Geomechanics and Engineering

  • 제34권5호
  • /
  • Pages.547-559
  • /
  • 2023
  • /
  • 2005-307X(pISSN)
  • /
  • 2092-6219(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Mean fragmentation size prediction in an open-pit mine using machine learning techniques and the Kuz-Ram model

  • Seung-Joong Lee (Infra Solution Business Team, Hanwha Corporation / Global) ;
  • Sung-Oong Choi (Department of Energy and Resources Engineering, Kangwon National University)
  • 투고 : 2023.02.05
  • 심사 : 2023.07.31
  • 발행 : 2023.09.10
⟨ 이전 논문 다음 논문 ⟩

초록

We evaluated the applicability of machine learning techniques and the Kuz-Ram model for predicting the mean fragmentation size in open-pit mines. The characteristics of the in-situ rock considered here were uniaxial compressive strength, tensile strength, rock factor, and mean in-situ block size. Seventy field datasets that included these characteristics were collected to predict the mean fragmentation size. Deep neural network, support vector machine, and extreme gradient boosting (XGBoost) models were trained using the data. The performance was evaluated using the root mean squared error (RMSE) and the coefficient of determination (r2). The XGBoost model had the smallest RMSE and the highest r2 value compared with the other models. Additionally, when analyzing the error rate between the measured and predicted values, XGBoost had the lowest error rate. When the Kuz-Ram model was applied, low accuracy was observed owing to the differences in the characteristics of data used for model development. Consequently, the proposed XGBoost model predicted the mean fragmentation size more accurately than other models. If its performance is improved by securing sufficient data in the future, it will be useful for improving the blasting efficiency at the target site.

키워드

과제정보

This research was partly supported by Energy & Mineral Resources Development Association of Korea (EMRD) grant funded by the Korea government (MOTIE) (Educational-Industrial Cooperation Consortium of Energy and Mineral Resources Development-Training Program for Specialists in Smart Mining) and National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT, ME, MOTIE) (NRF-2017M3D8A2085342, the National Strategic Project, Carbon Upcycling).

