Forecasting of slope displacement based on PSO-LSSVM with mixed kernel

ZHENG Zhi-cheng; XU Wei-ya; XU Fei; LIU Zao-bao

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Forecasting of slope displacement based on PSO-LSSVM with mixed kernel

更新时间：2026-06-25

- Forecasting of slope displacement based on PSO-LSSVM with mixed kernel
- Vol. 33, Issue 5, (2012)
- 作者机构：
  
  1. 河海大学岩土力学与堤坝工程教育部重点实验室,南京,210098
  2. 河海大学岩土工程科学研究所,南京,210098
  3. 海南省公路勘察设计院,海口,570206
- 作者简介：
- 基金信息：
- DOI：
  CLC： TU454
- Online First：14 May 2012，
  
  Published：2012
- 稿件说明：
移动端阅览
ZHENG Zhi-cheng, XU Wei-ya, XU Fei, et al. Forecasting of slope displacement based on PSO-LSSVM with mixed kernel[J]. 2012, 33(5).
DOI：

ZHENG Zhi-cheng, XU Wei-ya, XU Fei, et al. Forecasting of slope displacement based on PSO-LSSVM with mixed kernel[J]. 2012, 33(5). DOI：

摘要

支持向量机（SVM）的核函数类型和超参数对边坡位移时序预测的精度有重要影响。鉴于局部核函数学习能力强、泛化性能弱，而全局核函数泛化性能强、学习能力弱的矛盾，通过综合两类核函数各自优点构造了基于全局多项式核和高斯核的混合核函数，并引入粒子群算法（PSO）对最小二乘支持向量机（LSSVM）超参数进行全局寻优，提出了边坡位移时序预测的混合核函数PSO-LSSVM模型。将模型应用于锦屏一级水电站左岸岩石高边坡变形预测分析，并与传统核函数支持向量机预测结果进行对比分析。结果表明，该模型较传统方法在预测精度上有了明显提高，预测结果科学可靠，在边坡位移时序预测中具有良好的实际应用价值。

Abstract

The kernel and the parameters of support vector machine (SVM) have a significant impact on precision of the time series prediction to slope displacement. In view of better learning capability of local kernels and better generalization capability of global kernels

the mixed kernel is constructed by a typical local kernel-radial basis function (RBF) and a typical global kernel-polynomial kernel. By use of particle swarm optimization (PSO)

a new PSO-LSSVM model regression with mixed kernels is set up in this paper and applied to the left bank slope in Jinping Ⅰ Hydropower Station. Through comparing with the forecasting results of the existing SVM based on RBF

results demonstrate that the new model has great accuracy than the existing SVM with RBF only and has real application value in predicting deformations of slope.

关键词

Keywords

references

Views

2524

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study of applications of meeting ant colony algorithm to search non-circular critical slip surface of slope

A new search algorithm for strength anisotropy slope stability analysis based on numerical stress field

Gaussian process-based dynamic response surface method for estimating slope failure probability

Study of deformation characteristics of slope rockmass at project of water diversion from Hanjiang River to Weihe River

Reliability analysis of unsaturated slope considering spatial variability

Related Author

GAO Wei

ZHANG Fei-jun

CHEN Li-ping

ZHANG Ding-li

FANG Qian

YING Guo-gang

Huang Jun

SU Guo-shao

Related Institution

College of Civil and Transportation Engineering, Hohai University

Wuhan Construction Engineering (Group) Co., Ltd.

Key Laboratory for Urban Underground Engineering of Education Ministry, Beijing Jiaotong University

Jiangsu Transportation Research Institute Co., Ltd.

Key Laboratory of Disaster Prevention and Structural Safety of Ministry of Education, School of Civil and Architecture Engineering, Guangxi University

AI问答

⁰