This article proposes a novel vibration-based bridge health monitoring approach using convolutional neural networks (CNNs). Unlike other works that rely on precise feature extraction and suffer from environmental variability, the proposed methodology utilizes acceleration signals transformed into images of sinusoidal gratings via fast Fourier transform as an alternative solution. These images capture the natural frequencies of the bridge, which are sensitive indicators of damage. Three structures are analyzed to verify this novel approach: the Old ADA Bridge, the Z24 Bridge, and the Hell Bridge Test Arena. We employed ResNet50, DenseNet, and InceptionV3 CNN architectures to classify the structural condition. The models of the Old ADA Bridge, the Z24 Bridge, and the Hell Bridge Test Arena achieved F1 scores of 94.15, 98.39, and 99.97%, respectively, surpassing the performance of baseline techniques using acceleration signals as input by up to 13.46%. Furthermore, it was observed that the variability of the modal damage-sensitive features and the type of vibration of the system were not determining factors in the models’ performance. These results indicate the effectiveness of the proposed methodology in the early identification of potential structural problems on real-world bridges.
AtharSPHTaheriMSecristJ, et al. Neural network for structural health monitoring with combined direct and indirect methods. J Appl Remote Sens2020; 14(1): 014511.
4.
NickHAziminejadAHosseiniMH, et al. Damage identification in steel girder bridges using modal strain energy-based damage index method and artificial neural network. Eng Fail Anal2021; 119: 105010.
5.
GuJGulMWuX. Damage detection under varying temperature using artificial neural networks. Struct Control Health Monit2017; 24(11): e1998.
6.
LanYLiZLinW. Physics-guided diagnosis framework for bridge health monitoring using raw vehicle accelerations. Mech Syst Signal Process2024; 206: 110899.
7.
GeethaGKSimSH. Fast identification of concrete cracks using 1D deep learning and explainable artificial intelligence-based analysis. Autom Constr2022; 143: 104572.
8.
JiangSDengWOoiET, et al. Data-driven algorithm based on the scaled boundary finite element method and deep learning for the identification of multiple cracks in massive structures. Comput Struct2024; 291: 107211.
9.
SongHShanXZhangL, et al. Research on identification and active vibration control of cantilever structure based on NARX neural network. Mech Syst Signal Process2022; 171: 108872.
10.
KhodabandehlouHPekcanGFadaliMS, et al. Active neural predictive control of seismically isolated structures. Struct Control Health Monit2017; 25(1): e2061.
11.
ChaYJAliRLewisJ, et al. Deep learning-based structural health monitoring. Autom Constr2024; 161: 105328.
12.
YeXWJinTYunCB. A review on deep learning-based structural health monitoring of civil infrastructures. Smart Struct Syst2019; 24(5): 567–585.
13.
AvciOAbdeljaberOKiranyazS, et al. A review of vibration-based damage detection in civil structures: from traditional methods to Machine Learning and Deep Learning applications. Mech Syst Signal Process2021; 147: 107077.
14.
MiguelLFFLopezRHMiguelLFF. A hybrid approach for damage detection of structures under operational conditions. J Sound Vib2013; 332(18): 4241–4260.
15.
MiguelLFFMiguelLFFKaminski JJr, et al. Damage detection under ambient vibration by harmony search algorithm. Expert Syst Appl2012; 39(10): 9704–9714.
16.
MiguelLFFMiguelLFFKaminskiJJr.Stochastic system identification and damage detection using firefly algorithm. Int J Lifecycle Perform Eng2014; 1: 357–379.
17.
MonteiroDKMiguelLFFZeniG, et al. Whale optimization algorithm for structural damage detection, localization, and quantification. Discov Civ Eng2024; 1: 98.
18.
JuangJNPappaRS. An Eigensystem realization algorithm for modal parameter identification and model reduction. J Guid Control Dyn1985; 8(5): 620–627.
19.
Van OverscheePDe MoorB. Subspace identification for linear systems: theory – implementation – applications. Leuven: Kluwer Academic Publishers, 1996.
20.
PeetersBvan Der AuweraerH. PolyMAX: a revolution in operational modal analysis. In: Proceedings of the international operational modal analysis conference, IOMAC, Copenhagen, Denmark, 26–27 April, 2005.
21.
MonteiroDKMiguelLFFZeniG, et al. Detection, localization, and quantification of damage in structures via artificial neural networks. Shock Vib2023; 2023: 8829298.
22.
PachónPInfantesMCámaraM, et al. Evaluation of optimal sensor placement algorithms for the Structural Health Monitoring of architectural heritage. Application to the Monastery of San Jerónimo de Buenavista (Seville, Spain). Eng Struct2020; 202: 109843.
23.
ShiSDuDMercanO, et al. A novel data-driven sensor placement optimization method for unsupervised damage detection using noise-assisted neural networks with attention mechanism. Mech Syst Signal Process2024; 209: 11075.
24.
TanYZhangL. Computational methodologies for optimal sensor placement in structural health monitoring: a review. Struct Health Monit2020; 19(4): 1287–1308.
25.
SantanielloPRussoP. Bridge damage identification using deep neural networks on time–frequency signals representation. Sensors2023; 23(13): 6152.
26.
HeYChenHLiuD, et al. A framework of structural damage detection for civil structures using fast Fourier transform and deep convolutional neural networks. Appl Sci2021; 11: 9345.
