Study on Deformation Prediction of Landslide Based on Grey Theory and BP Neural Network

Abstract:

The stability of the landslide can be effectively evaluated and predicted by predicting the future development of landslide deformation according to the actual deformation of the landslide. Therefore, the accuracy of the prediction regarding the landslide deformation determines the validity of the landslide stability assessment. The GM (1.1) model in the grey system theory, uses displacement time series to establish the grey differential equation. By solving the equation, we can obtain a time response function, which can then be used to predict the landslide deformation. The BP neural network is a used for training and exercising on the deformed samples. After the error meets the requirement, we can then use the trained model to predict the landslide deformation. This paper use both grey system theory model and BP neural network model to predict Jinlong ditch application field landslide deformation.The prediction results are compared and analyzed to test the accuracy of these two predictions. Finding a more accurate prediction method for application in actual engineering project has practical significance.

• Periodical: Applied Mechanics and Materials (Volumes 204-208)
• Pages: 520-525
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.204-208.520
• Online since: October 2012
• Authors: Rong Yu Li, Yong Fen Ruan, Shi Sheng Li, Yong Hong Wu
• Keywords: BP Neural Network (BPNN), Deformation, Grey System Theory, Landslide, Prediction

References

[1] Julong Deng. Grey prediction and decision [M]. Wuhan: Huazhong University of Science and Technology Press, 2008 (in Chinese)

[2] Tianbin Li, Lansheng Wang. Stability of high slopes and its control in rock engineering[M].Beijing：Science Press, 2008 (in Chinese)

[3] Zhiquan Huang.The nonlinear theories of slope analysis and application [M].Henan: Yellow River Water Conservancy Press, (2005)

[4] Helin Fu, Sitian Peng, Rucai Han, Xianfeng He. Geotechnical engineering new methods of numerical analysis [M]. Hunan: Central South University Press, (2006)

[5] Feng Xu, Yang Wang, Juan Du, Jiang Ye. Study of displacement prediction model of slope based on time series analysis [J]. Chinese Journal of Rock Mechanics and Engineering, 2011, Vol. 30, No. 4:746-751

[6] Hanbo Wei, Qian Gao. Application of grey theory in slope rock mass deformation forecasting [J]. Transactions of Nonferrous Metals Society of China (mine part), 2008, Vol. 60. No. 2:31-33

[7] Yongyuan Jiang. Application of gray theory in the prediction of a rock slope stability analysis [J]. Soil Engineering and Foundation, 2003, Vol. 17. No.3:54-57

[8] Jianhui Deng, Zhuofen Li, Xiurun Ge. Application of BP network and genetic algorithm to displacement back analysis of rock slope [J]. Chinese Journal of Rock Mechanics and Engineering, 2001, Vol. 20, No. 1:1-5

[9] Xiao Liu, Xianghu Zeng, Chunyu Liu. Research on artificial neural network-time series analysis of slope nonlinear displacement [J]. Chinese Journal of Rock Mechanics and Engineering, 2005, Vol. 24.No. 19:3499-3504