نوع مقاله: علمی - پژوهشی

نویسندگان

1 گروه مهندسی معدن، دانشگاه کاشان

2 گروه مهندسی معدن، دانشگاه کاشان، ایران

3 عضو هیئت علمی

4 مجتمع مس شهربابک

10.22034/ijme.2020.37381

چکیده

به دلیل ارتباط زون‌های کانی‌سازی با تغییرپذیری عیار در کانسارهای مس پورفیری، تهیه مدل سه بعدی این زون‌ها یکی از گام‌های پیش از تخمین در ارزیابی این تیپ کانسارها به شمار می‌آید. کیفیت این مدل تأثیر بسزایی بر کیفیت تخمین‌های ارائه شده برای عیار، طراحی مناسب استخراج بلندمدت و درنهایت کاهش مشکلات بین معدن و کارخانه فرآوری خواهد داشت. روش معمول برای تهیه این مدل استفاده از روش مدلسازی محدود می‌باشد که فرآیندی پیچیده و زمان‌بر است. یکی از راه‌حل‌های ممکن برای تهیه این گونه مدل‌ها استفاده از روش‌های نامحدود همچون روش‌های هوشمند می‌باشد. در این مقاله تلاش شده است تا عملکرد دو روش هوشمند شبکه عصبی مصنوعی و ماشین بردار پشتیبان طبقه‌بندی‌کننده در جداسازی زون‌های کانی سازی (شامل زون شسته شده، زون هیپوژن، زون سوپرژن) کانسار مس میدوک مورد مطالعه و بررسی قرار گیرد. برای این منظور از مختصات جغرافیایی (طول و عرض و ارتفاع) داده‌های حاصل از گمانه‌های اکتشافی به عنوان ورودی و زون‌های کانی‌سازی مشاهده شده در آن‌ها به عنوان خروجی مدل استفاده شده است. بررسی نتایج حاصل از این الگوریتم‌های هوشمند در جداسازی زون‌های زمین شناسی نشان می‌دهد که روش ماشین بردار پشتیبان طبقه‌بندی‌کننده نسبت به شبکه عصبی مصنوعی عملکرد مطلوب‌تری دارد. عملکرد مطلوب‌تر روش روش ماشین بردار پشتیبان نسبت به شبکه عصبی مصنوعی، با استفاده از دقت بالاتر این روش در مراحل آموزش و آزمایش و همچنین مقایسه میان مدل بلوکی طبقه‌بندی شده با برداشت‌های صورت گرفته از چال‌های انفجاری نشان داده شده است.

کلیدواژه‌ها

عنوان مقاله [English]

Comparison of artificial neural networks and support vector machine classifiers for 3D modeling of mineralization zones (Case study: Miduk copper Deposit)

نویسندگان [English]

  • Zahra Shafiee 1
  • Maliheh Abbaszadeh 2
  • Saeed Soltani-Mohammadi 3
  • Mojtaba Dehghani 4

1 Department of Mining engineering, University of Kashan, Iran

2 Department of Mining engineering, University of Kashan, Iran

3 Department of mining engineering, University of Kashan, Iran

4 Shahrbabak copper complex

چکیده [English]

Due to the relation of mineralization zones with grade variability in porphyry copper deposits, the preparation of the three-dimensional model of these zones is one of the pre-estimation steps in evaluation this type of deposits. The quality of this model has a significant impact on the quality of the grade estimates, the proper design of long-term extraction and ultimately reducing the problems between the mine and the processing plant. The usual way to prepare this model is to use a constrained modeling technique, which is a complex and time consuming process. One of the possible solutions for the preparation of these models is the use of unconstrained methods, such as intelligent methods. This paper attempts to study the performance of artificial neural network and support vector machine in the separation of mineralization zones (including leached, hypogene and supergene zones) in Miduk copper deposit. The northing co-ordinate, easting co-ordinate and height of the samples are used as input variables, and the observed mineralization zones in them are used as the output variable. Investigating the results of these intelligent algorithms in the separation of geological zones shows that the support vector machine classifier has a better performance than the artificial neural network. The better performance of the support vector machine method is shown by 1) the higher accuracy of this method in the training and testing stages and 2) the comparison between the block model with the grade control observations.

