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

Authors:
Publisher website
Google Scholar
Abstract
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 ɛ-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. 基于最小二乘支持向量机算法预测小地锚的抗拔承载力。 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。 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 publication has 25 references indexed in Scilit: