A Constitutive Model of Grassroots-reinforced Soil Based on BP Neural Network

CHEN Chang-fu; PENG Zhao; LIU Huai-xing

您当前的位置：

首页 >

文章列表页 >

A Constitutive Model of Grassroots-reinforced Soil Based on BP Neural Network

- A Constitutive Model of Grassroots-reinforced Soil Based on BP Neural Network
- Bulletin of Soiland Water Conservation Vol. 27, Issue 3, Pages: 93-96(2008)
- 作者机构：
  
  湖南大学岩土工程研究所,湖南,长沙,410082
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2008
- 稿件说明：
移动端阅览
CHEN Chang-fu, PENG Zhao, LIU Huai-xing. A Constitutive Model of Grassroots-reinforced Soil Based on BP Neural Network[J]. Bulletin of Soiland Water Conservation, 2008, 27(3): 93-96.
DOI：

CHEN Chang-fu, PENG Zhao, LIU Huai-xing. A Constitutive Model of Grassroots-reinforced Soil Based on BP Neural Network[J]. Bulletin of Soiland Water Conservation, 2008, 27(3): 93-96. DOI：

摘要

用室内三轴试验方法得到了草根加筋土的应力—应变关系

并基于试验结果建立了素土和混和草根加筋土的BP神经网络本构模型。模型计算结果与试验结果对比分析表明

该神经网络本构模型具有很高的拟和精度和良好的泛化能力

能充分体现岩土材料的非线性关系。利用莫尔—库仑准则拟合得到的加筋土的强度指标分析了草根加筋土的护坡机理。研究结果对于合理建立草根土的本构关系和深入认识植被护坡机理具有指导意义。

Abstract

Laboratory triaxial tests were carried out to obtain the stress-strain relationship of grassroots-reinforced soil(GRS).BP neural network constitutive models of soil and GRS reinforcement in mixing were established based on test data.The result from comparing predicted values and measured values shows that the network constitutive model has good fitting precision and good generalization ability and can fully describe the non-linear relationship of geo-materials. The shear strength indexes of GRS fitted by Mohr-Columb criterion may be used to analyze the mechanism of GRS protection of slope.The research results are of importance for establishing the constitutive model of GRS and understanding the mechanism of vegetation protection of slope.

关键词

Keywords

references

Views

1576

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Intelligent Evaluation of Loess Collapsibility

Application of BP Neural Network to the Analyses of Runoff and Sediment Yield with Different Types of Vegetation

Experimental Study of the Cheep Behavior of Unsaturated Intact Loess

Application of Multi-classification Support Vector Machine in Regionalization of Debris Flow Hazards

Prediction of Forest Ecosystem Health Based on BP Neural Network

Related Author

LI Yingliang

SONG Xueqing

CUI Zhongxing

WU Yanqing

JING Yanlin

SHEN Bing

SONG Xiao-yu

ZHOU Jian-guo

Related Institution

Electronic Comprehensive Investigation and Surveying Institute of Ministry of Information Industry

Xi’an Design and Research Institute of Coal Industry

Xi’an University of Technology

College of Hydraulic Engineering,Changsha University of Science and Technology,,Hu’nan

⁰