کلیدواژه‌ها [English]

  • Artificial neural networks
  • Support Vector Machine
  • Porphyry copper deposit
  • Separation of geological zones

منابع
1. Sinclair, W., Porphyry deposits. Mineral deposits of Canada: A synthesis of major deposit-types, district metallogeny, the evolution of geological provinces, and exploration methods: Geological Association of Canada, Mineral Deposits Division, Special Publication, 2007. 5: p. 223-243.
2. Singer, D., V. Berger, and B. Moring, Porphyry copper deposits of the world: Database and grade and tonnage. 2008, USGS, 2008-1155: 3-42.
3. Ayuso, R.A., et al., Porphyry copper deposit model: Chapter B in Mineral deposit models for resource assessment. 2010, US Geological Survey.
4. Afzal, P., et al., Delineation of mineralization zones in porphyry Cu deposits by fractal concentration–volume modeling. Journal of Geochemical Exploration, 2011. 108(3): p. 220-232.
5. Emery, X., Probabilistic modelling of lithological domains and it application to resource evaluation. Journal of the Southern African Institute of Mining and Metallurgy, 2007. 107(12): p. 803-809.
6. Yu, X. and X. Li. The Application of Sequential Indicator Simulation and Sequential Gaussian Simulation in Modeling a Case in Jilin Oilfield. in Future Control and Automation. 2012. Berlin, Heidelberg: Springer Berlin Heidelberg.
7. Yunsel, T.Y. and A. Ersoy, Geological modeling of rock type domains in the Balya (Turkey) lead-zinc deposit using plurigaussian
simulation. Central European Journal of Geosciences, 2013. 5(1): p. 77-89.
8. Amirpoursaeid, F. and O. Asghari, Application of truncated gaussian simulation to ore-waste boundary modeling of Golgohar iron deposit. International Journal of Mining and Geo-Engineering, 2016. 50(2): p. 175-181.
9. de Souza, L.E. and J.F.C. Costa, Sample weighted variograms on the sequential indicator simulation of coal deposits. International Journal of Coal Geology, 2013. 112: p. 154-163.
10. Yamamoto, J.K., et al., Post-processing for uncertainty reduction in computed 3D geological models. Tectonophysics, 2014. 633(0): p. 232-245.
11. Wu, X. and Y. Zhou, Reserve estimation using neural network techniques. Computers & Geosciences, 1993. 19(4): p. 567-575.
12. Gholampour, O., et al., Delineation of alteration zones based on kriging, artificial neural networks, and concentration–volume fractal modelings in hypogene zone of Miduk porphyry copper deposit, SE Iran. Journal of Mining and Environment, 2018.
13. Hezarkhani, A., P. Tahmasbi, and O. Asghari, Separating the Sungun Copper Deposit Alteration Zones by Applying Artificial Neural Network. Journal of Geoscience, 2010. 20(77): p. 41-46.
14. Samanta, B., S. Bandopadhyay, and R. Ganguli, Data segmentation and genetic algorithms for sparse data division in Nome placer gold grade estimation using neural network and geostatistics. Exploration and mining geology, 2002. 11(1-4): p. 69-76.
15. Koike, K., et al., Neural network-based estimation of principal metal contents in the Hokuroku district, northern Japan, for exploring Kuroko-type deposits. Natural Resources Research, 2002. 11(2): p. 135-156.
16. Yama, B. and G. Lineberry, Artificial neural network application for a predictive task in mining. Mining engineering, 1999. 51(2): p. 59-64.
17. Ke, J., Neural-network modelling of placer ore grade spatial variability. 2002, University of Alaska Fairbanks.
18. Samanta, B., et al., Sparse data division using data segmentation and Kohonen network for
» مهندسی معدن « مقایسه عملکرد شبکه عصبی مصنوعی و ماشین بردار پشتیبان در تهیه مدل سه بعدی زون های کانی سازی ... نشریه علمی پژوهشی
