The cracks of bridges are not always completely open during vibrations but undergo an open and closed cycle mode under moving vehicles. Therefore, this study proposes a long short-term memory (LSTM)-based detection model for breathing cracks with multiple damage positions and degrees of beam-like bridges for the first time. The contact point displacement variation (CPDV), serving as an evaluation indicator of the bridge damage, is calculated by analyzing the acceleration history data of the vehicle that has passed over a randomly damaged bridge. At the same time, CPDV is also used as the input variable of an LSTM neural network to monitor the damage location and degree of the bridge. By employing the finite element simulation of the bridge half-vehicle model, a dataset was created for the training and prediction of LSTM. The numerical results show that the proposed method can accurately identify complex breathing crack information at different vehicle speeds, and it is also robust to road roughness. In addition, a laboratory experiment was conducted to verify the proposed method. The experimental results show that CPDV is sensitive to bridge cracks and LSTM can realize higher damage prediction.
SmythAWPeiJSMasriSF.System identification of the Vincent Thomas suspension bridge using earthquake records. Earthquake Eng Struct Dyn2003; 32: 339–367.
3.
VairoG.A numerical model for wind loads simulation on long-span bridges. Simul Model Pract Theory2003; 11: 315–351.
4.
XuZ-DWuZ.Simulation of the effect of temperature variation on damage detection in a long-span cable-stayed bridge. Struct Health Monit2007; 6: 177–189.
5.
XueM-SYiT-HQuC-X, et al. Rapid estimation of bridge key deflection through optimized substructural impact testing. J Bridge Eng2022; 27: 04022088.
6.
LynchJPLohKJ.A summary review of wireless sensors and sensor networks for structural health monitoring. Shock Vib Dig2006; 38: 91–130.
7.
MalekjafarianACorballyRGongW. A review of mobile sensing of bridges using moving vehicles: progress to date, challenges and future trends. Structures2022; 44: 1466–1489.
8.
ZhangJYiT-HQuC-X, et al. Detecting hinge joint damage in hollow slab bridges using mode shapes extracted from vehicle response. J Perform Constr Facil2022; 36: 04021109.
9.
WangLYiSYuY, et al. Automated ultrasonic-based diagnosis of concrete compressive damage amidst temperature variations utilizing deep learning, Mech Syst Signal Process2024; 221: 111719.
10.
YuYRashidiMDorafshanS, et al. Ground penetrating radar-based automated defect identification of bridge decks: a hybrid approach. J Civ Struct Health Monit2024: 1–23. https://doi.org/10.1007/s13349-024-00895-6
11.
BiondiBCaddemiS.Closed form solutions of Euler–Bernoulli beams with singularities. Int J Solids Struct2005; 42: 3027–3044.
12.
CaddemiSCalioI.Exact closed-form solution for the vibration modes of the Euler–Bernoulli beam with multiple open cracks. J Sound Vib2009; 327: 473–489.
13.
ElhattabAUddinNOBrienE.Drive-by bridge damage monitoring using Bridge Displacement Profile Difference. J Civ Struct Health Monit2016; 6: 839–850.
14.
LawSZhuX.Dynamic behavior of damaged concrete bridge structures under moving vehicular loads. Eng Struct2004; 26: 1279–1293.
15.
OBrienEJKeenahanJ.Drive-by damage detection in bridges using the apparent profile. Struct Control Health Monit2015; 22: 813–825.
16.
OBrienEJMalekjafarianA.A mode shape-based damage detection approach using laser measurement from a vehicle crossing a simply supported bridge. Struct Control Health Monit2016; 23: 1273–1286.
17.
SinhaJKFriswellMEdwardsS.Simplified models for the location of cracks in beam structures using measured vibration data. J Sound Vib2002; 251: 13–38.
18.
SarvestanVMirdamadiHRGhayourM, et al. Spectral finite element for vibration analysis of cracked viscoelastic Euler–Bernoulli beam subjected to moving load. Acta Mech2015; 226: 4259–4280.
19.
ZhangBQian WuY, et al. An effective means for damage detection of bridges using the contact-point response of a moving test vehicle. J Sound Vib2018; 419: 158–172.
20.
VaidyaTChatterjeeA.Crack estimation of beam under the moving mass using the dynamic characteristics based on two contact point theory. Iran J Sci Technol Trans Mech Eng2019; 43: 307–326.
21.
GuoDXiaoZQiX, et al. Safety monitor symmetry concerning beam bridge damage utilizing the instantaneous amplitude square method. Symmetry2023; 15: 365.
22.
ZhangWMaHZengJ, et al. Vibration responses analysis of an elastic-support cantilever beam with crack and offset boundary. Mech Syst Signal Process2017; 95: 205–218.
23.
AriaeiAZiaei-RadSGhayourM.Vibration analysis of beams with open and breathing cracks subjected to moving masses. J Sound Vib2009; 326: 709–724.
24.
NguyenKV.Comparison studies of open and breathing crack detections of a beam-like bridge subjected to a moving vehicle. Eng Struct2013; 51: 306–314.
25.
LiHWangTWuG.Nonlinear vibration analysis of beam-like bridges with multiple breathing cracks under moving vehicle load. Mech Syst Signal Process2023; 186: 109866.
26.
ZhuJZhangY.Damage detection for bridge structures under vehicle loads based on frequency decay induced by breathing cracks. Struct Infrastruct Eng2023; 19: 793–809.
27.
