。DenseNet独特的连接方式使得特征可以重复利用,从而大幅提升网络的学习效率。这使得DenseNet在结构健康监测领域有着广泛的应用前景[15]。为了降低计算成本,骆勇鹏等[16]采用单通道一维CNN并直接利用原始数据来实现对简支梁和钢框架的损伤识别,获得了很好的识别效果。骆剑彬等[17]考察了多通道一维CNN的损伤识别效果,结果表明多通道模型识别精度远好于单通道模型。为了提高输入数据的质量,叶壮等[18]利用经验模态分解(empirical mode decomposition,EMD)对原始信号进行分解重构后输入多通道CNN实现了齿轮箱的故障诊断。可见,一维卷积和多通道可以大幅提高计算效率,EMD则可以增强信号特征从而提高识别精度。
受上述研究启发,本文利用EMD和DenseNet搭建一种新的卷积神经网络模型E-DenseNet,以便更加准确地提取结构损伤特征。首先,介绍CNN、DenseNet、EMD的基本原理。其次,解析E-DenseNet的模型架构。最后,以某简支梁为例展开数值分析,比较不同通道和数据维度E-DenseNet的性能表现,并对网络学习到的特征进行可视化分析以揭示结构损伤的识别原理。
CNN[19-20]是一种深度学习模型或类似于人工神经网络的多层感知器,常用来分析视觉图像。一个典型的CNN包括卷积层、池化层和全连接层,且通常为顺序连接。卷积层通过人为设置的卷积核对输入的特征图进行卷积计算,即
式中:为第l层第j个元素(即该层输出);为第l-1层的第i个元素(即该层输入);Mj为第l-1层的第j个卷积区域;为卷积核权值;为对应的偏置;f为非线性激活函数。f通常采用ReLU激活函数,其表达式为
池化层通常设置在卷积层后面并对卷积层的输出进行采样,以便对特征图进行降维。常用的池化操作有平均池化和最大值池化,分别对池化区域内的特征点取平均值和最大值。全连接层一般位于整个卷积神经网络的最后面,其主要作用就是将前层(卷积、池化等层)学习到的特征空间进行组合,最后映射到样本的标签空间。
CNN的网络层数一般较深。当CNN的层数变深时,容易出现网络退化(即梯度消失或梯度爆炸)问题。DenseNet[13]是解决CNN网络退化问题的一种先进方案。DenseNet通过建立前面所有层与后面层的密集连接来实现特征重用,具有较优的计算性能。密集连接块(Dense block)和过渡层(Transition layer)DenseNet的2个重要模块,其简述如下。
密集连接块中每一层的输入均为前面所有层输出的拼接,其示意图如图1所示。密集连接的数学表达式为
式中:[x0x1...xl-1]为第l层之前所有特征图的拼接;xl为第l层的输出;Hl为非线性组合函数,通常包含BN-ReLU-Conv等一系列非线性变换。假设初始输入的特征图通道数为k0,且每一层的卷积核数量均为k,则对于第l层,其输入的通道数为k0 +(l-1)k。可见,输入通道数与网络层数呈线性递增关系,因此,k又被称为网络增长率。
包含密集连接块和过渡层的完整DenseNet示意图,如图2所示。在密集连接块中,每一层的特征图大小都相同,这样各层的连接操作才能顺利进行。为压缩整个训练模型的参数量,需要在密集连接块之间添加过渡层。一般在过渡层引入1×1卷积核来压缩特征图数量,并引入池化函数MaxPooling来进行采样。
EMD是由HUANG等[21]于1998年提出的一种自适应处理信号的算法。某时域信号经EMD处理后可以得到不同尺度的本征模态函数(IMF)分量以及一个残差分量,即
式中:xt)为原始时域信号;ci为第i个IMF分量;rn为残差分量;n为IMF的个数。EMD具体分解过程见文献[21]。
