Estimation of sand liquefaction based on support vector machines

Abstract

The origin and influence factors of sand liquefaction were analyzed, and the relation between liquefaction and its influence factors was founded. A model based on support vector machines (SVM) was established whose input parameters were selected as following influence factors of sand liquefaction: magnitude (M), the value of SPT, effective pressure of superstratum, the content of clay and the average of grain diameter. Sand was divided into two classes: liquefaction and non-liquefaction, and the class label was treated as output parameter of the model. Then the model was used to estimate sand samples, 20 support vectors and 17 borderline support vectors were gotten, then the parameters were optimized, 14 support vectors and 6 borderline support vectors were gotten, and the prediction precision reaches 100%. In order to verify the generalization of the SVM method, two other practical samples’ data from two cities, Tangshan of Hebei province and Sanshui of Guangdong province, were dealt with by another more intricate model for polytomies, which also considered some influence factors of sand liquefaction as the input parameters and divided sand into four liquefaction grades: serious liquefaction, medium liquefaction, slight liquefaction and non-liquefaction as the output parameters. The simulation results show that the latter model has a very high precision, and using SVM model to estimate sand liquefaction is completely feasible.

Keywords

sand liquefaction / influence factors / support vector machines / grade

References

[1] ChenY.-m., LiuH.-l., ZhouY.-dong.. Analysis on flow characteristics of liquefied and post-liquefied sand[J]. Chinese Journal of Geotechnical Engineering, 2006, 28(9): 1139-1143

[2] Shin-IchiN., HideyoshiS.. Reliability-based design of ground improvement for liquefaction mitigation[J]. Structural Safety, 2008, 30: 200-216

[3] AliA., ShahabS. Y., AliP.. Seismic active pressure distribution history behind rigid retaining walls[J]. Soil Dynamics and Earthquake Engineering, 2008, 28: 365-375

[4] JuangC. H., YuanH., LeeD. H., LinP. S.. Simplified cone penetration test-based method for evaluating liquefaction resistance of soil[J]. Geotech Engrg, ASCE, 2003, 129(1): 66-80

[5] DavisR. O., BerrillJ. B.. Energy dissipation and seism liquefaction in sands[J]. Earthquake Engineering and Structure Dynamics, 1982, 10(1): 68-70

[6] ChenW.-h., SunJ.-p., XuB.. Recent development and trend in seismic liquefaction study[J]. World Information on Earthquake Engineering, 1999, 15(2): 16-24

[7] WangM.-w., LuoG.-yu.. Application of reliability analysis to assessment of sand liquefaction potential[J]. Chinese Journal of Geotechnical Engineering, 2000, 22(5): 542-544

[8] PierreM. L., Drezet, RobertF., Harrison. A new method for sparsity control in support vector classification and regression[J]. Pattern Recognition, 2001, 34: 111-125

[9] VapnikV. N.The nature of statistical learning theory[M], 2000, New York, Springer

[10] VapnikV. N.Statistical learning theory [M], 2004, New York, Springer

[11] YuanX.-f., WangY.-n., SunW., YangH.-qian.. A hybrid learning algorithm for RBF neural networks based on support vector machines and BP algorithms[J]. Journal of Hunan University: Natural Sciences, 2005, 32(3): 88-92

[12] BURGES C. A tutorial on support vector machines for patter recognition[EB/OL]. http://www.kernel-machines.org/. 1998.

[13] CristianiniN., Shawe-TaylorJ.An introduction to support vector machines[M], 2000, Cambridge, Cambridge University Press

[14] YanX.-f., GeH.-w., YanQ.-sheng.. SVM with RBF kernel and its application research[J]. Computer Engineering and Design, 2006, 27(11): 1996-1997

[15] ZhangX.-y., LiuY.-cai.. The performance analysis of support vector machines with gauss kernel[J]. Computer Engineering, 2003, 29(8): 22-25

[16] WangZ.-z., LuoD.-gui.. Application of BP neural network based on genetic algorithm to the evaluation of sand liquefaction[J]. Soil Engineering and Foundation, 2007, 21(4): 49-53

[17] AnN.. Pre-determination of sand liquefaction in road subgrade by BP network[J]. Soil Engineering and Foundation, 2007, 21(4): 45-48