Article(id=1228653358949531684, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228653350485422347, articleNumber=null, orderNo=null, doi=10.16385/j.cnki.issn.1004-4523.2024.10.006, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1715097600000, receivedDateStr=2024-05-08, revisedDate=1722441600000, revisedDateStr=2024-08-01, acceptedDate=null, acceptedDateStr=null, onlineDate=1770863388049, onlineDateStr=2026-02-12, pubDate=1730044800000, pubDateStr=2024-10-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770863388049, onlineIssueDateStr=2026-02-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770863388049, creator=13701087609, updateTime=1770863388049, updator=13701087609, issue=Issue{id=1228653350485422347, tenantId=1146029695717560320, journalId=1225147924628267009, year='2024', volume='37', issue='10', pageStart='1625', pageEnd='1802', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1770863386031, creator=13701087609, updateTime=1770863862999, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1228655351092936954, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228653350485422347, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1228655351092936955, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228653350485422347, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1688, endPage=1697, ext={EN=ArticleExt(id=1228653359297658928, articleId=1228653358949531684, tenantId=1146029695717560320, journalId=1225147924628267009, language=EN, title=A data-driven dynamic load identification method based on time-delay neural networks, columnId=null, journalTitle=Journal of Vibration Engineering, columnName=null, runingTitle=null, highlight=null, articleAbstract=

The problem of load identification denotes identifying loads based on the measurement of structural responses,which is the inverse problem in structural dynamics. A load identification method based on time-delay neural network is proposed in this paper,and numerical examples based on simulation and experiments are provided to show that the method overperforms normal back-propagation neural network in accuracy of identification. Additionally,statistic pooling is introduced on the basis of the method,and it is proved that the method performs well in noisy environment compared with BP neural networks. based on the load identification methods mentioned above,a sensor placement optimization based on particle swarm optimization algorithm is proposed,and the optimal sensor placement is able to reduce the error of identification by 90% compared with the random sensor placements,meanwhile the minimum spacing of installation among sensors is also ensured during the optimization.

, 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=Lei WANG, Hao-yu ZHANG, Ju-xi HU, Kai-xuan GU, Zhen-yu WANG, Ying-liang LIU), CN=ArticleExt(id=1228653375139545701, articleId=1228653358949531684, tenantId=1146029695717560320, journalId=1225147924628267009, language=CN, title=数据驱动的时延神经网络动载荷识别方法, columnId=0, journalTitle=振动工程学报, columnName=, runingTitle=null, highlight=null, articleAbstract=

载荷识别是指根据测量的结构响应重构结构载荷的问题,属于力学中的反问题。本文提出了一种基于时延神经网络的载荷识别方法,通过实验和仿真相结合的数值算例验证表明,这一方法相比于一般的反向传播神经网络具有更高的识别精度;在时延神经网络的基础上,引入了统计池化的思想,并与普通的神经网络载荷识别方法相比较,证明了该方法在不同强度的噪声环境下均具有良好的识别效果;基于上述载荷识别方法,提出了一种基于粒子群优化算法的传感器布局优化策略,相比于随机的传感器布局,优化后的传感器布局可以在考虑传感器安装间距的同时,将载荷识别误差降低90%以上,有效提高了载荷识别精度。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
胡举喜(1981—),女,博士,研究员。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=XfG5WilCsoEFYgzn2VC7ew==, magXml=1i+7RaL2yUb3glNuI/DZaQ==, pdfUrl=null, pdf=cd+n6TUJoy0F+gdQ/CNjzw==, pdfFileSize=4436182, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ZyzwBNKqFN1eI9VgxOcZ0w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=CMANv6PeNAyu8RYzoIgI+g==, mapNumber=null, authorCompany=null, fund=null, authors=

王磊(1987—),男,博士,副教授。E-mail:

, authorsList=王磊, 张昊宇, 胡举喜, 顾凯旋, 王振宇, 刘英良)}, authors=[Author(id=1228662192409604434, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=leiwang_beijing@buaa.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228662192472518996, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662192409604434, language=EN, stringName=Lei WANG, firstName=Lei, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1National Key Laboratory of Strength and Structural Integrity,School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228662192522850645, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662192409604434, language=CN, stringName=王磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191, bio={"content":"

王磊(1987—),男,博士,副教授。E-mail:

"}, bioImg=null, bioContent=

王磊(1987—),男,博士,副教授。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228662192103420226, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=1, ext=[AuthorCompanyExt(id=1228662192111808835, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192103420226, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1National Key Laboratory of Strength and Structural Integrity,School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China), AuthorCompanyExt(id=1228662192120197444, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192103420226, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191)])]), Author(id=1228662192573182295, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228662192640291161, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662192573182295, language=EN, stringName=Hao-yu ZHANG, firstName=Hao-yu, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1National Key Laboratory of Strength and Structural Integrity,School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228662192699011418, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662192573182295, language=CN, stringName=张昊宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228662192103420226, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=1, ext=[AuthorCompanyExt(id=1228662192111808835, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192103420226, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1National Key Laboratory of Strength and Structural Integrity,School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China), AuthorCompanyExt(id=1228662192120197444, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192103420226, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191)])]), Author(id=1228662192757731676, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hu.juxi@sjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228662192820646238, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662192757731676, language=EN, stringName=Ju-xi HU, firstName=Ju-xi, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2School of Naval Architecture,Ocean & Civil Engineering,Shanghai Jiao Tong University,Shanghai 200240,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228662192870977887, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662192757731676, language=CN, stringName=胡举喜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2上海交通大学船舶海洋与建筑工程学院,上海 200240, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228662192183112005, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=2, ext=[AuthorCompanyExt(id=1228662192187306310, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192183112005, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Naval Architecture,Ocean & Civil Engineering,Shanghai Jiao Tong University,Shanghai 200240,China), AuthorCompanyExt(id=1228662192195694919, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192183112005, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2上海交通大学船舶海洋与建筑工程学院,上海 200240)])]), Author(id=1228662192925503841, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, 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=1228662192988418403, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662192925503841, language=EN, stringName=Kai-xuan GU, firstName=Kai-xuan, middleName=null, lastName=GU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Test Department,Aviation Industry Aerospace Lifesaving Equipment Co.,Ltd.,Xiangyang 441003,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228662193047138660, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662192925503841, language=CN, stringName=顾凯旋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3航空工业航宇救生装备有限公司试验部, 湖北 襄阳 441003, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228662192254415177, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=3, ext=[AuthorCompanyExt(id=1228662192262803786, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192254415177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Test Department,Aviation Industry Aerospace Lifesaving Equipment Co.,Ltd.,Xiangyang 441003,China), AuthorCompanyExt(id=1228662192266998091, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192254415177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3航空工业航宇救生装备有限公司试验部, 湖北 襄阳 441003)])]), Author(id=1228662193114247526, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, 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=1228662193177162088, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662193114247526, language=EN, stringName=Zhen-yu WANG, firstName=Zhen-yu, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1National Key Laboratory of Strength and Structural Integrity,School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228662193244270953, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662193114247526, language=CN, stringName=王振宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228662192103420226, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=1, ext=[AuthorCompanyExt(id=1228662192111808835, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192103420226, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1National Key Laboratory of Strength and Structural Integrity,School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China), AuthorCompanyExt(id=1228662192120197444, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192103420226, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191)])]), Author(id=1228662193294602603, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, 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=1228662193361711469, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662193294602603, language=EN, stringName=Ying-liang LIU, firstName=Ying-liang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4Marine Design & Research Institute of China,Shanghai,200011,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228662193479151982, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, authorId=1228662193294602603, language=CN, stringName=刘英良, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4中国船舶及海洋工程设计研究院,上海 200011, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228662192329912653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=4, ext=[AuthorCompanyExt(id=1228662192338301262, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192329912653, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Marine Design & Research Institute of China,Shanghai,200011,China), AuthorCompanyExt(id=1228662192346689871, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192329912653, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4中国船舶及海洋工程设计研究院,上海 200011)])])], keywords=[Keyword(id=1228662193609175407, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, orderNo=1, keyword=load identification), Keyword(id=1228662193663701360, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, orderNo=2, keyword=time-delay neural network), Keyword(id=1228662193722421617, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, orderNo=3, keyword=particle swarm optimization), Keyword(id=1228662193772753266, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, orderNo=4, keyword=inverse problem), Keyword(id=1228662193827279219, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, orderNo=1, keyword=载荷识别), Keyword(id=1228662193890193780, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, orderNo=2, keyword=时延神经网络), Keyword(id=1228662193944719733, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, orderNo=3, keyword=粒子群优化), Keyword(id=1228662193995051382, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, orderNo=4, keyword=反向题)], refs=[Reference(id=1228662201221837214, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=1943, volume=5, issue=null, pageStart=115, pageEnd=33, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=McCulloch W S, Pitts W, journalName=Bulletin of Mathematical Biophysics, refType=null, unstructuredReference=McCulloch W SPitts W. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biophysics19435: 115-33., articleTitle=A logical calculus of the ideas immanent in nervous activity, refAbstract=null), Reference(id=1228662201305723295, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=1958, volume=65, issue=6, pageStart=386, pageEnd=408, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Rosenblatt F, journalName=Psychological Review, refType=null, unstructuredReference=Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain[J]. Psychological Review195865(6): 386-408., articleTitle=The perceptron: a probabilistic model for information storage and organization in the brain, refAbstract=null), Reference(id=1228662201360249248, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=1986, volume=323, issue=6088, pageStart=533, pageEnd=536, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Rumelhart D E, Hinton G E, Williams R J, journalName=Nature, refType=null, unstructuredReference=Rumelhart D EHinton G EWilliams R J. Learning representations by back-propagating errors[J]. Nature1986323(6088): 533-536., articleTitle=Learning representations by back-propagating errors, refAbstract=null), Reference(id=1228662201418969505, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=1998, volume=86, issue=11, pageStart=2278, pageEnd=2324, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=LeCun Y, Bottou L, Bengio Y, journalName=Proceedings of the IEEE, refType=null, unstructuredReference=LeCun YBottou LBengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE199886(11): 2278-2324., articleTitle=Gradient-based learning applied to document recognition, refAbstract=null), Reference(id=1228662201490272674, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2006, volume=313, issue=5786, pageStart=504, pageEnd=507, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=Hinton G E, Salakhutdinov R R, journalName=Science, refType=null, unstructuredReference=Hinton G ESalakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science2006313(5786): 504-507., articleTitle=Reducing the dimensionality of data with neural networks, refAbstract=null), Reference(id=1228662201548992931, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=1998, volume=null, issue=null, pageStart=354, pageEnd=358, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=Omkar S N, Nagabhushanam J, journalName=null, refType=null, unstructuredReference=Omkar S NNagabhushanam J. Neural network controller for minimizing hub shear forces in helicopter[C]// 1998 IEEE International Symposium on Intelligent Control (ISIC) Held Jointly with IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA). Gaithersburg, USA, 1998 :354-358., articleTitle=Neural network controller for minimizing hub shear forces in helicopter, refAbstract=null), Reference(id=1228662201607713188, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2006, volume=14, issue=4, pageStart=379, pageEnd=395, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=Trivailo P M, Carn C L, journalName=Inverse Problems in Science and Engineering, refType=null, unstructuredReference=Trivailo P MCarn C L. The inverse determination of aerodynamic loading from structural response data using neural networks[J]. Inverse Problems in Science and Engineering200614(4): 379-395., articleTitle=The inverse determination of aerodynamic loading from structural response data using neural networks, refAbstract=null), Reference(id=1228662201662239141, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2020, volume=372, issue=null, pageStart=113402, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=Liu M L, Liang L, Sun W, journalName=Computer Methods in Applied Mechanics and Engineering, refType=null, unstructuredReference=Liu M LLiang LSun W. A generic physics-informed neural network-based constitutive model for soft biological tissues[J]. Computer Methods in Applied Mechanics and Engineering2020372: 113402., articleTitle=A generic physics-informed neural network-based constitutive model for soft biological tissues, refAbstract=null), Reference(id=1228662201716765094, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2019, volume=145, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=Wu R T, Jahanshahi M R, journalName=Journal of Engineering Mechanics, refType=null, unstructuredReference=Wu R TJahanshahi M R. Deep convolutional neural network for structural dynamic response estimation and system identification[J]. Journal of Engineering Mechanics2019145(1): 04018125., articleTitle=Deep convolutional neural network for structural dynamic response estimation and system identification, refAbstract=null), Reference(id=1228662201783873959, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2022, volume=237, issue=null, pageStart=107796, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=Liu Y R, Wang L, Gu K X, journalName=Knowledge-based Systems, refType=null, unstructuredReference=Liu Y RWang LGu K X, et al. Artificial neural network (ANN)-Bayesian probability framework (BPF) based method of dynamic force reconstruction under multi-source uncertainties[J]. Knowledge-based Systems2022237: 107796., articleTitle=Artificial neural network (ANN)-Bayesian probability framework (BPF) based method of dynamic force reconstruction under multi-source uncertainties, refAbstract=null), Reference(id=1228662201859371432, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2023, volume=185, issue=null, pageStart=109757, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=Yang H J, Jiang J H, Chen G P, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=Yang H JJiang J HChen G P, et al. Dynamic load identification based on deep convolution neural network[J]. Mechanical Systems and Signal Processing2023185: 109757., articleTitle=Dynamic load identification based on deep convolution neural network, refAbstract=null), Reference(id=1228662201922285993, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2019, volume=133, issue=null, pageStart=106292, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=Zhou J M, Dong L L, Guan W, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=Zhou J MDong L LGuan W, et al. Impact load identification of nonlinear structures using deep Recurrent Neural Network[J]. Mechanical Systems and Signal Processing2019133: 106292., articleTitle=Impact load identification of nonlinear structures using deep Recurrent Neural Network, refAbstract=null), Reference(id=1228662201985200554, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2022, volume=187, issue=null, pageStart=110227, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=Li J, Yan J J, Zhu J J, journalName=Measurement, refType=null, unstructuredReference=Li JYan J JZhu J J, et al. K-BP neural network-based strain field inversion and load identification for CFRP[J]. Measurement2022187: 110227., articleTitle=K-BP neural network-based strain field inversion and load identification for CFRP, refAbstract=null), Reference(id=1228662202048115115, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=3, pageStart=512, pageEnd=521, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=何文博, 许步锋, 冯振宇, journalName=振动工程学报, refType=null, unstructuredReference=何文博,许步锋,冯振宇,等. 利用冗余扩展余弦字典的复杂动载荷识别研究[J]. 