Predicts Based on Multi Modality Support Vector of the Settlement of Composite Foundation

Abstract:

Composite foundation settlement is affected by many factors, and settlement data is a non-linear changing process with complexity, suddenness and progressive nature and so on. So we must analyze and predict the stability of the foundation settlement. Because empirical mode decomposition (EMD) provides a new way for foundation settlement prediction, we can extract modal signals associated with the foundation settlement mechanisms by decomposing the monitoring data of settlement by EMD and use the support vector machine ( Support Vector Machine, SVM) modal to predict the obtained signal, Calculation results of the modal synthesis and accumulation of foundation settlement, get the evolution of Change with the time of foundation settlement. Combined with the engineering example for the application ,shows that the prediction model has good effect in multi modality support vector, a high degree of agreement with the monitoring values, indicating that this method has a promotional value.

• Periodical: Advanced Materials Research (Volumes 919-921)
• Pages: 716-722
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.919-921.716
• Online since: April 2014
• Authors: Li Hua Zhang, Hai Bo Liu, Feng Ping An
• Keywords: Empirical Mode Decomposition (EMD), Foundation Settlement, Modal, Predict, SVM

References

[1] LEI Xuewen, Bai Shiwei, Meng Qingshan. The application of grey forecasting to analysing soft foundation settlements [J]. Rock and Soil Mechanics, 2000, 21(2): 145－147.

[2] JING Hongjun, Yu Maohong. Model study for prediction of settlement of loess-fill high embankments [J]. China Civil Engineering Jourmal, 2006, 39(8): 113-116.

[3] YU C, Za J M, Liu S Y, etal. Research on the additional stress and deformation in the soil of composite pile foundation under vertically uniform loads[J]. Advances in Deep Foundations(GSP132), 2005, (157): 23-33.

DOI: 10.1061/40778(157)23

[4] CHEN Shanxiong, XU Xichang, ZHAO Wenguang. Experimental study on bearing characteristics of dry jet mixing pile omposite ground under flexible load[J]. Rock and Soil Mechanics, 2007, 28(2): 274-278.

[5] YAN Shenghua, YE Jianhua, CHEN Sisheng. Application of wavelet Neural networks to forecast deformation monitoring [J]. Hydrograph surveying and charting, 2009. 5 29(3): 71-73.

[6] Zhu Z, Sun Y, Li H. Hybrid of EMD and SVMs for short-term load forecasting[A]. In: IEEE International Conference on Control and Automation, 2007[C]. Pittsburgh: IEEE, 2007: 1044-1047.

DOI: 10.1109/icca.2007.4376516

[7] Wang Y, Liu X. Prediction of silicon content in hot metal based on the combined model of EMD and SVM[A]. In: Proceedings of the Second International Symposium on Intelligent Information Technology Application, vol 1[C]. Pittsburgh: IEEE, 2008: 561-565.

DOI: 10.1109/iita.2008.112