In this study, a field experiment was performed for damage detection on a PSC-I bridge based on a convolutional autoencoder using the damage detection approach proposed in a previous study by the authors. The field experiment measured the acceleration and strain data of the PSC-I bridge while a single vehicle passed the bridge; subsequently, these data were used to train and test the convolutional autoencoder–based damage detection model. The results of the test showed that the convolutional autoencoder–based model could perform accurate and robust damage detection. Furthermore, these findings indicate that the convolutional autoencoder–based damage detection could also perform satisfactorily in practice. The results of this study can form the basis to facilitate the adoption of the convolutional autoencoder–based damage detection method to monitor bridges in practice.
CasasJRMoughtyJJ. Bridge damage detection based on vibration data: past and new developments. Front Built Environ2017; 3: 4.
2.
LeeKJeongSSimSH, et al. A novelty detection approach for tendons of prestressed concrete bridges based on a convolutional autoencoder and acceleration data. Sensors2017; 19(7): 1633.
3.
StaszewskiWJMahzanSTraynorR. Health monitoring of aerospace composite structures–active and passive approach. Compos Sci Technol2009; 69(11–12): 1678–1685.
4.
GiurgiutiuV. Structural damage detection with piezoelectric wafer active sensors. J Phys Conf Ser2011; 305(1): 012123.
5.
GonzalezIKaroumiR. BWIM aided damage detection in bridges using machine learning. J Civ Struct Health Monit2015; 5(5): 715–725.
6.
DasSSahaPPatroSK. Vibration-based damage detection techniques used for health monitoring of structures: a review. J Civ Struct Health Monit2016; 6(3): 477–507.
7.
LeeKByunNShinD. A damage localization approach for Rahmen bridge based on convolutional neural network. KSCE J Civ Eng2020; 24: 1–9.
8.
KirmserPG. The effect of discontinuities of the natural frequency of beams. London: The College, 1944.
9.
CasasJRAparicioAC. Structural damage identification from dynamic-test data. J Struct Eng ASCE1994; 120: 2437–2450.
10.
LuQRenGZhaoY. Multiple damage location with flexibility curvature and relative frequency change for beam structures. J Sound Vib2002; 253(5): 1101–1114.
11.
CatbasFNGulMBurkettJL. Conceptual damage-sensitive features for structural health monitoring: laboratory and field demonstrations. Mech Syst Signal Pr2008; 22(7): 1650–1669.
12.
ChangKCKimCW. Modal-parameter identification and vibration-based damage detection of a damaged steel truss bridge. Eng Struct2016; 122: 156–173.
13.
BlachowskiBSwierczAGutkiewiczP, et al. Structural damage detectability using modal and ultrasonic approaches. Measurement2016; 85: 210–221.
14.
SomanRKyriakidesMOnoufriouT, et al. Numerical evaluation of multi-metric data fusion based structural health monitoring of long span bridge structures. Struct Infrastruct Eng2018; 14: 673–684.
15.
MaoJXWangHFengDM, et al. Investigation of dynamic properties of long-span cable-stayed bridges based on one-year monitoring data under normal operating condition. Struct Control Hlth Monitor2018; 25(5): e2146.
16.
MaoJXWangHFuYG, et al. Automated modal identification using principal component and cluster analysis: application to a long-span cable-stayed bridge. Struct Control Hlth Monitor2019; 26(10): e2430.
17.
KochHW. Determining the effects of vibration in buildings. VDIZ1953; 25(21): 744–747.
18.
SteffensRJ. Structural vibration and damage. Building Research Establishment report, HMSO, London, 1974.
19.
MansonG. Identifying damage sensitive, environment insensitive features for damage detection. In: Proceedings of the third international conference on identification in engineering systems, Paris, 10–12 July 2002, pp. 187–197.
20.
CrossEJMansonGWordenK, et al. Features for damage detection with insensitivity to environmental and operational variations. Proc Roy Soc A Math Phys Eng Sci2012; 468(2148): 4098–4122.
21.
WahWSLChenYTRobertsGW, et al. Damage detection of structures subject to nonlinear effects of changing environmental conditions. Procedia Eng2017; 188: 248–255.
22.
HouZNooriMAmandRS. Wavelet-based approach for structural damage detection. J Eng Mech2000; 126: 677–683.
23.
KhatamHGolafshaniAABeheshti-AvalS, et al. Harmonic class loading for damage identification in beams using wavelet analysis. Struct Health Monit2007; 6: 67–80.
24.
PnevmatikosNGBlachowskiBHatzigeorgiouGD, et al. Wavelet analysis based damage localization in steel frames with bolted connections. Smart Struct Syst2016; 18: 1189–1202.
25.
TjirkallisAKyprianouA. Damage detection under varying environmental and operational conditions using wavelet transform modulus maxima decay lines similarity. Mech Syst Signal Pr2016; 66: 282–297.
26.
NiYQZhouXTKoJM, et al. Vibration-based damage localization in Ting Kau bridge using probabilistic neural network. Adv Struct Dynam2000; 2: 1069–1076.
27.
LeeJJLeeJWYiJH, et al. Neural networks-based damage detection for bridges considering errors in baseline finite element models. J Sound Vib2005; 280(3–5): 555–578.
28.
MehrjooMKhajiNMoharramiH, et al. Damage detection of truss bridge joints using artificial neural networks. Expert Syst Appl2008; 35(3): 1122–1131.
29.
GaoZFChenXJ. Structure data processing and damage identification based on wavelet and artificial neural network. Res J Appl Sci Eng Tech2011; 3(1): 1203–1208.
30.
LinYZNieZHMaHW. Structural damage detection with automatic feature-extraction through deep learning. Comput aided Civ Inf2017; 32: 1025–1046.
31.
AbdeljaberOAvciOKiranyazS, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J Sound Vib2017; 388: 154–170.
32.
HintonGESalakhutdinovRR. Reducing the dimensionality of data with neural networks. Science2006; 313: 504–507.
33.
National Geographic Information Institute. National geographic information platform, http://map.ngii.go.kr/ (2015, accessed 5 December 2019).