振动工程学报202437(3):512-521., articleTitle=利用冗余扩展余弦字典的复杂动载荷识别研究, refAbstract=null), Reference(id=1228662202152972716, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=3, pageStart=512, pageEnd=521, url=null, language=null, rfNumber=[14], rfOrder=14, authorNames=He W B, Xu B F, Feng Z Y, journalName=Journal of Vibration Engineering, refType=null, unstructuredReference=He W BXu B FFeng Z Y, et al. Identification of complex dynamic load using redundant extended cosine transform dictionary[J]. Journal of Vibration Engineering202437(3):512-521., articleTitle=Identification of complex dynamic load using redundant extended cosine transform dictionary, refAbstract=null), Reference(id=1228662202236858797, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2023, volume=29, issue=19-20, pageStart=4479, pageEnd=4491, url=null, language=null, rfNumber=[15], rfOrder=15, authorNames=Tang Z H, Zhang Z F, Zan M, journalName=Journal of Vibration and Control, refType=null, unstructuredReference=Tang Z HZhang Z FZan M, et al. The determination of the regularization parameter based on signal-to-noise ratio in load identification[J]. Journal of Vibration and Control202329(19-20): 4479-4491., articleTitle=The determination of the regularization parameter based on signal-to-noise ratio in load identification, refAbstract=null), Reference(id=1228662202316550574, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2018, volume=60, issue=5, pageStart=359, pageEnd=362, url=null, language=null, rfNumber=[16], rfOrder=16, authorNames=欧阳运芳, 何鹏, 刘占生, journalName=汽轮机技术, refType=null, unstructuredReference=欧阳运芳,何鹏,刘占生. 基于有限元仿真的航空发动机振动传感器布局优化方法研究[J].汽轮机技术201860(5): 359-362., articleTitle=基于有限元仿真的航空发动机振动传感器布局优化方法研究, refAbstract=null), Reference(id=1228662202375270831, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2018, volume=60, issue=5, pageStart=359, pageEnd=362, url=null, language=null, rfNumber=[16], rfOrder=17, authorNames=Ouyang Y F, He P, Liu Z S, journalName=Turbine Technology, refType=null, unstructuredReference=Ouyang Y FHe PLiu Z S. Investigation of the optimization method of the vibration transducer layout of aero engine[J]. Turbine Technology201860(5): 359-362., articleTitle=Investigation of the optimization method of the vibration transducer layout of aero engine, refAbstract=null), Reference(id=1228662202429796784, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=10, pageStart=1085, pageEnd=1100, url=null, language=null, rfNumber=[17], rfOrder=18, authorNames=Błachowski B, Świercz A, Ostrowski M, journalName=Computer‐Aided Civil and Infrastructure Engineering, refType=null, unstructuredReference=Błachowski BŚwiercz AOstrowski M, et al. Convex relaxation for efficient sensor layout optimization in large‐scale structures subjected to moving loads[J]. Computer‐Aided Civil and Infrastructure Engineering202035(10): 1085-1100., articleTitle=Convex relaxation for efficient sensor layout optimization in large‐scale structures subjected to moving loads, refAbstract=null), Reference(id=1228662202559820209, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=10, pageStart=3778, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=19, authorNames=Lee E T, Eun H C, journalName=Sensors, refType=null, unstructuredReference=Lee E TEun H C. An optimal sensor layout using the frequency response function data within a wide range of frequencies[J]. Sensors202222(10): 3778., articleTitle=An optimal sensor layout using the frequency response function data within a wide range of frequencies, refAbstract=null), Reference(id=1228662202652094898, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=1988, volume=null, issue=null, pageStart=107, pageEnd=110, url=null, language=null, rfNumber=[19], rfOrder=20, authorNames=Waibel A, Hanazawa T, Hinton G, journalName=null, refType=null, unstructuredReference=Waibel AHanazawa THinton G, et al. Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models[C]//ICASSP-88, International Conference on Acoustics, Speech, and Signal Processing. New York, USA,1988:107-110., articleTitle=Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models, refAbstract=null), Reference(id=1228662202761146803, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=5329, pageEnd=5333, url=null, language=null, rfNumber=[20], rfOrder=21, authorNames=Snyder D, Garcia-Romero D, Sell G, journalName=null, refType=null, unstructuredReference=Snyder DGarcia-Romero DSell G, et al. X-vectors: Robust dnn embeddings for speaker recognition[C]// 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018). Calgary, Canada, 2018: 5329-5333., articleTitle=X-vectors: Robust dnn embeddings for speaker recognition, refAbstract=null), Reference(id=1228662202828255668, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=1995, volume=null, issue=null, pageStart=1942, pageEnd=1948, url=null, language=null, rfNumber=[21], rfOrder=22, authorNames=Kennedy J, Eberhart R, journalName=null, refType=null, unstructuredReference=Kennedy JEberhart R. Particle swarm optimization[C]//Proceedings of ICNN'95-International Conference on Neural Networks. Perth, Australia, 1995:1942-1948., articleTitle=Particle swarm optimization, refAbstract=null), Reference(id=1228662202895364533, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2002, volume=null, issue=null, pageStart=1215, pageEnd=1218, url=null, language=null, rfNumber=[22], rfOrder=23, authorNames=Xie X F, Zhang W J, Yang Z L, journalName=null, refType=null, unstructuredReference=Xie X FZhang W JYang Z L. Adaptive particle swarm optimization on individual level[C]//Proceedings of the 6th International Conference on Signal Processing(ICSP’02). 2002:1215-1218., articleTitle=Adaptive particle swarm optimization on individual level, refAbstract=null), Reference(id=1228662202970862006, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, doi=null, pmid=null, pmcid=null, year=2023, volume=253, issue=null, pageStart=108369, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=24, authorNames=Liu Y R, Wang L, journalName=International Journal of Mechanical Sciences, refType=null, unstructuredReference=Liu Y RWang L. Multiobjective-clustering-based optimal heterogeneous sensor placement method for thermo-mechanical load identification[J]. International Journal of Mechanical Sciences2023253: 108369., articleTitle=Multiobjective-clustering-based optimal heterogeneous sensor placement method for thermo-mechanical load identification, refAbstract=null)], funds=[Fund(id=1228662199737053597, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, awardId=JCKY2019205A006, language=CN, fundingSource=国防基础科研计划项目(JCKY2019205A006), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1228662192103420226, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=1, ext=[AuthorCompanyExt(id=1228662192111808835, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192103420226, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1National Key Laboratory of Strength and Structural Integrity,School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China), AuthorCompanyExt(id=1228662192120197444, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192103420226, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191)]), AuthorCompany(id=1228662192183112005, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=2, ext=[AuthorCompanyExt(id=1228662192187306310, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192183112005, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Naval Architecture,Ocean & Civil Engineering,Shanghai Jiao Tong University,Shanghai 200240,China), AuthorCompanyExt(id=1228662192195694919, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192183112005, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2上海交通大学船舶海洋与建筑工程学院,上海 200240)]), AuthorCompany(id=1228662192254415177, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=3, ext=[AuthorCompanyExt(id=1228662192262803786, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192254415177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Test Department,Aviation Industry Aerospace Lifesaving Equipment Co.,Ltd.,Xiangyang 441003,China), AuthorCompanyExt(id=1228662192266998091, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192254415177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3航空工业航宇救生装备有限公司试验部, 湖北 襄阳 441003)]), AuthorCompany(id=1228662192329912653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, xref=4, ext=[AuthorCompanyExt(id=1228662192338301262, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192329912653, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Marine Design & Research Institute of China,Shanghai,200011,China), AuthorCompanyExt(id=1228662192346689871, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, companyId=1228662192329912653, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4中国船舶及海洋工程设计研究院,上海 200011)])], figs=[ArticleFig(id=1228662194187989367, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.1, caption=The structure of ANN system, figureFileSmall=vOR3AB35fWKKANRF42TRuA==, figureFileBig=kSN4+7/IvSOu+pevValwvg==, tableContent=null), ArticleFig(id=1228662194263486840, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 1, caption=神经网络的一般结构, figureFileSmall=vOR3AB35fWKKANRF42TRuA==, figureFileBig=kSN4+7/IvSOu+pevValwvg==, tableContent=null), ArticleFig(id=1228662194347372921, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.2, caption=The structure of TDNN system, figureFileSmall=4JJ3aVTLkTa+//e+Ygam6w==, figureFileBig=QfkhXqWbtol6AWaGASeO+A==, tableContent=null), ArticleFig(id=1228662194401898874, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 2, caption=时延神经网络的结构, figureFileSmall=4JJ3aVTLkTa+//e+Ygam6w==, figureFileBig=QfkhXqWbtol6AWaGASeO+A==, tableContent=null), ArticleFig(id=1228662194460619131, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.3, caption=The process of statistic pooling, figureFileSmall=HAXx69kgDQPY+vMf/bPB2Q==, figureFileBig=IzJ/dbesOecegDhOacxQCA==, tableContent=null), ArticleFig(id=1228662194510950780, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 3, caption=池化过程示意图, figureFileSmall=HAXx69kgDQPY+vMf/bPB2Q==, figureFileBig=IzJ/dbesOecegDhOacxQCA==, tableContent=null), ArticleFig(id=1228662194578059645, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.4, caption=The flow chart of the strategy based on PSO algorithm for sensor placement optimization, figureFileSmall=bgkmXw3a3qkrEv3D3qB17w==, figureFileBig=u7sjXavFWTLN/QcoGsB3ig==, tableContent=null), ArticleFig(id=1228662194649362814, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 4, caption=针对传感器布局优化的PSO算法流程图, figureFileSmall=bgkmXw3a3qkrEv3D3qB17w==, figureFileBig=u7sjXavFWTLN/QcoGsB3ig==, tableContent=null), ArticleFig(id=1228662194699694463, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.5, caption=The appearance of the composite thin plate and the placement of the sensors, figureFileSmall=9j0d0kHLwaK01+OGBI9pEA==, figureFileBig=fPQZpoJMtLnU2EbrnvqHFA==, tableContent=null), ArticleFig(id=1228662194762609024, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 5, caption=复合材料薄板外观及传感器布置, figureFileSmall=9j0d0kHLwaK01+OGBI9pEA==, figureFileBig=fPQZpoJMtLnU2EbrnvqHFA==, tableContent=null), ArticleFig(id=1228662194817134977, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.6, caption=The finite element model of the composite thin plate, figureFileSmall=6DtFzSThznMDi0eJEyQsrw==, figureFileBig=lO+s0ilsm+FaD25OvPPr5g==, tableContent=null), ArticleFig(id=1228662194871660930, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 6, caption=复合材料薄板的有限元模型, figureFileSmall=6DtFzSThznMDi0eJEyQsrw==, figureFileBig=lO+s0ilsm+FaD25OvPPr5g==, tableContent=null), ArticleFig(id=1228662194921992579, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.7, caption=The structure of ANN, figureFileSmall=TLG7YSAhLlm8qMR6MrUOkg==, figureFileBig=i9xRt14ZPFPG/2uqrpwk0w==, tableContent=null), ArticleFig(id=1228662194980712836, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 7, caption=神经网络结构, figureFileSmall=TLG7YSAhLlm8qMR6MrUOkg==, figureFileBig=i9xRt14ZPFPG/2uqrpwk0w==, tableContent=null), ArticleFig(id=1228662195056210309, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.8, caption=The data of training sets in case 2, figureFileSmall=Ldn/3DITm3T+kRdqslU09Q==, figureFileBig=DLqvr5soV/3V7hJFDl+ATw==, tableContent=null), ArticleFig(id=1228662195114930566, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 8, caption=工况2训练集数据, figureFileSmall=Ldn/3DITm3T+kRdqslU09Q==, figureFileBig=DLqvr5soV/3V7hJFDl+ATw==, tableContent=null), ArticleFig(id=1228662195177845127, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.9, caption=Error of load identification with different steps of delay in TDNN system, figureFileSmall=md4ASa3HCAEGrzyNX4MJUg==, figureFileBig=b7nzATI+o+/uBkEk878YIw==, tableContent=null), ArticleFig(id=1228662195244953992, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 9, caption=不同延迟步数下的载荷识别误差, figureFileSmall=md4ASa3HCAEGrzyNX4MJUg==, figureFileBig=b7nzATI+o+/uBkEk878YIw==, tableContent=null), ArticleFig(id=1228662198470373769, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.10, caption=Comparison of absolute error with different steps of delay in TDNN system, figureFileSmall=jvYpy0/03WYTj993nOf35A==, figureFileBig=CcDRpPXhL4w4HYC5cHjpCA==, tableContent=null), ArticleFig(id=1228662198541676938, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 10, caption=不同延迟步数下的载荷识别绝对误差对比, figureFileSmall=jvYpy0/03WYTj993nOf35A==, figureFileBig=CcDRpPXhL4w4HYC5cHjpCA==, tableContent=null), ArticleFig(id=1228662198608785803, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.11, caption=Comparison of the results of load identification in noisy environment, figureFileSmall=nrW/YLQ5phMKEgXhUx/yRA==, figureFileBig=du3biVPuXtLcHss3r+rLNg==, tableContent=null), ArticleFig(id=1228662198663311756, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 11, caption=噪声环境下的载荷识别效果对比, figureFileSmall=nrW/YLQ5phMKEgXhUx/yRA==, figureFileBig=du3biVPuXtLcHss3r+rLNg==, tableContent=null), ArticleFig(id=1228662198747197837, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.12, caption=The result of load identification using TDNN based on statistic pooling considering 10% Gaussian noise, figureFileSmall=54x7C79IigGXFCQd0PuHHg==, figureFileBig=NHAC9uNealKKJg9ladur9w==, tableContent=null), ArticleFig(id=1228662198801723790, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图12, caption=10%噪声下基于统计池化的TDNN载荷识别结果, figureFileSmall=54x7C79IigGXFCQd0PuHHg==, figureFileBig=NHAC9uNealKKJg9ladur9w==, tableContent=null), ArticleFig(id=1228662198860444047, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.13, caption=The trending of the optimal of objective function during the iterations, figureFileSmall=gHjhRHnDO0XEPRTdYQ0mqA==, figureFileBig=JyT68iEY9e0N60xMRfUynw==, tableContent=null), ArticleFig(id=1228662198919164304, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 13, caption=迭代过程中目标函数最优值的变化趋势, figureFileSmall=gHjhRHnDO0XEPRTdYQ0mqA==, figureFileBig=JyT68iEY9e0N60xMRfUynw==, tableContent=null), ArticleFig(id=1228662198969495953, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.14, caption=The optimal value of the objective function with different conditions, figureFileSmall=4Sp+cP0ojzO2Pb4XYOAeaQ==, figureFileBig=7zhW+RBw6VOPe9udlEmUZA==, tableContent=null), ArticleFig(id=1228662199024021906, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 14, caption=不同条件下优化结果的目标函数最优值, figureFileSmall=4Sp+cP0ojzO2Pb4XYOAeaQ==, figureFileBig=7zhW+RBw6VOPe9udlEmUZA==, tableContent=null), ArticleFig(id=1228662199082742163, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.15, caption=The optimal sensor placement, figureFileSmall=j8qGSFCeHbZ3gq2HLR+stA==, figureFileBig=5oZiDnbLoZyTlTW3n5kyMw==, tableContent=null), ArticleFig(id=1228662199133073812, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图 15, caption=最优传感器布局示意图, figureFileSmall=j8qGSFCeHbZ3gq2HLR+stA==, figureFileBig=5oZiDnbLoZyTlTW3n5kyMw==, tableContent=null), ArticleFig(id=1228662199183405461, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Fig.A1, caption=The data of the measurement in experiments, figureFileSmall=FrdZDQdLLfnRZO8Y6hOuQA==, figureFileBig=z0moAW6DqVJY1rPyMAMFlA==, tableContent=null), ArticleFig(id=1228662199237931414, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=图A1, caption=试验实测数据, figureFileSmall=FrdZDQdLLfnRZO8Y6hOuQA==, figureFileBig=z0moAW6DqVJY1rPyMAMFlA==, tableContent=null), ArticleFig(id=1228662199296651671, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Tab.1, caption=

