THE USE OF SELF-ORGANIZING FEATURE MAP NETWORKS FOR THE PREDICTION OF THE CRITICAL FACTOR OF SAFETY OF AN ARTIFICIAL SLOPE

In this study, the performance of three different self organization feature map (SOFM) network models denoted as SOFM1, SOFM2, and SOFM3 having neighborhood shapes, namely, SquareKohonenful, LineKohonenful, and DiamondKohenenful, respectively, to predict the critical factor of safety (Fs) of a widely-used artificial slope subjected to earthquake forces was investigated and compared. For this purpose, the reported data sets by Erzin and Cetin (2012) [7], including the minimum (critical) Fs values of the artificial slope calculated by using the simplified Bishop method, were utilized in the development of the SOFM models. The results obtained from the SOFM models were compared with those obtained from the calculations. It is found that the SOFM1 model exhibits more reliable predictions than SOFM2 and SOFM3 models. Moreover, the performance indices such as the determination coefficient, variance account for, mean absolute error, root mean square error, and the scaled percent error were computed to evaluate the prediction capacity of the SOFM models developed. The study demonstrates that the SOFM1 model is able to predict the Fs value of the artificial slope, quite efficiently, and is superior to the SOFM2 and SOFM3.

[1]  R. Ulusay,et al.  Liquefaction-induced ground deformations on a lake shore (Turkey) and empirical equations for their prediction , 2006 .

[2]  N. Morgenstern,et al.  The analysis of the stability of general slip surfaces , 1965 .

[3]  S. Sarma.  STABILITY ANALYSIS OF EMBANKMENTS AND SLOPES , 1973 .

[4]  B. Satyanarayana,et al.  A Method of Analysis of the Stability of Embankments Assuming Parallel Inter-Slice Forces , 1967 .

[5]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[6]  Yusuf Erzin,et al.  The prediction of the critical factor of safety of homogeneous finite slopes using neural networks and multiple regressions , 2013, Comput. Geosci..

[7]  Fraser.  A New Method for Data Integration and Integrated Data Interpretation : Self-Organising Maps , 2007 .

[8]  Yusuf Erzin,et al.  Factors influencing the crushing strength of some Aegean sands , 2012, Bulletin of Engineering Geology and the Environment.

[9]  Guo Jia-yu.  Stability of Earth Slopes and Its Prevention Methodes , 2003 .

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

[11]  Rafael Baker,et al.  Stability charts for pseudo-static slope stability analysis , 2006 .

[12]  Hui-Ju Wu,et al.  Effective e-learning recommendation system based on self-organizing maps and association mining , 2008, Electron. Libr..

[13]  N. Janbu.  Application of composite slip surfaces for stability analysis , 1954 .

[14]  Mostafa Sharifzadeh,et al.  Development of a model for analysis of slope stability for circular mode failure using genetic algorithm , 2014, Environmental Earth Sciences.

[15]  R.,et al.  Computer methods and advances in geomechanics , 2007 .

[16]  B. Hanumantha Rao,et al.  Artificial neural network models for predicting soil thermal resistivity , 2008 .

[17]  Devendra Singh,et al.  Artificial neural network (ANN) models for determining hydraulic conductivity of compacted fine-grained soils , 2009 .

[18]  Lucia Luzi,et al.  Influence of earthquakes on the stability of slopes , 2007 .

[19]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[20]  Mehdi Nikoo,et al.  Determination of compressive strength of concrete using Self Organization Feature Map (SOFM) , 2013, Engineering with Computers.

[21]  Yusuf Erzin,et al.  The prediction of the critical factor of safety of homogeneous finite slopes subjected to earthquake forces using neural networks and multiple regressions , 2014 .

[22]  S. C. Pasternack,et al.  NUMERICAL METHODS IN THE STABILITY ANALYSIS OF SLOPES , 1988 .

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

[24]  Yusuf Erzin,et al.  The Prediction of Swell Percent and Swell Pressure by Using Neural Networks , 2011 .

[25]  B. Bakır,et al.  Analysis of a highway embankment failure associated with the 1999 Düzce, Turkey earthquake , 2005 .

[26]  B. Hanumantha Rao,et al.  Artificial neural network models for predicting electrical resistivity of soils from their thermal resistivity , 2010 .

[27]  Y. Erzin.  Artificial neural networks approach for swell pressure versus soil suction behaviour , 2007 .

[28]  W. Fellenius.  Calculation of stability of earth dam , 1936 .

[29]  H. Wang,et al.  Slope stability evaluation using Back Propagation Neural Networks , 2005 .

[30]  Yusuf Erzin,et al.  The use of neural networks for the prediction of the critical factor of safety of an artificial slope subjected to earthquake forces , 2012 .

[31]  Muhammad Mukhlisin,et al.  PREDICTION OF SLOPE STABILITY USING STATISTICAL METHOD AND FUZZY LOGIC , 2012 .

[32]  Yu Zhao,et al.  Slope Stability Analysis Using Slice-Wise Factor of Safety , 2014 .