• 中国科学引文数据库(CSCD)来源期刊
  • 中文核心期刊中文科技核心期刊
  • Scopus RCCSE中国核心学术期刊
  • 美国EBSCO数据库 俄罗斯《文摘杂志》
  • 《日本科学技术振兴机构数据库(中国)》
二维码

隧道建设(中英文) ›› 2014, Vol. 34 ›› Issue (1): 13-18.DOI: 10.3973/j.issn.1672-741X.2014.01.003

• 研究与探索 • 上一篇    下一篇

基于蚁群优化支持向量机的公路隧道围岩变形预测模型及应用

邱志刚   

  1. (新疆维吾尔自治区交通规划勘察设计研究院, 新疆乌鲁木齐 830006)
  • 收稿日期:2013-09-25 修回日期:2013-11-10 出版日期:2014-01-20 发布日期:2014-01-21
  • 作者简介:邱志刚(1982—),男,湖北麻城人,2004年毕业于新疆大学,测绘工程专业,本科,工程师,主要从事公路工程测绘工作。

Highway Tunnel Surrounding Rock Deformation Prediction Model Based on Support Vector Machine Optimized by Ant Colony Optimization and Its Application

QIU Zhigang   

  1. (Transportation Planning, Survey and Design Institute of Xinjiang Uygur Autonomous Region, Urumqi 830006, Xinjiang, China)
  • Received:2013-09-25 Revised:2013-11-10 Online:2014-01-20 Published:2014-01-21

摘要:

为及时掌握隧道施工中围岩变形趋势以便采取措施加以控制,采用基于结构风险最小化的支持向量机(SVM)进行预测。介绍支持向量机的基本原理,研究蚁群算法(ACO)实现支持向量机参数优化的方法,构建ACOSVM模型。对某公路隧道随机选取的2个监测断面的预测结果表明,该模型预测精度较高,泛化性能较好,用蚁群算法进行SVM参数优选是一种简单、优选的方法,可以有效指导隧道的施工。

关键词: 隧道工程, 围岩, 变形预测, 支持向量机, 蚁群算法, 参数优化

Abstract:

Support vector machine (SVM) based on structural risk minimization is used to predict the deformation of tunnel surrounding rocks, so as to understand the deformation trend of the surrounding rocks and to take measures to control the deformation. In the paper, the principle of support vector machine is described, the parameter optimization method based on ant colony optimization (ACO) is studied, and the ACOSVM model is established. The deformation prediction model has been applied in the construction of a highway tunnel, which shows that the model has high precision and can provide effective guidance for the tunnel construction. The paper can provide reference for similar projects in the future.

Key words: tunnel, surrounding rock, deformation, prediction, support vector machine, ant colony optimization, parameter optimization