SVM Model Based on the Influencing Factors Evaluation and Prediction of Ultimate Bearing Capacity of Statically-Pressured Pipe Pile

Abstract:

The prediction accuracy of vertical ultimate bearing capacity of statically-pressured pipe pile is difficult to ensure with traditional methods, because it is influenced by comprehensive factors, such as pile body, soil around pile and construction conditions. In this paper, a support vector machine (SVM) model based on the influencing factors importance evaluation was established to predict the vertical ultimate bearing capacity of single pile. This method would consider grey relational analysis and variable projection importance analysis as the attribute preprocessor facilities, which could determine the vertical bearing character in typical geological conditions through the analysis results of these two methods. Then, the SVM model was established with the main factors influencing ultimate bearing capacity as input to predict ultimate bearing capacity of single pile. The results showed that this method would have better precision of prediction, and the established model would have better generalization ability, which would open up a new way for the theoretical analysis of bearing characters of statically-pressured pipe pile and provide references for future relevant research.

• Periodical: Advanced Materials Research (Volumes 243-249)
• Pages: 2534-2542
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.243-249.2534
• Online since: May 2011
• Authors: Jian Bin Zhao, Chao Xu, Yong Qiang Shi, Xiao Yan Feng
• Keywords: Grey Relational Analysis (GRA), Prediction of Vertical Bearing Capacity of Single Pile, Statically-Pressured Pipe Pile, Support Vector Machine (SVM), Variable Projection Importance Analysis

References

[1] Jianbin Zhao, Yong Chen, and Jianqiu Ma, et al. Journal of Shenyang Jianzhu University (Natural Science), Vol. 22(6) (2006), pp.903-906 (in Chinese)

[2] Nengjun Wang, Yongjun Lei, Rongyue Zheng. Journal of Heilongjiang Institute of Science and Technology, Vol. 16 (2) (2006), pp.124-126. (in Chinese)

[3] Li-an Han: Calculation of the level-loading pile (Central South University Press, China 2004) (in Chinese)

[4] China Academy of Building Research: Technical Code for Building Pile Foundations JGJ 94-94 (China Architecture & Building Press, China 1994) (in Chinese)

[5] Fion Chow. Ground engineering, Vol. 7/8 (1995)

[6] D. J. White, M. D. Bolton. Geotechnique, Vol. 54(6) (2004), pp.375-397

[7] Jian Cai，Wanqing Zhou. Journal of Civil Engineering, Vol. 10 (10) (2006), pp.102-107 (in Chinese)

[8] Suhua Li, Jian Zhou, and WeihuangYang, et al. Chinese Journal of Rock Mechanics and Engineering, Vol. 22(9) (2003), pp.1571-1577 (in Chinese)

[9] Chenghua Wang, Wei Zhang. Rock and Soil Mechanics, 2002 (2):173-178 (in Chinese)

[10] Jiawei Han, Micheline Kamber: Data Mining: Concepts and Techniques (China Machine Press, China 2007) (in Chinese)

[11] Yuliang Lin. Uncertainty of Geotechnical and Structural Engineering and Analysis Methods (The Science Press, China 2009) (in Chinese)

[12] Lee I M, Lee J H. Computers and Geotechnics, Vol. 18(3) (1996), pp.189-199

[13] Ziliang Feng, Haitao Sun, and Shujuan Wang. Journal of Tongji University, Vol. 27(4) (1999), pp.397-401 (in Chinese)

[14] Yunkai Liu, Chunsheng Qiao, Shengfeng Tian, et al. Chineas Journal of Rock Mechanics and Engineering, Vol. 24 (2) (2005), pp.328-335 (in Chinese)

[15] Yanbing Gong, Senfa Chen. Industrial Construction, Vol. 36 (2) (2006), pp.50-53 (in Chinese)

[16] Minggui Liu, Junwei Peng. Industrial Construction, Vol. 37 (2) (2007), pp.60-54 (in Chinese)

[17] Sifeng Liu, Naiming Xie: the Grey System Theory and its Application (The Science Press, China 2008) (in Chinese)

[18] Huiwen Wang: Partial Least Squares Regression and its Application (National Defence Industry Press, China 1999) (in Chinese)

[19] Xingyuan Liu, Jingwen Kang, and Wenxiu Lin: Pile Foundation Work Characteristic Analysis of Neural Network Model (China Architecture & Building Press, China 1999) (in Chinese)

[20] Xun Zhu, Qiguo Rong. System Simulation, Vol. 21 (4) (2009), pp.1148-1154(in Chinese)

[21] Hello Cristianini, John Shawe-Taylor: An Introduction to Support Vector Machines and Other Kernel-based Learning Methods (Publishing House of Electronics Industry, China 2004)

DOI: 10.1017/cbo9780511801389