Slope reliability analysis using surrogate models via new support vector machines with swarm intelligence

Abstract Surrogate model methods are attractive ways to improve the efficiency of Monte Carlo simulation (MCS) for structural reliability analysis. An intelligent surrogate model based method for slope system reliability analysis is presented in this study. The novel machine learning technique ν-support vector machine (ν-SVM) is adopted to establish the surrogate model to predict the factor of safety via the samples generated by Latin hypercube sampling. Global optimization algorithms particle swarm optimization and artificial bee colony algorithm are adopted to select the hyper-parameters of ν-SVM model. The applicability of the ν-SVM based surrogate model for slope system reliability analysis is tested on four examples with obvious system effects. It is found that the proposed surrogate model combined with MCS can achieve accurate system failure probability evaluation using fewer deterministic slope stability analyzes than other approaches.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  J. Christian,et al.  Reliability Applied to Slope Stability Analysis , 1994 .

[3]  Jian Ji,et al.  Stratified Response Surfaces for System Probabilistic Evaluation of Slopes , 2012 .

[4]  Yu Wang,et al.  Risk de-aggregation and system reliability analysis of slope stability using representative slip surfaces , 2013 .

[5]  R. N. Chowdhury,et al.  Geotechnical system reliability of slopes , 1995 .

[6]  Yong Zhang,et al.  Uniform Design: Theory and Application , 2000, Technometrics.

[7]  Yu WangY. Wang,et al.  Practical reliability analysis of slope stability by advanced Monte Carlo simulations in a spreadsheet , 2011 .

[8]  Yung-ming Cheng,et al.  Performance studies on six heuristic global optimization methods in the location of critical slip surface , 2007 .

[9]  Junjie Li,et al.  An artificial bee colony algorithm for locating the critical slip surface in slope stability analysis , 2013 .

[10]  Shao Jingdong.  A NEW SLOPE DISPLACEMENT BACK ANALYSIS METHOD BASED ON v-SVR AND MVPSO ALGORITHM AND ITS APPLICATION , 2013 .

[11]  D. V. Griffiths,et al.  Risk Assessment in Geotechnical Engineering , 2008 .

[12]  Dazhou Zhu,et al.  The performance of ν-support vector regression on determination of soluble solids content of apple by acousto-optic tunable filter near-infrared spectroscopy , 2007 .

[13]  Junjie Li,et al.  Artificial Bee Colony Algorithm Optimized Support Vector Regression for System Reliability Analysis of Slopes , 2016, J. Comput. Civ. Eng..

[14]  Claudio Cherubini,et al.  Reliability Analysis Of Slopes , 1970 .

[15]  A. M. Hasofer,et al.  Exact and Invariant Second-Moment Code Format , 1974 .

[16]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[17]  Sung Eun Cho,et al.  First-order reliability analysis of slope considering multiple failure modes , 2013 .

[18]  Junjie Li,et al.  Artificial bee colony algorithm and pattern search hybridized for global optimization , 2013, Appl. Soft Comput..

[19]  D. Montgomery,et al.  Comparing Computer Experiments for the Gaussian Process Model Using Integrated Prediction Variance , 2013 .

[20]  Kok-Kwang Phoon,et al.  Application of the Kriging-Based Response Surface Method to the System Reliability of Soil Slopes , 2013 .

[21]  Tien H. Wu,et al.  System reliability of slope stability , 1990 .

[22]  Jerome Sacks,et al.  Choosing the Sample Size of a Computer Experiment: A Practical Guide , 2009, Technometrics.

[23]  Wilson H. Tang,et al.  Efficient system reliability analysis illustrated for a retaining wall and a soil slope , 2011 .

[24]  Hongbo Zhao.  Slope reliability analysis using a support vector machine , 2008 .

[25]  Junjie Li,et al.  Damage detection based on improved particle swarm optimization using vibration data , 2012, Appl. Soft Comput..

[26]  V. R. Greco.  EFFICIENT MONTE CARLO TECHNIQUE FOR LOCATING CRITICAL SLIP SURFACE , 1996 .

[27]  A. Bishop.  The use of the Slip Circle in the Stability Analysis of Slopes , 1955 .

[28]  D. Steinberg,et al.  Computer experiments: a review , 2010 .

[29]  Junjie Li,et al.  Structural inverse analysis by hybrid simplex artificial bee colony algorithms , 2009 .

[30]  Gordon A. Fenton,et al.  Influence of spatial variability on slope reliability using 2-D random fields. , 2009 .

[31]  Kok-Kwang Phoon,et al.  Efficient Evaluation of Reliability for Slopes with Circular Slip Surfaces Using Importance Sampling , 2009 .

[32]  Bernhard Schölkopf,et al.  Experimentally optimal v in support vector regression for different noise models and parameter settings , 2004, Neural Networks.

[33]  Wei Wang,et al.  Reliability analysis using radial basis function networks and support vector machines , 2011 .

[34]  Peng Zeng,et al.  System reliability analysis of layered soil slopes using fully specified slip surfaces and genetic algorithms , 2015 .

[35]  Sung Eun Cho,et al.  Probabilistic stability analyses of slopes using the ANN-based response surface , 2009 .

[36]  D. Karaboga,et al.  On the performance of artificial bee colony (ABC) algorithm , 2008, Appl. Soft Comput..

[37]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[38]  Junjie Li,et al.  Rosenbrock artificial bee colony algorithm for accurate global optimization of numerical functions , 2011, Inf. Sci..

[39]  Junjie Li,et al.  System probabilistic stability analysis of soil slopes using Gaussian process regression with Latin hypercube sampling , 2015 .

[40]  Dian-Qing Li,et al.  Extension of Hassan and Wolff method for system reliability analysis of soil slopes , 2013 .

[41]  Anthony T. C. Goh,et al.  Reliability assessment of serviceability performance of braced retaining walls using a neural network approach , 2005 .

[42]  Jianping Sun,et al.  Search for Critical Slip Surface in Slope Stability Analysis by Spline-Based GA Method , 2008 .

[43]  Prabir Bhattacharya,et al.  An Enhanced MEMS Error Modeling Approach Based on Nu-Support Vector Regression , 2012, Sensors.

[44]  E. Spencer.  A Method of Analysis of the Stability of Embankments Assuming Parallel Inter-Slice Forces , 1967 .