Browse > Article
http://dx.doi.org/10.12989/sss.2022.30.6.557

Vibration-based structural health monitoring using CAE-aided unsupervised deep learning  

Minte, Zhang (School of Civil Engineering, Southeast University)
Tong, Guo (School of Civil Engineering, Southeast University)
Ruizhao, Zhu (School of Civil Engineering, Southeast University)
Yueran, Zong (School of Civil Engineering, Southeast University)
Zhihong, Pan (School of Architecture and Civil Engineering, Jiangsu University of Science and Technology)
Publication Information
Smart Structures and Systems / v.30, no.6, 2022 , pp. 557-569 More about this Journal
Abstract
Vibration-based structural health monitoring (SHM) is crucial for the dynamic maintenance of civil building structures to protect property security and the lives of the public. Analyzing these vibrations with modern artificial intelligence and deep learning (DL) methods is a new trend. This paper proposed an unsupervised deep learning method based on a convolutional autoencoder (CAE), which can overcome the limitations of conventional supervised deep learning. With the convolutional core applied to the DL network, the method can extract features self-adaptively and efficiently. The effectiveness of the method in detecting damage is then tested using a benchmark model. Thereafter, this method is used to detect damage and instant disaster events in a rubber bearing-isolated gymnasium structure. The results indicate that the method enables the CAE network to learn the intact vibrations, so as to distinguish between different damage states of the benchmark model, and the outcome meets the high-dimensional data distribution characteristics visualized by the t-SNE method. Besides, the CAE-based network trained with daily vibrations of the isolating layer in the gymnasium can precisely recover newly collected vibration and detect the occurrence of the ground motion. The proposed method is effective at identifying nonlinear variations in the dynamic responses and has the potential to be used for structural condition assessment and safety warning.
Keywords
damage identification; on-site test; structural health monitoring; unsupervised deep learning; vibration assessment;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Wang, Y., Thambiratnam, D.P., Chan, T.H.T. and Nguyen, A. (2018b), "Damage detection in asymmetric buildings using vibration-based techniques", Struct. Control Health Monitor., 25(5), e2148. https://doi.org/10.1002/stc.2148   DOI
2 Wang, Z.C., Ren, W.X. and Chen, G. (2018c), "Time-frequency analysis and applications in time-varying/nonlinear structural systems: a state-of-the-art review", Adv. Struct. Eng., 21(10), 1562-1584. https://doi.org/10.1177/1369433217751969   DOI
3 Yan, A.M., Kerschen, G., De Boe, P. and Golinval, J.C. (2005), "Structural damage diagnosis under varying environmental conditions-part II: local PCA for non-linear cases", Mech. Syst. Signal Process., 19(4), 865-880. https://doi.org/10.1016/j.ymssp.2004.12.003   DOI
4 Yang, X.M., Yi, T.H., Qu, C.X., Li, H.N. and Liu, H. (2020), "Modal identification of high-speed railway bridges through free-vibration detection", J. Eng. Mech., 146(9), 04020107. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001847   DOI
5 Yi, T.H., Yao, X.J., Qu, C.X. and Li, H.N. (2019), "Clustering number determination for sparse component analysis during output-only modal identification", J. Eng. Mech.-ASCE, 145(1), 04018122. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001557   DOI
6 Abdeljaber, O., Avci, O., Kiranyaz, S., Gabbouj, M. and Inman, D. J. (2017), "Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks", J. Sound Vib., 388, 154-170. https://doi.org/10.1016/j.jsv.2016.10.043   DOI
7 Bayissa, W.L. and Haritos, N. (2007), "Structural damage identification in plates using spectral strain energy analysis", J. Sound Vib., 307(1-2), 226-249. https://doi.org/10.1016/j.jsv.2007.06.062   DOI
8 Cha, Y.J. and Choi, W. (2017), "Vision-based concrete crack detection using a convolutional neural network", In: Dynamics of Civil Structures, Springer, Volume 2, Cham, pp. 71-73.
9 Cheng-Zhong, Q. and Xu-Wei, L. (2012), "Damage identification for transmission towers based on HHT", Energy Procedia, 17, 1390-1394. https://doi.org/10.1016/j.egypro.2012.02.257   DOI
10 Cui, M., Wu, G., Chen, Z., Dang, J., Zhou, M. and Feng, D. (2021), "Geometric attention regularization enhancing convolutional neural networks for bridge rubber bearing damage assessment", J. Perform. Constr. Facil., 35(5), 04021061. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001634   DOI
11 Flah, M., Nunez, I., Ben Chaabene, W. and Nehdi, M.L. (2021), "Machine learning algorithms in civil structural health monitoring: a systematic review", Arch. Computat. Methods Eng., 28(4), 2621-2643. https://doi.org/10.1007/s11831-020-09471-9   DOI
12 Das, S. and Saha, P. (2018), "Structural health monitoring techniques implemented on IASC-ASCE benchmark problem: a review", J. Civil Struct. Health Monitor., 8(4), 689-718. https://doi.org/10.1007/s13349-018-0292-5   DOI
13 Doebling, S.W., Farrar, C.R. and Prime, M.B. (1998), "A summary review of vibration-based damage identification methods", Shock Vib. Digest, 30(2), 91-105.   DOI
14 Erdogan, Y.S., Gul, M., Catbas, F.N. and Bakir, P.G. (2014), "Investigation of uncertainty changes in model outputs for finite-element model updating using structural health monitoring data", J. Struct. Eng., 140(11), 04014078. https://doi.org/10.1061/(ASCE)ST.1943-541X.0001002   DOI
15 Gentile, C., Ruccolo, A. and Canali, F. (2019), "Continuous monitoring of the Milan Cathedral: dynamic characteristics and vibration-based SHM", J. Civil Struct. Health Monitor., 9(5), 671-688. https://doi.org/10.1007/s13349-019-00361-8   DOI
16 Goyal, D. and Pabla, B.S. (2016), "The vibration monitoring methods and signal processing techniques for structural health monitoring: a review", Arch. Computat. Methods Eng., 23(4), 585-594. https://doi.org/10.1007/s11831-015-9145-0   DOI
17 He, W.Y., Zhu, S. and Ren, W.X. (2018), "Progressive damage detection of thin plate structures using wavelet finite element model updating", Smart Struct. Syst., Int. J., 22(3), 277-290. https://doi.org/10.12989/sss.2018.22.3.277   DOI
18 Hera, A. and Hou, Z. (2004), "Application of wavelet approach for ASCE structural health monitoring benchmark studies", J. Eng. Mech., 130(1), 96-104. https://doi.org/10.1061/(ASCE)0733-9399(2004)130:1(96)   DOI
19 Jalali, M.H. and Rideout, D.G. (2022), "Substructural damage detection using frequency response function based inverse dynamic substructuring", Mech. Syst. Signal Process., 163, 108166. https://doi.org/10.1016/j.ymssp.2021.108166   DOI
20 Hsu, T.Y., Liu, C.Y., Hsieh, Y.M. and Weng, C.T. (2021), "Post-earthquake fast building safety assessment using smartphone-based interstory drifts measurement", Smart Struct. Syst., Int. J., 29(2), 287-299. https://doi.org/10.12989/sss.2022.29.2.287   DOI
21 Jiang, K., Han, Q., Du, X. and Ni, P. (2021), "A decentralized unsupervised structural condition diagnosis approach using deep auto-encoders", Comput.-Aided Civil Infrastr. Eng., 36(6), 711-732. https://doi.org/10.1111/mice.12641   DOI
22 Johnson, E.A., Lam, H.F., Katafygiotis, L.S. and Beck, J.L. (2004), "Phase I IASC-ASCE structural health monitoring benchmark problem using simulated data", J. Eng. Mech., 130(1), 3-15. https://doi.org/10.1061/(ASCE)0733-9399(2004)130:1(3)   DOI
23 Khayatazad, M., Honhon, M. and De Waele, W. (2022), "Detection of corrosion on steel structures using an artificial neural network", Struct. Infrastr. Eng., 1-12. https://doi.org/10.1080/15732479.2022.2069272   DOI
24 LeCun, Y., Bengio, Y. and Hinton, G. (2015), "Deep learning", Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539   DOI
25 Leon-Medina, J.X., Anaya, M., Pozo, F. and Tibaduiza, D. (2020), "Nonlinear feature extraction through manifold learning in an electronic tongue classification task", Sensors, 20(17), 4834. https://doi.org/10.3390/s20174834   DOI
26 MHURD-PRC (2010), Code for Seismic Design of Buildings, China Architecture & Building Press.
27 Qu, C.Z. and Lian, X.W. (2012), "Damage identification for transmission towers based on HHT", Energy Procedia, 17, 1390-1394. https://doi.org/10.1016/j.egypro.2012.02.257   DOI
28 Na, S., Heo, S., Han, S., Shin, Y. and Roh, Y. (2022), "Acceptance Model of Artificial Intelligence (AI)-Based Technologies in Construction Firms: Applying the Technology Acceptance Model (TAM) in Combination with the Technology-Organisation-Environment (TOE) Framework", Buildings, 12(2), 90. https://doi.org/10.3390/buildings12020090   DOI
29 Pan, H., Azimi, M., Yan, F. and Lin, Z. (2018), "Time-frequency-based data-driven structural diagnosis and damage detection for cable-stayed bridges", J. Bridge Eng., 23(6), 04018033. https://doi.org/10.1061/(ASCE)BE.1943-5592.0001199   DOI
30 Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L. and Desmaison, A. (2019), "Pytorch: An imperative style, high-performance deep learning library", Adv. Neural Inform. Process. Syst., 32. https://proceedings.neurips.cc/paper/2019/hash/bdbca288fee7f92f2bfa9f7012727740-Abstract.html
31 Reynolds, P. and Pavic, A. (2003), "Effects of false floors on vibration serviceability of building floors. I: Modal properties", J. Perform. Constr. Facil., 17(2), 75-86. https://doi.org/10.1061/(ASCE)0887-3828(2003)17:2(75)   DOI
32 Smarra, F., Girolamo, G.D.D., Gattulli, V., Graziosi, F. and D'Innocenzo, A. (2020), "Learning models for seismic-induced vibrations optimal control in structures via random forests", J. Optimiz. Theory Applicat., 187(3), 855-874. https://doi.org/10.1007/s10957-020-01698-7   DOI
33 Tiachacht, S., Bouazzouni, A., Khatir, S., Wahab, M.A., Behtani, A. and Capozucca, R. (2018), "Damage assessment in structures using combination of a modified Cornwell indicator and genetic algorithm", Eng. Struct., 177, 421-430. https://doi.org/10.1016/j.engstruct.2018.09.070   DOI
34 Wang, N., Zhao, Q., Li, S., Zhao, X. and Zhao, P. (2018a), "Damage classification for masonry historic structures using convolutional neural networks based on still images", Comput.- Aided Civil Infrastr. Eng., 33(12), 1073-1089. https://doi.org/10.1111/mice.12411   DOI
35 Tibaduiza Burgos, D.A., Gomez Vargas, R.C., Pedraza, C., Agis, D. and Pozo, F. (2020), "Damage identification in structural health monitoring: A brief review from its implementation to the use of data-driven applications", Sensors, 20(3), 733. https://doi.org/10.3390/s20030733   DOI