«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《建筑科学与工程学报》[ISSN:1673-2049/CN:61-1442/TU]

卷:

37卷

期数:

2020年06期

页码:

29-37

栏目:

出版日期:

2020-11-30

文章信息/Info

Title:

Application of Convolutional Neural Network in Structural Damage Identification

文章编号:

1673-2049(2020)06-0029-09

作者:

李书进¹,赵 源¹,孔 凡¹,张远进²

1. 武汉理工大学 土木工程与建筑学院,湖北 武汉 430070; 2. 武汉理工大学 安全科学与应急管理学院,湖北 武汉 430070

Author(s):

LI Shu-jin¹, ZHAO Yuan¹, KONG Fan¹, ZHANG Yuan-jin²

1. School of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, Hubei, China; 2. School of Safety Science and Emergency Management, Wuhan University of Technology, Wuhan 430070, Hubei, China

关键词:

损伤识别;  卷积神经网络;  深度学习;  框架结构;  小波变换

Keywords:

damage identification;  convolutional neural network;  deep learning;  frame structure;  wavelet transform

分类号:

TU312.3

DOI:

-

文献标志码:

A

摘要:

对卷积神经网络(CNN)在工程结构损伤诊断中的应用进行了深入探讨; 以多层框架结构节点损伤位置的识别问题为研究对象,构建了可以直接从结构动力反应信号中进行学习并完成分类诊断的基于原始信号和傅里叶频域信息的一维卷积神经网络模型和基于小波变换数据的二维卷积神经网络模型; 从输入数据样本类别、训练时间、预测准确率、浅层与深层卷积神经网络以及不同损伤程度的影响等多方面进行了研究。结果表明:卷积神经网络能从结构动力反应信息中有效提取结构的损伤特征,且具有很高的识别精度; 相比直接用加速度反应样本,使用傅里叶变换后的频域数据作为训练样本能使CNN的收敛速度更快、更稳定,并且深层CNN的性能要好于浅层CNN; 将卷积神经网络用于工程结构损伤诊断具有可行性,特别是在大数据处理和解决复杂问题能力方面与其他传统诊断方法相比有很大优势,应用前景广阔。

Abstract:

The application of convolutional neural network in damage identification of engineering structure was discussed in depth. Taking the identification of damage location of multi-layer frame structure nodes as the research object, a one-dimensional convolutional neural network model based on original signal and Fourier frequency domain information and a two-dimensional convolutional neural network model based on wavelet transform data were constructed, which could learn directly from the structural dynamic response signals and complete the classification diagnosis. The type of input data sample, training time, prediction accuracy, shallow and deep convolutional neural network and the influence of different damage degree on damage identification were studied. The results show that the convolutional neural network can effectively extract the damage features from the dynamic response information of the structure, and has a high recognition accuracy. Compared with using acceleration response sample directly, using frequency domain data after Fourier transform as training samples can make the CNN convergence faster and more stable, and the performance of deep CNN is better than that of shallow CNN. The convolutional neural network can be used in the damage diagnosis of engineering structures, especially in the big data processing and the ability to solve complex problems, and has great advantages and wide application prospects compared with the other traditional diagnosis methods.

参考文献/References:

