Application of neural network to back analysis of mechanical parameters and initial stress field of rock masses

JIN Chang-yu1; MA Zhen-yue1; ZHANG Yun-liang1; SHA Rui-hua1; CHEN Qing-fa2

doi:10.16285/j.rsm.2006.08.007

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Application of neural network to back analysis of mechanical parameters and initial stress field of rock masses

更新时间：2026-06-25

- Application of neural network to back analysis of mechanical parameters and initial stress field of rock masses
- Issue 8, Pages: 1263-1266(2006)
- 作者机构：
  
  1. 大连理工大学土木水利学院
  2. 武汉理工大学
- 作者简介：
- 基金信息：
- DOI：10.16285/j.rsm.2006.08.007
  CLC： TU45;TP183
- Published：2006
- 稿件说明：
移动端阅览
[1]金长宇,马震岳,张运良,沙瑞华,陈庆发.神经网络在岩体力学参数和地应力场反演中的应用[J].岩土力学,2006(08):1263-1266+1271.

JIN Chang-yu1, MA Zhen-yue1, ZHANG Yun-liang1, et al. Application of neural network to back analysis of mechanical parameters and initial stress field of rock masses[J]. 2006, (8): 1263-1266.
[1]金长宇,马震岳,张运良,沙瑞华,陈庆发.神经网络在岩体力学参数和地应力场反演中的应用[J].岩土力学,2006(08):1263-1266+1271. DOI： 10.16285/j.rsm.2006.08.007.

JIN Chang-yu1, MA Zhen-yue1, ZHANG Yun-liang1, et al. Application of neural network to back analysis of mechanical parameters and initial stress field of rock masses[J]. 2006, (8): 1263-1266. DOI： 10.16285/j.rsm.2006.08.007.

摘要

BP神经网络已广泛地应用于岩体力学参数和初始应力场的反演分析

但在实际应用中

BP网络存在着网络训练易于过度、收敛速度慢、易陷入局部极小以及隐层节点数难于确定等缺点。采用RBF网络和改进的BP网络

利用基于有限差分格式的快速拉格朗日算法进行正分析计算

依据若干测点的正应力数据

反演了计算区域的岩体力学参数以及初始应力场。算例表明

RBF神经网络与快速拉格朗日算法相结合

在样本容量相同的情况下

反演分析的精度、网络的拓扑结构以及学习、收敛速度

均优于采用BP网络的反演算法。

Abstract

At present

BP neural network has been widely used in back analysis of material parameters and initial stress field of rock masses in geomechanics.However

BP neural network is prone to over-being-trained

slow in convergence

not global minimum but local ones obtained and number of neurons in hidden layer hard to be determined.Authors using RBF neural network and BP neural network respectively identified mechanical parameters and initial stresses according to measured normal stresses of some specific points.Direct computations based on fast Lagrangian analysis of continuum（FLAC） were performed to get enough training samples for RBF neural network and BP neural network.An example shows that combination of RBF neural network with FLAC is more effective and rapid than application of BP neural network.

关键词

Keywords

references

Views

1001

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of neural network to back analysis of mechanical parameters and initial stress field of rock masses

Back analysis of dynamic parameters of dam materials based on earth-rockfill dam dynamic characteristics

Probability distribution characteristics of rock mass classification and its mechanical parameters based on fine description

Elastoplastic solutions to strain-softening behavior of surrounding rock masses of deep circular tunnels considering dilatancy effect

Methods to obtain mechanical parameters of weathered rock constructional elements of ancient buildings

Related Author

JIN Chang-yu

MA Zhen-yue

ZHANG Yun-liang

SHA Rui-hua

CHEN Qing-fa

LIU Zhen-ping

CHI Shi-chun

REN Xian-yong

Related Institution

School of Hydraulic Engineering, Dalian University of Technology

College of Civil and Architecture Engineering, Heilongjiang Institute of Technology

Quality Monitoring Station of Shandong Province Communications Department

College of Architecture and Civil Engineering, Xi'an University of Science and Technology

Engineering Research Center of Rock-Soil Drilling and Excavation and Protection of Ministry of Education, China University of Geosciences

AI问答

⁰