Application of a probabilistic neural network for liquefaction assessment

Xinhua Xue

Abstract


This paper presents a hybrid probabilistic neural network (PNN) and particle swarm optimization (PSO) techniques to predict the soil liquefaction. The PSO algorithm is employed in selecting the optimal smoothing parameter of the PNN to improve the forecasting accuracy. Seven parameters such as earthquake magnitude, normalized peak horizontal acceleration at ground surface, standard penetration number, penetration resistance, relative compaction, mean grain diameter and groundwater table are selected as the evaluating indices. The predictions from the PSO-PNN model were compared with those from two models: back-propagation neural network (BPNN) model and support vector machine (SVM) model. The study concluded that the proposed PSO-PNN model can be used as a reliable approach for predicting soil liquefaction.


Full Text:

PDF

References


AFSHAR M.H., RAJABPOUR R. Application of local and global particle swarm optimiza-tion algorithms to optimal design and operation of irrigation pumping systems. Irrig Drain.

, 58, pp. 321{331, doi: 10.1002/ird.412.

BOLAT B., YILDIRIM T. Performance increasing methods for probabilistic neural networks. Pakistan J Info Technol, 2003, 2(3), pp. 250-255, doi: 10.3923/itj.2003.250.255.

BELKHATIR M., SCHANZ T., ARAB A., DELLA N., KADRI A. Insight into the eects of gradation on the pore pressure generation of sand{silt mixtures. Geotech Test J, 2014, 37(5), pp. 922{931, doi: 10.1520/GTJ20130051.

CHERN S.G., LEE C.Y. CPT-based simplied liquefaction assessment by using fuzzy-neural network. J Mar Sci Technol, 2009, 17(4), pp. 326{331, doi: 10.6119/JMST~.

CLERC M., KENNEDY J. The particle swarm-explosion, stability, and convergence in a multidimensional complex space. IEEE Trans Evol Comput, 2002, 6(1), pp. 58{73, doi: 10.

/4235.985692.

GOH A.T.C. Probabilistic neural network for evaluating seismic liquefaction potential. Can Geotech J, 2002, 39(1), pp. 219{232, doi: 10.1139/t01-073.

GEORGIOU V.L., PAVLIDIS N.G., PAROPOULOS K.E., ALEVIZOS Ph.D., VRAHATIS

M.N. Optimizing the performance of probabilistic neural networks in a bioinformatics

task. In: Proceedings of the EUNITE 2004 conference, 2004, pp. 34{40.

GUETTAYA I., OUNI M.R.EL. In situ-based assessment of soil liquefaction potential-case

study of an earth dam in Tunisia. Front Struct Civ Eng, 2014, 8(4), pp. 456{461, doi: 10.

/s11709-014-0259-5.

JUANG C., YUAN H., LEE D., LIN P. Simplied cone penetration test-based method for

evaluating liquefaction resistance of soils. J Geotech Geoenviron Eng, 2003, 129(1), pp. 66{80,

doi: 10.1061/(ASCE)1090-0241(2003)129:1(66).

JUANG C.H., CHEN C.J., JIANG T., ANDRUS R.D. Risk-based liquefaction potential

evaluation using standard penetration tests. Canad Geotech J, 2000, 37, pp. 1195{1208,

doi: 10.1139/cgj-37-6-1195.

JHA S.K., SUZUKI K. Reliability analysis of soil liquefaction based on standard penetration

test. Comput Geotech, 2009, 36 (4), pp. 589{596, doi: 10.1016/j.compgeo.2008.10.004.

KENNEDY J., EBERHART R.C. Particle swarm optimization. In Proceedings of the 1995

IEEE International Conference on Neural Networks 4, Perth, Australia. IEEE Service Center:

Piscataway, NJ, 1995, pp. 1942{1948.

MARCUSON, W.F., III. Denition of terms related to liquefaction. J Geotech Eng Div

ASCE, 1978, 104(9), pp. 1197{1200.

ASTERS T. Practical neural network recipes in C++. Academic Press, San Diego, Calif.,

PARZEN E. On estimation of a probability density function and mode. Ann Math Statist,

, pp. 33, 1065{1076, doi: 10.1214/aoms/1177704472.

POUR M.N., ASAKEREH A. A comparison between two eld methods of evaluation of

liquefaction potential in the Bandar Abbas city. Am J Civ Eng, 2015, 3(2{2), pp. 1{5,

doi: 10.11648/j.ajce.s.2015030202.11.

PARSOPOULOS K.E. VRAHATIS M.N. Recent approaches to global optimization problems

through particle swarm optimization. Nat Comput, 2002, 1(2), pp. 235{306, doi: 10.1023/A.

SAMUI P., KARTHIKEYAN J. Determination of liquefaction susceptibility of soil: a least

square support vector machines approach. Int J Geotech Environ, 2011, 3(1), pp. 75{84,

doi: 10.1002/nag.2081.

SAMUI P., SITHARAM T.G. Machine learning modelling for predicting soil liquefaction sus-

ceptibility. Nat Hazards Earth Syst Sci, 2011, 11(1), pp. 1{9, doi: 10.5194/nhess-11-1-2011.

SAMUI P. Liquefaction prediction using support vector machine model based on cone pene-

tration data. Front Struct Civ Eng, 2013, 7(1), pp. 72{82, doi: 10.1007/s11709-013-0185-y.

SU Y.H., MA N., HU J., YANG X.L. Estimation of sand liquefaction based on sup-

port vector machines. J Cent South Univ Technol, 2008, 15(s2), pp. 15{20, doi: 10.1007.

s11771-008-0429-5.

SPECHT D.F. Probabilistic neural networks. Neural Networks, 1990, 3(1), pp. 109{118,

doi: 10.1016/0893-6080(90)90049-Q.

SPECHT D.F., ROMSDAHL H. Experience with adaptive probabilistic neural network and

adaptive general regression neural network. In Proceedings of the IEEE International Con-

ference on Neural Network, 1994, 2, pp. 1203{1208.

TRELEA I.C. The particle swarm optimization algorithm: Convergence analysis and pa-

rameter selection. Inform Process Lett, 2003, 85, pp. 317{325, doi: 10.1016/S0020-0190(02.

-7.

XU H.B., CHEN G.H. An intelligent fault identication method of rolling bearings based on

LSSVM optimized by improved PSO. Mech Syst Signal Pr, 2013, 35, pp. 167{175, doi: 10.

/j.ymssp.2012.09.005.

YILMAZ A.E., KUZUOGLU M. A particle swarm optimization approach for hexahedral

mesh smoothing. Int J Numer Meth Fluids, 2009, 60(1), pp. 55{78, doi: 10.1002/fld.1878.

ZHANG G., ROBERTSON P.K., BRACHMAN R.W.I. Estimating liquefaction-induced lat-

eral displacements using the standard penetration test or cone penetration test. J Geotech

Geoenviron Eng, 2004, 130(8), pp. 861{871, doi: 10.1061/(ASCE)1090-0241(2004)130.

(861).




DOI: http://dx.doi.org/10.14311/NNW.2017.1245

Refbacks

  • There are currently no refbacks.


Should you encounter an error (non-functional link, missing or misleading information, application crash), please let us know at nnw.ojs@fd.cvut.cz.
Please, do not use the above address for non-OJS-related queries (manuscript status, etc.).
For your convenience we maintain a list of frequently asked questions here. General queries to items not covered by this FAQ shall be directed to the journal editoral office at nnw@fd.cvut.cz.