میز خدمت الکترونیک
دوره ویراستاری

  اخبار و اعلانات

 آمار

تعداد نشریات127
تعداد شماره‌ها7,140
تعداد مقالات76,843
تعداد مشاهده مقاله154,469,560
تعداد دریافت فایل اصل مقاله116,530,850
Sharifi Teshnizi, Ebrahim, Ghafoori, Mohammad, Lashkaripour, Gholam Reza, Khademi Hamidi, Jafar, Yousefi, Amir Hossein. (1404). Assessment and Prediction of Rock Drillability in Hard Granitic Rocks Using Experimental Testing and Machine Learning Models. , (), -. doi: 10.22059/geope.2026.401662.648840
Ebrahim Sharifi Teshnizi; Mohammad Ghafoori; Gholam Reza Lashkaripour; Jafar Khademi Hamidi; Amir Hossein Yousefi. "Assessment and Prediction of Rock Drillability in Hard Granitic Rocks Using Experimental Testing and Machine Learning Models". , , , 1404, -. doi: 10.22059/geope.2026.401662.648840
Sharifi Teshnizi, Ebrahim, Ghafoori, Mohammad, Lashkaripour, Gholam Reza, Khademi Hamidi, Jafar, Yousefi, Amir Hossein. (1404). 'Assessment and Prediction of Rock Drillability in Hard Granitic Rocks Using Experimental Testing and Machine Learning Models', , (), pp. -. doi: 10.22059/geope.2026.401662.648840
Sharifi Teshnizi, Ebrahim, Ghafoori, Mohammad, Lashkaripour, Gholam Reza, Khademi Hamidi, Jafar, Yousefi, Amir Hossein. Assessment and Prediction of Rock Drillability in Hard Granitic Rocks Using Experimental Testing and Machine Learning Models. , 1404; (): -. doi: 10.22059/geope.2026.401662.648840

Assessment and Prediction of Rock Drillability in Hard Granitic Rocks Using Experimental Testing and Machine Learning Models

Geopersia
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 04 بهمن 1404    اصل مقاله (7.57 M)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22059/geope.2026.401662.648840
نویسندگان
Ebrahim Sharifi Teshnizi* 1؛ Mohammad Ghafoori1؛ Gholam Reza Lashkaripour1؛ Jafar Khademi Hamidi2؛ Amir Hossein Yousefi3
1Department of Geology, Faculty of Science, Ferdowsi University of Mashhad, Mashhad, P.O. Box 91775-1436, Iran
2Department of Mining Engineering, Faculty of Engineering, Tarbiat Modares University, Tehran, Iran
3Department of Civil Engineering, Shahi.C., Islamic Azad University, Shahinshahr, Iran
چکیده
Accurate prediction of rock drillability is critical for optimizing tunneling, mining, and excavation operations in hard rock environments. This study investigates the drillability of granitic rocks by integrating petrographic, physical, mechanical, and abrasivity parameters with both conventional regression and machine learning (ML) approaches. Laboratory tests were conducted on samples from six granitic rock groups, measuring properties such as brittleness, hardness, abrasivity indices, and the Drilling Rate Index (DRI). Statistical analyses, including linear and nonlinear regression, revealed
strong nonlinear relationships between DRI and engineering parameters, with R² values up to 0.95. Machine learning models, particularly Random Forest (RF) and Artificial Neural Networks (ANN), were applied independently, with RF achieving superior predictive performance (R² > 0.99) and lower error indices compared to ANN and regression models. The study also highlights the influence of different rock groups on model performance and discusses limitations related to dataset scale, in situ conditions, and model generalization. These results confirm that integrating laboratory measurements with ML techniques provides a reliable framework for predicting rock drillability, offering practical
guidance for excavation planning, equipment selection, and operational efficiency.
کلیدواژه‌ها
Granitic rocks؛ Drilling Rate Index (DRI)؛ Machine Learning؛ Random Forest؛ Artificial Neural Networks؛ Rock drillability؛ Abrasivity؛ Rock mechanics
آمار
تعداد مشاهده مقاله: 181
تعداد دریافت فایل اصل مقاله: 61





سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب