Skip Navigation Links
Journal of Vibration Testing and System Dynamics

C. Steve Suh (editor), Pawel Olejnik (editor),

Xianguo Tuo (editor)

Pawel Olejnik (editor)

Lodz University of Technology, Poland


C. Steve Suh (editor)

Texas A&M University, USA


Xiangguo Tuo (editor)

Sichuan University of Science and Engineering, China


Huge Size Structure Damage Localization and Severity Prediction: Numerical Modeling, Simulation and SVM Regression Method

Journal of Vcibration Testing and System Dynamics 2(3) (2018) 221--237 | DOI:10.5890/JVTSD.2018.09.003

Gang Jiang$^{1}$, Yiming Deng$^{2}$, Lili Liu$^{3}$, Canghai Liu$^{1}$, Zihong Liu$^{1}$, Yong Jiang$^{1}$

$^{1}$ Manufacturing Process Testing Key Lab of the Ministry of Education, Southwest University of Science and Technology, Mianyang, Sichuan, 621010, China

$^{2}$ Nondestructive Evaluation Laboratory, Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, 48824, USA

$^{3}$ School of Material Science and Engineering, Southwest University of Science and Technology, Mianyang, Sichuan, 621010, China

Download Full Text PDF



In systematic identification for real bridge engineering structural damage evaluation, lack of “negative samples” is the main reason for misjudgment and false classification. Aimed at this problem, the paper proposed a new kinetic-parameters-analysis-based method of damage identification for bridge structures, using both numerical simulation and real experiments under controlled lab conditions. PROE and ADAMS were adopted to build structural models and integrate with simulation experiments under virtual force, requency response data were gathered and used as “simulation datasets”. In real structural experiments, accelerators and advanced signal acquisition equipments were used to collect signals from real structures hit by real force. Signals gathered by equipments ere used as “real datasets”, corresponded with “simulation datasets”. After that, features were extracted from these two kinds of datasets. Authors found that numerical simulation models were not always accurate, while real model had its own advantages and isadvantages. To fill this gap, relationships between simulation and actual measurements were investigated in this paper. Finally, Support Vector Machine (SVM) method was used to perform pattern recognition experiments and showed its good performance on tructure damage identification. The proposed method is scalable and can be extended to a bigger structure, such as the entire bridge faults diagnosis.


Authors would like to thank the supports from Innovation Team Key Fund of Sichuan Provincial Department of Education (16TD0016) and Key Project of Science and Technology Plan of Mianyang City (KJ20170507).


