M. Kamran
Abstract
Drillability is one of the significant issues in rock engineering. The drilling rate index (DRI) is an important tool in analyzing the drillability of rocks. Several efforts have been made by the researchers to correlate and evaluate DRI of rocks. The ensemble learning methods including the decision ...
Read More
Drillability is one of the significant issues in rock engineering. The drilling rate index (DRI) is an important tool in analyzing the drillability of rocks. Several efforts have been made by the researchers to correlate and evaluate DRI of rocks. The ensemble learning methods including the decision tree (DT), adaptive boosting (AdaBoost), and random forest (RF) are employed in this research work in order to predict DRI of rocks. A drillability database with four parameters is compiled in this work. A relationship between the input parameters and DRI is established using the simple regression analysis. In order to train the model, different mechanical properties of rocks incorporating the uniaxial compressive strength (UCS), Brazilian tensile strength (BTS), brittleness test (S20), and sievers’ J-miniature drill value (Sj) are taken as the input variables. The original DRI database is randomly divided into the training and test sets with an 80/20 sampling method. Various algorithms are developed, and consequently, several approaches are followed in order to predict DRI of the rock samples. The model performance has revealed that RF predicts DRI with a high accuracy rate. Besides, the Monte Carlo simulations exhibit that this approach is more reliable in predicting the probability distribution of DRI. Therefore, the proposed model can be practiced for the stability risk management and the investigative design of DRI.
S. Hadi Hosseini; Mohammad Ataie; Hamid Aghababaie
Abstract
In this paper, after collecting the rock samples from eight mines and one high way slope, the tests for determination of dry density, Uniaxial Compressive Strength, tensile Strength (Brazilian Test), elastic modulus, Schmidt hammer rebound number have been done on samples. In addition, in order to calculating ...
Read More
In this paper, after collecting the rock samples from eight mines and one high way slope, the tests for determination of dry density, Uniaxial Compressive Strength, tensile Strength (Brazilian Test), elastic modulus, Schmidt hammer rebound number have been done on samples. In addition, in order to calculating the mean size of rock grains, quartz content, hardness and abrasivity, a thin sections of each rock have been studied. Then, the rock samples have been drilled using actual pneumatic top hammer drilling machine with 3½ inches diameter cross type bit. The regression analyses showed that Brazilian tensile strength (R2=0.81), uniaxial compressive strength (R2=0.77) and Schmidt hammer rebound (R2=0.73) are the most effective parameters on drilling rate and have a partly good correlation with drilling rate.
