基于最小二乘支持向量机算法的小地锚抗拔承载力研究（英文）被引量：1

Pullout capacity of small ground anchor: a least square support vector machine approach

导出

摘要目的:基于最小二乘支持向量机算法预测小地锚的抗拔承载力。方法:最小二乘支持向量机算法中的输入参数包括等效地锚直径,地锚埋置深度,平均顶椎阻力,平均椎套摩擦力以及安装工艺。使用现场试验的119组数据中的83组数据进行最小二乘支持向量机回归模型分析,并使用剩余的36组数据测试模型的拟合良好性;同时用敏感度分析研究每个输入参数的作用。结论:通过与人工神经网络模型的对比,发现最小二乘支持向量机的性能表现优异。 This study employs the least square support vector machine（LSSVM） for the prediction of pullout capacity of small ground anchor. LSSVM is firmly based on the theory of statistical learning and uses regression technique. In LSSVM, Vapnik and Lerner（1963）＇s ε-insensitive loss function was replaced by a cost function which corresponded to a form of ridge regression. The input parameters of LSSVM were equivalent anchor diameter, anchor embedment depth, average cone tip resistance, average cone sleeve friction, and installation technique. Using 83 out the available 119 in-situ test datasets, an LSSVM regression model was developed. The goodness of the model was tested using the remaining 36 data points. The developed LSSVM also gave an error bar of predicted data. A sensitivity analysis was conducted to determine the effect of each input parameter. The results were compared with the artificial neural network（ANN） model. Overall, LSSVM was shown to perform well.

作者 Pijush SAMUI Dookie KIM Bhairevi G.AIYER

机构地区 Centre for Disaster Mitigation and Management Department of Civil Engineering School of Mechanical and Building Science

出处《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》 SCIE EI CAS CSCD 2015年第4期295-301,共7页 浙江大学学报（英文版）A辑（应用物理与工程）

关键词人工神经网络法最小二乘支持向量机误差条地锚抗拔承载力现场试验敏感度分析 Artificial neural network（ANN） Least square support vector machine（LSSVM） Error bar Ground anchor Pullout capacity In-situ test

分类号 TU476 [建筑科学—结构工程]

引文网络
相关文献

参考文献31

1Basudhar, P.K., Singh, D.N., 1994. A generalized procedure for predicting optimal lower bound break-out factors of strip anchors. Geotechnique, 44(2):307-318. [doi:10. ! 680/geot.1994.44.2.307].
2Das, B.M., 1978. Model tests for uplift capacity of foundations m clay. 5Oils and Foundatio , 18(2):17-24. [doi:10. 3208/sandf1972.18.2_17].
3Das, B.M., 1980. A procedure for estimation of ultimate uplift capacity .of foundations in clay. Soils and Foundations, 20(1):77-82. [doi: 10.3208/sandf1972.20.77].
4Das, RM., 1987. Developments in Geotechnical Engineering, Theoretical Foundation Engineering. Elsevier. Das, B.M., Seeley, G.R., 1975. Breakout resistance of hori- zontal anchors. Journal of Geotechnologv Engineering Division, ASCE, 101(9):999-1003.
5Deng, S., Yeh, T.H., 2010. Applying least squares support vector machines to the airframe wing-box structural de- sign cost estimation. Expert Systems with Applications, 37(12):8417-8423. [doi: 10.1016/j.eswa.2010.05.038].
6Dickin, E.A., 1988. Uplift behaviour of horizontal anchor plates in sand. Journal of Geotechnology Engineering, ASCE, 114(11):1300-1317. [doi:10.1061/(ASCE)0733- 9410(1988)114:11 (1300)].
7Erzin, Y., Cetin, T., 2013. The prediction of the critical factor of safety of homogeneous finite slopes using neural networks and multiple regressions. Computer Geoscience, 51:305-313. [doi: 10.1016/j.cageo.2012.09.003].
8Huang, Z., Luo, J., Li, X., et aL, 2009. Prediction of effluent parameters of wastewater treatment plant based on im- proved least square support vector machine with PSO. 1st International Conference on Information Science and Engineering (ICISE), Nanjing, No. 5454606, p.4058-4061.
9Kecman, V., 2001. Leaming and Soft Computing Support Vector Machines, Neural Networks, and Fuzzy Logic Models. The MIT Press, Cambridge. Koutsabeloulis, N.C., Griffiths, D.V., 1989. Numerical mod- eling of the trap door problem. Geotechnique, 39(1): 77-89. [doi: 10.1680/geot. 1989.39.1.77].
10Kurup, P.U., Dudani, N.K., 2002. Neural networks for profiling stress history of clays from PCPT data. Journal of Geotechnical and Geoenvironmental Engineering, 128(7):569-579. [doi: 10.1061/(ASCE) 1090-0241 (2002) 128:7(569)].