23
neural network and geostatistical ore grade modeling in Nome offshore placer deposit. Natural resources research, 2004. 13(3): p. 189-200.
19. Samanta, B., R. Ganguli, and S. Bandopadhyay, Comparing the predictive performance of neural networks with ordinary kriging in a bauxite deposit. Mining Technology, 2005. 114(3): p. 129-139.
20. Mahmoudabadi, H., M. Izadi, and M.B. Menhaj, A hybrid method for grade estimation using genetic algorithm and neural networks. Computational Geosciences, 2009. 13(1): p. 91-101.
21. Tahmasebi, P. and A. Hezarkhani, Application of optimized neural network by genetic algorithm, IAMG09. 2009, Stanford University, California.
22. Jafrasteh, B. and N. Fathianpour, A hybrid simultaneous perturbation artificial bee colony and back-propagation algorithm for training a local linear radial basis neural network on ore grade estimation. Neurocomputing, 2017. 235: p. 217-227.
23. Jafrasteh, B., N. Fathianpour, and A. Suárez, Comparison of machine learning methods for copper ore grade estimation. Computational Geosciences, 2018. 22(5): p. 1371-1388.
24. Abbaszadeh, M., A. Hezarkhani, and S. Soltani-Mohammadi, An SVM-based machine learning method for the separation of alteration zones in Sungun porphyry copper deposit. Chemie der Erde-Geochemistry, 2013. 73(4): p. 545-554.
25. Abbaszadeh, M., A. Hezarkhani, and S. Soltani-Mohammadi, Classification of alteration zones based on whole-rock geochemical data using support vector machine. Journal of the Geological Society of India, 2015. 85(4): p. 500-508.
26. Abbaszadeh, M., A. Hezarkhani, and S. Soltani-Mohammadi, Proposing drilling locations based on the 3D modeling results of fluid inclusion data using the support vector regression method. Journal of Geochemical Exploration, 2016. 165: p. 23-34.
27. GODARZI, M.S., et al., COMPARISON OF SUPPORT VECTOR MACHINE, NEURAL NETWORK, AND MAXIMUM LIKELIHOOD METHODS FOR THE SEPARATION OF LITHOLOGICAL UNITS. 2012.
28. Mahvash Mohammadi, N. and A. Hezarkhani,
Application of support vector machine for the separation of mineralised zones in the Takht-e-Gonbad porphyry deposit, SE Iran. Journal of African Earth Sciences, 2018. 143: p. 301-308.
29. Al-Anazi, A. and I. Gates, Support vector regression for porosity prediction in a heterogeneous reservoir: A comparative study. Computers & Geosciences, 2010. 36(12): p. 1494-1503.
30. Chatterjee, S. and S. Bandopadhyay, Goodnews Bay Platinum Resource Estimation Using Least Squares Support Vector Regression with Selection of Input Space Dimension and Hyperparameters. Natural Resources Research, 2011. 20(2): p. 117-129.
31. Haykin, S., Neural networks: a comprehensive foundation, 1999. Mc Millan, New Jersey, 2010.
32. Dowd, P. and C. Sarac, A neural network approach to geostatistical simulation. Mathematical Geology, 1994. 26(4): p. 491-503.
33. Dutta, S., Predictive performance of machine learning algorithms for ore reserve estimation in sparse and imprecise data. 2006: ProQuest.
34. Berry, M.J. and G. Linoff, Data mining techniques: for marketing, sales, and customer support. 1997: John Wiley & Sons, Inc.
35. Haykin, S., Neural Network, A comprehensive Foundation-1994. Amerika Serikat.
36. Coulibaly, P., F. Anctil, and B. Bobee, Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. Journal of Hydrology, 2000. 230(3-4): p. 244-257.
37. Omid, M., M. Omid, and M. Esmaeeli Varaki. Modelling hydraulic jumps with artificial neural networks. in Proceedings of the Institution of Civil Engineers-Water Management. 2005. Thomas Telford Ltd.
