3D Back Analysis of Initial Stress Field Based on Neural Network RBF Model

Zhong Fu Wang; Han Dong Liu; Tong Jiang; Si Wei Wan

doi:10.4028/www.scientific.net/AMR.243-249.3223

Paper Titles

Deformation Characteristics of High Slope of Cihaxia Hydropower Station
p.3201

Physical Modelling of Joint Effects on Deformation and Failure of Tunnels
p.3205

The Characteristics and Mechanism of Large Scale Landslides between Huangjinping and Detuo in Daduhe River
p.3211

Effect of Rock Nonhomogeneous Characteristics on Threshold Permeability
p.3217

3D Back Analysis of Initial Stress Field Based on Neural Network RBF Model
p.3223

The Analysis of Feasibility and Prospect of the Depth Exploring for Ore-Deposit in ShangPing Tungsten Ore Area of Tie Shan Long
p.3229

In Situ Test Research for the Affect of Surface Water Seepage on the Ground Fissures Action
p.3233

Study on the Formation and Repeated Opening Mechanism of Ground Fissures under the Role of Surface Water
p.3238

Experimental Study on Bearing Behavior of Large-Diameter Overlength Squeezed Branch Pile
p.3244

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 243-2493D Back Analysis of Initial Stress Field Based on...

3D Back Analysis of Initial Stress Field Based on Neural Network RBF Model

Abstract:

Based on geological condition of underground factory building in Hohhot pumped storage power station, research and analysis are taken for the fundamental element which affect initial stress field, 3D finite element model of underground factory building is build for the analysis. Beigin with regrssion analysis, adopt linear elasticity caculation of finite element method to take linear regression analysis, and obtain range of optimized parameters. Adopt homogeneous design to definite various assemblies of optimized parameters at different levels. Obtain training sample by elasto plastic caculation of finite element, train for RBF model in oder to get inverse model of ground stress field. The calculation result shown that: RBF model overcome the disadvantages such as slow calculating speed and overfitting of BP model, and it could obtain distrubution rule of initial stress filed by inverse analysis in a reasonable way.

You might also be interested in these eBooks

Advances in Civil Engineering and Architecture

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 243-249)

Pages:

3223-3228

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.243-249.3223

Citation:

Cite this paper

Online since:

May 2011

Authors:

Zhong Fu Wang, Han Dong Liu, Tong Jiang, Si Wei Wan

Keywords:

Finite Element, Ground Stress, Neural Network (NN), Radial Basis Function (RBF), Regression Analysis

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Dingxiang Feng,Xianrong Gu,Jialing Yang : J.UndergroundEngineering. Vol. 2(1982),p.20

Google Scholar

[2] Youtian Zhang,Huichang Hu: J.Journal of Hydraulic Engineering. Vol. 4(1984),p.31

Google Scholar

[3] Ke Yang, Lixiang Zhang,Zhongkui Li: J.Chinese Journal of Rock Mechanics and Engineering. Vol. 11(2002),p.1639

Google Scholar

[4] Huizhi Guo,Qizhi Ma,Xichen Xue: J.Chinese Journal of Geotechnical Engineering. Vol. 3(1983),p.64

Google Scholar

[5] Huanchun Zhu, Haibin Zhao: J.Journal of Hydraulic Engineering. Vol. 5(1996),p.29

Google Scholar

[6] Qinglin Li:J.Chinese Journal of Geotechnical Engineering. Vol. 5(1998),p.68

Google Scholar

[7] Ming Xiao, Zhiming Liu: J.Yangtze River. Vol. 9(2000),p.42

Google Scholar

[8] Guojian Shao: J.Advances in Science and Technology of Water Resources. Vol. 5(2002),p.36

Google Scholar

[9] Pingfan Yan, Changshui Zhang:Artificial Neural Networks and Simulated Evolutionary Computation[M].( Beijing:Tsinghua University Press,2000)

Google Scholar

[10] Zhongming Jiang, Weiya Xu, Jianfu Shao: J.Journal of Hohai University. Vol. 3(2002),p.52

Google Scholar

[11] Zhongming Jiang, Weiya Xu: J.Rock and Soil Mechanics. Vol. 6(2002),p.737

Google Scholar