可以根据IMF分量与xt)之间的皮尔逊相关系数[22] ρ来判断它们之间的相关性。若|ρ| > 0.6,则认为该阶IMF与xt)之间为强相关,反之为弱相关。通过EMD,原始信号包含的损伤特征被主要分散到各阶强相关IMF分量。后文中,仅保留强相关IMF分量来重新组织网络模型的输入数据。将所有强相关IMF分量进行叠加可以得到重构信号。一般认为,该重构信号将极大保留原始特征信息,同时剔除噪声的干扰。
将EMD和DenseNet相结合,搭建适用于结构损伤识别的E-DenseNet模型,其架构(或流程)如图3所示。E-DenseNet模型由3个密集连接块和过渡层连接构成,全局平均池化层置于最后一个密集连接块后面,最后为目标层。根据输入数据的组织方式,设定3种E-DenseNet模型:①E-DenseNet1利用强相关IMF分量叠加后的重构信号建立一维单通道输入数据;②E-DenseNet2将各阶强相关IMF分量视作一个通道来建立一维多通道输入数据;③E-DenseNet3将各阶强相关IMF分量视作同一个二维矩阵的各行来建立二维单通道输入数据。
将结构的损伤位置与损伤程度映射到目标层的输出向量,并由携带激活函数tan h的全连接层来实现回归计算。tan h函数的计算公式为
式中:x为tan h函数的输入;tan h(x)为预测的损伤程度。
采用均方误差(MSE)作为损失函数,用来衡量预测的损伤向量与真实标签的差异程度。同时为避免过拟合,在损失函数中加入一个L2正则化项λ对权重参数进行惩罚。本文将λ设定为0.0002,对应的损失函数表达式为
式中:为损失值;w为权重矩阵;n为训练样本数量。还采用线性相关系数R来衡量预测值与真实值之间的匹配程度,R值介于0~1之间。总的来说,MSE值越小、R值越大,则模型的性能越好。
某1.6 m跨简支工字梁为例展开数值分析,如图4所示。梁的弹性模量为206 GPa、密度为7850 kg/m3、泊松比为0.3。该梁共包含11个节点和10个长度相等的单元。采用减小相应位置弹性模量的方式来模拟单元损伤。共建立包含无损工况在内的共25种损伤工况如表1所示。在5号节点施加白噪声激励,激励服从均值为300 N、标准差为30 N的正态分布。激励时长为400 s,采样频率为50 Hz。利用5号节点测得的竖直方向加速度响应数据来展开模型训练和测试。
一般而言,样本的数量越大则模型的评估效果越好,然而实际工程获得的数据往往是有限的。为获得更多的样本,采用滑窗重采样的方法对数据进行切片,如图5所示。滑窗长度为2000,滑窗步长为28。每种工况采集500组样本,共12 500组样本。将样本按75%、15%、15%划分为训练集、验证集和测试集。样本标签为结构损伤向量,如[0.12,0,0.02,0,…,0]表示1号单元损伤12%、3号单元损伤2%。同时为模拟测量噪声的干扰,将对样本添加不同信噪比[23]的噪声。表2给出了E-DenseNet网络结构超参数设置情况。
为评估网络模型的训练效果,将按比例划分好的数据集(仅训练集参与训练)送入训练模型。共训练500个epoch,选用Adam优化器,初始学习率设置为0.001,并采用阶梯型衰减策略,衰减数为0.95。整个模型的搭建和优化均在TensorFlow环境下进行。
以工况15(7号单元25.5%损伤)为例,考虑某个随机选取的验证集样本,DenseNet(采用原始信号作为输入数据)、E-DenseNet1~3的损伤识别结果如图6所示。由图可知,无论是否考虑噪声影响,E-DenseNet2和E-DenseNet3均可准确识别损伤位置,且定量识别结果非常接近真实值。其中,E-DenseNet2在无噪、10 dB和5dB噪声情形下的损伤识别值分别为25.683%、25.762%、24.934%,而E-DenseNet3则分别为25.453%、25.923%、26.123%,而且未损杆件对损伤杆件的识别仅有轻微干扰。相比之下,即使不考虑噪声影响,DenseNet和E-DenseNet1的损伤识别结果都比较差。这表明E-DenseNet2和E-DenseNet3比DenseNet和E-DenseNet1具有更好的损伤识别性能。
DenseNet、E-DenseNet1,E-DenseNet2,E-DenseNet3在统计意义上的评估结果如表3所示。从R值和MSE值判断,无论是否考虑噪声影响,E-DenseNet2和E-DenseNet3的损伤识别效果都要远好于DenseNet和E-DenseNet1。此外,E-DenseNet3计算耗时远超DenseNet、E-DenseNet1和E-DenseNet2。研究表明,采用一维多通道的E-DenseNet2可以兼顾计算效率和识别精度。
均采用一维多通道输入数据的E-DenseNet2、ResNet和CNN这3种网络模型在训练集和验证集的MSE值变化趋势,如图7所示。可以看出,在训练集上3种模型的MSE曲线收敛速度相差不大,但在验证集上E-DenseNet2的表现显然更好。可见,虽然均为一维多通道训练模型,但是E-DenseNet2比ResNet、CNN具有更好的泛化能力。
以工况10(5号单元微小损伤4.5%)为例,考虑某个随机选取的验证集样本,DenseNet2、ResNet和CNN这3种网络模型的损伤识别结果如图8所示。由图可知,无论是否考虑噪声影响,E-DenseNet2均可准确识别损伤位置,定量识别结果也非常接近真实值,且未损杆件对损伤杆件的识别几乎无干扰。相比之下,即使不考虑噪声影响,ResNet和CNN的损伤识别结果都很差,存在较多干扰或误判的情况。研究表明E-DenseNet2比ResNet和CNN具有更好的损伤识别性能。
DenseNet、ResNet和CNN在统计意义上的评估结果如表4所示。从R值和MSE值判断,无论是否考虑噪声影响,E-DenseNet2的损伤识别效果都要远好于ResNet和CNN,但计算耗时比ResNet略多而比CNN略少。
为了更好地理解训练模型各层输出特征的演变过程,以E-DenseNet2为例展开可视化分析。随机选取工况2(1号单元7.5%损伤)验证集3份样本(即一维输入数据多通道),分别记为信号一(无噪)、信号二(10 dB噪声)和信号三(5 dB噪声),如图9所示。将每个密集连接块的最后一个卷积层输出的特征图绘于图10~图12。观察特征图的浅层特征至深层特征的变化,可以发现不同信号之间的输出特征越来越相似,如图12(a)、(b)、(c)三者的第一张子图(1st)基本相同。这3个信号经全局平均池化后的结果如图13所示,全连接层的最终输出结果如图14所示。可以看出经过全局平均池化后,各个信号的输出特征已经非常相似,这使得全连接层的输出结果非常接近真实标签。
本文提出一种EMD和DenseNet相结合的结构损伤识别网络模型(E-DenseNet),结论如下:
1)直接利用未经EMD处理的原始信号作为输入数据的DenseNet识别精度较差,而采用经EMD处理后数据的E-DenseNet1~3识别效果均比DenseNet好,研究表明EMD有利于提高识别精度。
2)E-DenseNet2的识别精度远超ResNet和CNN(均采用一维多通道输入数据),研究表明采用密集连接方式有利于提升识别精度。
3)E-DenseNet2与E-DenseNet3的识别精度相当,但前者计算耗时仅为后者的约1/10,研究表明E-DenseNet2可以兼顾计算效率和识别精度。
  • 国家自然科学基金项目(51868026)
  • 江西省自然科学基金项目(20202BAB204028)
  • 江西省研究生创新专项资金项目(YC2022-S695)
参考文献 引证文献
排序方式:
[1]
李宏男,李东升. 土木工程结构安全性评估、健康监测及诊断述评[J]. 地震工程与工程振动200222(3):82-90.
