بهبود تخمین سه‌بعدی عیار مس در گستره کانسار مس سرچشمه با روش‌های یادگیری عمیق

نوع مقاله : علمی-پژوهشی

نویسندگان

1 کارشناسی ارشد، گروه مهندسی معدن، دانشکده مهندسی معدن، دانشگاه صنعتی اصفهان، اصفهان

2 دانشیار، گروه مهندسی معدن، دانشکده مهندسی معدن، دانشگاه صنعتی اصفهان، اصفهان

چکیده

امروزه کاهش خطای تخمین عیار با استفاده از روش‌های نوین، نقش تعیین‌کننده‌ای در بهینه‌سازی عملیات معدنکاری و کاهش ریسک عدم موفقیت اقتصادی پروژه‌های معدنی ایفا می‌کند. هدف از تحقیق حاضر ارایه روشی برای بهبود تخمین سه‌بعدی عیار مس در گستره کانسار مس سرچشمه با استفاده از روش‌های هوشمند یادگیری عمیق و مقایسه با نتایج روش‌های مرسوم و متداول هندسی است. کانسار مس سرچشمه یکی از بزرگ‌ترین کانسارهای مس پورفیری و روی کمربند آتشفشانی ارومیه-دختر در جنوب استان کرمان در ایران مرکزی واقع ‌شده است. در این پژوهش، از 526 گمانه در دسترس، حاوی 38006 نمونه مغزه عیارسنجی شده برای عیار مس کل استفاده‌ شده است. میانگین عیار مس در نمونه‌ها برابر با 54/0 و حداکثر مقدار آن 43/3 درصد به دست آمده است. قبل از انجام تخمین عیار مس، پیش‌پردازش‌هایی شامل اصلاح داده‌های خارج از ردیف و هم‌پایه سازی داده‌ها روی‌ داده‌ها انجام شد و در نهایت بیضوی ناهمسانگردی عیار مس با استفاده از ماتریس کوواریانس به دست آمد. برای تخمین عیار مس، از دو روش شامل الگوریتم یادگیری عمیق با معماری ResNet-50 و وزن‌دهی عکس فاصله به عنوان نماینده روش‌های متداول هندسی استفاده گردید که در نهایت و در مرحله بررسی عملکرد روش‌های یاد شده از طریق اعتبارسنجی مشخص شد که نتایج الگوریتم ResNet-50 با مقدار RMSE برابر 45/0 عملکرد بهتری نسبت به روش وزن‌دهی عکس فاصله با مقدار RMSE برابر 6/0 داشته است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Improving the 3D Estimation of Copper Grade in Sarcheshme Copper Deposit using Deep Learning Methods

نویسندگان [English]

  • H. Norouzi 1
  • N. Fathianpour 2
1 M.Sc, Dept. of Mining Engineering, Isfahan University of Technology, Isfahan, Iran
2 Associate Professor, Dept. of Mining Engineering, Isfahan University of Technology, Isfahan, Iran
چکیده [English]

Minimizing grade estimation errors through modern methods is crucial for optimizing mining operations and mitigating the risk of economic failure in mining projects. The current research is an attempt to enhance the three-dimensional estimation of copper grades in the Sarcheshmeh copper deposit by employing advanced deep-learning techniques and comparing their outcomes with those of traditional geometric methods. The Sarcheshmeh copper deposit is among the largest porphyry copper deposits located within the Urmia-Dokhtar volcanic belt, south of Kerman in central Iran. In this study, data from a number of 526 boreholes containing 38,006 core samples assayed for total copper were deployed. The average copper grade in the samples is 0.54 percent, with a maximum value of 3.43. Prior to grade estimation, preprocessing steps were performed, including outlier correction and data compositing. The anisotropy ellipsoid of the copper grade was determined using the covariance matrix. Two methods were applied for grade estimation: a deep learning algorithm based on the ResNet-50 architecture and the inverse distance weighting (IDW) method, a conventional geometric approach. Validation results indicated that the ResNet-50 algorithm, with an RMSE of 0.45, outperformed the IDW method, which had an RMSE of 0.6.

