Prediction Method of Vertical Ultimate Bearing Capacity of Single Pile Based on Support Vector Machine

Yong Jian Liu; Shi Hua Liang; Jia Wu Wu; Na Fu

doi:10.4028/www.scientific.net/AMR.168-170.2278

Paper Titles

Effects of TiO₂ on Crystal Phases of Mold Fluxes
p.2254

Nonlinear Coupling Analysis on Working Behaviour of Pile Group
p.2259

Finite Element Model Updating of a PSC Box Girder Bridge Using Ambient Vibration Test
p.2263

Study of Constructive Materials and Structure inside Long Highway Tunnel Based on Environment Factors
p.2271

Prediction Method of Vertical Ultimate Bearing Capacity of Single Pile Based on Support Vector Machine
p.2278

Establishment of the Principle of Total Potential Energy with Least Value in Elastic System Dynamics
p.2283

The Connection of Welded Seam Three Dimensional Appearance with Performance for Joints of Stainless Steel Plate Laser Welding
p.2293

New Denatonium Benzoate/tin Heterogeneous Catalyst to Obtain Biodiesel via Low Temperature Transesterification Process(LTTP)
p.2299

Behavior of Channel Shear Connectors in Normal and Light Weight Aggregate Concrete (Experimental and Analytical Study)
p.2303

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 168-170Prediction Method of Vertical Ultimate Bearing...

Prediction Method of Vertical Ultimate Bearing Capacity of Single Pile Based on Support Vector Machine

Abstract:

By comprehensively analyzing the main factors affecting vertical ultimate bearing capacity of single pile, a prediction model of Support Vector Machine (SVM), which discusses the nonlinear relationship between vertical ultimate bearing capacity of single pile and influencing factors and analyzes the parameters on the performance of the model through sample knowledge learning, is established in this paper. The research results indicate that, SVM model, which is compared with BP neural networks model, possesses simple structure, flexible adaptability, high precision and powerful generalization ability, and can accurately reflect the actual mechanical characteristics of pile, therefore, SVM is an effective method for predicting vertical ultimate bearing capacity of single pile.

You might also be interested in these eBooks

Advances in Building Materials, ICSBM 2011

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 168-170)

Pages:

2278-2282

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.168-170.2278

Citation:

Cite this paper

Online since:

December 2010

Authors:

Yong Jian Liu, Shi Hua Liang, Jia Wu Wu, Na Fu

Keywords:

Artificial Neural Network (ANN), Single Pile, Support Vector Machine (SVM), Vertical Ultimate Bearing Capacity

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Burge C J C. A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery , Vo2 : 121-167(1998).

Google Scholar

[2] John C Platt . Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines. Technical Report MSR-TR-98-14(1998).

DOI: 10.7551/mitpress/1130.003.0016

Google Scholar

[3] Vapnik V N. The nature of statistical learning theory. New York: Springer(2000).

Google Scholar

[4] L. Yongjian, Prediction mothed of ultimate bearing capacity of single pile based on chaos optomal method and neural networks, Industrial Construction, Vo35(3): 38-41(2005) (in Chinese).

Google Scholar

[5] L. Yongjian, Study of prediction method of vertical ultimate bearing capacity based on genetic algorithm and neural network, Rock and Soil Mechanics, Vo25(1): 59-63(2008), (in Chinese).

Google Scholar