Material properties of the structure

, figureFileSmall=null, figureFileBig=null, tableContent=
材料密度/(kg·m‒3)弹性模量/MPa泊松比
EXEYEZ
115507680071400714000.32
215503072028560285600.32
), ArticleFig(id=1228662199355371928, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=表1, caption=

结构的材料属性

, figureFileSmall=null, figureFileBig=null, tableContent=
材料密度/(kg·m‒3)弹性模量/MPa泊松比
EXEYEZ
115507680071400714000.32
215503072028560285600.32
), ArticleFig(id=1228662199414092185, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Tab.2, caption=

Error of load identification with different steps of delay in TDNN system

, figureFileSmall=null, figureFileBig=null, tableContent=
时延步数误差/%
工况1工况2
05.1733.857
14.7432.227
22.3971.585
31.8991.605
43.9302.239
51.9242.194
62.0501.137
72.1640.445
84.5600.473
92.5141.567
104.2561.016
111.3881.006
123.3560.434
133.1351.132
143.6080.728
153.2200.495
164.4240.787
173.5030.601
183.4810.547
193.5490.800
203.7490.743
), ArticleFig(id=1228662199489589658, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=表2, caption=

不同延迟步数下的载荷识别误差

, figureFileSmall=null, figureFileBig=null, tableContent=
时延步数误差/%
工况1工况2
05.1733.857
14.7432.227
22.3971.585
31.8991.605
43.9302.239
51.9242.194
62.0501.137
72.1640.445
84.5600.473
92.5141.567
104.2561.016
111.3881.006
123.3560.434
133.1351.132
143.6080.728
153.2200.495
164.4240.787
173.5030.601
183.4810.547
193.5490.800
203.7490.743
), ArticleFig(id=1228662199548309915, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=EN, label=Tab.3, caption=

Relative error of load identification based on different convolutional kernel

, figureFileSmall=null, figureFileBig=null, tableContent=
卷积核大小卷积核相对误差/%
0%噪声1%噪声3%噪声5%噪声10%噪声
无卷积核(一般BP神经网络)3.8575.3636.2048.78524.751
5[0.2,0.2,0.2,0.2,0.2]3.2993.4994.3685.7067.281
5[0.1,0.2,0.4,0.2,0.1]3.0484.2385.0756.1637.089
7[0.143,0.143,0.143,0.143,0.143,0.143,0.143]3.2253.2753.2534.1825.754
7[0.05,0.1,0.15,0.4,0.15,0.1,0.05]3.6543.7134.6045.1957.164
), ArticleFig(id=1228662199611224476, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228653358949531684, language=CN, label=表3, caption=

