Structural Damage Localization Based on AR Model and BP Neural Network

Abstract:

When the AR model is used to identify the structural damage, one problem is often met, that is the method can only make a decision whether the structure is damaged, however, the damage location can not be identified exactly. A structural damage localization method based on AR model in combination with BP neural network is proposed in this paper. The AR time series models are used to describe the acceleration responses. The changes of the first 3-order AR model parameters are extracted and composed as damage characteristic vectors which are put into BP neural network to identify the damage location. The effectiveness of the method is validated by the results of numerical simulation and experiment for a four-layer offshore platform. Only the acceleration responses can be used adequately to localize the structural damage, without the usage of modal parameter and excitation force. Thus the dependence on the modal parameter and excitation can be avoided in this method.

• Periodical: Applied Mechanics and Materials (Volumes 94-96)
• Pages: 1211-1215
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.94-96.1211
• Online since: September 2011
• Authors: Yan Song Diao, Fei Yu, Dong Mei Meng
• Keywords: Autoregressive AR Model, BP Neural Network (BPNN), Damage Localization, Time-Series

References

[1] Bement M T．Farrar C R. Issues for the application of statistical models in damage detection[c]//SPIE Vo1.4062,Proceedings of IMAC-18:A Conference on Structural Dynamics.San Antonio,Texas,2000:1392~1398.

[2] Yi Liu, Aiqun Li, Ding Youliang, Fei qingguo. The damage characteristic extraction and alarming method based on time series analysis. Applied Mechanics Joural. 2008,Vol.25(2), 253~257. (In Chinese)

[3] Krishnan Nair K, Anne S Kiremidjian, Kincho H Lawb. Time series based damage detection and localization algorithm with application to the ASCE benchmark structure.Journal of Sound and Vibration,2006,291(1):349~368.

DOI: 10.1016/j.jsv.2005.06.016

[4] Gao Ma, etc. On line structural damage diagnosis based on time series. Wuhan University Journal,2008,41(1):82~84. (In Chinese)

[5] E.P. Carden, J.M. Brownjohn. ARMA model time-series classification for Structural Health Monitoring of civil infrastructure, Mechanical Systems and Signal Processing,2008,22 (2):295~314.

DOI: 10.1016/j.ymssp.2007.07.003

[6] Linghong Wu, etc. Structural damage detection based on time series analysis. Colliery Mechanical& Electrical Technology, 2009,(4):71~75. (In Chinese)

[7] G.E. Box, G.M. Jenkins, G.C. Reinsel. Time Series Analysis: Forecasting and Control, Prentice-Hall, Englewood Cliffs, NJ, USA, 1994.

[8] Shaofei Jiang. Structural optimization and damage detection based on neural network. Beijing: Science Press, 2002. (In Chinese)

[9] Yansong Diao. Study on the damage detection of offshore platform based on neural network and wavelet analysis. Qingdao: Chinese Ocean University,2006. (In Chinese)