Prediction of slope stability using adaptive neuro-fuzzy inference system based on clustering methods

Slope stability analysis is an enduring research topic in the engineering and academic sectors. Accurate prediction of the factor of safety (FOS) of slopes, their stability, and their performance is not an easy task. In this work, the adaptive neuro-fuzzy inference system (ANFIS) was utilized to build an estimation model for the prediction of FOS. Three ANFIS models were implemented including grid partitioning (GP), subtractive clustering method (SCM), and fuzzy c-means clustering method (FCM). Several important parameters such as cohesion coefficient, internal angle of friction, slope height, slope angle, and unit weight of slope material were utilized as the input parameters, while FOS was used as the output parameter. A comparison was made between these three models, and the results obtained showed the superiority of the ANFIS-SCM model. Also performance of the ANFIS-SCM model was compared with multiple linear regression (MLR). The results obtained demonstrated the effectiveness of the ANFIS-SCM model.

Keywords:

Slope Stability , Factor of Safety , ANFIS-Grid Partitioning , ANFIS-Subtractive Clustering Method , ANFIS-Fuzzy C-Means Clustering Method