Performance evaluation of intelligent estimators for three-dimensional modeling of Shahrak Iron ore deposit

Authors

1 M.Sc Student, Dept. of Mining Engineering, Imam khomeini International University

2 Assistant Professor, Dept. of Mining Engineering, Imam khomeini International University

Abstract

Accurate estimation of ore deposit grade plays an important role for mine planning n .and evaluation. There can be seen problems associated with some conventional methods such as Kriging for grade estimation, this paper investigates with the effectiveness of intelligent estimators such as neural network and fuzzy logic for grade estimation in Shahrak Iron ore deposit near Bijar, Kurdestan province, Iran. For this purpose, data from 9 boreholes were used for reserve estimation process. In fuzzy logic method, the data are first clustered using Fuzzy c-means clustering (FCMC) technique followed by the grade estimation done at the center of each cluster. Based on such data and an appropriate fuzzy grade control, it is possible to estimate grade at the considered points. In neural network, first a few well data are chosen as a set of data for validation and the rest of boreholes are considered as training data for the assessment of the designed network. After training the neural network, the accuracy of estimated validation data was found to be in order of 80%. The results shows that neural networks had better performance than other method.

Keywords

References

[1]     Pham, T. D. (1997). “Grade Estimation Using Fuzzy-Set Algorithms”. Mathematical Geology, 29(2): 293-296.
[2]     حسنی پاک، ع.؛ 1391؛ "تحلیل داده های اکتشافی"، انتشارات دانشگاه تهران.،چاپ سوم، ص 552-553.
[3]     Jalloh, A. B., Kyuro, S., Jalloh, Y., and Karim Barrie, A. (2016). “Integrating artificial neural networks 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.
[4]     Siregar, I., Niu, Y., Mostaghimi, P., and Armstrong, R.T. (2017). “Coal ash content estimation using fuzzy curves and ensemble neural networks for well log analysis”. International Journal of Coal Geology, 181:  11-22.
[5]     Tahmasebi, P., and Hezarkhani, A. (2012). “A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation”. Computers & Geosciences, 42: 18–27.
[6]     Kapageridis, I. (2002). “Grade Interpolation Using Radial Basis Function Networks”. In 11th International Symposium on Mine Planning and Equipment Selection (MPES), Technical University of Ostrava, Prague, pp. 5.
[7]     Azizi Shotorkheft, H. (2003). “Petrogenesis of contact metamorphic rocks and related Fe skarn in Shahrak area, east of Takab”. M.Sc.Thesis, 2-3.
[8]     Tahmasebi, P., and Hezarkhani, A. (2010). “Comparison of optimized neural network with fuzzy logic for ore grade estimation”.  Australian Journal of Basic and Applied Sciences, 4(5): 764-772.
[9]     Nascimento, S., and Mirkin, B. (1999). “A Fuzzy Clustering Model of Data and Fuzzy C-Means”. Department of Computer Science, Birkbeck College, London, UK., pp .2.
[10]  Dowd, P. A., and Sarac, C. (1994). “A neural Network Approach to Geostatistical Simulation”. Mathematical Geology, 26(4): 491-503.
[11]  Berry, M. J. A., and Linoff. G. (1997). “Data mining techniques”. John Wiley & Sons, 454: 221-222.
[12]  پورنیک، پ.؛ 1393؛ "معدن-زمین شناسی و گزارش ارزیابی ذخیره آهن در شهرک"، ص350.
 
Journal of Mineral Resources Engineering
Volume 2, Issue 3
December 2017
Pages 15-23

Files

History

  • Receive Date: 20 December 2017
  • Accept Date: 20 December 2017

Share

How to cite

Statistics