Unplanned dilution prediction in open stope mining: developing new design charts using Artificial Neural Network classifier

• Autorzy: Korigov Sultan , Adoko Amoussou Coffi , Sengani Fhatuwani

Identyfikatory

DOI

10.46873/2300-3960.1356

• Języki publikacji: EN

Abstrakty

EN

Minimizing dilution is essential in open stope mine design as excessive unplanned dilution can compromise the operation's profitability. One of the main challenges associated with the empirical dilution graph method used to design open stopes is how to determine the boundary of the dilution zones objectively. Hence, this paper explores the implementation of machine learning classifiers to bridge this gap in the conventional dilution graph method. Stope performance data consisting of the stope dilution (unplanned dilution), the modified stability number, and the hydraulic radius were compiled from a mine located in Kazakhstan. First, the conventional dilution graph methods were used to assess the dilution. Next, a Feed-Forward Neural Network (FFNN) classifier was implemented to predict each level of dilution. Overall, the FFNN results indicated that 97% of the stope surfaces were correctly classified, indicating an excellent classification performance, while the conventional dilution graph method did not show a good performance. In addition, the outputs of the FFNN were used to plot new dilution graphs with a probabilistic interpretation illustrating its practicability. It was concluded that the FFNN-based classifier could be a useful tool for open stope design in underground mines.

Słowa kluczowe

EN

open stope; dilution graph; stope overbreak; neural network classifier

PL

system otwartych komór; klasyfikator sieci neuronowej

• Wydawca: Elsevier ; Główny Instytut Górnictwa
• Czasopismo: Journal of Sustainable Mining
• Rocznik: 2022
• Tom: Vol. 21, iss. 2
• Strony: 157--168
• Opis fizyczny: Bibliogr. 41 poz.

Twórcy

autor

Korigov Sultan

• Nazarbayev University, School of Mining and Geosciences

• https://orcid.org/0000-0002-9932-0180

autor

Adoko Amoussou Coffi

• Nazarbayev University, School of Mining and Geosciences

• https://orcid.org/0000-0003-1396-7811

autor

Sengani Fhatuwani

• University of Limpopo, Department of Geology and Mining

• https://orcid.org/0000-0003-4886-1072

Bibliografia

• [1] Pakalnis RT, Poulin R, Hadjigeorgiou J. Quantifying the cost of dilution in underground mines. Min Eng 1995;47:1136-41.
• [2] Potvin Y, Hudyma M. Open stope mining in Canada. In: MassMin 2000. Brisbane, Queensland, Australia: Australasian Institute of Mining and Metallurgy; 2000.
• [3] Henning JG, Mitri HS. Numerical modelling of ore dilution in blasthole stoping. Int J Rock Mech Min Sci 2007;44:692-703.
• [4] Adoko AC, Yakubov K, Alipov A. Mine stope performance assessment in unfavorable rock mass conditions using neural network-based classifiers. In: YSRM2019 & REIF2019. Okinawa, Japan: ISRM & The Japanese Society for Rock Mechanics; 2019.
• [5] Capes GW. Open stope hangingwall design based on general and detailed data collection in rock masses with unfavourable hangingwall conditions. Ann Arbor: The University of Saskatchewan; 2009. p. 301 (Canada).
• [6] Wang J, Milne D, Wegner L, Reeves M. Numerical evaluation of the effects of stress and excavation surface geometry on the zone of relaxation around open stope hanging walls. Int J Rock Mech Min Sci 2007;44:289-98.
• [7] El Mouhabbis HZ. Effect of stope construction parameters on ore dilution in narrow vein mining. In: Department of mining and materials engineering. Montreal, Canada: McGill University; 2013.
• [8] Heidarzadeh S, Saeidi A, Rouleau A. Use of probabilistic numerical modeling to evaluate the effect of geomechanical parameter variability on the probability of open-stope failure: a case study of the niobec mine. Quebec (Canada): Rock Mechanics and Rock Engineering; 2019.
• [9] Diederichs MS, Kaiser PK. Tensile strength and abutment relaxation as failure control mechanisms in underground excavations. Int J Rock Mech Min Sci 1999;36:69-96.
• [10] Cepuritis PM, Villaescusa E, Beck DA, Varden R. Back analysis of over-break in a longhole open stope operation using non-linear elasto-plastic numerical modelling. In: 44th U.S. Rock mechanics symposium and 5th U.S.-Canada rock mechanics symposium. Salt Lake City, Utah: American Rock Mechanics Association; 2010. p. 11.
• [11] Pakalnis R. Empirical design methods in practice. In: Potvin Y, editor. Proceedings of the international seminar on design methods in underground mining. Perth: Australian Centre for Geomechanics; 2015. p. 37-56.
• [12] Potvin Y. Empirical open stope design in Canada. The University of British Columbia; 1988.
• [13] Clark LM. Minimizing dilution in open stope mining with a focus on stope design and narrow vein longhole blasting. In: Mining engineering. Vancouver: University of British Columbia; 1998.
• [14] Mathews K, Hoek E, Wyllie D, Stewart S. Prediction of stable excavation spans at depths below 1000m in hard rock mines CANMET Report, DSS Serial No. OSQ80-00081. 1981.
• [15] Zhao X, Niu J a. Method of predicting ore dilution based on a neural network and its application. Sustainability 2020;12.
• [16] Jang H, Topal E, Kawamura Y. Illumination of parameter contributions on uneven break phenomenon in underground stoping mines. Int J Min Sci Technol 2016;26:1095-100.
• [17] Zhalel M, Adoko AC, Korigov S. An approach to stope stability assessment in open stope mining environment. In: 54th U.S. Rock mechanics/geomechanics symposium, (physical event cancelled: American rock mechanics association; 2020. p. 6.
• [18] Mawdesley C, Trueman R, Whiten WJ. Extending the Mathews stability graph for open-stope design. Min Technol 2001;110:27-39.
• [19] Papaioanou A, Suorineni FT. Development of a generalized dilution-based stability graph for open stope design. Min Technol 2016;125:121-8.
• [20] Jang H, Topal E, Kawamura Y. Unplanned dilution and ore loss prediction in longhole stoping mines via multiple regression and artificial neural network analyses. J S Afr Inst Min Metall 2015;115:449-56.
• [21] Stewart PC, Trueman R. Strategies for minimising and predicting dilution in narrow vein mines e the narrow vein dilution method. In: Narrow vein mining conference 2008. Ballarat, Australia: Australasian Institute of Mining and Metallurgy; 2008.
• [22] Jang H, Topal E, Kawamura Y. Decision support system of unplanned dilution and ore-loss in underground stoping operations using a neuro-fuzzy system. Appl Soft Comput 2015;32:1-12.
• [23] Mohseni M, Ataei M, Khaloo Kakaie R. A new classification system for evaluation and prediction of unplanned dilution in cut-and-fill stoping method. J Mining Environ 2018;9:873-92.
• [24] Bazarbay B, Adoko AC. Development of a knowledge-based system for assessing unplanned dilution in open stopes IOP Conference Series. Earth Environ Sci 2021;861:062086.
• [25] Bazarbay B, Adoko AC. A comparison of prediction and classification models of unplanned stope dilution in open stope design. In: 55th U.S. Rock mechanics/geomechanics symposium; 2021.
• [26] Qi C, Fourie A, Zhao X. Back-analysis method for stope displacements using gradient-boosted regression tree and firefly algorithm. J Comput Civ Eng 2018;32:10.
• [27] Wang J, Milne D, Pakalnis R. Application of a neural network in the empirical design of underground excavation spans. Min Technol 2002;111:73-81.
• [28] Vallejos JA, Delonca A, Fuenzalida J, Burgos L. Statistical analysis of the stability number adjustment factors and implications for underground mine design. Int J Rock Mech Min Sci 2016;87:104-12.
• [29] Barton N, Lien R, Lunde J. Engineering classification of rock masses for the design of tunnel support. Publikasjon - Norges Geotekniske Institutt; 1974.
• [30] Stewart SBV, Forsyth WW. The Mathews method for open stope design. Cim Bull 1995;88:45-53.
• [31] Adoko AC, Vallejos J, Trueman R. Stability assessment of underground mine stopes subjected to stress relaxation. Min Technol: Trans Inst Min Metall 2020;129:30-9.
• [32] Veelenturf LPJ. Analysis and applications of artificial neural networks. Midsomer Norton: Prentice Hall International (UK) Ltd; 1995.
• [33] Demuth H, Beale M. Neural network toolbox for use with MATLAB. MA, USA: The MathWorks, Inc.; 2002.
• [34] Fausett LV. Fundamentals neural networks: architecture, algorithms, and applications. Englewood Cliffs, New Jersey: Prentice-Hall, Inc; 1994.
• [35] KAZZINC 2019 Ridder-Sokolny mine operation. https://www.kazzinc.com/eng/.
• [36] Qi C, Fourie A, Du X, Tang X. Prediction of open stope hangingwall stability using random forests. Nat Hazards 2018;92:1179-97.
• [37] Adoko AC, Vallejos J, Trueman R. Stability assessment of underground mine stopes subjected to stress relaxation. Min Technol 2020;129:30-9.
• [38] Suorineni FT, Kaiser PK, Tannant DD. Likelihood statistic for interpretation of the stability graph for open stope design. Int J Rock Mech Min Sci 2001;38:735-44.
• [39] Stewart PC. Minimising dilution in narrow vein mines. In: Julius Kruttschnitt mineral research centre. Queensland: The University of Queensland; 2005.
• [40] Suorineni FT. The stability graph after three decades in use: experiences and the way forward. Int J Min Reclamat Environ 2010;24:307-39.
• [41] Madenova Y, Suorineni FT. On the question of original versus modified stability graph factors e a critical evaluation. Min Technol 2020;129:40-52

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).