Estimation of Uniaxial Compressive Strength and Modulus of Deformability of the Asmari Limestone, Using Neuro-Fuzzy System

The uniaxial compressive strength (UCS) and modulus of deformability (E-s) of intact rocks are essential parameters in rock engineering and engineering geology projects. Because of the difficulty involved in measuring these parameters, indirect methods are often used to estimate these parameters. In this research, some predictive models using multiple regression analysis and Adaptive Neuro-Fuzzy Infrence System (ANFIS) were developed for predicting UCS and E-s of the limestone outcropped of Asmari formation in Lordegan, Chaharmahal and Bakhtiari Province, Iran. For this purpose, a series of important and easy-to-obtain parameters, such as density, porosity, and indirect tensile strength (Brazilian test) were used as the model inputs. Because the measured values of UCS and E-s of samples varied in a wide range, rock samples were classified as medium- to high- and very high-strength rocks according to the ISRM UCS classification (1978), and then, the ANFIS models were improved for these groups. The variation of coefficient of determination (R-2), Variance Accounted For (VAF), and Root Mean Square Error (RMSE) were calculated for the UCS and the modulus of deformability obtained from the multiple regression and the neuro-fuzzy models. The results revealed that the forecasting performance and accuracy of the neuro-fuzzy system are very higher than those of multiple regression models.