27.
LeiYZhangYMiJ, et al. Detecting structural damage under unknown seismic excitation by deep convolutional neural network with wavelet-based transmissibility data. Struct Health Monit2021; 20(4): 1583–1596.
28.
WangRLiJChencho, et al. Densely connected convolutional networks for vibration-based structural damage identification. Eng Struct2021; 245: 112871.
29.
TangZChenZBaoY, et al. Convolutional neural network-based data anomaly detection method using multiple information for structural health monitoring. Struct Control Health Monit2019; 26(1): e2296.
30.
BaoYTangZLiH, et al. Computer vision and deep learning–based data anomaly detection method for structural health monitoring. Struct Health Monit2019; 18(2): 401–421.
31.
DosovitskiyABeyerLKolesnikovA, et al. An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3–7, 2021.
32.
GoodfellowIBengioYCourvilleA. Deep learning. The MIT Press, Cambridge, MA, USA, 2016.
33.
RosenblattF. Principles of neurodynamics: perceptrons and the theory of brain mechanisms. Washington, DC: Spartan Books, 1962.
34.
RumelhartDEHintonGEWilliamsRJ. Learning representations by back-propagating errors. Nature1986; 323(6088): 533–536.
35.
LeCunYBoserBDenkerJS, et al. Backpropagation applied to handwritten zip code recognition. Neural Comput1989; 1(4): 541–551.
36.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, June 27–30, 2016, pp. 770–778.
37.
IoffeSSzegedyC. Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning, Lille, France, 6–11 July 2015, vol. 37, 2015. JMLR W&CP.
38.
RussakovskyODengJSuH, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis2015; 115: 211–252.
39.
HuangGLiuZvan der MaatenL, et al. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, USA, July 21–26, 2017, pp. 4700–4708.
40.
SzegedyCVanhouckeVIoffeS, et al. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2016, pp. 2818–2826.
41.
KimCWChangKCKitauchiS, et al. A field experiment on a steel Gerber-truss bridge for damage detection utilizing vehicle-induced vibrations. Struct Health Monit2016; 15(2): 174–192.
42.
FigueiredoEYanoMOda SilvaS, et al. Transfer learning to enhance the damage detection performance in bridges when using numerical models. J Bridge Eng2022; 28(1): 04022134.
43.
SalawuOS. Detection of structural damage through changes in frequency: a review. Eng Struct1997; 19(9): 718–723.
44.
KingmaDPBaJ. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980. In: 3rd International conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015.
45.
DavisJGoadrichM. The relationship between precision-recall and ROC curves. In: Proceedings of the 23rd international conference on machine learning (ICML 2006), Pittsburgh, Pennsylvania, USA, June 25–29, 2006.
46.
BreimanL. Random forests. Mach Learn2001; 45(1): 5–32.
47.
ChenTGuestrinC. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, San Francisco, California, USA, August 13–17, 2016, pp. 785–794.
48.
BergstraJKomerBEliasmithC, et al. Hyperopt: a Python library for model selection and hyperparameter optimization. Comput Sci Discov2015; 8(1): 014008.
49.
SonySSadhuA. Synchrosqueezing transform-based identification of time-varying structural systems using multi-sensor data. J Sound Vib2020; 486: 115576.
50.
KimCWZhangFLChangKC, et al. Ambient and vehicle-induced vibration data of a steel truss bridge subject to artificial damage. J Bridge Eng2021; 26(7): 04721002.
51.
KimCWZhangFLChangKC, et al. Old_ada_bridgedamage_vibration_data. Mendeley Data; 2021b. doi:10.17632/sc8whx4pvm.2.
52.
LundbergSMLeeSI. A unified approach to interpreting model predictions. In: 31st Conference on neural information processing systems (NIPS 2017), Long Beach, CA, USA, December 4–9, 2017.
53.
De RoeckG. The state-of-the-art of damage detection by vibration monitoring: the SIMCES experience. J Struct Control2003; 10(2): 127–134.
54.
MaeckJDe RoeckG. Description of Z24 benchmark. Mech Syst Signal Process2003; 17(1): 127–131.
55.
ReyndersEDe RoeckG. Continuous vibration monitoring and progressive damage testing on the Z24 bridge. In: ChristianBFu-KuoCYozoF. (ed.). Encyclopedia of structural health monitoring. New York, NY: John Wiley & Sons, 2009, pp. 2149–2158.
SvendsenBT. Numerical and experimental studies for damage detection and structural health monitoring of steel bridges. Thesis for the Degree of Philosophiae Doctor, Norwegian University of Science and Technology, Trondheim, Norway, 2021.
58.
SvendsenBTFrøsethGTØisethO, et al. A hybrid structural health monitoring approach for damage detection in steel bridges under simulated environmental conditions using numerical and experimental data. Struct Health Monit2023; 22(1): 540–561.
59.
SvendsenBTFrøsethGTØisethO, et al. A data based structural health monitoring approach for damage detection in steel bridges using experimental data. J Civ Struct Health Monit2022; 12: 101–115.
60.
SvendsenBTFrøsethGTØisethO, et al. A data set from an extensive experimental benchmark study of the Hell Bridge Test Arena subject to imposed damage (Version 1). Zenodo, 2024.
