Prediction of Slope Stability Using Statistical Method and Fuzzy Logic

Abstract

The main goal of this research is to predict the stability of slope using fuzzy logic, Adaptive Neuro Fuzzy Inference System (ANFIS), and statistical method, Multiple Linear Regression (MLR). Four limit equilibrium methods (LEM) i.e. Morgenstern-Price, Janbu, Bishop and Ordinary were used to calculate the safety factors for various designs of slope. For prediction, five parameters were used as the inputs i.e. height of slope, unit weight of slope material, angle of slope, coefficient of cohesion, and internal angle of friction, while the output parameters are factors of safety. MLR obtained regression square (R2) of 0.470 for Bishop, 0.459 for Janbu, 0.470 for Morgenstern-Price, and 0.468 for Ordinary Method, while ANFIS obtained regression square (R2) of 0.9996 for Bishop, 0.9994 for Janbu, 0.9995 for Morgenstern-Price, and 0.9997 for Ordinary Method. The result showed that ANFIS could predict the safety factors with high accuracy compare with MLR