참고문헌

  1. Adams, T., Demuth, R., Margolin, L. and Nicholas, B. (1983), "Simulation of rock blasting with the shale code", Proceedings of the 1st International Symposium on Rock Fragmentation by Blasting, Lulea, Sweden, August.
  2. Amoako, R., Jha, A. and Zhong, S. (2022), "Rock fragmentation prediction using an artificial neural network and support vector regression hybrid approach", Mining, 2(2), 233-247. https://doi.org/10.3390/mining2020013.
  3. Ash, R.L. (1963), "The mechanics of the rock breakage (Part 1)", Pit and Quarry, 56(2), 98-100.
  4. Bamford, T., Esmaeili, K. and Schoellig, A.P. (2021), "A deep learning approach for rock fragmentation analysis", Int. J. Rock Mech. Min. Sci., 145, 104839. https://doi.org/10.1016/j.ijrmms.2021.104839.
  5. Bengio, Y., Courville, A. and Vincent, P. (2013), "Representation learning: a review and new perspectives", IEEE T. Pattern Anal., 35(8), 1798-1828. https://doi.org/10.1109/tpami.2013.50.
  6. Bergmann, O.R., Wu, F.C. and Edl, J.W. (1974), "Model rock blasting measures effect of delays and hole patterns on rock fragmentation", Int. J. Rock Mech. Min. Sci. Geomech. Abstracts, 175(6), 124-127. https://doi.org/10.1016/0148-9062(74)90634-2.
  7. Burges, C.J.C. (1998), "A tutorial on support vector machines for pattern recognition", Data Mining and Knowledge Discovery, 2, 121-167. https://doi.org/10.1023/a:1009715923555.
  8. Choi, Y., Lee, C., Lee, J. and Kim, J. (2004), "Analysis of in-situ rock conditions for fragmentation prediction in bench blasting", Tunn. Undergr. Sp. Tech., 14(5), 353-362.
  9. Choi, Y.K. (2005), "Determinants analysis and prediction of rock fragmentation in bench blasting", Ph.D. Thesis, Seoul National University, Seoul, Republic of Korea
  10. Cunningham, C. (1983), "The Kuz-Ram model for production of fragmentation from blasting", Proceedings of the 1st International Symposium on Rock Fragmentation by Blasting, Lulea, Sweden, August.
  11. Cunningham, C. (1987), "Fragmentation estimations and the Kuz-Ram model-four years on", Proceedings of the 2nd international symposium on rock fragmentation by blasting Keystone, Colorado, USA, August.
  12. Cunningham, C. (2005), "The Kuz-Ram fragmentation model-20 years on", Proceedings of the Brighton Conference Proceedings, Brighton, UK, October.
  13. Dahl, G.E., Sainath, T.N. and Hinton, G.E. (2013), "Improving deep neural networks for LVCSR using rectified linear units and dropout", Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, May.
  14. Dumakor-Dupey, N.K., Sampurna, A. and Jha, A. (2021), "Advances in blast-induced impact prediction-A review of machine learning applications", Minerals, 11, 601. https://doi.org/10.3390/min11060601.
  15. Ebrahimi, E., Monjezi, M., Khalesi, M.R. and Armaghani, D.J. (2015), "Prediction and optimization of back-break and rock fragmentation using an artificial neural network and a bee colony algorithm", Bull. Eng. Geol. Environ., 75, 27-36. https://doi.org/10.1007/s10064-015-0720-2.
  16. Fukushima, K. (1975), "Cognitron: a self-organizing multilayered neural network", Biol. Cybern., 20(3), 121-136. https://doi.org/10.1007/BF00342633.
  17. Gebreyesus, Y., Dalton, D., Nixon, S., Chiara, D.D. and Chinnici, M. (2023), "Machine learning for data center optimizations: feature selection using Shapley Additive exPlanation (SHAP)", Future Internet, 15(88), 1-18. https://doi.org/10.3390/fi15030088.
  18. Gheibie, S., Aghababaei, H., Hoseinie, S.H. and Pourrahimian, Y. (2009), "Modified Kuz-Ram fragmentation model and its use at the Sungun Copper Mine", Int. J. Rock Mech. Min. Sci., 46(6), 967-973. https://doi.org/10.1016/j.ijrmms.2009.05.003.
  19. Hekmat, A., Munoz, S. and Gomez, R. (2019) "Prediction of rock fragmentation based on a modified Kuz-Ram model", Proceedings of the 27th International Symposium on Mine Planning and Equipment Selection-MPES 2018, New York, NY, USA.
  20. Katsabanis, P.D., Tawadrous, A., Braun, C. and Kennedy, C. (2006), "Timing effects on the fragmentation of small-scale blocks of granodiorite", Int. J. Blast. Fragmentation, 10, 83-93. https://doi.org/10.1080/13855140600858339.
  21. Kim, Y., Hong, J., Shin, J. and Kim, B. (2022), "Shield TBM disc cutter replacement and wear rate prediction using machine learning techniques", Geomech. Eng., 29(3), 249-258. https://doi.org/10.12989/gae.2022.29.3.249.
  22. Koulli, S. and Rustan, P. (1993), "Computerized design and result prediction of bench blasting", Proceedings of the 4th International Symposium on Rock Fragmentation by Blasting, Vienna, Austria, July.
  23. Kuznetsov, V.M. (1973), "The mean diameter of the fragments formed by blasting rock", Soviet Min. Sci., 9, 144-148. https://doi.org/10.1007/bf02506177.
  24. Kwak, N.S. and Ko, T.Y. (2022), "Machine learning-based regression analysis for estimating Cershar abrasivity index", Geomech. Eng., 29(3), 219-228. https://doi.org/10.12989/gae.2022.29.3.219.
  25. Langefors, U. and Kihlstrom, B. (1978), The modern technique of rock blasting, 3rd Ed., Wiley, New York, NY, USA.
  26. Lee, K.B., Shin, H.S., Kim, S.H., Ha, D.M. and Choi, I. (2019), "A study on automatic classification of characterized ground regions on slopes by a deep learning based image segmentation", Tunn. Undergr. Sp. Tech., 29(6), 508-522. https://doi.org/10.7474/TUS.2019.29.6.508.
  27. Lee, S.J. (2016), "Prediction model for rock fragmentation based on field data and 3D measurement of muck pile with UAV", Ph.D. Thesis, Kangwon National University, Chuncheonsi, Ganwondo, Republic of Korea
  28. Li, E., Yang, F., Ren, M., Zhang, X. and Zhou, J. (2021), "Prediction of blasting mean fragment size using support vector regression combined with five optimization algorithms", J. Rock Mech Geotech. Eng., 13(6), 1380-1397. https://doi.org/10.1016/j.jrmge.2021.07.013.
  29. Li, J., Yang, Y., Hu, Y., Zhu, X., Ma, X. and Yuan, X. (2023), "Using multidimensional data to analyze freeway real-time traffic crash precursors based on XGBoost-SHAP algorithm", J. Adv. Transport., 2023, 1-18. https://doi.org/10.1155/2023/5789573.
  30. Lilly, P. (1986), "An empirical method of assessing rock mass blastability", Proceedings of the Large Open Pit Mining Conference, Newman, Australia, October.
  31. Lundberg, S.M. and Lee S.I. (2017), "A unified approach to interpreting model predictions", Proceedings of the 31st Conference on Neural Information Processing System (NIPS 2017), Long Beach, CA, USA. https://doi.org/10.48550/arXiv.1705.07874.
  32. Mahmoodzadeh, A., Nejati, H.R., Mohammadi, M., Ibrahim, H.H., Mohammed, A.H. and Rashid, S. (2022b), "Assessment of wall convergence for tunnels using machine learning techniques", Geomech. Eng., 31(3), 265-279. https://doi.org/10.12989/gae.2022.31.3.265.
  33. Mahmoodzadeh, A., Nejati, H.R., Mohammadi, M., Ibrahim, H.H., Rashidi, S. and Mohammed, A.H., (2022a), "Meta-heuristic optimization algorithms for prediction of fly-rock in the blasting operation of open-pit mines", Geomech. Eng., 30(6), 489-502. https://doi.org/10.12989/gae.2022.30.6.489.
  34. McFall, G.P., Bohn, L., Gee, M., Drouin, S.M., Fah, H., Han, W., Li, L., Camicioli, R. and Dixon, R.A. (2023), "Identifying key multi-modal predictors of incipient dementia in Parkinson's disease: a machine learning analysis and tree SHAP interpretation", Front. Aging Neurosci., 15, 1-16. https://doi.org/10.3389/fnagi.2023.1124232.
  35. McHugh, S. (1983), "Computational simulations of dynamically induced fracture and fragmentation", Proceedings of the 1st International Symposium on Rock Fragmentation by Blasting, Lulea, Sweden, August.
  36. Singh, P.K., Roy, M.P., Paswan, R.K., Sarim, M., Kumar, S. and Ranjan, R. (2016), "Rock fragmentation control in opencast blasting", J. Rock Mech. Geotech. Eng., 8(2), 225-237. https://doi.org/10.1016/j.jrmge.2015.10.005.
  37. Vapnik, V. (1999), The nature of statistical learning theory, 2nd Ed., Springer science & business media, New York, NY, USA.