LI Hongnan, LI Dongsheng. Safety assessment, health monitoring and damage diagnosis for structures in civil engineering[J]. Earthquake Engineering and Engineering Dynamics, 2002, 22(3): 82-90. (in Chinese)
[2]
张家滨,唐催,王磊,. 基于频率变化率的结构刚度非均匀退化识别[J]. 振动. 测试与诊断201838(3):486-493.
ZHANG Jiabin, TANG Cui, WANG Lei, et al. Identification of non-uniform stiffness degradation in structure based on the change rate of frequency[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(3): 486-493. (in Chinese)
[3]
朱宏平,余璟,张俊兵. 结构损伤动力检测与健康监测研究现状与展望[J]. 工程力学201128(2):1-11, 17.
ZHU Hongping, YU Jing, ZHANG Junbing. A summary review and advantages of vibration-based damage identification methods in structural health monitoring[J]. Engineering Mechanics, 2011, 28(2): 1-11, 17. (in Chinese)
[4]
LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521: 436-444.
[5]
FLAH M, RAGAB M, LAZHARI M, et al. Localization and classification of structural damage using deep learning single-channel signal-based measurement[J]. Automation in Construction, 2022, 139: 104271.
[6]
张伟. 基于卷积神经网络的轴承故障诊断算法研究[D]. 哈尔滨:哈尔滨工业大学,2017.
ZHANG Wei. Study on bearing fault diagnosis algorithm based on convolutional neural network[D]. Harbin: Harbin Institute of Technology, 2017. (in Chinese)
[7]
李泽东,李志农,陶俊勇,. 基于特征融合的注意力增强卷积神经网络的航空发动机滚动轴承故障诊断方法[J]. 兵工学报202243(12):3228-3239.
LI Zedong, LI Zhinong, TAO Junyong, et al. Fault diagnosis for aero-engine rolling bearings based on an attention augmented convolutional neural network with feature fusion[J]. Acta Armamentarii, 2022, 43(12): 3228-3239. (in Chinese)
[8]
李雪松,马宏伟,林逸洲. 基于卷积神经网络的结构损伤识别[J]. 振动与冲击201938(1):159-167.
LI Xuesong, MA Hongwei, LIN Yizhou. Structural damage identification based on convolution neural network[J]. Journal of Vibration and Shock, 2019, 38(1): 159-167. (in Chinese)
[9]
罗雨舟,向天宇,郝柳青. 卷积神经网络在结构损伤检测中的应用[J]. 土木工程与管理学报202037(3):155-161, 173.
LUO Yuzhou, XIANG Tianyu, HAO Liuqing. Application of convolutional neural network in structural damage diagnosis[J]. Journal of Civil Engineering and Management, 2020, 37(3): 155-161, 173. (in Chinese)
[10]
李书进,赵源,孔凡,. 卷积神经网络在结构损伤诊断中的应用[J]. 建筑科学与工程学报202037(6):29-37.
LI Shujin, ZHAO Yuan, KONG Fan, et al. Application of convolutional neural network in structural damage identification[J]. Journal of Architecture and Civil Engineering, 2020, 37(6): 29-37. (in Chinese)
[11]
骆勇鹏,王林堃,郭旭,. 利用单传感器数据基于GAF-CNN的结构损伤识别[J]. 振动.测试与诊断202242(1):169-176, 202, 203.
LUO Yongpeng, WANG Linkun, GUO Xu, et al. Structural damage identification using single sensor data based on GAF-CNN[J]. Journal of Vibration, Measurement & Diagnosis, 2022, 42(1): 169-176, 202, 203. (in Chinese)
[12]
BENGIO Y, SIMARD P, FRASCONI P. Learning long-term dependencies with gradient descent is difficult[J]. IEEE Transactions on Neural Networks, 1994, 5(2): 157-166.
[13]
HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA. Piscataway, NJ, USA: IEEE, 2017: 2261-2269.
