Prediksi Kecepatan Pengeboran Menggunakan Regresi LASSO pada Lapisan Interburden Batubara
DOI:
https://doi.org/10.29303/goescienceed.v7i3.2280Keywords:
Pulldown Pressure, Rotational Pressure, Rate of Penetration, LASSO Regression, Pit Bendili.Abstract
Rotary drilling operations at Pit Bendili, PT Kaltim Prima Coal, require operational parameter optimization to achieve the company’s target Rate of Penetration (ROP) of 110 m/h. Drilling speed is significantly influenced by the interaction between mechanical operational factors and rock characteristics. Pit Bendili has an average Uniaxial Compressive Strength (UCS) of 15.46 MPa, classified as weak rock, yet hardness variations between coal seams cause workload fluctuations. This study aims to model and analyze the combination of pulldown pressure (PP) and rotational pressure (RP) on the velocity of penetration (VP) to meet the ROP target. Operational parameters were modeled using the Python-based Least Absolute Shrinkage and Selection Operator (LASSO) Regression method. Analysis of 134 blast hole operational datasets yielded a Mean Absolute Percentage Error (MAPE) of 7.9%, indicating excellent predictive model accuracy. Through this LASSO model, PP and RP combinations can be precisely adjusted to ensure drilling velocity consistently meets or exceeds the 110 m/h target across various rock layers.
References
Bieniawski, Z.T. (1989). Engineering Rock Mass Classifications: A Complete Manual for Engineers and Geologists in Mining, Civil, and Petroleum Engineering. New York, USA: John Wiley & Sons.
Denis, D.J. (2026). Multivariate Statistics and Machine Learning: An Introduction to Applied Data Science Using R and Python. Boca Raton, USA: CRC Press.
Friedman, J., Hastie, T., & Tibshirani, R. (2010). Regularization Paths for Generalized Linear Models via Coordinate Descent. Journal of Statistical Software, 33(1), 1–22. doi: https://doi.org/10.18637/jss.v033.i01
Gokhale, B. V. (2011). Rotary Drilling and Blasting in Large Surface Mines. CRC Press Balkema.
Hair, J.F., Black, W.C., Babin, B.J., & Anderson, R.E. (2014). Multivariate Data Analysis (7th ed.). Harlow, England: Pearson Education Limited.
IBM Corporation. (2025). LASSO Regression Analysis and L1 Regularization Path User Guide. New York, USA: IBM Technical Support.
Jimeno, C.L., Jimeno, E.L., & Carcedo, F.J.A. (1995). Drilling and Blasting of Rocks. Rotterdam, Netherlands: A.A. Balkema Publishers.
Kahraman, S., Bilgin, N., & Feridunoglu, C. (2003). Dominant Rock Properties Affecting the Penetration Rate of Percussive Drills. International Journal of Rock Mechanics and Mining Sciences, 40(5), 711–723.
Lewis, C.D. (1982). Industrial and Business Forecasting Methods. London, England: Butterworth Scientific.
Montgomery, D.C., Peck, E.A., & Vining, G.G. (2012). Introduction to Linear Regression Analysis (5th ed.). Hoboken, USA: John Wiley & Sons.
Sandvik Mining and Rock Technology. (2020). Technical specification and operational manual for rotary blasthole drill Sandvik D55SP. Alachua, USA: Sandvik Product Support.
Schlumberger. (2018). Rock mechanics and geomechanics properties classification guidelines. Houston, USA: Schlumberger Technical Information Center.
Tibshirani, R. (1996). Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society: Series B (Methodological), 58(1), 267–288. doi: https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
