An Improved Correction Method for Bridge Deflection Sensor Base on Support Vector Machine

Abstract:

The initial state of deflection sensor after replacement is not easy to be found. In order to overcome this disadvantage of the existing method,an improved deflection correction method is presented in this paper. The new method converts the problem into anglicizing the deviation of monitoring point. By using correlation analysis and SVM,the theoretical value can be obtained. The deflection deviation could be calculated by analyzing the theoretical value and the measured value. And then the deflection after correction is easy to be obtained. Numbers of experiments are done by using the real data of Caiyuanba Yangtze River Bridge. Results show that the mean square error of the new method is less than the existing method. The new method solves the problem of finding the initial state, and the precision is improved at the same time.

• Periodical: Applied Mechanics and Materials (Volume 344)
• Pages: 99-102
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.344.99
• Online since: July 2013
• Authors: Shun Ren Hu, Wen Chao Xiong, Hong Zhao
• Keywords: Bridge Monitoring, Correction Method, Deflection Deviation, Support Vector Machine (SVM)

References

[1] Andrew Kusiak, Zhe Song, Sensor Fault Detection in Power Plants. Journal of Energy Engineering, 135 (2009) 127-137.

DOI: 10.1061/(asce)0733-9402(2009)135:4(127)

[2] Tao Wei, Yufei Huang, C. L. Philip Chen, Adaptive Sensor Fault Detection and Identification Using Particle Filter Algorithms. IEEE Transactions on Systems, man, and cybernetics, 39 (2009) 201-213.

DOI: 10.1109/tsmcc.2008.2006759

[3] ShunRen Hu, WeiMing Cheng, Research of Deflection Adaptive Correction Method of the Bridge Structural Health Monitoring System. Highway, 10(2011) 62-66.

[4] Xiaowei Huang, Weimin Chen, Peng Zhang, Shunren Hu, Research on deflection sensor validity based on K-neighbor algorithm. Chinese Journal of Scientific Instrument, 33 (2012) 1090-1095.

[5] Yanwei Huang, Dengguo Wu, Zhonghua Liu, Jun Li, Lost Strain Data Reconstruction Based on Least Squares Support Vector Machine. Measurement & Control Technology, 29 (2010) 8-12.

[6] David Vines-Cavanaugh, Yinghong Cao, Ming L. Wang, Support Vector Machine for Abnormality Detection on a Cable-Stayed Bridge. Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems, 7647 (2010) 1-12.

DOI: 10.1117/12.849248