Displacement back analysis of deep foundation pit for metro based on genetic algorithm and neural network

PENG Jun-long; ZHANG Xue-min; YANG Jun-sheng; ZHANG Qi-sen1

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Displacement back analysis of deep foundation pit for metro based on genetic algorithm and neural network

更新时间：2026-06-25

- Displacement back analysis of deep foundation pit for metro based on genetic algorithm and neural network
- Vol. 28, Issue 10, (2007)
- 作者机构：
  
  1. 长沙理工大学公路学院,长沙,410076
  2. 中南大学土木建筑学院,长沙,410075
- 作者简介：
- 基金信息：
- DOI：
  CLC： TB115
- Online First：15 October 2013，
  
  Published：2007
- 稿件说明：
移动端阅览
PENG Jun-long, ZHANG Xue-min, YANG Jun-sheng, et al. Displacement back analysis of deep foundation pit for metro based on genetic algorithm and neural network[J]. 2007, 28(10).
DOI：

PENG Jun-long, ZHANG Xue-min, YANG Jun-sheng, et al. Displacement back analysis of deep foundation pit for metro based on genetic algorithm and neural network[J]. 2007, 28(10). DOI：

摘要

针对目前已有的各种位移反分析方法存在的缺陷，利用神经网络具有的非线性映射能力和遗传算法具有的全局随机搜索能力，提出了一种基于遗传神经网络进行深基坑支护的位移反分析方法。该方法改变了BP算法依赖梯度信息的指导来调整网络权值的方法，而是利用遗传算法全局性搜索的特点，寻找最合适的网络连接权和网络结构等来达到优化的目的。结合地铁深基坑支护位移计算，应用该方法对某一地铁深基坑土体的力学参数进行了反演。结果表明：将位移观测值作为网络输入数据，土体力学参数作为输出数据，在较大的解空间内，该位移反分析方法收敛速度快、解的稳定性好、反演结果精度高，是一种理想的位移反分析方法。最后，采用该软件结合一个工程实例实现了应用遗传神经网络进行的基坑支护位移反分析。

Abstract

Aiming at subsistent limitation in diversified displacement back analysis methods

an approach based on neural network and genetic algorithm for displacements back analysis of deep foundation pit for metro is proposed. This approach utilizes nonlinearity of neural network and whole random search capability of genetic algorithm. It can search the best appropriate weight and framework of neural network by using whole searching characteristic of genetic algorithm

which formerly depends on gradient information to adjust weight of network. The proposed approach has been used to carry out inverse calculation for soil mechanical parameters of deep foundation pit for metro. A case is conducted using the software developed in the paper. The result shows: considering measured deformation value as input data and taking soil dynam parameter as output data of neural network

the approach can rapidly get a stable and accurate solution within a relatively large solution space; and the approach is superior to current back analysis approaches.

关键词

Keywords

references

Views

1542

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on constitutive model and its parameter’s back analysis of creep deformation for the high rockfill embankment and their application

Prediction of soft soil foundations settlements based on genetic algorithm

A methodology combining genetic algorithm and finite element method for back analysis of initial stress field of rock masses

Study on GA-NN model for forecasting the displacement of landslides affected by rainfall

An evolutionary neural network model for suction prediction of unsaturated soils

Related Author

CAO Wen-gui

LI Peng

CHENG Ye

XIA Jiang

YAN Ping

ZHUANG Yi-zhou

XU Xiang-ming

YI Da

Related Institution

Geotechnical Engineering Institute, Hunan University

Hunan Bureau of Expressway Administration

Department of Civil Engineering, Zhejiang University

College of Civil Engineering, Tongji University

Zhejiang Education Development Center

AI问答

⁰