Slope Deformation Prediction Based on Chaotic-SVM

Abstract:

This paper principally studies the prediction of slope deformation based on Support Vector Machine (SVM). To explore the prediction process, phase space is reconstructed. The geological body’s displacement data obtained from chaotic time series are used as SVM’s training samples. Slope displacement caused by multivariable coupling is predicted by means of single variable. Results show that this model is of high fitting accuracy and generalization, and provides reference for deformation prediction in slope engineering.

• Periodical: Applied Mechanics and Materials (Volumes 353-356)
• Pages: 673-677
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.353-356.673
• Online since: August 2013
• Authors: Lei Jia, Yuan Li, Yong Ping Xie
• Keywords: Chaotic Time Series , Chaotic-SVM, Deformation Prediction, Phase-Space Reconstruction

References

[1] Casdagli M: Physica D, Vol. 35(1989),P. 335-356.

[2] LIU Han, LIU Ding, LI Qi: System Engineering Theory and Practice, Vol. 9(2005): 94- 99, in Chinese.

[3] TAN Xiaolong, XU Weiya, LIANG Guilan: Rock and Soil Mechanics, Vol. 31(2010),P. 1 633-1 650, in Chinese.

[4] Zhao Hongbo, Feng Xiating: Chinese Journal of Rock Mechanics and Engineering, Vol. 24(2003),P. 241-245, in Chinese.

[5] HE Haoxiang, YAN Weiming, PENG Lingyun: Journal of Highway and Transportation Research and Development, Vol. 25 (2008),P. 65- 69+89, in Chinese.