کلیدواژه‌ها [English]

  • Grade modeling
  • Neural networks
  • Deep learning methods
  • Inverse distance weighting method
  • Grade estimation

مراجع

  1. Bishop, C. M. (1995). “Neural networks for pattern recognition”. Oxford University Press, Oxford, pp. 482.
  2. Krizhevsky, A., and Sutskever, I., and Hinton, G. E. (2012). “ImageNet classification with deep convolutional neural networks”. In: Pereira, F., Burges, C. J. C., Bottou, L., and Weinberger, K. Q. (Eds.), Advances in Neural Information Processing Systems, Vol. 25, Curran Associates, Inc., Red Hook, NY, 1097-1105.
  3. Xiong, Y., and Zuo, R. (2016). “Recognition of geochemical anomalies using a deep autoencoder network”. Computers & Geosciences, 86: 75-82.
  4. He, M., Zhang, Z., Ren, J., Huan, J., Li, G., Chen, Y., and Li, N. (2019). “Deep convolutional neural network for fast determination of the rock strength parameters using drilling data”. International Journal of Rock Mechanics and Mining Sciences, 123: 104084.
  5. Guo, H., Zhou, J., Koopialipoor, M., Jahed Armaghani, D., and Tahir, M. M. (2019). “Deep neural network and whale optimization algorithm to assess flyrock induced by blasting”. Engineering with Computers, 37: 173-186. DOI: https://doi.org/10.1007/s00366-019-00816-y.
  6. Pradip, Gautham, B. P., Reddy, S., and Runkana, V. (2019). “Future of mining, mineral processing and metal extraction industry”. Transactions of the Indian Institute of Metals, 72: 2159-2177. DOI: https://doi.org/10.1007/s12666-019-01790-1.
  7. Wel, J., Guo, L., Xu, X., and Yan, G. (2015). “Soft sensor modeling of mill level based on convolutional neural network”. The 27th Chinese Control and Decision Conference, CCDC, 23-25 May 2015, 4738-4743.
  8. Karpatne, A., Ebert-Uphoff, I., Ravela, S., Babaie, H. A., and Kumar, V. (2018). “Machine learning for the geosciences: challenges and Opportunutues”. In: IEEE Transactions on Knowledge and Data Engineering, 31(8): 1544-1554. DOI: https://doi.org/10.1109/TKDE.2018.2861006.
  9. Rendu, J. M. (2017). “Risk Management in Evaluating Mineral Deposites”. Society for Mining, Metallurgy, and Exploration, Inc., pp. 320.
  10. Kapageridis, I. K., and Denby, B. (1998). “Neural network modelling of ore grade spatial variability”. In: Niklasson, L., Bodén, M., and Ziemke, T. (Eds.), ICANN 98. ICANN 1998. Perspectives in Neural Computing. Springer, London. DOI: https://doi.org/10.1007/978-1-4471-1599-1_28.
  11. Kapageridis, I. K., and Denby, B. (1998). “Ore grade estimation with modular neural network systems, A case study, Information Technology in the Mineral Industry”. In: Panagiotou, G. (Ed.), Information technology in the minerals industry (MineIT’ 97). AA Balkema, Rotterdam.
  12. Samanta, B. Bandopadhyay, S., and Ganguli, R. (2002). “Data segmentation and genetic algorithms for sparse data division in nome placer gold grade estimation using neural network and geostatistics”. Exploration and Mining Geology, 11(1-4): 69-76. DOI: https://doi.org/10.2113/11.1-4.69.
  13. Chatterjee, S., Bhattacherjee, A., Samanta, B., and Pal, S. K. (2006). “Ore grade estimatation of a limestone deposit in india using an artificial neural network”. Applied GIS, 2(1): 3.1-3.20.
  14. Samanta, B., and Bandopadhyay, S. (2009). “Construction of a radil basis function nrtwork using an evolutionary algorithm for grade estimation in a placer gold deposit”. Computers & Geosciences, 35(8): 1592-1602.
  15. Badel, M., Angorani, S., and Panahi, M. Shariat, (2011). “The application of median indicator Kriging and neural network in modeling mixed population in an iron ore deposite”. Computers & Geosciences, 37(4): 530-540.
  16. Abu Bakarr, J., Sasaki, K., Yaguba, J., and Abubakarr Karim, B. (2016). “Integration artificial neural network and geostatistics for optimum 3D geological block modeling in mineral reserve estimation: A case study”. International Journal of Mining Science and Technology, 26(4): 581-585.
  17. Goswami, A., Mishra, M., and Patra, D. (2017). “Investigation of general reression neural network architecture for grade estimation of an indian iron ore deposit”. Arbian Journal Geosciences, 10(4): 80.
