东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2004, Vol. 25 ›› Issue (8): 793-795.DOI: -

• 论著 • 上一篇    下一篇

由工程实例获取隧洞围岩最大变形的支持向量机方法

姜谙男;冯夏庭   

  1. 东北大学资源与土木工程学院;东北大学资源与土木工程学院 辽宁沈阳　110004
  • 收稿日期:2013-06-24 修回日期:2013-06-24 出版日期:2004-08-15 发布日期:2013-06-24
  • 通讯作者: Jiang, A.-N.
  • 作者简介:-
  • 基金资助:
    国家重点基础研究发展规划项目(2002CB412708)

Case-based SVM method for maximal deformation forecasting of surrounding rocks of tunnels

Jiang, An-Nan (1); Feng, Xia-Ting (1)   

  1. (1) Sch. of Resources and Civil Eng., Northeastern Univ., Shenyang 110004, China
  • Received:2013-06-24 Revised:2013-06-24 Online:2004-08-15 Published:2013-06-24
  • Contact: Jiang, A.-N.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

462

摘要： 在收集隧洞工程实例的基础上,将最小平方支持向量机用于提取地下隧洞工程实例的尺寸规模、埋深和围岩质量诸因素与围岩最大允许变形之间映射规律,建立了围岩最大允许变形预测的支持向量机模型·并结合样本的情况确定了支持向量机的模型参数:核函数参数和惩罚因子·通过对样本的学习和预测的结果表明,最大误差为14 4%,能满足工程要求·

关键词: 围岩, 最大变形, 函数拟合, 统计学习理论, 支持向量机, 核函数

Abstract: Based on the collection of samples of tunneling projects, the mapping relation of the project factors including dimension, submergence and surrounding rock quality to the maximal deformation of surrounding rock is regressed using the least squares support vector machines and a forecast model of maximal deformation of surrounding rocks is built. The kernel function parameters and penalty factors are optimized according to the learning samples. Compared with testing samples, the forecast has a maximal relative error of 14.4%, which indicates that the method is effective.

中图分类号: