Rock abrasiveness prediction by multivariable regression and random forest algorithm

In rock tunneling, the interaction between excavation tools and rocks will result in tool wear or deterioration, with the abrasiveness of rocks playing a significant role in this process. To assess the abrasiveness of rocks, Cerchar abrasivity tests and rock drilling tests were conducted on ten rock blocks. Initially, the Cerchar abrasivity index (CAI) of rock samples was obtained based on Cerchar abrasivity tests. The transformational relations between the CAI and other hardness and strength indexes (weighted hardness, equivalent quartz content, uniaxial compressive strength, etc.) were established using the multivariable regression. Afterward, measurement-while-drilling (MWD) data were collected during rock drilling tests. The MWD data and CAI of the ten rocks were integrated into a dataset, from which the MWD-CAI model was developed using the random forest algorithm. The results show that rock abrasiveness is more closely associated with hardness, while the correlation with compressive strength appears less significant. The transformational relations enable to predict CAI values by rock hardness and strength. Moreover, the MWD-CAI model is capable of predicting CAI values using drilling data. The findings can provide a reference for the quick assessment of rock abrasiveness.