[1] Miao Linchang, Yu Xin,. Research on prediction of soil suction in expansive soil [J]. Journal of Southeast University (English Edition), 2004, 20 (3): 364-368. [doi:10.3969/j.issn.1003-7985.2004.03.020]

Copy

Research on prediction of soil suction in expansive soil()

膨胀土中的吸力预测研究

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

20

Issue:

2004 3

Page:

364-368

Research Field:

Civil Engineering

Publishing date:

2004-09-30

Info

Title:

Research on prediction of soil suction in expansive soil

膨胀土中的吸力预测研究

Author(s):

Miao Linchang¹, Yu Xin²

¹College of Transportation, Southeast University, Nanjing 210096, China
²Institute of Earthquake Engineering of Jiangsu Province, Nanjing 210014, China

缪林昌¹, 于昕²

¹东南大学交通学院, 南京 210096; ²江苏省地震工程研究院, 南京 210014

Keywords:

expansive soil;  soil-water characteristic curve(SWCC);  artificial neural network(ANN);  suction

膨胀土;  水分特征曲线;  人工神经网络;  吸力

PACS:

U414.73

DOI:

10.3969/j.issn.1003-7985.2004.03.020

Abstract:

Soil-water characteristic curves of expansive clay are usually measured in the laboratory, but soil suction in the field is extremely difficult and time consuming. In this paper, the method of artificial neural network(ANN)is adopted to predict soil suction in the field by using measured water contents. This is done by training the network using laboratory measured soil-water characteristics. Prediction soil suctions using the ANN with some limited in-situ measured water contents are compared with actual suction measurements in the field. Prediction results are discussed.

膨胀土的水分特征曲线通常是在实验室测得的, 在现场测量膨胀土的吸力不仅费时而且也非常困难. 本文采用人工神经网络技术用现场测得的含水量来预测土的吸力. 网络训练首先采用水分特征曲线相应的试验数据进行监督训练, 然后利用监督训练得到的网络单元的连接权值对现场测得含水量数据进行吸力预测, 预测结果与实测结果相近, 同时并对预测结果进行了分析讨论.

References:

[1] Fredlund D G, Xing A. Equations for the soil-water characteristic curve [J]. Can Geotech J, 1994, 31(3): 521-532.
[2] Holmstrom L. Using additive noise in back-propagation training [J]. IEEE Trans Neural Network, 1992, 3(1): 35-43.
[3] Rojas E. Modeling the soil-water characteristic curve during wetting and drying cycles[A]. In: Proceedings of the 3rd International Conference on Unsaturated Soils[C]. Receife, Brazil, 2002. 215-220.
[4] Gerscovich D M S, Sayao A S F J. Evaluation of the soil-water characteristic curve equations for soils from Brazil [A]. In: Proceedings of the 3rd International Conference on Unsaturated Soils [C]. Receife, Brazil, 2002. 295-300.
[5] Kassif G, Shalom A B. Experimental relationship between swell pressure and suction [J]. Geotechnique, 1971, 21(2): 249-255.
[6] Vanapalli S K, Fredlund D G, Pufahl D E, et al. Model for the prediction of shear strength with respect to soil suction [J]. Can Geotech J, 1996, 33(3): 379-392.
[7] Vanapalli S K, Pufahl D E, Fredlund D G. The effect of stress on the soil-water characteristic behavior of a compacted sandy-clay till[A]. In: 51st Canadian Geotechnical Conference[C]. Edmonton, 1998. 81-86.
[8] Parker D B. Learning logic [R]. Stanford, California: Stanford University, 1982.
[9] Rummelhart D E, Hinton G E, Williams R J. Learning internal representations by error propagation [A]. In: Feldman J A, Hayes P J, Rummelhart D E, eds. Parallel Distributed Processing: Expirations in the Microstructure of Cognition—Volume 1: Foundations [C]. Cambridge, Massachusetts: MIT Press, 1986. 318-362.
[10] Rich E. Artificial intelligence[M]. New York: McGraw-Hill Book Co., 1983. 436.
[11] Winston P H. Artificial intelligence[M]. Massachusetts: Addison-Wesley, 1984. 524.
[12] Stone G O. An analysis rule and the learning of statistical associations[A]. In: Feldman J A, Hayes P J, Rummelhart D E, eds. Parallel Distributed Processing: Expirations in the Microstructure of Cognition—Volume 1: Foundations[C]. Cambridge, Massachusetts: MIT Press, 1986. 444-459.

Memo

Memo:

Biography: Miao Linchang(1961—), male, doctor, professor, lc.miao@seu.edu.cn.

Common functions