Akademik Veri Yönetim Sistemi
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, cilt.84, sa.11, 2025 (SCI-Expanded)
In underground development gallery and tunnelling operations, efficiency in excavation mainly depends on drillability properties of the formation to be excavated. This information can be obtained by detailed and costly field experiments. In this study, it is investigated whether drillability properties of rocks can be determined rapidly and reliably depending on the brittleness index of rocks. There exist many equations in literature to compute brittleness index of rocks. In this study, a new equation has been proposed for brittleness index. Effectiveness of this equation has been tested using linear and multiple regression models and compared with other brittleness equations in literature. In addition to brittleness index, effect of uniaxial compressive strength, tensile strength, three other brittleness equations, shore hardness and density variables are examined on drilling rate index value of rocks. Univariate regression, multiple regression and artificial neural networks are employed to estimate drilling rate index. Within the results, univariate regression models and first degree multiple regression models have provided poor correlations. However, second degree multiple regression and artificial neural network models are found to be effective in estimating drilling rate index. Within second degree multiple regression models R2 values up to 99% could be achieved. ANN modeling turned out to be even more successful. Among the seven set of ANN experiments, 99% of R2 is achieved in six of the sets. These results have shown that correlation between DRI and other variables cannot be represented simply by linear relations but is dependent on more complex and higher order relations.