Vibration-based damage assessment approaches use modal parameters, such as frequency response functions, mode shapes, and natural frequencies, as indicators of structural damage. Nevertheless, these parameters are sensitive not only to damage but also to temperature variations. Most civil engineering structures are exposed to varying environmental conditions, thus hindering vibration-based damage assessment. Therefore, in this article, a new damage assessment algorithm based on pattern recognition is proposed to scrutinize the healthy state of a structure in the presence of uncertainties such as noise and temperature. The algorithm adopts a combination of couple sparse coding and deep neural network as an ensemble system to assess damage. The proposed method is validated using a numerical model of a truss bridge and experimental data of the I-40 bridge. The results demonstrate its efficiency in the localization and quantification of damages under varying temperature conditions.
KhoshnoudianFTalaeiS. A new damage index using FRF data, 2D-PCA method and pattern recognition techniques. Int J Struct Stab Dy. Epub ahead of print 28November2016. DOI: 10.1142/S0219455417500900.
FanWQiaoP. Vibration-based damage identification methods: a review and comparative study. Struct Health Monit2011; 10: 83–111.
4.
YanYJChengLWuZY. Development in vibration-based structural damage detection technique. Mech Syst Signal Pr2007; 21: 2198–2211.
5.
SippleJDSanayeiM. Finite element model updating using frequency response functions and numerical sensitivities. Struct Control Hlth2014; 21: 784–802.
6.
MaiaNMMSilvaJMMAlmasEAM. Damage detection in structures: from mode shape to frequency response function methods. Mech Syst Signal Pr2003; 17: 489–498.
7.
ShadanFKhoshnoudianFEsfandiariA. A frequency response-based structural damage identification using model updating method. Struct Control Hlth2016; 23: 286–302.
8.
ShadanFKhoshnoudianFInmanDJ. Experimental validation of a FRF-based model updating method. J Vib Control. Epub ahead of print 16August2016. DOI: 10.1177/1077546316664675.
9.
XiaYHaoHZanardoG. Long term vibration monitoring of an RC slab: temperature and humidity effect. Eng Struct2006; 28: 441–452.
AlampalliS. Influence of in-service environment on modal parameters. In: Proceedings of the 16th international modal analysis conference (IMAC), Santa Barbara, CA, 2–5 February 1998, vol. 3243, pp. 111–116. Bellingham, WA: SPIE.
12.
XiaYChenBWengS. Temperature effect on vibration properties of civil structures: a literature review and case studies. J Civ Struct Health Monit2012; 2: 29–46.
13.
LiuCDeWolfJT. Effect of temperature on modal variability of a curved concrete bridge under ambient loads. J Struct Eng: ASCE2007; 133: 1742–1751.
14.
YangDYouliangDAiqunL. Structural condition assessment of long-span suspension bridges using long-term monitoring data. Earthq Eng Eng Vib2010; 9: 123–131.
15.
LiHLiSOuJ. Modal identification of bridges under varying environmental conditions: temperature and wind effects. Struct Control Hlth2010; 17: 495–512.
16.
DesjardinsSLLondonoNALauDT. Real-time data processing, analysis and visualization for structural monitoring of the confederation bridge. Adv Struct Eng2006; 9: 141–157.
17.
ZhouHFNiYQKoJM. Constructing input to neural networks for modeling temperature-caused modal variability: mean temperatures, effective temperatures, and principal components of temperatures. Eng Struct2010; 32: 1747–1759.
18.
NiYQHuaXGFanKQ. Correlating modal properties with temperature using long-term monitoring data and support vector machine technique. Eng Struct2005; 27: 1762–1773.
19.
PeetersBDe RoeckG. One-year monitoring of the Z24-bridge: environmental effects versus damage events. Earthq Eng Struct D2001; 30: 149–171.
20.
FarrarCRJaureguiDA. Comparative study of damage identification algorithms applied to a bridge: I. Experiment. Smart Mater Struct1998; 7: 720–731.
21.
CornwellPFarrarCRDoeblingSW. Environmental variability of modal properties. Exp Techniques1999; 23: 45–48.
22.
NiYQFanKQZhengG. Automatic modal identification and variability in measured modal vectors of a cable-stayed bridge. Struct Eng Mech2005; 19: 123–139.
23.
SohnHDzwonczykMStraserEG. An experimental study of temperature effect on modal parameters of the Alamosa Canyon Bridge. Earthq Eng Struct D1999; 28: 879–897.
24.
SohnHWordenKFarrarCR. Novelty detection under changing environmental conditions. In: Proceedings of the SPIE’s 8th annual international symposium on smart structures and materials, Newport Beach, CA, 4 March 2001, pp. 108–118. Bellingham, WA: SPIE.
25.
KoJMChakKKWangJY. Formulation of an uncertainty model relating modal parameters and environmental factors by using long-term monitoring data. In: Proceedings of the SPIE smart structures and materials 2003 conference, San Diego, CA, 2 March 2003, pp. 298–307. Bellingham, WA: SPIE.
26.
KullaaJ. Eliminating environmental or operational influences in structural health monitoring using the missing data analysis. J Intel Mat Syst Str2009; 20: 1381–1390.
27.
