Abstract
Embankment settlement prediction and control is one of the most critical problems for constructing and maintaining the High-speed railway (HSR). The grey model is one of the popular methods used for predicting embankment settlement, because it is of easy-to-use and low computer load. However, it needs many observations and more suit for short-term prediction. The artificial neural network has been widely used in prediction system in many other fields, and it is of robustness and self-adaptive. In this paper, these two methods are combined to give a new Hybrid prediction model to improve the performance and precision of settlement prediction model. The experiments based on real data sets validate the proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cai, J.J., Wang, X.H.: Prediction on Post-construction Settlement of Bridge Group Pile Foundation base on Grey Theory. Subgrade Engineering 2(2), 142–143 (2010)
Chen, P.Y., Duan, X.S.: Establishment and improvement of non-equal interval GM(1,1) model of building subsidence. Geotechnical Investigation & Surveying (3), 77–80 (2010)
Chen, Z.H.: Final Settlement Method of Subgrade. Soil Engineering and Foundation 25(1), 7–9 (2011)
Chen, Z.L., He, C.N., Tang, L.M.: The application of Grey prediction model for Embankment settlement. Journal of China & Foreign Highway 30(1), 60–64 (2010)
Chi, H.Y., Li, H.X., Zhao, X.H.: Prediction and Analysis of Land Subsidence Based on Improved BP Neural Network Model. Journal of Tianjin University 42(1), 60–64 (2009)
Du, Y.L., Ji, L., Liu, X.F.: Grey prediction model for construction settlement forecast of embankment of high-speed railway and its application. Journal of Railway Science and Engineering 6(1), 36–40 (2009)
Gu, S.F., Liu, S.S., Liu, Y.Y.: Study of application of Asaoka method to settlement prediction. Rock and Soil Mechanics 31(7), 2238–2240 (2010)
Huang, J.F., Lou, X.M., Yang, J.: Comparison of common settlement predicting methods in application of a project case of surcharge preloading method. Geotechnical Investigation & Surveying (3), 18–23 (2011)
Ovidio, J., Santos, J., Tarcisio, B.C.: Artificial neural networks analysis of Sao Paulo subway tunnel settlement data. Tunnelling and Underground Space Technology 23(5), 481–491 (2008)
Pooya, F., Nejad, M.B., Jaksa, M., Kakhi, B.A.M.: Prediction of pile settlement using artificial neural networks based on standard penetration test data. Computer and Geotechnics 36(7), 1125–1133 (2009)
Ma, W.T.: Forecasting slope displacements based on grey least square support vector machines. Rock and Soil Mechanics 31(5), 1670–1674 (2010)
Maier, H.R., Dandy, G.C.: Neural networks for the prediction and forecasting of water resources variables: a review of modeling issues and applications. Environmental Modelling & Software 15(1), 101–124 (2000)
Mohamed, A., Shahin, Holger, R.M., Jaksa, M.B.: Predicting Settlement of Shallow Foundations using Neural Networks. Journal of Geotechnical & Geoenvironmental Engineering 128(9), 785–794 (2002)
Wang, H.H., Wang, N.S., Xu, S.J.: Research on Amendatory Unequal Interval Grey Model. Mathematics in Practice and Theory 41(8), 108–114 (2011)
Wang, X.Z., Zheng, W.H.: Study on Application of Artificial Neural Network to Soft Base Settlement Prediction. Subgrade Engineering 1(3), 128–130 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, T.G., Hu, Z.B., Yang, C.F., Liu, Y. (2012). Hybrid Prediction Model for High-Speed Railway Embankment Settlement Using Grey Artificial Neural Network. In: Ni, YQ., Ye, XW. (eds) Proceedings of the 1st International Workshop on High-Speed and Intercity Railways. Lecture Notes in Electrical Engineering, vol 148. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27963-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-27963-8_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27962-1
Online ISBN: 978-3-642-27963-8
eBook Packages: EngineeringEngineering (R0)