  1. [1]  Alampalli, S. and Rehm, K.C. (2011), Impact of I-35W bridge failure on state transportation agency bridge inspection and evaluation programs, Structures Congress, 1019-1026.
  2. [2]  Wang, T., Celik, O., and Catbas, F.N. (2016), Damage detection of a bridge model based on operational dynamic strain measurements, Advances in Structural Engineering, 19(9), 1379-1389.
  3. [3]  Zhao, J. and Dewolf, J.T. (1999), Sensitivity study for vibration parameters used in damage detection, Journal of Structural Engineering, 125, 410-416.
  4. [4]  Pandey, A.K. and Biswas, M. (1994), Damage detection in structures using changes inflexibility, Journal of Sound and Vibration, 169, 3-17.
  5. [5]  Toksoy, T. and Aktan, A.E. (1994), Bridge condition assessment by modal flexibility, Experimental Mechanics, 34, 271-278.
  6. [6]  Zhang, Z. and Aktan, A.E.(1998), Application of modal flexibility and its derivatives in structural identification, Research in Nondestructive Evaluation, 10, 43-61.
  7. [7]  Park, H., Koo, K., and Yun, C. (2007), Modal flexibility-based damage detection technique of steel beam by dynamic strain measurements using FBG sensors, Steel Structures, 7, 11-18.
  8. [8]  Catbas, F.N., Gul, M., and Burkett, J.L. (2008), Damage assessment using flexibility and flexibility-based curvature for structural health monitoring, Smart Materials and Structures, 17, 1-12.
  9. [9]  Bernal, D. (2002), Load vectors for damage localization, Journal of Engineering Mechanics, 128, 7-14.
  10. [10]  Gao, Y., Spencer, B.F., and Bernal, D. (2007), Experimental verification of the flexibility-based damage locating vector method, Journal of Engineering Mechanics, 133, 1043-1049.
  11. [11]  Bernal, D. (2004), Load vectors for damage location in systems identified from operational loads, Journal of Engineering Mechanics, 136, 31-39.
  12. [12]  Koo, K., Lee, J., Yun, C., and Kim, J. (2008), Damage detection in beam-like structures using deflections obtained by modal flexibility matrices, Smart Structures and Systems, 4, 605-628.
  13. [13]  Kazemi, S., Rahai, A.R., Daneshmand, F., and Fooladi, A. (2011), Implementation of modal flexibility variation method and genetically trained ANNs in fault identification, Ocean Engineering, 38, 774-781.
  14. [14]  Sung, S.H., Koo, K.Y., and Jung, H.J. (2014), Modal flexibility-based damage detection of cantilever beamtype structures using base line modification, Journal of Sound and Vibration, 333, 4123-4138.
  15. [15]  Farrar, C.R., Doebling, S.W., and Nix, D.A. (2001), Vibration-based structural damage identification, Philo sophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences, 359, 131-149.
  16. [16]  Fan, W. and Qiao, P. (2011), Vibration-based damage identification methods: a review and comparative study, Structural Health Monitoring, 10(1), 83-111.
  17. [17]  Rucka, M. (2011), Damage detection in beams using wavelet transform on higher vibration modes, Journal of Theoretical and Applied Mechanics, 49(2), 399-417.
  18. [18]  Moradi, S.H. and Kargozarfard, M. (2013), On multiple crack detection in beam structures, Journal of Mechanical Science and Technology, 27, 47-55.
  19. [19]  Nassar, M., Matbuly, M.S., and Ragb, O. (2013), Vibration analysis of structural elements using differential quadrature method, Journal of Advance Research, 4, 93-102.
  20. [20]  Chen, L.H., Sun, Y., and Zhang, W. (2012), Study of vibration characteristics of cantilever rectangular plate with side crack, Applied Mechanics and Materials, 226-228(5), 113-118.
  21. [21]  Lee, H.L. and Chang, W.J. (2012), Dynamic response of a cracked atomic force microscope cantilever used for nanomachining, Nanoscale research letters, 7, 131-137.
  22. [22]  Seyedpoor, S.M. (2012), Two stage method for structural damage detection using a modal strain energy based index and particle swarm optimization, International Journal of Non-Linear Mechanics, 47(1), 1-8.
  23. [23]  Naseralavi, S.S., Fadaee, M.J., and Salajegheh, J. (2011), Subset solving algorithm: a novel sensitivity-based method for damage detection of structures, Applied Mathematical Modeling, 35(5), 2232-2252.
  24. [24]  Vapnik, V.N. (1998), Statistical Learning Theory, New York: Wiley Publishing House.
  25. [25]  Cristianini, N. and Taylor, J.S. (2000), An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, England: Cambridge University Press.
  26. [26]  Villegas, S., Li, X.O., and Yu, W. (2015), Detection of building structure damage with support vector machine, 12th International Conference on Networking, Sensing and Control, 619-624.
  27. [27]  Dong, X., Wei, B., Sun, Q., and Hou, X. (2010), Investigation on damage self-diagnosis of fiber smart structures based on LS-SVM, 2nd IEEE International Conference on Information Management and Engineering, 626-638.
  28. [28]  Rivera-Castillo, J., Rivas-López, M., Nieto-Hipolito, J.I., and et al. (2014), Structural Health Monitoring based on Optical Scanning Systems and SVM. 23rd International Symposium on Industrial Electronics (ISIE), 1961-1966.
  29. [29]  Zhang, X.Z., Yao, W.J., and Tian, F. (2012), Structural damage identification based on time-varying arma model and support vector machine, Journal of Basic Science and Engineering, 21(6), 1094-1102.