使用不同卷积核的载荷识别相对误差

, figureFileSmall=null, figureFileBig=null, tableContent=
卷积核大小卷积核相对误差/%
0%噪声1%噪声3%噪声5%噪声10%噪声
无卷积核(一般BP神经网络)3.8575.3636.2048.78524.751
5[0.2,0.2,0.2,0.2,0.2]3.2993.4994.3685.7067.281
5[0.1,0.2,0.4,0.2,0.1]3.0484.2385.0756.1637.089
7[0.143,0.143,0.143,0.143,0.143,0.143,0.143]3.2253.2753.2534.1825.754
7[0.05,0.1,0.15,0.4,0.15,0.1,0.05]3.6543.7134.6045.1957.164
)], attaches=null, journal=Journal(id=1225147830491308032, delFlag=0, nameCn=振动工程学报, nameEn=Journal of Vibration Engineering, nameHistory1=null, nameHistory2=null, issn=1004-4523, eissn=null, cn=32-1349/TB, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=null, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Vibration Engineering, journalRemark=null, publicationField=null, createdTime=1770027604939, updatedTime=1770169610881, createdBy=18614031015, updatedBy=18614031015, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=null, picEn=null, jcr=null, cjcr=null, exts=[JournalExt(id=1225743346702925905, language=CN, name=振动工程学报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国振动工程学会, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770169587064, updatedTime=1770169587064, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionEditorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionReviewUrl=https://www.manuscripts.com.cn/zdgcxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1225743346765840466, language=EN, name=Journal of Vibration Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770169587079, updatedTime=1770169587079, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionEditorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionReviewUrl=https://www.manuscripts.com.cn/zdgcxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1225147924628267009, websiteList=[Website(id=1225150618881404985, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225147924628267009, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zdgcxb/CN, language=CN, createTime=1770028269739, createBy=18614031015, updateTime=1770028293069, updateBy=18614031015, name=振动工程学报-中文, tplId=1146099689490845704, title=振动工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225151164178673750, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=articleTextType, value=kx, createTime=1770028399748, updateTime=1770028399748, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164157702227, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=banner, value=null, createTime=1770028399743, updateTime=1770028399743, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164203839577, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=grayFlag, value=0, createTime=1770028399754, updateTime=1770028399754, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164145119314, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=logo, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic?fileId=L7mSU8YPwm66NWFMoTG4aQ==, createTime=1770028399740, updateTime=1770028399740, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164212228187, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=minRunFlag, value=0, createTime=1770028399756, updateTime=1770028399756, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164170285141, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/file/pic, createTime=1770028399746, updateTime=1770028399746, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164208033882, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=silenceFlag, value=0, createTime=1770028399755, updateTime=1770028399755, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164166090836, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770028399745, updateTime=1770028399745, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164187062359, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=themeColor, value=null, createTime=1770028399750, updateTime=1770028399750, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164195450968, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=themeStyle, value=null, createTime=1770028399752, updateTime=1770028399752, creator=18614031015, updator=18614031015)]), Website(id=1225150619003039804, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225147924628267009, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zdgcxb/EN, language=EN, createTime=1770028269768, createBy=18614031015, updateTime=1770028309190, updateBy=18614031015, name=振动工程学报-英文, tplId=1146101810881728533, title=Journal of Vibration Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225151193366835296, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=articleTextType, value=kx, createTime=1770028406707, updateTime=1770028406707, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193350058077, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=banner, value=null, createTime=1770028406703, updateTime=1770028406703, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193387806819, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=grayFlag, value=0, createTime=1770028406712, updateTime=1770028406712, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193341669468, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=logo, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic?fileId=L7mSU8YPwm66NWFMoTG4aQ==, createTime=1770028406701, updateTime=1770028406701, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193400389733, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=minRunFlag, value=0, createTime=1770028406715, updateTime=1770028406715, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193362640991, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic, createTime=1770028406706, updateTime=1770028406706, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193392001124, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=silenceFlag, value=0, createTime=1770028406713, updateTime=1770028406713, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193354252382, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770028406704, updateTime=1770028406704, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193371029601, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=themeColor, value=null, createTime=1770028406708, updateTime=1770028406708, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193379418210, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=themeStyle, value=null, createTime=1770028406710, updateTime=1770028406710, creator=18614031015, updator=18614031015)])], journalTitle=振动工程学报, weixinUrl=null, journalUrl=http://zdgcxb.csve.org.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Vibration Engineering, journalPhotoCn=null, journalPhotoEn=null, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2024.10.006, detailUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/10.16385/j.cnki.issn.1004-4523.2024.10.006, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/PDF/10.16385/j.cnki.issn.1004-4523.2024.10.006, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/PDF/10.16385/j.cnki.issn.1004-4523.2024.10.006, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
数据驱动的时延神经网络动载荷识别方法
收藏切换
PDF下载
王磊 1 , 张昊宇 1 , 胡举喜 2 , 顾凯旋 3 , 王振宇 1 , 刘英良 4
振动工程学报 | 2024,37(10): 1688-1697
收起
收藏切换
振动工程学报 | 2024, 37(10): 1688-1697
数据驱动的时延神经网络动载荷识别方法
全屏
王磊1 , 张昊宇1, 胡举喜2 , 顾凯旋3, 王振宇1, 刘英良4
作者信息
  • 1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191
  • 2上海交通大学船舶海洋与建筑工程学院,上海 200240
  • 3航空工业航宇救生装备有限公司试验部, 湖北 襄阳 441003
  • 4中国船舶及海洋工程设计研究院,上海 200011
  • 王磊(1987—),男,博士,副教授。E-mail:

通讯作者:

胡举喜(1981—),女,博士,研究员。E-mail:
A data-driven dynamic load identification method based on time-delay neural networks
Lei WANG1 , Hao-yu ZHANG1, Ju-xi HU2 , Kai-xuan GU3, Zhen-yu WANG1, Ying-liang LIU4
Affiliations
  • 1National Key Laboratory of Strength and Structural Integrity,School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China
  • 2School of Naval Architecture,Ocean & Civil Engineering,Shanghai Jiao Tong University,Shanghai 200240,China
  • 3Test Department,Aviation Industry Aerospace Lifesaving Equipment Co.,Ltd.,Xiangyang 441003,China
  • 4Marine Design & Research Institute of China,Shanghai,200011,China
出版时间: 2024-10-28 doi: 10.16385/j.cnki.issn.1004-4523.2024.10.006
文章导航
收藏切换

载荷识别是指根据测量的结构响应重构结构载荷的问题,属于力学中的反问题。本文提出了一种基于时延神经网络的载荷识别方法,通过实验和仿真相结合的数值算例验证表明,这一方法相比于一般的反向传播神经网络具有更高的识别精度;在时延神经网络的基础上,引入了统计池化的思想,并与普通的神经网络载荷识别方法相比较,证明了该方法在不同强度的噪声环境下均具有良好的识别效果;基于上述载荷识别方法,提出了一种基于粒子群优化算法的传感器布局优化策略,相比于随机的传感器布局,优化后的传感器布局可以在考虑传感器安装间距的同时,将载荷识别误差降低90%以上,有效提高了载荷识别精度。

载荷识别  /  时延神经网络  /  粒子群优化  /  反向题

The problem of load identification denotes identifying loads based on the measurement of structural responses,which is the inverse problem in structural dynamics. A load identification method based on time-delay neural network is proposed in this paper,and numerical examples based on simulation and experiments are provided to show that the method overperforms normal back-propagation neural network in accuracy of identification. Additionally,statistic pooling is introduced on the basis of the method,and it is proved that the method performs well in noisy environment compared with BP neural networks. based on the load identification methods mentioned above,a sensor placement optimization based on particle swarm optimization algorithm is proposed,and the optimal sensor placement is able to reduce the error of identification by 90% compared with the random sensor placements,meanwhile the minimum spacing of installation among sensors is also ensured during the optimization.

load identification  /  time-delay neural network  /  particle swarm optimization  /  inverse problem
王磊, 张昊宇, 胡举喜, 顾凯旋, 王振宇, 刘英良. 数据驱动的时延神经网络动载荷识别方法. 振动工程学报, 2024 , 37 (10) : 1688 -1697 . DOI: 10.16385/j.cnki.issn.1004-4523.2024.10.006
Lei WANG, Hao-yu ZHANG, Ju-xi HU, Kai-xuan GU, Zhen-yu WANG, Ying-liang LIU. A data-driven dynamic load identification method based on time-delay neural networks[J]. Journal of Vibration Engineering, 2024 , 37 (10) : 1688 -1697 . DOI: 10.16385/j.cnki.issn.1004-4523.2024.10.006
近年来,随着计算机软硬件的进步,机器学习算法蓬勃发展,不少学科领域开始引入机器学习方法进行研究,其中较为常见的就是神经网络算法。自20世纪40年代McCulloch等1首次提出人工神经网络的概念以来,里程碑式的发明不断涌现,例如感知机模型2、反向传播算法3、卷积神经网络4、深度学习5等。
在结构动力学中,载荷识别问题是一类根据测量所得的结构响应来重构结构载荷的逆问题。在基于神经网络的载荷识别方法被提出之前,传统的载荷识别方法主要分为两种:频域法和时域法,这两种方法发展较早,各有其优缺点。近年来,随着机器学习方法的快速发展,一些基于人工智能算法衍生而来的载荷识别新方法逐渐进入了人们的视野。由于神经网络在数据处理方面的巨大潜力,以及可直接建立数据映射关系的独特优势,该算法也逐渐开始被应用于解决载荷识别问题中。而近年来对基于神经网络的载荷识别方法的研究也展现出神经网络在该领域中的广阔前景。将载荷识别与机器学习相结合的研究起步于20世纪末,Omkar等6在研究直升机桨毂的受力时,利用神经网络算法解决了剪切应力的最小化问题。Trivailo等7利用神经网络实现了气动力载荷重构;近几年来,基于机器学习的载荷识别算法有了进一步的发展,在机器学习算法的推动下,载荷识别的精度得到了进一步的改善,且有更多的新方法、神经网络的新应用被提出。Liu等8提出了一种新的通用物理信息神经网络材料(NNMat)模型,该模型采用分层学习策略实现了对生物软组织本构建模中的机械行为的应力分析;Wu等9提出了一种基于深度卷积神经网络(CNN)的方法来估计线性单自由度(SDOF)系统、非线性SDOF系统、以及3层多自由度(MDOF)系统的钢框架的动态响应;Liu等10建立了一种虚拟载荷场方法来重构结构表面的分布气动力;Liu等10针对工程结构中普遍存在的多源不确定因素,提出了一种基于人工神经网络(Artificial Neural Network,ANN)和贝叶斯概率框架(BPF)的动态力载荷重构方法;Yang等11提出了一种基于深度扩张卷积神经网络(DCNN)的动态载荷识别方法,该方法具有很强的抗噪声能力,并且在参数、测量点分布不确定的情况下具有良好的精度、可靠性鲁棒性和频率数据;Zhou等12针对非线性结构,提出了一种利用深度循环神经网络(RNN)的冲击载荷识别方法,即使在冲击位置未知的情况下也能成功识别复杂的冲击载荷;Li等13提出了将插值模型与反向传播(Back Propagation,BP)神经网络相结合的K-BP模型,提高了应变场反演和载荷识别的精度,并证明该方法能够以较少的样本获得良好的载荷识别效果。
在实际工程应用中,对结构或系统的测量中总会包含系统误差,而一些载荷识别方法对噪声等不确定性十分敏感,频域法可能会因为噪声而发生矩阵病态现象,基于模型的模态分析法等时域分析方法会因为噪声而产生累计误差。也有一些研究针对载荷识别中的噪声问题进行了改良,何文博等14提出了一种基于冗余扩展余弦变换字典的L1范数正则化载荷识别方法,该方法在实际测量噪声的影响下取得了准确的识别结果,具有良好的鲁棒性;Tang等15提出了一种基于脉冲响应函数矩阵的最大奇异值和信噪比的正则化参数方法,有效提高了噪声环境下的载荷识别准确性。
在载荷识别中,传感器是结构响应的直接来源,传感器布局位置在载荷识别过程中也起着重要作用。有不少机器学习方法被应用于传感器最优布局的求解中。欧阳运芳等16基于振动分量,根据平均值筛选原则来优化振动传感器测点,克服了航空发动机结构复杂、激励源多的主要困难;Błachowski等17使用贪心算法和凸松弛-凸优化方法,以Kammer有效独立性(Kammer’s Effective Independence,EFI)为准则,解决了承受移动载荷的大型土木工程结构中载荷相关的最佳传感器布局问题;Lee等18设计了一种基于模态置信准则(Modal Assurance Criterion,MAC)和有效独立性(EFI)的算法,经过迭代从而求出最优传感器布局。
与时域法、频域法等载荷识别方法相比,传统的载荷识别方法,例如模态分析方法等,往往是基于模型本身,当模型较为复杂时,计算量会变得极大,且有限的模型信息往往难以描述整个模型,因此精度也会严重地受到影响;而神经网络具有直接建立数据之间的直接映射关系的特点,因此在载荷识别中,神经网络可以忽略物理模型本身,直接建立响应数据与载荷数据之间的联系,可以解决对于复杂模型以及复杂载荷的载荷识别问题,这是神经网络方法最为明显的优点之一;另外,由于神经网络模型的高度非线性化特点,因此噪声等不确定性干扰的环境对载荷识别结果的影响较小。在神经网络算法中,时延神经网络(Time Delay Neural Networks,TDNN)是一类被用于处理序列数据的人工神经网络,最早于1988年被Waibel等19提出,被应用于语音信息的处理与识别;考虑到神经网络在载荷识别问题中表现出的优势,因此,本文提出了一种基于时延神经网络的动态载荷识别方法,通过测量结构的时域信号重构结构载荷,利用时延神经网络处理信号输入,并对噪声环境下的载荷识别的效果进行对比研究。在此基础上,本文进一步提出了一种基于粒子群优化的传感器布局多层优化策略,以载荷识别精度为优化目标,求解最优传感器布局,以实现载荷识别精度的最大化。
人工神经网络(ANN)是一种模仿生物神经网络的构造和工作原理、模拟人脑神经系统对复杂信息的处理机制的数学模型。神经网络模型具有高度的非线性、强大的自学习、自组织和自适应能力,能够构建数据之间的直接映射。在一般的神经网络的基础上,时延神经网络基于输入信号的上下文进行建模、提取特征;在TDNN 中,每层神经网络结构中的每个神经单元不仅接收来自下层的特征输入,还会接收来自上下文的输入,以实现对输入模式的分类。
一个人工神经网络一般由输入层、一个或多个隐藏层以及输出层组成。神经网络通过调整权重,不断训练和学习,得出输入和输出之间的关系。以BP网络的学习为例,其学习过程由四个过程组成:首先是模式传递过程,输入模式由输入层经由中间层向输出层传递;其次是误差传递过程,该过程先计算误差信号,即网络的期望输出与网络的实际输出之差,再将误差信号由输出层经由中间层向输入层逐层修正连接权;然后是网络记忆训练过程,通过模式顺传播与误差逆传播的反复交替实现;最后是网络趋向收敛的学习收敛过程,即网络的全局误差趋向极小值。当目标实际输出的偏差小于阈值或训练次数达到给定限制时,学习过程结束。其一般结构如图 1所示。神经网络的搭建步骤如下:
(1)收集数据以构建训练集,应包括输入和输出两部分,并具有一一对应关系;
(2)标准化、归一化等数据预处理工作,以免出现梯度爆炸或消失的问题;
(3)构建神经网络结构,确认训练参数;
(4)训练神经网络;
(5)验证与测试。
传统的神经网络处理时域信号时,往往是一个离散时间点内的输入信号对应于一个离散时间点的输出;为了更好地处理时序问题,在普通的神经网络的基础上进一步引入时延神经网络的概念。该网络与普通的神经网络最主要的区别在于它可以同时输入多个时间点的输入数据。时延神经网络的结构如图2所示,图中展示了一个时延步数为d的神经网络。该神经网络系统首先对原始输入信号进行了时延处理,将输入信号向量,…,合并为一个新的向量,其中下标表示离散时间点编号;将处理后的序列作为神经网络的输入进行运算。
上一节中介绍了时延神经网络的基本结构与形式。然而,若输入信号含有噪声等干扰,该时延神经网络的识别效果会受到较明显的影响。Snyder等20在处理语音信号时,在时延神经网络中引入了统计池化的处理方法,这一方法通过对信号的卷积运算,将信号进行“池化”,从而达到提取信号特征的目的。这一处理方式有助于降低噪声等干扰对载荷识别结果的影响。
在一个时延步数为d的神经网络中,将原始输入信号向量,…,进行加权和计算处理,得到一个新的序列,即
式中  被称为卷积核。为了使变换后的序列的时间长度与原始信号长度一致,需要在原始信号的开始与结尾两端加入“0”作为填充,如图3所示。
对于第k个离散时间点的信号,若时延神经网络读入的输入信号上下文范围为 ,则需要先在原始信号的起点处加入个“0”,在结束后加入个“0”作为填充。
训练一个用于解决载荷识别问题的时延神经网络包含以下4个步骤:
(1)为神经网络的训练集样本设定随机载荷样本,并定义对应的数据格式;
(2)有限元分析计算载荷样本对应的结构响应,形成训练集数据集;
(3)设计TDNN的参数。一方面,对于神经网络自身来说,需要确定其隐藏层层数、神经元及其激活函数、收敛条件以及学习速率等训练参数;另一方面,对于TDNN,还需要确定该神经网络中的时延步数、卷积核的取值。设定完毕后,根据训练集训练神经网络模型;
(4)训练完成后,将待识别的结构响应数据输入到神经网络中,并定义相关指标,以分析识别结果的准确性。对于动态集中载荷的重构,可以把识别误差定义为重构结果和真实值之间的相对误差,即
式中  表示L2范数。
传感器布局优化也是载荷识别中的一个重要问题。一方面,由于传感器的数量远少于结构的有限元模型的自由度,因此,需要找出传感器的最优布局,以改善载荷识别的效果;另一方面,由于在实际的载荷识别问题中,在结构表面安装传感器存在一定的难度,因此传感器的数量、传感器之间的间距等方面也会受到限制,所以需要确保设定的传感器布局方案可以应用于实际的载荷识别问题中。传感器布局的优化可以通过粒子群优化(Particle Swarm Optimization,PSO)算法来完成。
