基于卷积神经网络的荷载大小与位置同步识别

TU311.3; 结构健康监测和状态评估中现有大多数研究均需要精确的荷载作用位置或详细的荷载时程,为了同时获得荷载大小和位置,构建并训练了同时具备分类和回归能力的两分支卷积神经网络,建立了融合分类问题和回归问题的损失函数,提取结构响应与荷载大小、结构响应与荷载位置间的映射关系.通过数值简支梁算例和三层试验框架验证了该方法识别结构荷载大小和位置的精度.结果表明:噪声条件下数值模型的荷载识别误差在8％以内,荷载位置识别准确率在95％以上;实际结构的荷载识别误差在18％以内,荷载位置识别准确率为100％.两分支卷积神经网络可以很好地同时识别荷载大小和位置....

Full description

Saved in:
Bibliographic Details
Published in东南大学学报（自然科学版） Vol. 54; no. 1; pp. 110 - 116
Main Authors 翁顺, 郭街震, 于虹, 陈志丹, 颜永逸, 赵丹阳
Format Journal Article
LanguageChinese
Published 华中科技大学土木与水利工程学院,武汉 430074%中铁第四勘察设计院集团有限公司,武汉 430063 2024
Subjects
convolutional neural network(CNN)
deep learning
卷积神经网络
荷载识别
深度学习
加速度响应
acceleration response
load identification
Online AccessGet full text
ISSN1001-0505
DOI10.3969/j.issn.1001-0505.2024.01.014

Cover

Abstract TU311.3; 结构健康监测和状态评估中现有大多数研究均需要精确的荷载作用位置或详细的荷载时程,为了同时获得荷载大小和位置,构建并训练了同时具备分类和回归能力的两分支卷积神经网络,建立了融合分类问题和回归问题的损失函数,提取结构响应与荷载大小、结构响应与荷载位置间的映射关系.通过数值简支梁算例和三层试验框架验证了该方法识别结构荷载大小和位置的精度.结果表明:噪声条件下数值模型的荷载识别误差在8％以内,荷载位置识别准确率在95％以上;实际结构的荷载识别误差在18％以内,荷载位置识别准确率为100％.两分支卷积神经网络可以很好地同时识别荷载大小和位置.
AbstractList TU311.3; 结构健康监测和状态评估中现有大多数研究均需要精确的荷载作用位置或详细的荷载时程,为了同时获得荷载大小和位置,构建并训练了同时具备分类和回归能力的两分支卷积神经网络,建立了融合分类问题和回归问题的损失函数,提取结构响应与荷载大小、结构响应与荷载位置间的映射关系.通过数值简支梁算例和三层试验框架验证了该方法识别结构荷载大小和位置的精度.结果表明:噪声条件下数值模型的荷载识别误差在8％以内,荷载位置识别准确率在95％以上;实际结构的荷载识别误差在18％以内,荷载位置识别准确率为100％.两分支卷积神经网络可以很好地同时识别荷载大小和位置.
Abstract_FL Most of the existing research in structural health monitoring and status assessment requires accurate load action locations or detailed dynamic load schedules.To simultaneously obtain the size and location of the dynamic load,a two-branch convolutional neural network with both classification and regression capabili-ties is constructed and trained.A loss function that integrates classification and regression problems is estab-lished to capture the mapping relationship between structural response and load magnitude,as well as be-tween structural response and load location.The identification accuracy of load magnitude and location is demonstrated through numerical cantilever beam examples and a three-layer experimental framework.Results show that under noisy conditions,the error in load magnitude identification of the numerical model is within 8％,and the accuracy of load location identification is above 95％.For real structures,the error in load magnitude identification is within 18％,and the accuracy of load location identification is 100％.The two-branch convolutional neural network can effectively identify both the magnitude and location of dynamic loads.
Author 于虹
翁顺
赵丹阳
陈志丹
郭街震
颜永逸
AuthorAffiliation 华中科技大学土木与水利工程学院,武汉 430074%中铁第四勘察设计院集团有限公司,武汉 430063
AuthorAffiliation_xml – name: 华中科技大学土木与水利工程学院,武汉 430074%中铁第四勘察设计院集团有限公司,武汉 430063
Author_FL Chen Zhidan
Zhao Danyang
Yu Hong
Weng Shun
Guo Jiezhen
Yan Yongyi
Author_FL_xml – sequence: 1
  fullname: Weng Shun
– sequence: 2
  fullname: Guo Jiezhen
– sequence: 3
  fullname: Yu Hong
– sequence: 4
  fullname: Chen Zhidan
– sequence: 5
  fullname: Yan Yongyi
– sequence: 6
  fullname: Zhao Danyang
Author_xml – sequence: 1
  fullname: 翁顺
– sequence: 2
  fullname: 郭街震
– sequence: 3
  fullname: 于虹
– sequence: 4
  fullname: 陈志丹
– sequence: 5
  fullname: 颜永逸
– sequence: 6
  fullname: 赵丹阳
BookMark eNo9j89Kw0AYxPdQwVr7FoKnxG-_ZDdZ8CLFf1DwoueSzSbSIltwEfsAIh5sq1cRvVh6EK23SkveJnHzGEYUYWBgDjPzWyM13dcJIRsUXE9wsdVzu8ZolwJQBxgwFwF9F2glv0bq__kqaRrTlUARBSDyOtkunhf5YlQM53Y6s5Mnuxzb7N4uH-3DVTmcl1lWvEyLj3H-Ocqzoc3ei7vbr7dJObsubl7XyUoanZmk-ecNcrK3e9w6cNpH-4etnbZjaPXDiVDxABULEKXPGDKOSZR4ccoTlLEKKYQeAktFAJEUNAiV70umeCrCWEkAr0E2f3svI51G-rTT61-c62qxo7QaDOQPLdCK1fsGM41jyA
ClassificationCodes TU311.3
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.3969/j.issn.1001-0505.2024.01.014
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL Synchronized identification of dynamic load magnitude and location based on convolutional neural network
EndPage 116
ExternalDocumentID dndxxb202401014
GrantInformation_xml – fundername: (国家重点研发计划); (国家自然科学基金); (国家自然科学基金); (华中科技大学交叉研究支持计划资助项目); (中铁第四勘察设计院集团有限公司资助项目); (中铁第四勘察设计院集团有限公司资助项目)
  funderid: (国家重点研发计划); (国家自然科学基金); (国家自然科学基金); (华中科技大学交叉研究支持计划资助项目); (中铁第四勘察设计院集团有限公司资助项目); (中铁第四勘察设计院集团有限公司资助项目)
GroupedDBID 2B.
4A8
92I
93N
ADMLS
ALMA_UNASSIGNED_HOLDINGS
PSX
TCJ
ID FETCH-LOGICAL-s1024-a2d672d5722b4552562eae3cf6e2bcd81083205f970ab9178d44b5d6f98cdb003
ISSN 1001-0505
IngestDate Thu May 29 04:08:38 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords convolutional neural network(CNN)
deep learning
卷积神经网络
荷载识别
深度学习
加速度响应
acceleration response
load identification
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1024-a2d672d5722b4552562eae3cf6e2bcd81083205f970ab9178d44b5d6f98cdb003
PageCount 7
ParticipantIDs wanfang_journals_dndxxb202401014
PublicationCentury 2000
PublicationDate 2024
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 2024
PublicationDecade 2020
PublicationTitle 东南大学学报（自然科学版）
PublicationTitle_FL Journal of Southeast University(Natural Science Edition)
PublicationYear 2024
Publisher 华中科技大学土木与水利工程学院,武汉 430074%中铁第四勘察设计院集团有限公司,武汉 430063
Publisher_xml – name: 华中科技大学土木与水利工程学院,武汉 430074%中铁第四勘察设计院集团有限公司,武汉 430063
SSID ssib012290226
ssib002258162
ssib036435511
ssib008679709
ssib023167012
ssib000947520
ssib021009659
ssib057620145
ssib000969306
ssib001128997
ssib006563446
ssib002039847
ssib006703054
ssib051368071
ssib004675274
Score 2.379443
Snippet TU311.3;...
SourceID wanfang
SourceType Aggregation Database
StartPage 110
Title 基于卷积神经网络的荷载大小与位置同步识别
URI https://d.wanfangdata.com.cn/periodical/dndxxb202401014
Volume 54
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NaxQxFB_qFsSLKCp-00Nzkq2TzCSTgJfJ7pQi6sUWeivzqact2BZKTx5EPNhWryJ6sfQgWm-Vlv1vuk7_DN_LpLtpqZ8wDG-zL-_93nvZfXkhk_G8SZXzyM9L2c6rDAoU5at2liraVkUVqCpP8UgW3G3xSMzMhffn-fxY67mza2llOZvK1059ruR_ogptEFd8SvYfIjsUCg1AQ3zhDhGG-1_FmCScqGmiY5KEeJcJtsgu0RFJIhLDNW0IYEuQ0JpI06K7RFHbojpIKOgekkQedZfIAxcIjEMUBYT2TXfQJY2uEBmAvxEYG-0KeECgIHEX9YIcwCCFAQa0dmfDVhQCMLBVdEwdShAOIYiMjUwwuYPSEC1YFyMAAK-FtRpNG_aCr5RhbnoNFz4MaoAGvIrElIxWLLBBBtgf0VMDSyHKUdJ2HA74FdHK7awahRzlY2djpWWxKyxstLZqjbcOlUbv0Axjs_RP9wtAgvADDxCxdAIjMFQ6PHK6MljMOEDJwKMdOQZvzODHdhQ242tNwVl3wgCnf4RxBxx0CIzfQFYHL4Si8UJ9QBjbIewITuK40IklYjrSh4S2QwMIbDGWQLgaHmXMltyqgKEHAH6J0mawJsGaLXzc524Gbo4RP_ZP06RTarc8l_aTOC3pB0ook_RRwdRQwRSG0hzJ2zylfOJY9aJXrK5myGNeV33GG2dRRHnLG4-7Dx88dkqQMOJuSaXw5aHukYu4ZOEsefiBcnceQL6UVLhH6IE4p-SCeipwl2SEScGj7_FATOeIRYrvZ3BKJkYR0agkYXiyhVPCBFBxcOcIQk4DIZ0SkMNkCHcWmE0h1nNnvUnr1ru_c6p5zLFXpb0nzox89oJ33pbSE3Hzv3jRG1t7esm7N_i4d7C3MVjfrbd36q0P9f5m3X9b77-v3704XN897PcHn7YH3zYPvm8c9Nfr_tfBm9c_vmwd7rwcvPp82ZubTmY7M237hpj2EhRGYTtlhYhYwSPGspBzKN9YmZZBXomSZXkhKRSYzOcVeDDNFI1kEYYZL0SlZF7ghOaK1-ot9sqr3kQFrSUUa0KmPKwCKTNVslzQKi1LFQp2zZuw1i7YDLC0cGIMXf8zyw3vHNLNGu5Nr7X8bKW8BVXNcnbbDryf_ovqqA
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E8%8D%B7%E8%BD%BD%E5%A4%A7%E5%B0%8F%E4%B8%8E%E4%BD%8D%E7%BD%AE%E5%90%8C%E6%AD%A5%E8%AF%86%E5%88%AB&rft.jtitle=%E4%B8%9C%E5%8D%97%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5%EF%BC%88%E8%87%AA%E7%84%B6%E7%A7%91%E5%AD%A6%E7%89%88%EF%BC%89&rft.au=%E7%BF%81%E9%A1%BA&rft.au=%E9%83%AD%E8%A1%97%E9%9C%87&rft.au=%E4%BA%8E%E8%99%B9&rft.au=%E9%99%88%E5%BF%97%E4%B8%B9&rft.date=2024&rft.pub=%E5%8D%8E%E4%B8%AD%E7%A7%91%E6%8A%80%E5%A4%A7%E5%AD%A6%E5%9C%9F%E6%9C%A8%E4%B8%8E%E6%B0%B4%E5%88%A9%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E6%AD%A6%E6%B1%89+430074%25%E4%B8%AD%E9%93%81%E7%AC%AC%E5%9B%9B%E5%8B%98%E5%AF%9F%E8%AE%BE%E8%AE%A1%E9%99%A2%E9%9B%86%E5%9B%A2%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8%2C%E6%AD%A6%E6%B1%89+430063&rft.issn=1001-0505&rft.volume=54&rft.issue=1&rft.spage=110&rft.epage=116&rft_id=info:doi/10.3969%2Fj.issn.1001-0505.2024.01.014&rft.externalDocID=dndxxb202401014
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fdndxxb%2Fdndxxb.jpg