Prediction of rock drillability using gray wolf optimization and teaching-learning-based optimization techniques

An important index to evaluate the rock drilling ability in mines, tunnel drilling and underground drilling is the drilling rate index (DRI). Due to the complexity and nonlinearity of mechanical and physical properties of rocks, there are many uncertainties in DRI evaluation. For this reason, teaching-learning-based optimization (TLBO) and gray wolf optimization (GWO) have been used to consider uncertainties and establish a precise nonlinear relationship in the estimation of the DRI. In this study, 32 different rock types included metamorphic, igneous and sedimentary rocks were investigated in the laboratory to investigate the relationships between the DRI and input parameters. The modeling results show that the relationships determined for estimating the DRI by TLBO and GWO algorithms are accurate and close to the real value. It can also be concluded that the use of optimization algorithms to predict the DRI is very efficient.