Exploitation
Ali Nemati vardin; Masoud Monjezi; Hasel Amini Khoshalan; Jafar Hamidi Khademi; Mojtaba Rezakhah
Abstract
Drilling is one of the most important operations in open-pit mining, and the penetration rate of drill bits is a key performance measure. This paper presents research on the penetration rate of drill bits based on mining rock mass rating, thrust pressure (weight on bit), rotational pressure, and Schmidt ...
Read More
Drilling is one of the most important operations in open-pit mining, and the penetration rate of drill bits is a key performance measure. This paper presents research on the penetration rate of drill bits based on mining rock mass rating, thrust pressure (weight on bit), rotational pressure, and Schmidt hammer rebound hardness. To achieve this, a dataset comprising the drilling operations of 85 blastholes from the Sungun copper mine in Iran was prepared and analyzed using statistical and intelligent methods. Multivariate regression analysis and artificial neural networks developed in Python, utilizing optimization algorithms such as gradient descent, stochastic gradient descent, and adaptive moment estimation, were applied to predict the penetration rate of drill bits in this study. The coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE) served as performance indicators to evaluate the methods employed. Among these, the adaptive moment estimation (Adam)-based model exhibited superior performance compared to alternative models, achieving values of R² = 0.96, MAE = 4.55, and RMSE = 4.30. Furthermore, the sensitivity analysis revealed that mining rock mass rating is the most influential factor on the rate of penetration, while thrust pressure has the least impact.
Yahia ElSayed Khamis; Shady Galal El-Rammah; Adel M Salem
Abstract
The rate of penetration plays a key role in maximizing drilling efficiency, so it is essential for the drilling process optimization and management. Traditional mathematical models have been used with some success to predict the rate of penetration in drilling. Due to the high complexity and non-linear ...
Read More
The rate of penetration plays a key role in maximizing drilling efficiency, so it is essential for the drilling process optimization and management. Traditional mathematical models have been used with some success to predict the rate of penetration in drilling. Due to the high complexity and non-linear behavior of drilling parameters with the rate of penetration, these mathematical models cannot accurately and comprehensively predict the rate of penetration. Machine learning (ML) seems to be an attractive alternative to model this complicated physical process. This research paper introduces new data-driven models used to predict ROP using different parameters such as (depth, weight on bit (WOB), revolution per minute (RPM), Torque (T), standpipe pressure (SPP), flow in pump (pumping flow rate(Q), mud weight, hours on bit (HOB), revolutions on bit, bit diameter, total flow area (TFA), pore pressure, overburden pressure, and pit volume). Data-driven models are built using two different machine learning techniques, using 1771 raw real field data. The coding is built using the python programming language. The k-nearest neighbors (KNN) model predicting ROP for the training dataset show a correlation coefficient (R2) of 0.94. The multi-layer perceptron (MLP) model predicting ROP for the training dataset show a correlation coefficient (R2) of 0.98. We can conclude that MLP has a better accuracy, and removing outliers enhances model performance.
Sh. Khosravimanesh; M. Cheraghi Seifabad; R. Mikaeil; R. Bagherpour
Abstract
In most rock drilling operations, the low rate of penetration (ROP) can be primarily attributed to the presence of the cuttings produced during drilling and the thermal stresses caused by friction at the bit-rock interface, which can be exacerbated with the increasing strength, hardness, and abrasivity ...
Read More
In most rock drilling operations, the low rate of penetration (ROP) can be primarily attributed to the presence of the cuttings produced during drilling and the thermal stresses caused by friction at the bit-rock interface, which can be exacerbated with the increasing strength, hardness, and abrasivity of the drilled rock. In order to improve ROP, drill bit lifetime, and cutting power, it is necessary to minimize the process forces due to the mechanical bit-rock interaction and the thermal stresses generated in the drill hole. Any improvement in these areas is extremely important from both the technical and the economic perspectives. This improvement can be achieved by the use of appropriate cooling/lubricating fluids in the drilling process in order to increase ROP, reduce the temperature of the drilling environment, and create a clean drill hole free of cuttings. In this work, a series of laboratory drilling tests are performed to investigate and compare ROP in the drilling of seven samples of hard and soft rock in the presence of six different cooling-lubricating fluids. The drilling tests are performed on the cubic specimens with a laboratory-scale drilling rig at several different rotation speeds and thrust forces. The statistical analyses are performed in order to investigate the relationship between ROP and the mechanical properties of the rock, properties of the fluid, and machining parameters of the drilling rig. These analyses show that under similar conditions in terms of mechanical properties of the rock using Syncool with a concentration of 1:100 and soap water with a concentration of 1:120 instead of pure water leads to the average 31% and 37% increased ROP in granite, 36% and 43% increased ROP in marble, and 47% and 61% increased ROP in travertine, respectively. These results demonstrate the good performance of these cooling/lubricating fluids in increasing ROP.
