Settlement prediction of tunnel based on multiple kernels learning mode

FAN Si-xia; ZHOU Qi-cai; XIONG Xiao-lei; ZHAO Jiong

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Settlement prediction of tunnel based on multiple kernels learning mode

更新时间：2026-06-25

- Settlement prediction of tunnel based on multiple kernels learning mode
- Vol. 34, Issue S2, (2013)
- 作者机构：
  
  同济大学机械与能源工程学院,上海,201804
- 作者简介：
- 基金信息：
- DOI：
  CLC： TU452
- Online First：19 November 2013，
  
  Published：2013
- 稿件说明：
移动端阅览
FAN Si-xia, ZHOU Qi-cai, XIONG Xiao-lei, et al. Settlement prediction of tunnel based on multiple kernels learning mode[J]. 2013, 34(S2).
DOI：

FAN Si-xia, ZHOU Qi-cai, XIONG Xiao-lei, et al. Settlement prediction of tunnel based on multiple kernels learning mode[J]. 2013, 34(S2). DOI：

摘要

为提高支持向量机的预测精度，提出一种基于自适应多核学习模型的预测方法。自适应多核学习算法中采用树形筛选结构，通过生枝、剪枝操作完成核函数间的相加、相乘处理，增强了多核函数的非线性与多样性。采用网格遍历和粒子群算法对核参数、权重系数及模型参数进行寻优处理，弥补了训练样本缺少先验知识对参数赋值产生的偏差。将多核学习方法用于地铁隧道沉降预测，并与单核函数的预测数值进行对比。试验结果表明，自适应多核学习模型有效提高了预测模型的预测精度及泛化性能。

Abstract

To improve the prediction precise of support vector machine model

an adaptive multiple kernels learning (AMKL) method is proposed. In this method

a tree structure is used to screen the kernels. Additionally

this processing can be implemented with growing and cutting branches manipulation for adding and multiplying the kernels in each layer. This would enhance the nonlinear and diversity characteristics of multi-kernels. Grid traversal and particle swarm optimization method are applied to solve the optimization problem of kernel parameters

weight coefficient and model parameters. It could offset the assignment deviation of parameters which occurs in the lack of a prior knowledge of the training samples. AMKL method is used to predict the settlement of metro tunnel. Comparisons between experimental results of AMKL and the ones of single kernel functions show that AMKL effectively improves the accuracy and generalization.

关键词

Keywords

references

Views

1304

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of peak particle velocity induced by underwater blasting based on the combination of grey relational analysis and genetic neural network

Integrate intelligent method for multi message of tunnel open excavation adjoining bridge pile

Simulation of soil-water characteristic curves during drying and wetting cycles

Swelling characteristics of Gaomiaozi bentonite saturated by salt solution and their prediction

Consolidation coefficient inversion of seawall foundation and prediction of its post construction settlement based on fractal theory

Related Author

LIU Ya-qun

LI Hai-bo

PEI Qi-tao

ZHANG Wei

JIANG An-nan

SHA Quan-xian

SONG Zhan-ping

LI Peng

Related Institution

State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences

Highway and Bridge Engineering Institute, Dalian Maritime University

China Railway 13th Bureau Group 1st Engineering Co. Ltd.

Department of Civil Engineering, Shanghai University

State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology

AI问答

⁰