粒子群优化算法类似于鸟类觅食的过程:分散在各处的鸟群最终会在食物最多的地点聚集21。而粒子群优化算法首先在全局展开搜索,找到可能的极值点范围后就会在此区间进行更密集的搜索,经过多次迭代后就能找到全局最优解。
粒子群优化算法的一般流程为:
首先构造函数,量化特定传感器布局下的载荷识别效果。在传感器布局中主要考虑精度以及传感器间距限制两个方面,因此可以表示为:
式中  error项表示在当前传感器布局下载荷识别的误差,其定义方式即式(2);而为了防止传感器之间的间距过小,设定了penalty项用于排除这些不符合传感器安装条件限制的布局,其定义为:
式中  K为传感器总数;为第i个传感器的位置向量;为设定的传感器最小安装间距。布局中的传感器坐标可以用一个向量来表示,构成了算法中的自变量,即
因此,传感器布局优化的问题就转化为求解函数Obj的最小值点的问题。
然后进行初始化,设定粒子运动的范围、运动速度范围;随机设定粒子初始位置与速度;定义学习率参数的值;确定粒子数量、迭代周期上限、传感器数量范围等。
接着,启动PSO算法,每一步迭代中,粒子的速度和位置会按照局部极值和全局极值进行更新,对于第i步的更新为:
式中  分别表示第j个粒子的位置和速度;为在区间[0,1]上的随机数;G分别为目前的局部最优解和全局最优解,二者分别表示单个粒子曾到达过的极值点和所有粒子曾到达过的极值点;为惯性参数;为学习参数。
受到一项关于自适应PSO算法的研究启发22,为了改善算法的搜索能力与效率,在迭代计算过程中,学习参数也会更新自身:
一般取为设定的迭代步数上限。
最后,经过多次迭代,当满足终止条件时,G的取值即为全局最优解。
2.1节给出了传感器布局优化的基本方法。然而,本文中的传感器布局优化问题包含了三个方面的优化:首先,需要确定传感器的数量;其次,要确认TDNN模型延迟的步数;最后,在上述两个基本条件下,找出传感器的最优布局位置。针对上述三个方面,本文提出了如图 4所示的多层优化流程。其基本思想为通过遍历不同的优化条件,找出最佳的传感器数量和TDNN延迟步数组合,并在该参数组合下求解最优传感器布局。
本节以一个复合材料薄板及其修正后的有限元模型为例,分析其在冲击载荷、以及集中动态载荷作用下的响应,并以此为输入进行载荷识别;最后,将载荷识别结果与真实载荷数据作对比,分析载荷识别方法的识别误差。
图 5图 6展示了该复合材料薄板的实物外观、传感器布置以及对应的有限元模型。其中圆孔处即为加载点;复合材料的铺层方式为[45/0]5。材料属性如表1所示。
对于图 5所示的模型,首先通过试验加载的结果来修正图 6中的模型,使模型在同等加载条件下的结构响应与试验结果一致(具体图表详见附录);然后,在加载点处按如下两种工况进行加载,并通过有限元正向计算传感器位置处的数据:
工况1:冲击载荷,分别于0.480 s和1.200 s时产生峰值约为400 N和725 N的冲击力;
工况2:动力集中载荷,用关于时间的函数可以近似表示为
图 7展示了所构建的神经网络的结构。其中,神经网络的训练是基于Levenberg-Marquardt优化算法实现的,隐藏层共包含三层,采用的激活函数类型分别为线性、双极性S函数、线性,神经元个数分别为4,11,2个;图 8展示了工况2中的训练集数据,该训练集由20组随机的载荷样本及其对应的结构响应数据组成。表2图 9列举并对比了不同延迟步数的TDNN在载荷识别中的相对误差。特别地,当延迟步数为0时,TDNN即为一般的BP神经网络系统。从表2图 9中可知,相比于一般的BP神经网络(延迟步数为0),延迟1~20步的TDNN在载荷识别中的精度均优于无延迟的普通神经网络;在两种工况中,当延迟步数分别为11和12步时,载荷识别的精度最高。在工况1中,误差最小的为延迟11步的TDNN,其相对识别误差为1.388%,相比于普通的BP网络,误差降低了73.2%,而工况2中延迟12步的TDNN则将相对误差降低了88.7%,说明在TDNN中选用恰当的延迟步数可以显著改善载荷识别的精度。两个最优解的识别误差与普通BP网络的识别结果对比如图 10所示。
通过上述对比,发现当TDNN延迟步数为11或12步,即延迟步数适中时,可以最大限度地降低载荷识别误差。这是因为当延迟步数较少时,输出的识别载荷值只与较少的时间点相关联,因此精度不高;而当延迟步数较多时,识别载荷值与过多的时间点相关联,输入信号的时间跨度过大,反而又会对载荷识别结果构成干扰,因此精度会下降;只有当延迟步数适中时,才能取得最佳的载荷识别精度。
在实际的载荷识别问题中,传感器自身存在着测量误差,且结构实际工作环境中必然存在噪声,因此,有必要在载荷识别问题中考虑噪声带来的影响。
本算例通过有限元仿真的方式来模拟高斯白噪声环境下的载荷识别。此类噪声对原始信号的干扰量符合标准高斯分布N(0,1),因此,将有限元计算得到的响应信号中按照如下方式进行变换:
式中  s’s分别为含噪声信号和原始信号的n维向量; SNR为信噪比,表示信号和噪声干扰量的比值;randn(1,1)为按照标准高斯分布产生单个随机数的函数。
图 11分别展示了无噪声、5%噪声和10%噪声下,针对3.1节中的冲击载荷工况,基于一般的BP神经网络的载荷识别结果。从图中不难看出,当输入的信号含有较强噪声时,载荷识别结果将会表现出很明显的波动与偏差,在图像中表现为幅度极大的锯齿状。表3中也展示了噪声环境下载荷识别的相对误差,说明噪声对载荷识别的精度有极其显著的负面影响。为了降低噪声带来的干扰,本算例利用第1.3节中提及的基于统计池化的TDNN处理含噪信号。
表3展示了基于4种不同取值的卷积核的TDNN对噪声环境下载荷识别效果的改善情况。对于卷积核的取值,有两种思路:其一,将时间点及其相邻时间点的输入信号以相同的权重相加,例如延迟5步的卷积核,其取值为[0.2,0.2,0.2,0.2,0.2];其二,降低相邻时间点的权重,与给定时间点之间间隔越远的输入,其权重越低,例如延迟5步的卷积核,其取值为[0.1,0.2,0.4,0.2,0.1]。值得说明的是,本节所采用的卷积方法仅为探究TDNN在噪声环境下的载荷识别表现,不代表该取值是最优的。图 12展示了在10%噪声环境下,延迟步数为5步、卷积核取值为[0.2,0.2,0.2,0.2,0.2]的TDNN的载荷识别效果。与图 11中基于普通BP神经网络的载荷识别结果相比,可以看出基于统计池化的TDNN载荷识别方法在噪声环境下也有较好的表现,对于含噪信号的处理有着明显的优势。
在3.1节动载荷识别的基础上,对传感器布局进行优化。在基于TDNN的载荷识别方法中,除了传感器位置以外,需要考虑如下两个相互独立的优化变量:传感器的数量和TDNN的延迟步数。在本算例中,考虑传感器的数量为3~9个,TDNN的延迟步数为9~13步;而PSO优化算法的过程已经在2.2节给出,其中各项参数的取值为:粒子数N = 10,传感器安装最小间距为10 mm,最大迭代步数为250步。
在优化开始之前,需要先计算所有样本点中结构的所有传感器备选位置处的结构响应,以构成训练集;在优化的过程中,每一次改变传感器布局的位置,都需要根据传感器的布局位置从训练集中选取数据,并重新训练和测试神经网络。而这一过程消耗的计算时间只与神经网络构造、训练学习参数、训练集的规模有关,与模型自身的复杂程度无关,保证了该优化算法的优化效率。
图13展示了迭代过程中目标函数最优值的变化过程。在优化的早期,学习参数c1较大,c2较小,在全局的搜索范围比较广泛,因此目标函数值迅速下降,逼近最优解;而后期c1减小,c2增大,则加强了算法的局部搜索能力,能够以更短的搜索步长对最优解进行更详细地搜索,从而提高了该方法的优化效率。
将不同传感器数量、不同TDNN时延步数下的优化结果汇总,并针对目标函数最优值进行比较,最终得出在TDNN延迟10步、传感器数量为6个时取得传感器布局的最优解,如图 14所示。具体的传感器布局位置如图 15所示。
最后,再对比分析传感器布局优化对载荷识别效果的改进情况。仍以图 13为例,图中的优化条件为TDNN延迟10步、传感器数量6个,观察优化迭代过程的第一迭代步和最后一步可知,在初始化时随机选取的传感器布局方案中,载荷识别的相对误差达到了29.4%;而通过基于PSO算法的传感器布局优化找出的全局最优解中,载荷识别的误差降低到了2.46%。上述数据表明,传感器布局优化可以明显改善载荷识别的精度。
本文提出了一种基于时延神经网络的载荷识别方法,研究了时延神经网络在载荷识别问题中的应用;同时,提出了基于统计池化方法的噪声环境下的载荷识别方法;最后在载荷识别方法的基础上,针对给定结构进行了传感器布局优化,改善了载荷识别效果。从本文的工作中可以初步得出以下结论:
(1) 通过动载荷加载、冲击载荷加载这两种比较具有代表性的加载工况的数值算例验证了基于时延神经网络的载荷识别方法的效果,经验证,该方法的识别精度优于一般的BP神经网络载荷识别方法;并研究了不同延迟时间步数下的载荷识别精度,确定了在给定的两种加载工况中最佳的延迟步数为11或12步。
(2) 在TDNN中应用统计池化的思想,通过与一般的BP神经网络载荷识别方法的对比,表明了基于统计池化的TDNN载荷识别方法在不同强度的噪声环境下具有更高的载荷识别精度。
(3)在上述载荷识别方法的基础上,针对给定结构实施了基于粒子群优化算法的面向精度的传感器布局多层优化策略,该优化方法在确保传感器布局方案现实可行的同时,还确定了最佳的传感器数量、神经网络延迟步数以及对应的传感器布置位置,最终的传感器布局最优解经验证,将载荷识别误差降低至2.46%,相比于初始时的随机布局,误差指标降低了91.6%,证实了该方法的可行性和效果。
(4)本文中的传感器布局优化方法是基于已知的载荷,即优化算法是与载荷相关的。因此,在启动该优化算法前,需要根据结构的工作环境对载荷作用点与形式作初步的估计,而这也是该方法的主要局限性。如果要实现与载荷无关的传感器布局优化,则需要对结构特性进行进一步的分析。例如,在文献[23]中,传感器布局优化是基于模态、插值精度等多目标进行的,其优化过程与载荷无关。未来将进一步研究与载荷无关的传感器优化问题。
  • 国防基础科研计划项目(JCKY2019205A006)
参考文献 引证文献
排序方式:
[1]
McCulloch W SPitts W. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biophysics19435: 115-33.
[2]
Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain[J]. Psychological Review195865(6): 386-408.
[3]
Rumelhart D EHinton G EWilliams R J. Learning representations by back-propagating errors[J]. Nature1986323(6088): 533-536.
[4]
LeCun YBottou LBengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE199886(11): 2278-2324.
[5]
Hinton G ESalakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science2006313(5786): 504-507.
[6]
Omkar S NNagabhushanam J. Neural network controller for minimizing hub shear forces in helicopter[C]// 1998 IEEE International Symposium on Intelligent Control (ISIC) Held Jointly with IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA). Gaithersburg, USA, 1998 :354-358.
[7]
Trivailo P MCarn C L. The inverse determination of aerodynamic loading from structural response data using neural networks[J]. Inverse Problems in Science and Engineering200614(4): 379-395.
[8]
Liu M LLiang LSun W. A generic physics-informed neural network-based constitutive model for soft biological tissues[J]. Computer Methods in Applied Mechanics and Engineering2020372: 113402.
[9]
Wu R TJahanshahi M R. Deep convolutional neural network for structural dynamic response estimation and system identification[J]. Journal of Engineering Mechanics2019145(1): 04018125.
[10]
Liu Y RWang LGu K X, et al. Artificial neural network (ANN)-Bayesian probability framework (BPF) based method of dynamic force reconstruction under multi-source uncertainties[J]. Knowledge-based Systems2022237: 107796.
[11]
Yang H JJiang J HChen G P, et al. Dynamic load identification based on deep convolution neural network[J]. Mechanical Systems and Signal Processing2023185: 109757.
[12]
Zhou J MDong L LGuan W, et al. Impact load identification of nonlinear structures using deep Recurrent Neural Network[J]. Mechanical Systems and Signal Processing2019133: 106292.
[13]
Li JYan J JZhu J J, et al. K-BP neural network-based strain field inversion and load identification for CFRP[J]. Measurement2022187: 110227.
[14]
何文博,许步锋,冯振宇,等. 利用冗余扩展余弦字典的复杂动载荷识别研究[J]. 振动工程学报202437(3):512-521.
He W BXu B FFeng Z Y, et al. Identification of complex dynamic load using redundant extended cosine transform dictionary[J]. Journal of Vibration Engineering202437(3):512-521.
[15]
Tang Z HZhang Z FZan M, et al. The determination of the regularization parameter based on signal-to-noise ratio in load identification[J]. Journal of Vibration and Control202329(19-20): 4479-4491.
[16]
欧阳运芳,何鹏,刘占生. 基于有限元仿真的航空发动机振动传感器布局优化方法研究[J].汽轮机技术201860(5): 359-362.
Ouyang Y FHe PLiu Z S. Investigation of the optimization method of the vibration transducer layout of aero engine[J]. Turbine Technology201860(5): 359-362.
[17]
Błachowski BŚwiercz AOstrowski M, et al. Convex relaxation for efficient sensor layout optimization in large‐scale structures subjected to moving loads[J]. Computer‐Aided Civil and Infrastructure Engineering202035(10): 1085-1100.
[18]
Lee E TEun H C. An optimal sensor layout using the frequency response function data within a wide range of frequencies[J]. Sensors202222(10): 3778.
[19]
Waibel AHanazawa THinton G, et al. Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models[C]//ICASSP-88, International Conference on Acoustics, Speech, and Signal Processing. New York, USA,1988:107-110.
[20]
Snyder DGarcia-Romero DSell G, et al. X-vectors: Robust dnn embeddings for speaker recognition[C]// 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018). Calgary, Canada, 2018: 5329-5333.
[21]
Kennedy JEberhart R. Particle swarm optimization[C]//Proceedings of ICNN'95-International Conference on Neural Networks. Perth, Australia, 1995:1942-1948.
[22]
Xie X FZhang W JYang Z L. Adaptive particle swarm optimization on individual level[C]//Proceedings of the 6th International Conference on Signal Processing(ICSP’02). 2002:1215-1218.
[23]
Liu Y RWang L. Multiobjective-clustering-based optimal heterogeneous sensor placement method for thermo-mechanical load identification[J]. International Journal of Mechanical Sciences2023253: 108369.
2024年第37卷第10期
PDF下载
106
55
引用本文
BibTeX
文章信息
doi: 10.16385/j.cnki.issn.1004-4523.2024.10.006
  • 接收时间:2024-05-08
  • 首发时间:2026-02-12
  • 出版时间:2024-10-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-05-08
  • 修回日期:2024-08-01
基金
国防基础科研计划项目(JCKY2019205A006)
作者信息
    1北京航空航天大学航空科学与工程学院强度与结构完整性全国重点实验室,北京 100191
    2上海交通大学船舶海洋与建筑工程学院,上海 200240
    3航空工业航宇救生装备有限公司试验部, 湖北 襄阳 441003
    4中国船舶及海洋工程设计研究院,上海 200011

通讯作者:

胡举喜(1981—),女,博士,研究员。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2024.10.006
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