Experimental study on structural damage identification of multi-sensor separated channel network

被引：2

作者：

Liu, Zhao ^{[1
]}

Guo, Huiyong ^{[1
]}

机构：

[1] Chongqing Univ, Sch Civil Engn, Chongqing 400045, Peoples R China

来源：

MEASUREMENT | 2023年 / 220卷

基金：

中国国家自然科学基金;

关键词：

Structural damage identification; Structural health monitoring; Deep learning; Multi-sensor; Vibration; CONVOLUTIONAL NEURAL-NETWORK; TIME FOURIER-TRANSFORM; EXTENDED KALMAN FILTER; FRAMEWORK;

D O I：

10.1016/j.measurement.2023.113382

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Structural damage identification, the core driver of structural health monitoring (SHM), has gradually shifted to data-driven models in recent years. For the characteristics of multi-sensors in the SHM system of buildings, this paper proposes a neural network structure for damage identification called multi-sensor separated channel network (MSSCN). It is dedicated to extracting damage sensitive features from a single measurement channel while maintaining the spatial information of the sensor, thus completely decoupling intra-channel time and interchannel spatial features. The proposed framework is validated by applying to the Qatar University Grandstand Simulator (QUGS) with a decentralized sensor arrangement. Further, we study vertical structures with strong channel correlation via experiments simulating linear and nonlinear multiple complex operating conditions to identify damage in transmission tower. Based on the above, it is demonstrated that the proposed model exhibits good diagnostic capability and performs competitive in noise immunity and small sample tests.

引用

页数：16

共 45 条

[11] Chiou DJ, 2011, STRUCT ENG MECH, V39, P1
[12] A data-driven structural damage identification approach using deep convolutional-attention-recurrent neural architecture under temperature variations
Fathnejat, Hamed
Ahmadi-Nedushan, Behrouz
Hosseininejad, Sahand
Noori, Mohammad
Altabey, Wael A.
[J]. ENGINEERING STRUCTURES, 2023, 276
[13] EFFECTS OF DAMAGE AND REDUNDANCY ON STRUCTURAL RELIABILITY
FRANGOPOL, DM
CURLEY, JP
[J]. JOURNAL OF STRUCTURAL ENGINEERING-ASCE, 1987, 113 (07): : 1533 - 1549
[14] Ghazvineh S., 2021, arXiv
[15] Recent advances in convolutional neural networks
Gu, Jiuxiang
Wang, Zhenhua
Kuen, Jason
Ma, Lianyang
Shahroudy, Amir
Shuai, Bing
Liu, Ting
Wang, Xingxing
Wang, Gang
Cai, Jianfei
Chen, Tsuhan
[J]. PATTERN RECOGNITION, 2018, 77 : 354 - 377
[16] A Review of Deep Learning Models for Time Series Prediction
Han, Zhongyang
Zhao, Jun
Leung, Henry
Ma, King Fai
Wang, Wei
[J]. IEEE SENSORS JOURNAL, 2021, 21 (06) : 7833 - 7848
[17] Recurrent Neural Networks for Time Series Forecasting: Current status and future directions
Hewamalage, Hansika
Bergmeir, Christoph
Bandara, Kasun
[J]. INTERNATIONAL JOURNAL OF FORECASTING, 2021, 37 (01) : 388 - 427
[18] Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
[19] Hu J, 2018, PROC CVPR IEEE, P7132, DOI [10.1109/CVPR.2018.00745, 10.1109/TPAMI.2019.2913372]
[20] A comprehensive review on convolutional neural network in machine fault diagnosis
Jiao, Jinyang
Zhao, Ming
Lin, Jing
Liang, Kaixuan
[J]. NEUROCOMPUTING, 2020, 417 : 36 - 63

← 1 2 3 4 5 →