[1] LECUN Y,BENGIO Y,HINTON G.Deep Learning[J].Nature,2015,521(7553):436-444.
[2]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based Learning Applied to Document Recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[3]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet Classification with Deep Convolutional Neural Networks[J].Communications of the ACM,2017,60(6):84-90.
[4]黄新波,胡潇文,朱永灿,等.基于卷积神经网络算法的高压断路器故障诊断[J].电力自动化设备,2018,38(5):136-140,147. HUANG Xin-bo,HU Xiao-wen,ZHU Yong-can,et al.Fault Diagnosis of High-voltage Circuit Breaker Based on Convolution Neural Network[J].Electric Power Automation Equipment,2018,38(5):136-140,147.
[5]吴春志,江鹏程,冯辅周,等.基于一维卷积神经网络的齿轮箱故障诊断[J].振动与冲击,2018,37(22):51-56. WU Chun-zhi,JIANG Peng-cheng,FENG Fu-zhou,et al.Faults Diagnosis Method for Gearboxes Based on a 1-D Convolutional Neural Network[J].Journal of Vibration and Shock,2018,37(22):51-56.
[6]ABDELJABER O,AVCI O,KIRANYAZ S,et al.Real-time Vibration-based Structural Damage Detection Using One-dimensional Convolutional Neural Networks[J].Journal of Sound and Vibration,2017,388:154-170.
[7]李雪松,马宏伟,林逸洲.基于卷积神经网络的结构损伤识别[J].振动与冲击,2019,38(1):159-167. LI Xue-song,MA Hong-wei,LIN Yi-zhou.Structural Damage Identification Based on Convolution Neural Network[J].Journal of Vibration and Shock,2019,38(1):159-167.
[8]ZHANG Y,MIYAMORI Y,MIKAMI S,et al.Vibration-based Structural State Identification by a 1-Dimensional Convolutional Neural Network[J].Computer-aided Civil and Infrastructure Engineering,2019,34(9):822-839.
[9]朱宏平,张 源.基于自适应BP神经网络的结构损伤检测[J].力学学报,2003,35(1):110-116. ZHU Hong-ping,ZHANG Yuan.Application of Self-adaptive BP Neural Networks to the Detection of Structural Damage[J].Acta Mechanica Sinica,2003,35(1):110-116.
[10]杨佑发,熊 丽,陈 远.基于神经网络的框架结构损伤多重分步识别[J].建筑科学与工程学报,2011,28(1):106-111. YANG You-fa,XIONG Li,CHEN Yuan.Multi-stage Damage Identification for Frame Structures Based on Neural Network[J].Journal of Architecture and Civil Engineering,2011,28(1):106-111.
[11]YU D,DENG L.Deep Learning and Its Applications to Signal and Information Processing[J].IEEE Signal Processing Magazine,2011,28(1):145-154.
[12]HE K,ZHANG X,REN S,et al.Delving Deep into Rectifiers:Surpassing Human-level Performance on ImageNet Classification[C]//IEEE.International Conference on Computer Vision.New York:IEEE,2015:1026-1034.
[13]LI T,MENG Z J,NI B B,et al.Robust Geometric l_p-norm Feature Pooling for Image Classification and Action Recognition[J].Image and Vision Computing,2016,55(S1):64-76.
[14]MANCEV D,TODOROVIC B.A Primal Sub-gradient Method for Structured Classification with the Averaged Sum Loss[J].International Journal of Applied Mathematics and Computer Science,2014,24(4):917-930.
[15]GHOSH A,KUMAR H,SASTRY P.Robust Loss Functions Under Label Noise for Deep Neural Networks[C]//AAAI.31st AAAI Conference on Artificial Intelligence.Palo Alto:AAAI,2017:1919-1925.
[16]CHUI C K.Introduction to Wavelets[M].New York:Academic Press,1992.
[17]DOKKYUN Y,JAEHYUN A,SANGMIN J.An Effective Optimization Method for Machine Learning Based on ADAM[J].Applied Sciences,2020,10(3):1073.
[18]SUN P,LI A Q,DING Y L,et al.Study on Parameters for Identification of Wavelet Packet Energy Spectrum for Structural Damage Alarming[J].Advanced Materials Research,2011,163-167:2693-2698.
[19]DURANT T,OLSON E,SCHULZ W,et al.Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes[J].Clinical Chemistry,2017,63(12):1847-1855.

相似文献/References:

[1]薛刚,王崇阁.基于能量法的简支钢梁损伤识别试验及有限元分析[J].建筑科学与工程学报,2014,31(03):112.
　XUE Gang,WANG Chong-ge.Damage Identification Test and Finite Element Analysis of Simply Supported Steel Beam Based on Energy Dissipation Method[J].Journal of Architecture and Civil Engineering,2014,31(06):112.
[2]李宏男,林世伟,伊廷华.基于静力虚拟变形法的结构损伤识别研究[J].建筑科学与工程学报,2016,33(05):1.
　LI Hong-nan,LIN Shi-wei,YI Ting-hua.Study on Structural Damage Identification by Static Virtual Distortion Method[J].Journal of Architecture and Civil Engineering,2016,33(06):1.
[3]吴 多,刘来君,张筱雨,等.基于曲率模态曲线变化的桥梁损伤识别[J].建筑科学与工程学报,2018,35(02):119.
　WU Duo,LIU Lai-jun,ZHANG Xiao-yu,et al.Bridge Damage Identification Based on Curvature-mode Curve[J].Journal of Architecture and Civil Engineering,2018,35(06):119.
[4]秦世强,苏 晟,杨 睿.基于多标签卷积神经网络的结构损伤识别[J].建筑科学与工程学报,2024,41(03):108.[doi:10.19815/j.jace.2022.07014]
　QIN Shiqiang,SU Sheng,YANG Rui.Structural damage identification based on multi-label convolution neural network[J].Journal of Architecture and Civil Engineering,2024,41(06):108.[doi:10.19815/j.jace.2022.07014]
[5]杨 铄,许清风,王卓琳.基于卷积神经网络的结构损伤识别研究进展[J].建筑科学与工程学报,2022,39(04):38.[doi:10.19815/j.jace.2022.02043]
　YANG Shuo,XU Qing-feng,WANG Zhuo-lin.Research Progress on Structural Damage Detection Based on Convolutional Neural Networks[J].Journal of Architecture and Civil Engineering,2022,39(06):38.[doi:10.19815/j.jace.2022.02043]

备注/Memo

备注/Memo:

收稿日期:2020-02-14 基金项目:国家自然科学基金项目(51678464) 作者简介:李书进(1967-),男,湖北仙桃人,教授,博士研究生导师,工学博士,E-mail:sjli@whut.edu.cn。

常用功能

更新日期/Last Update: 1900-01-01