Prediction of Uniaxial Compressive Strength of Some Sedimentary Rocks by Fuzzy and Regression Models

The purpose of this research is to construct predictive models to estimate the uniaxial compressive strength (UCS) of grainstone, wackestone-mudstone, boundstone, gypsum, and silty marl in the Qom area (central Iran). For this purpose, a series of rock mechanics tests were applied and indices such as block punch index, point load strength index (I_s(50)), Schmidt rebound hardness and ultrasonic P-wave velocity (V_p) were determined for these rocks. Then, linear multiple regression and the Sugeno-type fuzzy algorithm were compared to check their accuracy. To improve the accuracy of the Sugeno fuzzy inference system, the weighted if-then rules are extracted. In addition to correlation coefficient, the variance account for (VAF) and the root mean square error (RMSE) were also calculated to check the predictive performances of these models. Obviously, performances of all four indices are reasonably good in predicting UCS (R² > 0.76) from simple regression analyses. However, ultrasonic P-wave velocity does not give appropriate value (R² = 0.67). The VAF and RMSE were calculated as 90% and 10.80 for the uniaxial compressive strengths obtained from the multiple regression model and 90% and 12.82 for uniaxial compressive strengths obtained from the fuzzy inference system, respectively. Thereby, both multiple regression analyses and fuzzy inference system exhibit better predictive performances for UCS than simple regression analyses. The predictive performances of multiple regression analyses and the fuzzy inference system show both models are comparable. Seemingly, fuzzy inference system is an efficient approach to predict UCS of rock materials from indices due to its efficiency in handling uncertainties of test results with transparency.