土工基础

土工基础 ›› 2022, Vol. 36 ›› Issue (1): 57-60.

• 专题论述 • 上一篇    下一篇

横向受荷桩承载力预测的支持向量机模型

唐灵明1,2,3，宋 宇1,3，陈学军1,3，黄 翔1,3，蒋振华4   

  1. (1.桂林理工大学土木与建筑工程学院，广西桂林 541004；2.广西师范大学，广西桂林 541004；3.广西岩土力学与工程重点实验室，广西桂林 541004；4.中国电子科技集团公司第三十四研究所，广西桂林 541004)
  • 收稿日期:2020-09-24 修回日期:2020-10-26 出版日期:2022-02-28 发布日期:2022-03-09
  • 作者简介:唐灵明（1987-），男，硕士，工程师，研究方向为岩土工程、地质灾害预测与防治。
  • 基金资助:
    国家自然科学基金项目（41967037）；国家自然科学基金项目（41762022）

Prediction of Bearing Capacity of Laterally Loaded Piles Based on Support Vector Machine

TANG Lingming1,2，3, SONG Yu1,3, CHEN Xuejun1,3, HUANG Xiang1,3, JIANG Zhenhua4   

  1. (1.College of Civil and Architectural Engineering, Guilin University of Technology, Guilin 541004;
    2.Open Research Fund of Guangxi Karst Dynamics Laboratory, Guilin 541004;
    3.Guangxi Key Laboratory of Geomechanics and Geotechnical Engineering, Guilin 541004;
    4.The 34th Research Institute of China CETC, Guilin 541004)
  • Received:2020-09-24 Revised:2020-10-26 Online:2022-02-28 Published:2022-03-09

摘要： 桩基作为土建工程的基础，水平向承载力是横向受荷桩承载力验算重要参数之一，为建立其与相关影响因素之间的非线性映射关系，建立了一种支持向量机（SVM）横向受荷桩承载力预测模型。该模型通过对少量样本的学习，就可以对仅知道影响因素的预测样本进行精准预测。通过支持向量机模型与BP神经网络模型的预测结果对比，验证该模型的精确度；同时采用平均相对误差和均方差两个指标评价各个模型的整体性能和稳定情况；通过置信区间验证了该模型预测结果的可靠性高，预测值全部处于置信区间90%、95%、97%之间。SVM的最大相对误差为5.41%，平均相对误差为2.81%，均方根误差为2.027 8，相对于BP神经网络的预测结果，SVM结果更为精确。因此，SVM模型在横向受荷桩承载力预测方面具有可行性，为它的获取提供一种新方法。

关键词: 支持向量机, 横向受荷, 桩承载力, 预测模型

Abstract: The lateral load capacity of a single pile is an important parameter in the civil engineering design practice. To establish the nonlinear relationships among potential influencing factors, a Support Vector Machine (SVM) model for predicting the capacity of laterally loaded piles was established. By learning from a small number of samples, this model can accurately predict the prediction samples that only know the potential influencing factors. The accuracy of the model was verified by comparing the prediction results of the SVM model and BP neural network model. Both the mean relative error and the root mean square error are used to evaluate the overall performance and stability of each model. The high reliability of the predicted results was verified by the confidence interval, and all the predicted values are within the confidence interval of 90%, 95% and 97%. The Maximum Relative Error (MXAE) of SVM is 5.41%, the MRE is 2.81%, and the RMSE is 2.0278. Compared with the prediction results of BP neural network, the SVM results are more accurate. The SVM model is therefore feasible in predicting the bearing capacity of laterally loaded piles and provides a new method for its acquisition.

Key words: support vector machines, laterally loaded, pile bearing capacity, prediction model

中图分类号: