结合多通道MTF和CNN的框架结构损伤识别方法
TU312.3%TH825; 为提高复杂框架结构损伤识别的准确率,提出了一种基于多通道马尔可夫变迁场(multi-channel Markov transition field,简称MCMTF)和卷积神经网络(convolutional neural network,简称CNN)的框架结构损伤识别方法.首先,采用MCMTF理论将原始一维振动信号转换为二维图像,实现数据升维和多通道数据融合;其次,以MCMTF转换后的图像数据集作为输入训练CNN模型;最后,经调参优化自动提取损伤敏感特征,并实现损伤识别.将该方法应用于IASC-ASCE Benchmark框架结构数值模型及3层钢框架结构模型试验,...
Saved in:
| Published in | 振动、测试与诊断 Vol. 44; no. 2; pp. 217 - 224 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
中南大学土木工程学院 长沙,410075%中建二局第一建筑工程有限公司 北京,100023
01.04.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1004-6801 |
| DOI | 10.16450/j.cnki.issn.1004-6801.2024.02.002 |
Cover
| Abstract | TU312.3%TH825; 为提高复杂框架结构损伤识别的准确率,提出了一种基于多通道马尔可夫变迁场(multi-channel Markov transition field,简称MCMTF)和卷积神经网络(convolutional neural network,简称CNN)的框架结构损伤识别方法.首先,采用MCMTF理论将原始一维振动信号转换为二维图像,实现数据升维和多通道数据融合;其次,以MCMTF转换后的图像数据集作为输入训练CNN模型;最后,经调参优化自动提取损伤敏感特征,并实现损伤识别.将该方法应用于IASC-ASCE Benchmark框架结构数值模型及3层钢框架结构模型试验,对比研究了多通道MTF、单通道MTF和原始数据矩阵3种数据输入方式,CNN、长短时记忆(long short term memory,简称LSTM)神经网络和深度神经网络(deep neural network,简称DNN)3种网络模型,以及噪声对框架结构损伤识别准确率的影响.结果表明:MCMTF与CNN结合方法的损伤识别准确率最优且具有良好的鲁棒性,其对Benchmark框架数值模型模拟损伤的识别准确率可达94.4%,对3层钢框架试验模型实际损伤的识别准确率可达98.4%. |
|---|---|
| AbstractList | TU312.3%TH825; 为提高复杂框架结构损伤识别的准确率,提出了一种基于多通道马尔可夫变迁场(multi-channel Markov transition field,简称MCMTF)和卷积神经网络(convolutional neural network,简称CNN)的框架结构损伤识别方法.首先,采用MCMTF理论将原始一维振动信号转换为二维图像,实现数据升维和多通道数据融合;其次,以MCMTF转换后的图像数据集作为输入训练CNN模型;最后,经调参优化自动提取损伤敏感特征,并实现损伤识别.将该方法应用于IASC-ASCE Benchmark框架结构数值模型及3层钢框架结构模型试验,对比研究了多通道MTF、单通道MTF和原始数据矩阵3种数据输入方式,CNN、长短时记忆(long short term memory,简称LSTM)神经网络和深度神经网络(deep neural network,简称DNN)3种网络模型,以及噪声对框架结构损伤识别准确率的影响.结果表明:MCMTF与CNN结合方法的损伤识别准确率最优且具有良好的鲁棒性,其对Benchmark框架数值模型模拟损伤的识别准确率可达94.4%,对3层钢框架试验模型实际损伤的识别准确率可达98.4%. |
| Abstract_FL | To improve the accuracy of damage identification on complicated frame structures,a damage identifi-cation method based on multi-channel Markov transition field(MCMTF)and convolutional neural network(CNN)is proposed.First,MCMTF is adopted to transform the original one-dimensional vibration signals into two-dimensional images,which can realize the data dimension elevation and multi-channel data fusion.Then,the image datasets transformed by MCMTF are used as the input to train the CNN models.Finally,the sensi-tive damage features are automatically extracted after parameter tuning and optimization to identify the damage patterns.This method is applied to the IASC-ASCE Benchmark model and an experimental three-layer steel frame structure.The influence of three different data input modes including multi-channel MTF,single-channel MTF and original data matrix are investigated.Further,three different models including CNN,long short-term memory(LSTM)neural network and deep neural network(DNN)are compared,and the different noise levels on damage identification performance are obtained.The results show that the proposed method combing MCMTF with CNN has advantages in the accuracy of damage identification and good robustness.The damage identification accuracy of the method is 94.4%for the numerical Benchmark model and 98.4%for the laboratory three-layer steel frame structure,respectively. |
| Author | 叶涛萍 黄天立 李守文 方佳畅 梁韬 |
| AuthorAffiliation | 中南大学土木工程学院 长沙,410075%中建二局第一建筑工程有限公司 北京,100023 |
| AuthorAffiliation_xml | – name: 中南大学土木工程学院 长沙,410075%中建二局第一建筑工程有限公司 北京,100023 |
| Author_FL | LIANG Tao YE Taoping LI Shouwen HUANG Tianli FANG Jiachang |
| Author_FL_xml | – sequence: 1 fullname: LIANG Tao – sequence: 2 fullname: YE Taoping – sequence: 3 fullname: LI Shouwen – sequence: 4 fullname: FANG Jiachang – sequence: 5 fullname: HUANG Tianli |
| Author_xml | – sequence: 1 fullname: 梁韬 – sequence: 2 fullname: 叶涛萍 – sequence: 3 fullname: 李守文 – sequence: 4 fullname: 方佳畅 – sequence: 5 fullname: 黄天立 |
| BookMark | eNo9j71KA0EUhaeIYIx5DxF2vHd29q-UxagQYxPrMLuzIxtlAg4iplIIIYWCGLRIERHSWVgIgujjuBPzFq4oVgcOh-_wrZCK7umMkHUEij73YKNLU32U09wYTRGAO34ISBkwToFRAFYh1f9-mdSNyRMAz8XIjViVRPP3cXEzKmaTxcVkcTneazeK26u41ZpPBvZxaKev5cBOB_b64fNj9vU8LEZP9v7NvtytkiUljk1W_8saOWhsteMdp7m_vRtvNh2D4HJHyQABhWJuAJJnSiWIocx8HqqUKd_zUwYKUbAAUEWpFyUpEzL0gkwyDFTo1sjaL_dMaCX0YafbOz3R5WOnL1Nz3pc_rsBKRfcbTKVg5w |
| ClassificationCodes | TU312.3%TH825 |
| 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 | 10.16450/j.cnki.issn.1004-6801.2024.02.002 |
| 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 |
| Discipline | Engineering |
| DocumentTitle_FL | Damage Identification Method Using Multi-channel Markov Transition Field and Convolutional Neural Network for Frame Structures |
| EndPage | 224 |
| ExternalDocumentID | zdcsyzd202402004 |
| GrantInformation_xml | – fundername: (国家自然科学基金); (中国建筑第二工程局有限公司青年课题资助项目) funderid: (国家自然科学基金); (中国建筑第二工程局有限公司青年课题资助项目) |
| GroupedDBID | -03 2B. 4A8 5XA 5XD 92H 92I 93N ALMA_UNASSIGNED_HOLDINGS ARCSS CCEZO CEKLB PSX TCJ TGT U1G U5M |
| ID | FETCH-LOGICAL-s1034-fd7101af2370d4effb118de648fc2f656c20f11a2701f9c59bc2ad857ed217f83 |
| ISSN | 1004-6801 |
| IngestDate | Thu May 29 04:11:31 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 2 |
| Keywords | data fusion 多通道马尔可夫变迁场 卷积神经网络 convolutional neural network 振动响应 数据升维 vibration response multi-channel Markov transition field 数据融合 损伤识别 damage identification data dimension elevation |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1034-fd7101af2370d4effb118de648fc2f656c20f11a2701f9c59bc2ad857ed217f83 |
| PageCount | 8 |
| ParticipantIDs | wanfang_journals_zdcsyzd202402004 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-04-01 |
| PublicationDateYYYYMMDD | 2024-04-01 |
| PublicationDate_xml | – month: 04 year: 2024 text: 2024-04-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 振动、测试与诊断 |
| PublicationTitle_FL | Journal of Vibration，Measurement & Diagnosis |
| PublicationYear | 2024 |
| Publisher | 中南大学土木工程学院 长沙,410075%中建二局第一建筑工程有限公司 北京,100023 |
| Publisher_xml | – name: 中南大学土木工程学院 长沙,410075%中建二局第一建筑工程有限公司 北京,100023 |
