RESEARCH ON NEURAL NETWORK MODEL OF DEFORMATION BEHAVIOR OF SOFT SOIL

Zhou Qiujuan; Chen Xiaoping; Zeng Lingling

doi:10.13204/j.gyjz200806014

Volume 38 Issue 6

Dec. 2014

Turn off MathJax

Article Contents

Article Navigation > INDUSTRIAL CONSTRUCTION > 2008 > 38(6): 48-53

Zhou Qiujuan, Chen Xiaoping, Zeng Lingling. RESEARCH ON NEURAL NETWORK MODEL OF DEFORMATION BEHAVIOR OF SOFT SOIL[J]. INDUSTRIAL CONSTRUCTION, 2008, 38(6): 48-53. doi: 10.13204/j.gyjz200806014

Citation:

Zhou Qiujuan, Chen Xiaoping, Zeng Lingling. RESEARCH ON NEURAL NETWORK MODEL OF DEFORMATION BEHAVIOR OF SOFT SOIL[J]. INDUSTRIAL CONSTRUCTION, 2008, 38(6): 48-53. doi: 10.13204/j.gyjz200806014

Zhou Qiujuan, Chen Xiaoping, Zeng Lingling. RESEARCH ON NEURAL NETWORK MODEL OF DEFORMATION BEHAVIOR OF SOFT SOIL[J]. INDUSTRIAL CONSTRUCTION, 2008, 38(6): 48-53. doi: 10.13204/j.gyjz200806014

Citation:

Zhou Qiujuan, Chen Xiaoping, Zeng Lingling. RESEARCH ON NEURAL NETWORK MODEL OF DEFORMATION BEHAVIOR OF SOFT SOIL[J]. INDUSTRIAL CONSTRUCTION, 2008, 38(6): 48-53. doi: 10.13204/j.gyjz200806014

PDF( 0 KB)

RESEARCH ON NEURAL NETWORK MODEL OF DEFORMATION BEHAVIOR OF SOFT SOIL

doi: 10.13204/j.gyjz200806014

1.
1. Department of Mechanics and Civil Engineering,Jinan University Guangzhou 510632;
2.
2. Institute of Geotechnical Engineering,Southeast University Nanjing 210096

Received Date: 2007-10-13
Publish Date: 2008-06-20

Abstract

Abstract

Based on the triaxial test results of soft soil and the neural network technology,the BP model of soft soil in different stress paths and the creep BP model of soft soil are set up.The reliability of the models is validated by the data of other tests.It shows that neural network model is an effective way to set up constitutive model of soils.Through the contrast training and forecasting,some useful conclusions could be drawn.Neural network model is most suitable for interpolation forecasting,and it can be used as a supplementary way for deformation test of soft soil.In addition,the magnitude and reliability of the training samples are important impacts on model precision.
- neural network,
- soft soil,
- stress path,
- water content,
- creep

FullText(HTML)

References(14)

References

[2] Roscoe K H,Burland J B. On the Generalized Stress-Strain Behavior of Wet Clay[M].Cambridge,england:cambridge University Press,1968.539-609.

Roscoe K H,Schofield A N,Thurairajah A. Yielding of Clays in States Wetter than Critical[J].Gotechnique,1963,(03):211-240.doi: 10.1680/geot.1963.13.3.211.

[3] Duncan J M,Chang C Y. Nonlinear Analysis of Stress and Strain in Soils[J].Journal of Soil Mechanic and Foundation Engineering Division ASCE,1970,(SM5):1629-1633.

[4] 陈宗基. 固结及时间效应的单维问题[J].土木工程学报,1958,(01):1-10.

[5] Folque J. Rheology Properties of Compacted Unsaturated Soils[A].France:Paris,1961.113.

[6] 詹美礼,钱家欢,陈绪禄. 软土流变特性试验及流变模型[J].岩土工程学报,1993,(03):54-62.

[7] 陈晓平,白世伟. 软土蠕变-固结特性及计算模型研究[J].岩石力学与工程学报,2003,(05):728-734.doi: 10.3321/j.issn:1000-6915.2003.05.008.

[8] Chen Xiaoping,Bai Shiwei,Yang Chunhe. Viscous Elastic Plastic Consolidation Model and Finite Element Analysis for Soft Foundation[A].Tucson,USA,2001.1823-1825.

[9] Yin Z Z. A Constitutive Model with Two Yield Surfaces for Soils.Numerical Methods in Geomechanics[A].Innsbruck,Austria,1988.447-451.

[10] 姚辉,王靖涛. 多重应力路径下黏土本构关系的神经网络模型[J].岩石力学与工程学报,2003,(09):1454-1457.doi: 10.3321/j.issn:1000-6915.2003.09.010.

[11] 曾静,冯夏庭,王靖涛. 不同应力路径下砂土的神经网络弹塑性本构模型研究[J].岩土力学,2004,(06):896-900.doi: 10.3969/j.issn.1000-7598.2004.06.011.

[12] 飞思科技产品研发中心. 神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005.

[13] 陈晓平,朱鸿鹄,张芳枝. 软土变形时效特性的试验研究[J].岩石力学与工程学报,2005,(12):2142-2148.doi: 10.3321/j.issn:1000-6915.2005.12.023.

[14] 刘国明,周军. 路堤软土地基沉降有限元非线性分析[J].福州大学学报(自然科学版),2003,(04):470-473.doi: 10.3969/j.issn.1000-2243.2003.04.022.

Relative Articles

Supplements(0)

Cited By

Proportional views