Browse > Article

Development of Neural Network Model for Estimation of Undrained Shear Strength of Korean Soft Soil Based on UU Triaxial Test and Piezocone Test Results  

Kim Young-Sang (Ocean Engrg., Yosu National Univ.)
Publication Information
Journal of the Korean Geotechnical Society / v.21, no.8, 2005 , pp. 73-84 More about this Journal
Abstract
A three layered neural network model was developed using back propagation algorithm to estimate the UU undrained shear strength of Korean soft soil based on the database of actual undrained shear strengths and piezocone measurements compiled from 8 sites over the Korea. The developed model was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was also compared with conventional empirical methods. It was found that the number of neuron in hidden layer is different for the different combination of transfer functions of neural network models. However, all piezocone neural network models are successful in inferring a complex relationship between piezocone measurements and the undrained shear strength of Korean soft soils, which give relatively high coefficients of determination ranging from 0.69 to 0.72. Since neural network model has been generalized by self-learning from database of piezocone measurements and undrained shear strength over the various sites, the developed neural network models give more precise and generally reliable undrained shear strengths than empirical approaches which still need site specific calibration.
Keywords
Korean soft soils; Artificial neural network; Piezocone; UU triaxial test; Undrained shear strength;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 김영상 (2003), '피에조콘을 이용한 점토의 비배수전단강도 추정에의 인공신경망 이론 적용', 한국지반공학회논문집, 제19권 4호, pp.287-298
2 Chen, B. S. Y. and Mayne, P. W. (1993), 'Piezocone Evaluation of Undrained Shear Strength in Clays', 11th Southeast Asian Geotechnical Conference, 4-8 May, Singapore, pp.91-98
3 Hornik, K., Stinchcombe, M., and White, H. (1989), 'Multilayer feed-forward networks are universial approximators', Neural Networks, 2(5), pp.359-366   DOI   ScienceOn
4 Goh, A. T. C. (1994), 'Seismic liquefaction potential assessed by neural-networks', ASCE Journal of Geotechnical Engineering, Vol.120, No.9, pp.1467-1480   DOI   ScienceOn
5 Mayne, P. W. (1980), 'Cam Clay predictions of undrained strength', ASCE Journal of Geotechnical Engineering, 106, 11, pp.1219-1242
6 Konard, J. -M. and Law, K. T. (1987), 'Undrained Strength from piezocone tests', Canadian Geotechnical Journal, Vol.24, pp.392-405   DOI   ScienceOn
7 Kurup, P. U. and Dudani, N. (2002), 'Neural networks for profiling stress history of clays from PCPT data', ASCE Journal of Geotechnical and Geoenvironmental Engineering, Vol.128, No.7, pp.569-579   DOI   ScienceOn
8 Ladd, C. C. and Foott, R. (1974), 'New Design Procedure for Stability of Soft Clays', ASCE Journal of Geotechnical Engineering, 100, No.GT.7, pp.763-786
9 김영상, 이승래, 김종수 (2002), '피에조콘을 이용한 연약지반 선행압밀하중 결정의 인공신경망 이론 적용 연구', 대한토목학회논문집, 제22권, 제6-C호, pp.623-633
10 장인성, 이선재, 정충기, 김명모 (2001), '국내 점성토 지반의 피에조콘 계수', 한국지반공학회논문집, 제17권 6호, pp. 15-24
11 Chen, B. S. Y. (1994), Profiling stress history of clays using piezocone with dual pore pressure measurements, Ph.D thesis, Georgia Institute of Technology, p.350
12 Garson, G. D.(1991), 'Interpreting neural-network connection weights', AI expert, 6(7), pp.47-51
13 Rad, N.R. and Lunne, T. (1988), 'Direct Correlations between Piezocone Test Results and Undrained Shear Strength of Clay', ISOPT-1, Vol.2, pp.911-917