Damage Identification for Simply-Supported Bridge Based on SVM Optimized by PSO (PSO-SVM)

Abstract:

A support vector machine (SVM) optimized by particle swarm optimization (PSO)-based damage identification method is proposed in this paper. The classification accuracy of the damage localization and the detection accuracy of severity are used as the fitness function, respectively. The best and can be obtained through velocity and position updating of PSO. A simply supported beam bridge with five girders is provided as numerical example, damage cases with single and multiple suspicious damage elements are established to verify the feasibility of the proposed method. Numerical results indicate that the SVM optimized by PSO method can effectively identify the damage locations and severity.

• Periodical: Applied Mechanics and Materials (Volumes 80-81)
• Pages: 490-494
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.80-81.490
• Online since: July 2011
• Authors: Han Bing Liu, Yu Bo Jiao, Ya Feng Gong, Hai Peng Bi, Yan Yi Sun
• Keywords: Damage Identification, Numerical Simulation, Particle Swarm Optimization Algorithm (PSO), Simply-Supported Bridge, Support Vector Machine (SVM)

References

[1] Xie Jun, Han Dajian, Numerical simulation of damage detection for simply-supported reinforced concrete T-beam bridge, China Journal of Highway and Transport. 17 (2004) 45-49.

[2] S.W. Doebling, C.R. Farrar, M.B. Prime, A summary review of vibration based damage identification methods, Shock vib dig. 30 (1998) 91-105.

DOI: 10.1177/058310249803000201

[3] M. Mehrjoo, N. Khaji, H. Moharrami, A. Ba hreininejad, Damage detection of truss bridge joints using artificial neural networks, Expet Syst Appl. 35 (2008) 1122-1131.

DOI: 10.1016/j.eswa.2007.08.008

[4] Jong Jae Lee, Jong Won Lee, Jin Hak Yi, Chung Bang Yun, Hie Young Jung, Neural networks-based damage detection for bridges considering errors in baseline finite element models, J Sound Vib. 280 (2005) 555-578.

DOI: 10.1016/j.jsv.2004.01.003

[5] Y.Q. Ni, X.T. Zhou, J.M. Ko, B.S. Wang, Vibration-based damage localization in Ting Kau bridge using probabilistic neural network, Advances in structural dynamics. 2 (2000) 1069-1076.

[6] Yang JY, Zhang YY, Zhu YS, Intelligent fault diagnosis of rolling element bearing based on SVMs and fractal dimention, Mech Syst Signal Pr. 23 (2009) 384-404.

[7] Liu Lixia, Zhuang Yiqi, Liu Xueyong, Tax forecasting theory and model based on SVM optimized by PSO, Expet Syst Appl. 38 (2011) 116-120.

[8] Luke Bornn, Charles R. Farrar, Gyuhae Park, Damage detection in initially nonlinear systems, INT J ENG SCI. 48 (2010) 909-920.

DOI: 10.1016/j.ijengsci.2010.05.011

[9] Pao-Shan Yu, Shien-Tsung Chen, I-Fan Chang, Support vector regression for real-time flood stage forecasting, J Hydrol. 328 (2006) 704-716.

DOI: 10.1016/j.jhydrol.2006.01.021

[10] Aliaksei Kerhet, Mirco Raffetto, Andrea Boni, Andrea Massa, A SVM-based approach to microwave breast cancer detection, ENG APPL ARTIF INTEL. 19 (2006) 807-818.

DOI: 10.1016/j.engappai.2006.05.010

[11] Hanbing Liu, Yubo Jiao, Curvature modal shape and neural networks-based damage identification for simply supported T-beam bridge, J Jilin univ. (In Press).