YanA-MKerschenGDe BoeP. Structural damage diagnosis under varying environmental conditions—part I: a linear analysis. Mech Syst Signal Pr2005; 19: 847–864.
28.
YanAMKerschenGDe BoeP. Structural damage diagnosis under varying environmental conditions—part II: local PCA for non-linear cases. Mech Syst Signal Pr2005; 19: 865–880.
29.
SohnHWordenKFarrarCR. Statistical damage classification under changing environmental and operational conditions. J Intel Mat Syst Str2002; 13: 561–574.
30.
LimongelliMP. Frequency response function interpolation for damage detection under changing environment. Mech Syst Signal Pr2010; 24: 2898–2913.
31.
MeruaneVHeylenW. Structural damage assessment under varying temperature conditions. Struct Health Monit2012; 11: 345–357.
32.
ZangCImregunM. Structural damage detection using artificial neural networks and measured FRF data reduced via principal component projection. J Sound Vib2001; 242: 813–827.
33.
HuangYBeckJLLiH. Hierarchical sparse Bayesian learning for structural damage detection: theory, computation and application. Struct Saf2017; 64: 37–53.
34.
ChaY-JBuyukozturkO. Structural damage detection using modal strain energy and hybrid multiobjective optimization. Comput-Aided Civ Inf2015; 30: 347–358.
35.
MeruaneVHeylenW. Structural damage assessment with anti-resonances versus mode shapes using parallel genetic algorithms. Struct Control Hlth2011; 18: 825–839.
36.
MehrjooMKhajiNMoharramiH. Damage detection of truss bridge joints using Artificial Neural Networks. Expert Syst Appl2008; 35: 1122–1131.
37.
KhoshnoudianFTalaeiSFallahianM. Structural damage detection using FRF data, 2D-PCA, artificial neural networks and imperialist competitive algorithm simultaneously. Int J Struct Stab Dy. Epub ahead of print 7September2016. DOI: 10.1142/S0219455417500730.
38.
PadilKHBakharyNHaoH. The use of a non-probabilistic artificial neural network to consider uncertainties in vibration-based-damage detection. Mech Syst Signal Pr2017; 83: 194–209.
39.
ChangKCKimCW. Modal-parameter identification and vibration-based damage detection of a damaged steel truss bridge. Eng Struct2016; 122: 156–173.
40.
HintonGESalakhutdinovRR. Reducing the dimensionality of data with neural networks. Science2006; 313: 504–507.
41.
BrucksteinAMDonohoDLEladM. From sparse solutions of systems of equations to sparse modeling of signals and images. SIAM Rev2009; 51: 34–81.
42.
WrightJMaYiMairalJ. Sparse representation for computer vision and pattern recognition. P IEEE2010; 98: 1031–1044.
43.
ZhouX-QXiaYWengS. L1 regularization approach to structural damage detection using frequency data. Struct Health Monit2015; 14: 571–582.
44.
ZolfaghariMJourablooAGozlouSG. 3D human pose estimation from image using couple sparse coding. Mach Vision Appl2014; 25: 1489–1499.
45.
WolpertDH. The supervised learning no-free-lunch theorems. In: RoyRDiplom-PhysMKOvaskaS. (eds) Soft computing and industry. London: Springer, 2002, pp. 25–42.
46.
HansenLKSalamonP. Neural network ensembles. IEEE T Pattern Anal1990; 12: 993–1001.
47.
OpitzDWShavlikJW. Actively searching for an effective neural-network ensemble. Connect Sci1996; 8: 337–353.
48.
PerroneMPCooperLN. When networks disagree: ensemble methods for hybrid neural network. In: MammoneRJ (ed.) Neural networks for speech and image processing. Boca Raton, FL: Chapman Hall, 1993, pp. 126–142.
49.
DackermannULiJSamaliB. Identification of member connectivity and mass changes on a two-storey framed structure using frequency response functions and artificial neural networks. J Sound Vib2013; 332: 3636–3653.
50.
MarwalaT. Damage identification using committee of neural networks. J Eng Mech: ASCE2000; 126: 43–50.
51.
BatesLBeachTArnottM. Determination of the temperature dependence of Young’s modulus for stainless steel using a tuning fork. J Undergrad Res Phys1999; 18: 9–13.
52.
ChenJYoungBUyB. Behavior of high strength structural steel at elevated temperatures. J Struct Eng: ASCE2006; 132: 1948–1954.
53.
EwinsDJ. Modal testing: theory and practice. Philadelphia, PA: Research Studies Press, 1984.
54.
PearsonK. LIII. On lines and planes of closest fit to systems of points in space. Philos Mag1901; 2: 559–572.
55.
HintonGDengLYuD. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Proc Mag2012; 29: 82–97.
56.
GlorotXBengioY. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th international conference on artificial intelligence and statistics (AISTATS), Sardinia, 13–15 May 2010, vol. 9, pp. 249–256, PMLR.
57.
AlampalliSFuGDillonEW. Signal versus noise in damage detection by experimental modal analysis. J Struct Eng: ASCE1997; 123: 237–245.
MayesRL. An experimental algorithm for detecting damage applied to the I-40 bridge over the Rio Grande. In: Proceedings of the 13th international modal analysis conference, Nashville, TN, 13–16 February 1995, pp. 219–225. Bethel, CT: Society for Experimental Mechanics.