[14]
HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. Piscataway, NJ, USA: IEEE, 2016: 770-778.
[15]
WANG R H, LI J, Chen cho, et al. Densely connected convolutional networks for vibration based structural damage identification[J]. Engineering Structures, 2021, 245: 112871.
[16]
骆勇鹏,王林堃,廖飞宇,. 基于一维卷积神经网络的结构损伤识别[J]. 地震工程与工程振动202141(4):145-156.
LUO Yongpeng, WANG Linkun, LIAO Feiyu, et al. Vibration-based structural damage identification by 1-dimensional convolutional neural network[J]. Earthquake Engineering and Engineering Dynamics, 2021, 41(4): 145-156. (in Chinese)
[17]
骆剑彬,刘越生,姜绍飞,. 基于卷积神经网络和迁移学习的结构损伤识别[J]. 福州大学学报(自然科学版)202250(4):546-552.
LUO Jianbin, LIU Yuesheng, JIANG Shaofei, et al. Structural damage detection based on convolutional neural networks and transfer learning[J].Journal of Fuzhou University (Natural Science Edition), 2022, 50(4): 546-552. (in Chinese)
[18]
叶壮,余建波. 基于多通道一维卷积神经网络特征学习的齿轮箱故障诊断方法[J]. 振动与冲击202039(20):55-66.
YE Zhuang, YU Jianbo. Gearbox fault diagnosis based on feature learning of multi-channel one-dimensional convolutional neural network[J]. Journal of Vibration and Shock, 2020, 39(20): 55-66. (in Chinese)
[19]
张健飞,蔡东成. 基于多尺度卷积神经网络的结构损伤识别研究[J]. 地震工程与工程振动202242(1):132-142.
ZHANG Jianfei, CAI Dongcheng. Research on structural damage identification based on multi-scale convolutional neural networks[J]. Earthquake Engineering and Engineering Dynamics, 2022, 42(1): 132-142. (in Chinese)
[20]
戴伦,张文达,田石柱. 桥梁线弹性地震反应的卷积神经网络估计[J]. 地震工程与工程振动202141(4):188-195.
DAI Lun, ZHANG Wenda, TIAN Shizhu. Convolutional neural network estimation of bridge linear elastic seismic response[J]. Earthquake Engineering and Engineering Dynamics, 2021, 41(4): 188-195. (in Chinese)
[21]
HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995.
[22]
陶洋,祝小钧,杨柳. 基于皮尔逊相关系数和信息熵的多传感器数据融合[J]. 小型微型计算机系统202344(5):1075-1080.
TAO Yang, ZHU Xiaojun, YANG Liu. Multi-sensor data fusion based on pearson coefficient and information entropy[J]. Journal of Chinese Computer Systems, 2023, 44(5): 1075-1080. (in Chinese)
[23]
伍晓顺,程润辉. 阶跃激励下网架结构的动力响应扩展及其误差分析[J]. 振动与冲击202241(17):213-220, 261.
WU Xiaoshun, CHENG Runhui. Dynamic response expansion and its error analysis of space truss structures under step excitation[J]. Journal of Vibration and Shock, 2022, 41(17): 213-220, 261. (in Chinese)
2024年第44卷第3期
PDF下载
56
28
引用本文
BibTeX
文章信息
doi: 10.13197/j.eeed.2024.0306
  • 接收时间:2023-03-25
  • 首发时间:2026-03-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-03-25
  • 修回日期:2023-06-10
基金
国家自然科学基金项目(51868026)
江西省自然科学基金项目(20202BAB204028)
江西省研究生创新专项资金项目(YC2022-S695)
作者信息
    1.江西理工大学 土木与测绘工程学院(南昌),江西 南昌 330013
    2.江西交通职业技术学院 信息工程学院,江西 南昌 330013

通讯作者:

蔡晓丽(1985—),女,讲师,硕士,主要从事结构健康监测和BIM技术的研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/10.13197/j.eeed.2024.0306
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