ChondrosTGDimarogonasADYaoJ.Vibration of a beam with a breathing crack. J Sound Vib2001; 239: 57–67.
28.
PugnoNSuraceCRuotoloR.Evaluation of the non-linear dynamic response to harmonic excitation of a beam with several breathing cracks. J Sound Vib2000; 235: 749–762.
29.
DoukaEHadjileontiadisL.Time–frequency analysis of the free vibration response of a beam with a breathing crack. NDT & E Int2005; 38: 3–10.
30.
CicirelloAPalmeriA.Static analysis of Euler–Bernoulli beams with multiple unilateral cracks under combined axial and transverse loads. Int J Solids Struct2014; 51: 1020–1029.
31.
CicirelloA.On the response bounds of damaged Euler–Bernoulli beams with switching cracks under moving masses. Int J Solids Struct2019; 172: 70–83.
32.
GianniniOCasiniPVestroniF.Nonlinear harmonic identification of breathing cracks in beams. Comput Struct2013; 129: 166–177.
33.
PrawinJRaoARMLakshmiK.Nonlinear identification of structures using ambient vibration data. Comput Struct2015; 154: 116–134.
34.
PrawinJLakshmiKRaoARM. A novel vibration based breathing crack localization technique using a single sensor measurement. Mech Syst Signal Process2019; 122: 117–138.
35.
TanCUddinN.Hilbert transform based approach to improve extraction of “drive-by” bridge frequency. Smart Struct Syst2020; 25: 265.
36.
JianXXiaYSunL.An indirect method for bridge mode shapes identification based on wavelet analysis. Struct Control Health Monit2020; 27: e2630.
37.
O’BrienEJMalekjafarianAGonzálezA.Application of empirical mode decomposition to drive-by bridge damage detection. Eur J Mech A Solids2017; 61: 151–163.
38.
YangZWangCLiY, et al. Finite element–based data-driven method to detect multiple damages of 1D beam model and 2D slab model of bridges: a theoretical and experimental study. Measurement2025; 241: 115709.
39.
YangYZhangBQianY, et al. Contact-point response for modal identification of bridges by a moving test vehicle. Int J Struct Stab Dyn2018; 18: 1850073.
40.
SonySDunphyKSadhuA, et al. A systematic review of convolutional neural network-based structural condition assessment techniques. Eng Struct2021; 226: 111347.
41.
LiuJZouZGaoK, et al. A novel digital unit cell library generation framework for topology optimization of multi-morphology lattice structures. Compos Struct2025; 354: 118824.
42.
CerdaFChenSBielakJ, et al. Kovacevic, Indirect structural health monitoring of a simplified laboratory-scale bridge model. Smart Struct Syst2014; 13: 849–868.
43.
JinCJangSSunX, et al. Damage detection of a highway bridge under severe temperature changes using extended Kalman filter trained neural network. J Civ Struct Health Monit2016; 6: 545–560.
44.
LockeWSybrandtJRedmondL, et al. Using drive-by health monitoring to detect bridge damage considering environmental and operational effects. J Sound Vib2020; 468: 115088.
45.
LiHWangTWuG. Dynamic response prediction of vehicle-bridge interaction system using feedforward neural network and deep long short-term memory network. Structures2021; 34: 2415–2431.
46.
LiHWangTWuG.A Bayesian deep learning approach for random vibration analysis of bridges subjected to vehicle dynamic interaction. Mech Syst Signal Process2022; 170: 108799.
47.
ShinROkadaYYamamotoK.Application of C-LSTM networks to automatic labeling of vehicle dynamic response data for bridges. Sensors2022; 22: 3486.
48.
BahramiOWangWHouR, et al. A sequence-to-sequence model for joint bridge response forecasting. Mech Syst Signal Process2023; 203: 110690.
49.
LiHWangTYangJP, et al. Deep learning models for time-history prediction of vehicle-induced bridge responses: a comparative study. Int J Struct Stab Dyn2023; 23: 2350004.
GersFASchmidhuberJCumminsF.Learning to forget: continual prediction with LSTM. Neural Comput2000; 12: 2451–2471.
52.
NguyenKVTranHT.Multi-cracks detection of a beam-like structure based on the on-vehicle vibration signal and wavelet analysis. J Sound Vib2010; 329: 4455–4465.
YangY-BYauJYaoZ, et al. Vehicle-bridge interaction dynamics: with applications to high-speed railways. Singapore: World Scientific, 2004.
55.
VibrationIM.Road surface profiles—reporting of measured data. ISO 8608. Geneve: International Standards Organisation, 2016.
56.
YangYLiYChangK.Effect of road surface roughness on the response of a moving vehicle for identification of bridge frequencies. Interact Multiscale Mech2012; 5: 347–368.
57.
YangYZhangBChenY, et al. Bridge damping identification by vehicle scanning method. Engineering Struct2019; 183: 637–645.
58.
YangYXiongFWangZ, et al. Extraction of bridge frequencies inclusive of the higher modes by the ESMD using the contact-point response. Int J Struct Stab Dyn2020; 20: 2050045.
59.
LiuJChenSBergésM, et al. Diagnosis algorithms for indirect structural health monitoring of a bridge model via dimensionality reduction. Mech Syst Signal Process2020; 136: 106454.
60.
KimC-WIsemotoRMcGetrickP, et al. Drive-by bridge inspection from three different approaches. Smart Struct Syst2014; 13: 775–796.
