Damage in a structure is defined as changes to its geometric and material properties, leading to a reduction in the structural stiffness which negatively affects the performance of the structure. Reduction in the structural stiffness produces changes in the modal parameters such as the natural frequencies and mode shapes. Artificial neural networks (ANNs) have been applied extensively in recent years due to their excellent pattern recognition ability that is useful for structural damage identification purposes. In this paper, ANNs based damage identification techniques were developed and applied for damage localization and severity identification in I-beam structures using dynamic parameters. Experimental modal analysis and numerical simulations were applied to generate dynamic parameters of the first five flexural modes of structures. In damage identification using ANNs, five individual networks corresponding to mode 1 to mode 5 were trained, and then a method based on neural network ensemble was proposed to combine the outcomes of the individual neural networks into a single network. The ensemble network has the advantages of all the individual networks from different vibrational modes. The results showed that ensemble neural networks have a strong potential for structural damage identification.
Abdul RazakHChoiFC (2001) The effect of corrosion on the natural frequency and modal damping of reinforced concrete beams. Engineering Structures23(9): 1126–1133.
2.
Akhand MAH (2009) Ensembles of diverse neural networks. PhD Thesis, University of Fukui, Japan.
3.
AvitabilePO’CallahaJ (2009) Efficient techniques for forced response involving linear modal components interconnected by discrete nonlinear connection elements. Mechanical Systems and Signal Processing23(1): 45–67.
4.
BakharyNHaoHDeeksAJ (2010) Structure damage detection using neural network with multi-stage substructuring. Advances in Structural Engineering13(1): 1–16.
5.
BohlooliHNazariAKaykhaMM (2012) Microhardness profile prediction of functionally graded steels by artificial neural networks. International Journal of Damage Mechanics22(1): 17–36.
6.
ChowCLJieM (2009) Anisotropic damage-coupled sheet metal forming limit analysis. International Journal of Damage Mechanics18: 371–392.
7.
ChowCLWangJ (1987) Ananisotropic theory of continuum damage mechanics for ductile fracture. Engineering Fracture Mechanics27: 547–558.
8.
ChowCLWangJ (1988) Ductile fracture characterization with an anisotropic continuum damage theory. Engineering Fracture Mechanics30: 547–563.
9.
ChowCLMaoJShenJ (2011) Nonlocal damage gradient model for fracture characterization of aluminum alloy. International Journal of Damage Mechanics20: 1073.
10.
Das HC and Parhi DR (2009) Application of neural network for fault diagnosis of cracked cantilever beam. In: World Congress on nature & biologically inspired computing (NaBIC 2009), Coimbatore, India, Article No. 5393733, pp. 1303–1308.
11.
DemuthHBealeMHaganM (2005) Neural Network Toolbox User’s Guide. Version 4.0.6. The Math Works Inc., Natick, MA, USA.
HakimSJSNoorzaeiJJaafarMS (2011) Application of artificial neural networks to predict compressive strength of high strength concrete. International Journal of the Physical Sciences (IJPS)6((5): 975–981.
14.
HakimSJSAbdul RazakH (2014) Frequency response function-based structural damage identification using artificial neural networks – a review. Research Journal of Applied Sciences, Engineering and Technology7(9): 1750–1764.
15.
HakimSJSAbdul RazakH (2013) Adaptive neuro-fuzzy inference system (ANFIS) and artificial neural networks (ANNs) for structural damage identification. Structural Engineering and Mechanics45(6): 779–802.
16.
HakimSJSAbdul RazakH (2011) Application of combined artificial neural networks and modal analysis for structural damage identification in bridge girder. International Journal of the Physical Sciences (IJPS)6(35): 7991–8001.
17.
HansenLKSalamonP (1990) Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence12(10): 993–1001.
18.
HaykinS (1999) Neural Networks: A Comprehensive Foundation, 2nd ed. Upper Saddle River, NJ: Prentice Hall.
19.
JadidMNFairbairnDR (1996) Neural network applications in predicting moment-curvature parameters from experimental data. Journal of Engineering Application Artificial Intelligent9(3): 309–319.
20.
KanwarVKwatraNAggarwalP (2007) Damage detection for framed RCC buildings using ANN modeling. International Journal of Damage Mechanics16(4): 457–472.
21.
LeeJJLeeJWYiJH (2005) Neural networks-based damage detection for bridges considering errors in baseline finite element models. Journal of Sound and Vibration280(3–5): 555–578.
22.
LevinRILievenNAJ (1998) Dynamic finite element model updating using neural networks. Journal of Sound and Vibration210(5): 593–607.
23.
LuYTuZ (2004) A two-level neural network approach for dynamic FE model updating including damping. Journal of Sound and Vibration275: 931–952.
24.
MaiaNMMSilvaJMMHeJ (1997) Theoretical and Experimental Modal Analysis, Hertfordshire, UK: Research Studies Press.
25.
MarwalaTHuntHEM (1999) Fault identification using finite element models and neural networks. Mechanical Systems and Signal Processing13: 475–490.
26.
MehrjooMKhajiNMoharramiH (2008) Damage detection of truss bridge joints using artificial neural networks. Journal of Expert Systems with Applications35(3): 1122–1131.
27.
NazariARiahiS (2012) Prediction of physical and mechanical properties of high strength concrete containing CuO nanoparticles by artificial neural network and genetic programming. International Journal of Damage Mechanics21(2): 207–236.
28.
NiYQZhouXTKoJM (2006) Experimental investigation of seismic damage identification using PCA-compressed frequency response functions and neural networks. Journal of Sound and Vibration290: 242–263.
29.
NoorzaeiJHakimSJSJaafarMS (2008) An approach to predict ultimate bearing capacity of surface footings using artificial neural network. Indian Geotechnical Journal38(4): 515–528.
30.
NoorzaeiJHakimSJSJaafarMS (2007) An optimal architecture of artificial neural network for predicting of compressive strength of concrete. Indian Concrete Journal81(8): 17–24.
31.
Ramsey KA (1982) Experimental modal analysis, structural modifications and FEM analysis on a desktop computer. In: Proceedings of the 1st international modal analysis conference (IMAC I), Society for Experimental Mechanics (SEM), November 8–10, Orlando, FL.
32.
RosalesMBFilipichCPBuezasFS (2009) Crack detection in beam-like structures. Journal of Engineering Structures31: 2257–2264.
SollichPKroghA (1996) Learning with Ensembles: How Overfitting can be Useful. Advances in Neural Information Processing Systems, Denver, CO: MIT Press, pp. 190–196.
35.
SuhMWShimMBKimMY (2000) Crack identification using hybrid neuro-genetic technique. Journal of Sound and Vibration234(4): 617–635.
