Prediction of slope stability using artificial neural network (case study: Noabad, Mazandaran, Iran)

AbstractInvestigations of failures of soil masses are subjects touching both geology and engineering. These investigations call the joint efforts of engineering geologists and geotechnical engineers. Geotechnical engineers have to pay particular attention to geology, ground water, and shear strength of soils in assessing slope stability. Artificial neural networks (ANNs) are very sophisticated modeling techniques, capable of modeling extremely complex functions. In particular, neural networks are nonlinear. In this research, with respect to the above advantages, ANN systems consisting of multilayer perceptron networks are developed to predict slope stability in a specified location, based on the available site investigation data from Noabad, Mazandaran, Iran. Several important parameters, including total stress, effective stress, angle of slope, coefficient of cohesion, internal friction angle, and horizontal coefficient of earthquake, were used as the input parameters, while the slope stability was the output parameter. The results are compared with the classical methods of limit equilibrium to check the ANN model’s validity.ملخصدراسة إخفاقات التربة مواضيع تخص علم الأرض والهندسة. هذه الدراسة تحتاج إلى مجهودات المهندسين في الجيولوجيا والمهندسين الجيوتقنيين. المهندس الجيوتقني يجب أن يهتم بالجيولوجيا، بالمياه الجوفية ومدى قوة التربة للإستقرار في الإنحدار. يعتبر نموذج الشبكة الشوكي الإصطناعي (ش.ش.ص) طريقة لدراسة الوظائف المعقدة. في هذه الدراسة، استعملنا هذا النموذج لتحديد مدى استقرار الإنحدار في منطقة معينة معتمدين على بيانات سابقة بمنطقة نًُوبَادْ/مزَنْدَرانْ وإيران. معالم عديدة تخص القوة الإجمالية، القوة الفعالة، زاوية الإنحدار، عامل التماسك، زاوية الإحتكاك الداخلي، والعامل الأفقي للزلزال، هذه البيانات كانت محددة، بينما الإستقرار للإنحدار كان مستنتجا. نتائج هذه الدراسة قورنت بالطرق المعروفة في استنتاج حدود التوازن، لمراجعة مدى شرعية النموذج.

[1]  Alec Westley Skempton,et al.  STABILITY OF NATURAL SLOPES AND EMBANKMENT FOUNDATIONS , 1969 .

[2]  I. Cormeau,et al.  Numerical stability in quasi‐static elasto/visco‐plasticity , 1975 .

[3]  K. Terzaghi,et al.  Mechanism of Landslides , 1950 .

[4]  Ian Flood,et al.  Neural networks in civil engineering. II: Systems and application , 1994 .

[5]  Wang Yan,et al.  Slope stability analyses for materials with a non-linear failure envelope , 1988 .

[6]  Gordon A. Fenton,et al.  Probabilistic slope stability analysis by finite elements , 2004 .

[7]  Sidney Paige,et al.  Application of geology to engineering practice , 1950 .

[8]  Zhichao Guo,et al.  Use of artificial neural networks to analyze nuclear power plant performance , 1992 .

[9]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .

[10]  Nii O. Attoh-Okine Combining use of rough set and artificial neural networks in doweled-pavement-performance modeling: A hybrid approach , 2002 .

[11]  Peter Keith Woodward,et al.  Artificial neural network for stress-strain behavior of sandy soils: Knowledge based verification , 2005 .

[12]  edited by Hans F. Winterkorn Hsai-Yang Fang Foundation Engineering Handbook , 2017 .

[13]  L. Ishihara,et al.  Stability of Natural Deposits during Earthquakes , 1985 .

[14]  Ian Flood,et al.  Neural Networks in Civil Engineering. I: Principles and Understanding , 1994 .

[15]  J. A. Charles,et al.  Stability of compacted rockfill slopes , 1984 .

[16]  D. V. Griffiths,et al.  SLOPE STABILITY ANALYSIS BY FINITE ELEMENTS , 1999 .

[17]  R. Legget,et al.  Geology and engineering , 1939 .