|Table of Contents|

Damage diagnosis of beam bridges based on dynamic signature and GTO-1D CNN-BiLSTM model(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2025年03期
Page:
90-101
Research Field:
桥梁与隧道工程
Publishing date:

Info

Title:
Damage diagnosis of beam bridges based on dynamic signature and GTO-1D CNN-BiLSTM model
Author(s):
XIANG Chang-sheng1; 2;  ZHAO Hua1;  SU Tian-tao3;  LIU Qi-yang4;  LI Feng5
Keywords:
bridge engineering;  damage diagnosis;  generalized flexibility matrix;  proportional flexibility matrix;  grey relational analysis;  1D CNN-BiLSTM;  GTO algorithm
PACS:
U448.21
DOI:
10.19721/j.cnki.1671-8879.2025.03.008
Abstract:
Aiming at the vulnerability of serving beam bridges to the influence of factors such as materials and environment, a three-span continuous beam bridge was taken as the research object, and a beam bridge graded damage identification method based on dynamic fingerprint constructed by grey relational generalized proportional flexibility curvature difference(GMGPFCD-A)and artificial gorilla group optimization algorithm(GTO)-one-dimensional convolutional neural network(1D CNN)-bidirectional long short-term memory network(BiLSTM)prediction model was proposed. Firstly, the generalized flexibility matrix and proportional flexibility matrix constructed by low-order modal parameters were combined with grey relational analysis(GRA)to construct dynamic fingerprint to identify the damage position of the structure, and the index was input into the 1D CNN-BiLSTM damage prediction model for quantitative analysis. Finally, the hyperparameters of the GTO optimization prediction model were introduced to improve its prediction performance of the structural damage degree. The research results show that the model can not only accurately identify the damage location of the structure without measuring the external environmental excitation, but also has a certain noise resistance within 10% of the noise level; the prediction model after GTO optimization has an accuracy rate of 93.548% for the damage degree of the identified damaged parts; the proposed model converges faster, is more stable, and has higher prediction accuracy and stronger robustness.4 tabs, 10 figs, 28 refs.

References:

[1] 王凌波,王秋玲,朱 钊,等.桥梁健康监测技术研究现状及展望[J].中国公路学报,2021,34(12):25-45.
WANG Ling-bo, WANG Qiu-Ling, ZHU Zao, et al. Current statusand prospects of research on bridge health monitoring technology[J]. China Journal of Highway and Transport, 2021, 34(12): 25-45.
[2]赵一男,公茂盛,杨 游.结构损伤识别方法研究综述[J].世界地震工程,2020,36(2):73-84.
ZHAO Yi-nan, GONG Mao-sheng, YANG You. A reviewof structure damage identification methods[J]. World Earthquake Engineering, 2020, 36(2): 73-84.
[3]FENG D M, MARIA Q F. Computer vision forSHM of civil infrastructure: From dynamic responsemeasurement to damage detection-A review[J].Engineering Structures, 2018, 156: 105-117.
[4]孙利民,尚志强,夏 烨.大数据背景下的桥梁结构健康监测研究现状与展望[J].中国公路学报,2019,32(11):1-20.
SHUN Li-min, SHANG Zhi-qiang, XIA Ye. Developmentand prospect of bridge structural health monitoring in thecontext of big data[J]. China Journal of Highway andTransport, 2019, 32(11): 1-20.
[5]PANDEY A K, BISWAS M. Damage detection in structuresusing changes in flexibility[J]. Journal of Sound and Vibration, 1994, 169(1): 3-17.
[6]LI J, WU B, ZENG Q C, et al. A generalized flexibilitymatrix based approach for structural damage detection[J]. Journal of Sound and Vibration, 2010, 329(22): 4583-4587.
[7]PENG X, YANG Q W. Sensor placement and structuraldamage evaluation by improved generalized flexibility[J]. IEEE Sensors Journal, 2021, 21(10): 11654-11664.
[8]LIU H, LI Z. An improved generalized flexibility matrixapproach for structural damage detection[J]. Inverse Problems in Science and Engineering, 2020, 28(6): 877-893.
[9]李国庆,罗 帅,苏 睿,等.环境激励下基于柔度矩阵分解的损伤诊断[J].应用数学和力学,2021,42(3):292-298.
LI Guo-qing, LUO Shuai, SU Rui, et al. Research ondamage diagnosis based on flexibility matrixdecomposition[J]. Applied Mathematics and Mechanics,2021, 42(3): 292-298.
[10]DUAN Z, YAN G, OU J, et al. Damage localization inambient vibration by constructing proportional flexibilitymatrix[J]. Journal of Sound and Vibration, 2005, 284(1-2):455-466.
[11]李子奇,蒋柱虎,王 力,等.基于深度学习的工程结构损伤识别研究进展[J].中国安全生产科学技术,2022,18(12):43-48.
LI Zi-qi, JIANG Zhu-hu, WANG Li, et al. Researchprogress in damage identification of engineeringstructure based on deep learning[J]. Journal of SafetyScience and Technology, 2022, 18(12): 43-48.
[12]朱劲松,李 欢,王世芳.基于卷积神经网络和迁移学习的钢桥病害识别[J].长安大学学报(自然科学版),2021,41(3):52-63.
ZHU Jing-song, LI Huan, WANG Shi-fang. Defectrecognition for steel bridge based on convolutional neuralnetwork and transfer learning[J]. Journal of Chang'anUniversity(Natural Science Edition), 2021, 41(3): 52-63.
[13]乔 朋,梁志强,徐 凯,等.基于机器学习的中小跨径桥梁技术状况评估[J].长安大学学报(自然科学版),2021,41(6):39-52.
QIAO Peng, LIANG Zhi-qiang, XU Kai, et al. Evaluationof technical condition of medium and small span bridgebased on machine learning[J]. Journal of Chang'anUniversity(Natural Science Edition), 2021, 41(6): 39-52.
[14]李禹剑,李 剑,辛伟瑶.一种基于BP神经网络的老旧桥梁健康诊断方法[J].国外电子测量技术,2020,39(2):19-22.
LI Yu-jian, LI Jian, XIN Wei-yao. Health diagnosismethod for old bridges based on BP neural network[J]. Electronic Measurement Technology, 2020, 39(2): 19-22.
[15]TANG Z, CHEN Z, BAO Y, et al. Convolutional neuralnetwork-based data anomaly detection method usingmultiple information for structural health monitoring[J].Structural Control and Health Monitoring, 2019, 26(1): e2296.
[16]张博耀.基于LSTM网络的某斜拉桥地震响应建模方法研究[D].哈尔滨:哈尔滨工业大学,2021.
ZHANG Bo-yao. Research on seismic response modelingmethod of a cable-stayed bridge based on LSTMnetwork[D]. Harbin: Harbin Institute of Technology, 2021.
[17]王子凡,张健飞.一种基于LSTM循环神经网络和振动测试的结构损伤检测方法[J].噪声与振动控制,2021,41(5):127-133.
WANG Zi-fan, ZHANG Jian-fei. A structural damagedetection method based on LSTM recurrent neutralnetwork and vibration testing[J]. Noise and Vibration Control, 2021, 41(5): 127-133.
[18]单德山,石 磊,谭康熹.联合卷积神经网络与长短期记忆深度网络的桥梁损伤识别[J].桥梁建设,2023,53(4):41-46.
SHAN De-shan, SHI Lei, TAN Kang-xi. Bridge damageidentification based on joint CNN and LSTM deepnetwork[J]. Bridge Construction, 2023, 53(4): 41-46.
[19]LIU S, YANG Y, FORREST J. Grey data analysis[M]. Singapore: Springer Singapore, 2017.
[20]ABDOLLAHZADEH B, SOLEIMANIAN G F, MIRJALILI S. Artificial gorilla troops optimizer: A new nature-inspired metaheuristic algorithm for global optimization problems[J]. International Journal of Intelligent Systems, 2021, 36(10): 5887-5958.
[21]杨秋伟,王学航,李翠红.基于高次广义柔度灵敏度的结构损伤识别[J].固体力学学报,2019,40(2):157-168.
YANG Qiu-wei, WANG Xue-hang, LI Cui-hong. Damage identification of engineering structure based onhigh-order generalized flexibility sensitivity[J]. ChineseJournal of Solid Mechanics, 2019, 40(2): 157-168.
[22]段忠东,闫桂荣,欧进萍,等.结构比例柔度矩阵[J].哈尔滨工业大学学报,2006(8):1236-1238,1242.
DUAN Zhong-dong, YAN Gui-rong, OU Jin-ping, et al. Proportional flexibility matrix of structures[J]. Journal ofHarBin Institute of Technology, 2006(8): 1236-1238, 1242.
[23]邓聚龙.灰色系统基本方法[M].4版.武汉:华中理工大学出版社,1996.
DENG Ju-long. Basic method of grey system[M]. 4th ed.Wuhan: Huazhong University of Technology Press, 1996.
[24]邱锡鹏.神经网络与深度学习[M].北京:机械工业出版社,2021.
QIU Xi-peng. Neural networks and deep learning[M]. Beijing: Mechanical Industry Press, 2021.
[25]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(4):38-57.
YANG Shuo, XU Qing-feng, WANG Zuo-lin. Researchprogress on structure damage detection based on convolutional neural networks[J]. Journal of Architecture and Civil Engineering, 2022, 39(4): 38-57.
[26]魏佳恒,郭惠勇.基于贝叶斯优化BiLSTM模型的输电塔损伤识别[J].振动与冲击,2023,42(1):238-248.
WEI Jia-heng, GUO Hui-yong. Damage identification oftransmission tower based on BO-BiLSTM model[J]. Journal of Vibration and Shock, 2023, 42(1): 238-248.
[27]FU T C, BOGY D B. Dynamic load head-diskinterface durability of 50 percent sliders and polisheddisks[J]. IEEE Transactions on Magnetics, 1996, 32(5): 3747-3749.
[28]曹 晖,林秀萍.结构损伤识别中噪声的模拟[J].振动与冲击,2010,29(5):106-109,243-244.
CAO Hui, LIN Xiu-ping. Simulation of noise instructural damage identification[J]. Journal of Vibrationand Shock, 2010, 29(5): 106-109, 243-244.

Memo

Memo:
-
Last Update: 2025-05-30