Prediction of peak shear strength of rock joints using fuzzy C means clustering

Studying the behavior of rock mass involves surviving both parameters which control shear strength of discontinuities and behavior of joints must be simulated using a constitutive model. The objective of this study is to predict the value of peak shear stress of rocks based on data from experimental data and using them to construct model by Fuzzy C means clustering (FCM) techniques. In this Study two models were designed based on Mamdani and Sugeno Fuzzy Systems. Results showed that Sugeno fuzzy system could predict this value with correlation coefficient square more than 0.92, but result showed that Mamdani model could not predict this parameter accurately in comparison with Sugeno model. So a model which is constructed us in Sugeno type FCM could be used to predict the value of shear strength of discontinuities based on data gained from that discontinuity

کلیدواژه ها:

peak shear stress ، Fuzzy C means clustering ، Sugeno FI