38. Watanachaturaporn, P., M.K. Arora, and P.K. Varshney. Hyperspectral image classification using support vector machines: A comparison with decision tree and neural network classifiers. in American Society for Photogrammetry & Remote Sensing (ASPRS) 2005 Annual Conference, Reno, NV. 2006.
39. Burges, C.J., A tutorial on support vector machines for pattern recognition. Data mining
» مهندسی معدن « زهرا شفیعی، ملیحه عباس زاده، سعید سلطانی محمدی، مجتبی دهقانی جوزم نشریه علمی پژوهشی
24
and knowledge discovery, 1998. 2(2): p. 121-167.
40. Lorena, A.C. and A.C. De Carvalho, Evolutionary tuning of SVM parameter values in multiclass problems. Neurocomputing, 2008. 71(16-18): p. 3326-3334.
41. Zuo, R. and E.J.M. Carranza, Support vector machine: a tool for mapping mineral prospectivity. Computers & Geosciences, 2011. 37(12): p. 1967-1975.
42. Cortes, C. and V. Vapnik, Support-vector networks. Machine learning, 1995. 20(3): p. 273-297.
43. Tax, D.M. and R.P. Duin, Support vector domain description. Pattern recognition letters, 1999. 20(11-13): p. 1191-1199.
44. Hsu, C., C. Chang, and C. Lin, A practical guide to support vector classification. Taipei: Department of Computer Science National Taiwan University. 2010.
45. Aliani, F., et al., Geochemistry and petrography of the Meiduk porphyry copper deposit, Kerman, Iran. Australian Journal of Basic and Applied Sciences, 2009. 3(4): p. 3786-3800.
46. Zhou, P., et al., Source mapping and determining of soil contamination by heavy metals using statistical analysis, artificial neural network, and adaptive genetic algorithm. Journal of Environmental Chemical Engineering., 2015. 3(4, Part A,): p. 2569-2579.
47. Karsoliya, S., Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. International Journal of Engineering Trends and Technology, 2012. 3(6): p. 714-717.
48. Rumelhart, D.E., G.E. Hinton, and R.J. Williams, Learning representations by back-propagating errors. nature, 1986. 323(6088): p. 533.
49. Cherkassky, V. and Y. Ma, Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks, 2004.
17(1): p. 113-126.
50. Hsu, C.-W., C.-C. Chang, and C.-J. Lin, A practical guide to support vector classification. 2003.
51. Lin, S.-W., et al., Parameter determination of support vector machine and feature selection using simulated annealing approach. Applied soft computing, 2008. 8(4): p. 1505-1512.
52. Momma, M. and K.P. Bennett. A pattern search method for model selection of support vector regression. in Proceedings of the 2002 SIAM International Conference on Data Mining. 2002. SIAM.
53. Chang, C.-C. and C.-J. Lin, LIBSVM: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2011. 2(3): p. 27.
54. Frohlich, H. and A. Zell. Efficient parameter selection for support vector machines in classification and regression via model-based global optimization. in Neural Networks, 2005. IJCNN'05. Proceedings. 2005 IEEE International Joint Conference on. 2005. IEEE.
55. Luo, L., et al., A new parameter selection method for support vector machine based on the decision value. Journal of Convergence Information Technology, 2010. 5(8): p. 36-41.
56. Zhang, D., et al., Parameter optimization for support vector regression based on genetic algorithm with simplex crossover operator. JOURNAL OF INFORMATION &COMPUTATIONAL SCIENCE, 2011. 8(6): p. 911-920.
57. Huang, Q., J. Mao, and Y. Liu. An improved grid search algorithm of SVR parameters optimization. in Communication Technology (ICCT), 2012 IEEE 14th International Conference on. 2012. IEEE.
58. Lee, C.-Y. and S.-G. Chern, Application of a support vector machine for liquefaction assessment. Journal of Marine Science and Technology, 2013. 21(3): p. 318-324.