| SSID | ssib005319392 ssib023168178 ssib036436293 ssj0040362 ssib001129465 ssib051372451 ssib007286666 ssib001051226 ssib003154303 |
| Score | 2.4185946 |
| Snippet | TU312.3%TH825; 为提高复杂框架结构损伤识别的准确率,提出了一种基于多通道马尔可夫变迁场(multi-channel Markov transition field,简称MCMTF)和卷积神经网... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 217 |
| Title | 结合多通道MTF和CNN的框架结构损伤识别方法 |
| URI | https://d.wanfangdata.com.cn/periodical/zdcsyzd202402004 |
| Volume | 44 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: Directory of Open Access Journals issn: 1004-6801 databaseCode: DOA dateStart: 20210101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: true ssIdentifier: ssj0040362 providerName: Directory of Open Access Journals |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1Na9RANJQKogfxEz9LBedi2bozyUxmjpNsliK0pxZ6K7tJRkVYwbYH96RQSg8KYtFDDxWhNw8eBEH057hb-y987yXdnWrBKizh7eR9v-zMm-zLSxDckbkuNOz_G3kpdSPirmx0HS8a2BNbxXloSmrqM7-g5pai-8tyeWJyyqtaWl_rzub9Y58r-Z-owhjEFZ-S_YfIjpjCAMAQXzhChOF4ohizLGZJwkzIMslMk2mNgI2YsSwzVMRQARxw5hfbhCaYTtOFBaSFszpimWKWM60QMBlLlMeWRioc3WIGOEQsSVFEppltE5VEuTYhZMUSg0ASsuqtloeJL3FIkQTxLbOgaogagm6ID4NJzdNIkqKZzg6l2Jr5uHkkaS2I2qBe4xaSJKBNZig8GuKL3jlCbFrEH9yVkd-I_3hV9qwBXVpoEDoMWEv_Ronw62vw0q5Vty1SA1wW1yGxFdBillxmUvKmQsBS2JKYWYlC4Cv6YoQM9hmwdYYgwCOyROCoSCOsP5FMyCOCIXqJpRGLXscRjs5G7il-agc3PeQYaQ0_ThXSUptaFUNUWhKfytd6hqCUzCWpcE6knBodeese1iMpXburXhirxpz1BCCOrHKxlzCJ6iH4P9ZiFckmLcZ57_EjEjM7EjOLAaqa5YpxJjKqD-0X-eqzfoFITUHtfk-JWCnh3TKpbmdAuir89ofCRN6_9iHsD0KvygDXm9CrIoiFVt72XeBL3Pi4vV0I2bry0mHJw1hEclRCFmH2R9UUtVWng7uHht_7q9n0lGDPdXoPvIR28Xxwrt6JTttqWrkQTPQfXgzOev1JLwVm_9v24PXWYG_n4PnOwYttmEIGb17C5LG_szH8sDnc_QIIw92N4av3P77v_fy0Odj6OHz3dfj57eVgqZ0tpnON-l0rjVXeDKOGK2CrwTtOhHGziErnupzrolSRdrlwsOnLRdNx3hFxkzuTS9PNRafQMi4LuBqcDq8Ek70nvfJqMC2cjl2py0gbGXWEMoobx-NCKydj4H4tuF0bvlLPpasrvwf8-glwbgRnxj_zm8Hk2tP18hbsENa6U3SZ_ALsacAg |
| linkProvider | Directory of Open Access Journals |
| 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=%E7%BB%93%E5%90%88%E5%A4%9A%E9%80%9A%E9%81%93MTF%E5%92%8CCNN%E7%9A%84%E6%A1%86%E6%9E%B6%E7%BB%93%E6%9E%84%E6%8D%9F%E4%BC%A4%E8%AF%86%E5%88%AB%E6%96%B9%E6%B3%95&rft.jtitle=%E6%8C%AF%E5%8A%A8%E3%80%81%E6%B5%8B%E8%AF%95%E4%B8%8E%E8%AF%8A%E6%96%AD&rft.au=%E6%A2%81%E9%9F%AC&rft.au=%E5%8F%B6%E6%B6%9B%E8%90%8D&rft.au=%E6%9D%8E%E5%AE%88%E6%96%87&rft.au=%E6%96%B9%E4%BD%B3%E7%95%85&rft.date=2024-04-01&rft.pub=%E4%B8%AD%E5%8D%97%E5%A4%A7%E5%AD%A6%E5%9C%9F%E6%9C%A8%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2+%E9%95%BF%E6%B2%99%2C410075%25%E4%B8%AD%E5%BB%BA%E4%BA%8C%E5%B1%80%E7%AC%AC%E4%B8%80%E5%BB%BA%E7%AD%91%E5%B7%A5%E7%A8%8B%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8+%E5%8C%97%E4%BA%AC%2C100023&rft.issn=1004-6801&rft.volume=44&rft.issue=2&rft.spage=217&rft.epage=224&rft_id=info:doi/10.16450%2Fj.cnki.issn.1004-6801.2024.02.002&rft.externalDocID=zdcsyzd202402004 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fzdcsyzd%2Fzdcsyzd.jpg |