  18. Jafrasteh, B., Fathianpour, N., and Suorez, A. (2018). “Comparison of machine learning methods for copper ore grade estimation”. Computational Geosciencs, 22(5): 1371-1383.
  19. Abbaszadeh, M. (2021). “The copper grade estimation of porphyry deposits using machine learning algorithms and Henry gas solubility optimization”. Earth Science Informatics, 14: 2049-2075.
  20. Yang, N. (2021). “A Convolutional Neural Network of GoogLeNet Applied in Mineral Prospectivity Prediction Based on Multi-source Geoinformation”. Natural Resources Research, 30: 3905-3923.
  21. Erdogan Erten, G. (2021). “Grade estimation by a machine learning model using coordinate rotations”. Applied Earth Science, 130: 57-61.
  22. Mousavi, J., Shayestehfar, M., and Moarefvand, P. (2022). “Comparison of Various Estimation and Simulation Methods for Orebody Grade Variations Modeling”. Journal of Mining Science, 58: 163-172.
  23. Singh, R., Ray, D., and Sarkar, B. (2022). “Mineral deposit grade assessment using a hybrid model of kriging and generalized regression neural network”. Neural Computing and Applications, 34: 10611-10627.
  24. Soltani-Mohammadi, S., Hoseinian, F., Abbaszadeh, M., and Khodadadzadeh, M. (2022). “Grade estimation using a hybrid method of back-propagation artificial neural network and particle swarm optimization with integrated samples coordinate and local variability”. Computers and Geosciences, 159: 104981.
  25. Batlile, T. N. (2023). “Application of Artificial Neural Network for the Prediction of Copper Ore Grade”. Minerals, 13: 628.
  26. Zaki, M. M., Chen, S., Zhang, J., Feng, F., Khoreshok, A. A., Mahdy, M. A., and Salim, K. M. (2023). “A Novel Approach for Resource Estimation of Highly Skewed Gold Using Machine Learning Algorithms”. Minerals, 12(7): 900. DOI: https://doi.org/10.3390/min12070900.
  27. Battalgazy, N., Valenta, R., Gow, P., Spier, C., and Forbes, G. (2023). “Addressing Geological Challenges in Mineral Resource Estimation: A Comparative Study of Deep Learning and Traditional Techniques”. Minerals, 13: 982.
  28. Kiranyaz, S., Zabihi, M., Bahrami Rad, A., Ince, T., Hamila, R., and Gabbouj, M. (2020). “Real-time phonocardiogram anomaly detection by adaptive 1D Convolutional Neural Networks”. Neurocomputing, 411: 291-301.
  29. Li, Y., Zou, L., Jiang, L., and Zhou, X. (2019). “Fault Diagnosis of Rotating Machinery Based on Combination of Deep Belief Network and One-dimensional Convolutional Neural Network”. IEEE, 7: 165710-165723.
  30. Zhong, Y. (2021). “Risk Assessment and Prediction of Construction Project Based on 1D-CNN-Attention-BP”. World Journal of Engineering and Technology, 9: 861-876.
  31. Jana, G., Sharma, R., and Agrawal, A. (2020). “A 1D-CNN-Spectrogram Based Approach for Seizure Detection from EEG Signal”. Procedia Computer Science, 167: 403-412.
  32. Li, J., and Heap, A. D. (2008). “A review of Spatial Interpolation Methods for Environmental Scientists”. Geoscience Australia, Record 2008/23, pp. 137.
  33. Hassanipak, A. A., and Sharafodin, M. (2004). “GET: a function for Prefetional site selection borehole drilling”. Exploration and Mining Geology, 13(1-4): 139-146.
  34. O’Shea, K., and Nash, R. (2015). “An Introduction to Convolutional Neural Networks”. arXiv. DOI: https://doi.org/10.48550/arXiv.1511.08458.
  35. He, K., Zhang, X., Ren, Sh., and Sun, J.  (2016). “Deep Residual Learning for Image Recognition”. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 770-778. DOI: https://doi.org/10.1109/CVPR.2016.90.
  36. Waterman, G. C., and Hamilton, R. L. (1975). “The Sar Cheshmeh porphyry copper deposit”. Economic Geology, 70(3): 568-576.
  37. Rohit, M. (2021). “ResNet-Understand and Implement from scratch”. Economic Geology, 70: 568-576.
  38. Murphy, K. P. (2012). “Machine Learning: A Probabilistic Perspective”. The MIT Press, Cambridge, Massachusetts, pp. 1104.
  39. Olivier, L. E., Maritz, M. G., and Craig, I. k. (2020). “Estimating Ore Particle Size Distribution using a Deep Convolutional Neural Network”. IFAC-PapersOnLine, 53(2): 12038-12043.

فایل ها

سابقه مقاله

  • تاریخ دریافت: 26 مرداد 1403
  • تاریخ بازنگری: 29 مرداد 1404
  • تاریخ پذیرش: 02 دی 1403

هم رسانی

ارجاع به این مقاله

آمار