Application of Reinforcement Machine Learning Models in Predicting Penetration Rate of Rotary Blast Holes

Document Type : Research - Paper

Authors

1 M.Sc, Dept. of Mining Engineering, Tarbiat Modares University, Tehran, Iran

2 Ph.D Student, Dept. of Mining Engineering, Tarbiat Modares University, Tehran, Iran

3 Associate Professor, Dept. of Mining Engineering, University of Hamedan, Hamedan, Iran

Abstract

Drilling with the help of a rotary drilling machine is an important tool for exploration and extraction in mines. On the other hand, estimating the costs and efficiency of the rotary drilling machine is a fundamental step in the design of mining and construction projects. Drilling Penetration Rate (PR) is a suitable indicator for estimating the costs and efficiency of rotary drilling rigs. Therefore, achieving the optimal amount of PR in the rotary drilling machine will reduce costs and increase the efficiency of the rotary drilling machine. For this purpose, in this article, one of the enhanced Machine Learning (ML) methods that combines Light Gradient Boosting (LGB) and Random Forest (RF) with Meta-Heuristic algorithms (MH), including Grey Wolf Optimizer (GWO) and Harris hawk (HHO), has been done to estimate PR. In order to validate the developed models, the models were implemented on the collected data sets. The dataset, including 7 independent input variables, was used. The independent input variables are drilling Diameter in inches (D), rotational speed in Revolutions Per Minute (RPM), Weight On Bit (WOB), Uniaxial Compressive Strength (UCS) of rock in megapascals, Tensile (T) strength of rock in terms of megapascals, the Joints Spacing (JS) in the ground in centimeters, and the relative accuracy of the Joints in Degrees (JD). The obtained results show that the RF-GWO method (R2 = 0.987 and RMSE = 3.059) is more accurate than LGB-GWO (0.912 and 8.045), LGB-HHO (0.917 and 7.831), and RF-HHO (0.912 and 8.044) in training data. Also, sensitivity analysis studies indicate that RPM and JD parameters have the most and least effect on the PR of the rotary drilling machine, respectively.

