Earth slope reliability analysis under seismic loadings using neural network

Abstract

A new method was proposed to cope with the earth slope reliability problem under seismic loadings. The algorithm integrates the concepts of artificial neural network, the first order second moment reliability method and the deterministic stability analysis method of earth slope. The performance function and its derivatives in slope stability analysis under seismic loadings were approximated by a trained multi-layer feed-forward neural network with differentiable transfer functions. The statistical moments calculated from the performance function values and the corresponding gradients using neural network were then used in the first order second moment method for the calculation of the reliability index in slope safety analysis. Two earth slope examples were presented for illustrating the applicability of the proposed approach. The new method is effective in slope reliability analysis. And it has potential application to other reliability problems of complicated engineering structure with a considerably large number of random variables.

Keywords

slope reliability analysis / neural network / seismic loadings

References

[1] ChowdhuryR N, XuD W. Rational polynomial technique in slope-reliability analysis[J]. Journal of Geotechnical Engineering Division, 1993, 119(12): 1910-1928

[2] ChristianJ T, LaddC C, BaecherG B. Reliability applied to slope stability analysis [J]. Journal of Geotechnical Engineering Division, 1994, 120(12): 2180-2207

[3] ChristianJ T, UrzuaA. Probabilistic evaluation of earthquake-induced slope failure [J]. Journal of Geotechnical and Geoenvironmental Engineering, 1998, 124(11): 1140-1143

[4] LiK S. Probabilistic design of slopes[J]. Canadial Geotech Journal, 1987, 24(4): 520-535

[5] BergadoD T. Reliability-based analysis of embankment on soft Bangkok clay [J]. Structural Safety, 1994, 13(4): 247-266

[6] MalkawiA I, HassanW F, AbdullaF A. Uncertainty and reliability analysis applied to slope stability [J]. Structural Safety, 2000, 22(2): 161-187

[7] HaldarA, MahadevanSReliability assessment using stochastic finite element analysis[M], 2000, New York, John Wiley and Sons Inc

[8] HornikK, StinchcombeM, WhiteH. Universal approximation of an unknown mapping and its derivatives using multi-layer feed-forward networks [J]. Neural Networks, 1990, 3(5): 551-560

[9] HornikK, StinchcombeM, WhiteH. Multi-layer feed-forward networks are universal approximators [J]. Neural networks, 1989, 2(3): 359-368

[10] DengJian, GuDe-sheng. Structural reliability analysis for implicit performance functions using artificial neural network[J]. Structural Safety, 2005, 27(1): 25-48

[11] CardaliaguetP, EuvrandG. Approximation of a function and its derivatives with a neural network [J]. Neural Networks, 1992, 5(2): 207-220

[12] ScarselliF, TsoiA C. Universal approximation using feed forward neural networks: a survey of some existing methods and some new results[J]. Neural Networks, 1998, 11(1): 15-37

[13] DingDe-xin, ZhangZhi-jun. Artificial neural network based inverse design method for circular sliding slopes[J]. Journal of Central South University of Technology, 2004, 11(1): 89-92

[14] HarrM EReliability-based Design in Civil Engineering[M], 1997, New York, McGraw-hill

[15] ZhuYu-xueSlope Reliability Analysis[M], 1993, Beijing, Metallurgical Industry Press(in Chinese)

[16] HuangY HStability Analysis of Earth Slopes[M], 1983, New York, Van Norstrand Reinhold Company