Izvorni znanstveni članak
https://doi.org/10.17794/rgn.2026.5.12
BENCHMARKING MACHINE LEARNING MODELS FOR PENETRATION RATE PREDICTION IN ROTARY DRILLING: A CASE STUDY FROM THE SUNGUN COPPER MINE
Ali Nemati Vardin
; Department of Mining Engineering, Faculty of Engineering, Tarbiat Modares University, Tehran, Iran
Masoud Monjezi
; Department of Mining Engineering, Faculty of Engineering, Tarbiat Modares University, Tehran, Iran
Mojtaba Rezakhah
; Department of Mining Engineering, Faculty of Engineering, Tarbiat Modares University, Tehran, Iran
Manoj Khandelwal
; Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, VIC, Australia; Laboratory of Sustainable Development in Natural Resources and Environment, Institute for Advanced Study in Technology, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam; Faculty of Environment and Labour Safety, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam
*
Hasel Amini Khoshalan
; Department of Mining Engineering, Faculty of Engineering, University of Kurdistan, Sanandaj, Iran
* Dopisni autor.
Sažetak
Mining operations require an accurate prediction of rotary drilling penetration rate (ROP) to optimize efficiency and reduce costs. ROP estimation is challenging due to complex, nonlinear relationships among rock properties, equipment specifications, and operational parameters. This study applies six machine learning models, Random Forest, CatBoost, LightGBM, XGBoost, Support Vector Machine, and Extra Trees to forecast ROP using data from 85 drillholes at the Sungun copper mine, Iran. Input features include mining rock mass rating, Schmidt hammer rebound number, rotation pressure, and weight on bit. The Extra Trees model achieved the best performance, with R² values of 1 (training) and 0.93 (testing) and RMSE of 0 and 0.937, respectively, demonstrating high accuracy and generalization. The results confirm that machine learning, particularly Extra Trees, can effectively model complex ROP dependencies, enabling improved equipment selection, operational planning, and cost estimation in rotary drilling.
Ključne riječi
Rate of penetration; Drilling; Mining; Machine learning models; Sungun copper mine
Hrčak ID:
352878
URI
Datum izdavanja:
27.10.2026.
Posjeta: 0 *