Keywords

Main Subjects

References

  1. Kazemi, M. M. K., Nabavi, Z., and Armaghani, D. J. (2024). “A novel hybrid XGBoost methodology in predicting Penetration rate of rotary based on rock-mass and material pPRerties”. Arabian Journal for Science and Engineering, 49: 5225-5241. DOI: https://doi.org/10.1007/s13369-023-08360-0.
  2. Najjarpour, M., Jalalifar, H., and Norouzi-Apourvari, S. (2022). “Half a century experience in rate of penetration management: Application of machine learning methods and optimization algorithms - A review”. Journal of Petroleum Science and Engineering, 208: 109575. DOI: https://doi.org/10.1016/j.petrol.2021.109575.
  3. Darbor, M., Faramarzi, L., and Sharifzadeh, M. (2019). “Performance assessment of rotary drilling using non-linear multiple regression analysis and multilayer perceptron neural network”. Bulletin of Engineering Geology and the Environment, 78: 1501-1513. DOI: https://doi.org/10.1007/s10064-017-1192-3.
  4. Sharifinasab, M. H., Emami-Niri, M., and Masroor, M. (2023). “Developing GAN-boosted Artificial Neural Networks to model the rate of drilling bit penetration”. Applied Soft Computing, 136: 110067. DOI: https://doi.org/10.1016/j.asoc.2023.110067.
  5. Shaygan, K., and Jamshidi, S. (2023). “Prediction of rate of penetration in directional drilling using data mining techniques”. Geoenergy Science and Engineering, 221: 111293. DOI: https://doi.org/10.1016/j.petrol.2022.111293.
  6. Mirjalili, S. A., Mirjalili, S. M., and Lewis, A. (2014). “Grey Wolf Optimizer”. Advances in Engineering Software, 69: 46-61. DOI: http://dx.doi.org/10.1016/j.advengsoft.2013.12.007.
  7. Zhou, Y., Chen, X., Wu, M., and Cao, W. (2023). “A novel optimization method for geological drilling vertical well”. Information Sciences, 634: 550-563. DOI: https://doi.org/10.1016/j.ins.2023.03.082.
  8. Mahmoodzadeh, A., Nejati, H. R., Mohammadi, M., Ibrahim, H. H., Rashidi, S., and Rashid, T. A. (2022). “Forecasting tunnel boring machine penetration rate using LSTM deep neural network optimized by grey wolf optimization algorithm”. Expert Systems with Applications, 209: 118303. DOI: https://doi.org/10.1016/j.eswa.2022.118303.
  9. Astarita, V., Haghshenas, S. S., Guido, G., and Vitale, A. (2023). “Developing new hybrid grey wolf optimization-based artificial neural network for predicting road crash severity”. Transportation Engineering, 12: 100164. DOI: https://doi.org/10.1016/j.treng.2023.100164.
  10. Ghalambaz, M., Jalilzadeh-Yengejeh, R., and Davami, A. H. (2021). “Building energy optimization using Grey Wolf Optimizer (GWO)”. Case Studies in Thermal Engineering, 27: 101250. DOI: https://doi.org/10.1016/j.csite.2021.101250.
  11. Brownlee, J. (2020). “Ensemble learning algorithms with Python: Make better predictions with bagging, boosting, and stacking”. Machine Learning Mastery, Accessed 2021 Apr 26. https://machinelearningmastery.com/wp-content/uploads/2021/03/ensemble_learning_algorithms_with_python_sample.pdf.
  12. Li, Y., Xie, Y., Yu, C., Yu, F., Jiang, B., and Khushi, M. (2017). “Feature importance recap and stacking models for forex price prediction”. arXiv. DOI: https://doi.org/10.48550/arXiv.2107.14092.
  13. Torky, M., Bakhiet, A., Bakrey, M., Ahmed-Adel, I., and Ahmed, I. B. S. (2023). “Recognizing Safe Drinking Water and Predicting Water Quality Index using Machine Learning Framework”. International Journal of Advanced Computer Science and Applications (IJACSA), 14(1): 23-33. DOI: https://doi.org/10.14569/IJACSA.2023.0140103.
  14. Mirjalili, S., Aljarah, I., Mafarja, M., Heidari, A. A., and Faris, H. (2020). “Grey Wolf Optimizer: Theory, Literature Review, and Application in Computational Fluid Dynamics Problems”. In: Mirjalili, S., Song Dong, J., and Lewis, A. (Eds.), Nature-Inspired Optimizers. Studies in Computational Intelligence, Vol. 811, Springer, Cham. DOI: https://doi.org/10.1007/978-3-030-12127-3_6.
  15. Faris, H., Aljarah, I., Al-Betar, M. A., and Mirjalili, S. (2018). “Grey wolf optimizer: a review of recent variants and applications”. Neural Computing and Applications, 30: 413-435. DOI: https://doi.org/10.1007/s00521-017-3272-5.
  16. Zhao, G., Wang, H., Jia, D., and Wang, Q. (2019). “Feature selection of grey wolf optimizer based on quantum computing and uncertain symmetry rough set”. Symmetry, 11: 1470. DOI: https://doi.org/10.3390/sym11121470.
  17. Banaie-Dezfouli, M., Nadimi-Shahraki, M. H., and Beheshti, Z. (2021). “R-GWO: Representative-based grey wolf optimizer for solving engineering problems”. Applied Soft Computing, 106: 107328. DOI: https://doi.org/10.1016/j.asoc.2021.107328.
  18. Yamni, M., Daoui, A., Karmouni, H., Elmalih, S., Ben-fares, A., Sayyouri, M., Qjidaa, H., Maaroufi, M., Alami, B., and Jamil, M. O. (2023). “Copyright protection of multiple CT images using Octonion Krawtchouk moments and grey Wolf optimizer”. Journal of the Franklin Institute, 360: 4719-4752. DOI: https://doi.org/10.1016/j.jfranklin.2023.03.008.
  19. Duan, Y., and Yu, X. (2023). “A collaboration-based hybrid GWO-SCA optimizer for engineering optimization problems”. Expert Systems with Applications, 213: 119017. DOI: https://doi.org/10.1016/j.eswa.2022.119017.
  20. Lefebvre, L., Whittle, P., Lascaris, E., and Finkelstein, A. (1997). “Feeding innovations and forebrain size in birds”. Animal Behaviour, 53(3): 549-560. DOI: https://doi.org/10.1006/anbe.1996.0330.
  21. Hariprasad, C. H., Kayalvizhi, R., and Karthik, N. (2022). “Optimization for Position and Rating of Distributed Generating units using Harris Hawk Optimization Algorithm to Reduce Power Losses”. Journal of Electrical Systems, 18(2): 205.
  22. Yu, Z., Shi, X., Zhou, J., Chen, X., and Qiu, X. (2020). “Effective Assessment of Blast-Induced Ground Vibration Using an Optimized Random Forest Model Based on a Harris Hawks Optimization Algorithm”. Applied Sciences, 10: 1403. DOI: https://doi.org/10.3390/app10041403.
  23. Jinyan, Y., Yongbai, S., Yanli, C., and Xiaoying, Z. (2022). “A Novel Ensemble of Arithmetic Optimization Algorithm and Harris Hawks Optimization for Solving Industrial Engineering Optimization Problems”. Journal of Machines, 10(8): 602. DOI: https://doi.org/10.3390/machines10080602.
  24. فیاضی، ع.، دوست محمدی، ر.؛ 1401؛ "بررسی استفاده از ترسیب میکروبی کلسیم‌کربنات در ترمیم سنگ‌های ساختمانی". نشریه مهندسی معدن، دوره 17، شماره 54، ص 62-40. DOI: https://doi.org/10.22034/IJME.2021.141646.1841.
  25. Fayyazi, A., and Doostmohammadi, R. (2022). “Investigation of the Effective Parameters of Travertine Stones Healing Using Bio-Grouting”. Journal of Mining Science, 58: 1069-1083. DOI: https://doi.org/10.1134/S1062739122060217.
  26. Nabavi, Z., Mirzehi, M., Dehghani, H., and Ashtari, P. (2023). “A hybrid model for Backbreak prediction using XGBoost machine learning and metaheuristic algorithms in Chadormalu iron mine”. Journal of Mining and Environment, 14(2): 689-712. DOI: https://doi.org/10.22044/jme.2023.12796.2323.
  27. Mirzehi Kalateh Kazemi, M., Nabavi, Z., and Khandelwal, M. (2023). “Prediction of blast-induced air overpressure using a hybrid machine learning model and gene expression programming (GEP): A case study from an iron ore mine”. AIMS Geosciences, 9(2): 357-381. DOI: https://doi.org/10.3934/geosci.2023019.
Journal of Mineral Resources Engineering
Volume 10, Issue 2 - Serial Number 36
September 2025
Pages 91-115

Files

History

  • Receive Date: 02 June 2024
  • Revise Date: 19 August 2025
  • Accept Date: 27 November 2024

Share

How to cite

Statistics