ترکیب الگوریتم خوشه¬بندی Fuzzy c-means با شبکه عصبی پرسپترون چند لایه برای افزایش دقت تخمین غلظت عناصر ژئوشیمیایی، مثال موردی – محدوده شرقی کانسار مس پورفیری سوناجیل
محورهای موضوعی :محرم جهانگیری 1 , سیدرضا قوامی ریابی 2 , بهزاد تخم¬چی 3
1 - دانشگاه صنعتی شاهرود
2 - دانشگاه صنعتی شاهرود
3 - دانشگاه صنعتی شاهرود
کلید واژه: تخمین غلظت عناصر ژئوشیمیایی الگوریتم خوشه¬, بندی FCM شبکه عصبی چند لایه بهبود دقت تخمین.,
چکیده مقاله :
روش های شناسایی الگو توانایی کشف روابط پنهان موجود در بین داده های اکتشافی را دارند و با بهره-گیری از این روش ها، الگوی پراکندگی ژئوشیمیایی حاکم بر عناصر در محدوده مورد مطالعه قابل شناسایی و تعمیم است. یکی از روش های شناسایی الگو، شبکه عصبی چند لایه است که در تخمین غلظت عناصر ژئوشیمیایی در مطالعات معدنی استفاده می شود و دقت قابل قبولی ارائه می نماید. در این مطالعه، روش شبکه عصبی چند لایه به‌عنوان تخمینگر انتخاب شده و با 1755 نمونه سنگی آنالیز شده با روش ICP، طراحی تخمینگر انجام پذیرفته است. در تحلیل ها برای بالا بردن دقت تخمین شبکه عصبی از الگوریتم خوشه بندی FCM استفاده شده است. پس از شناسایی تعداد خوشه بهینه موجود در داده های ژئوشیمیایی، اقدام به خوشه بندی شده و مجموعه داده برای طراحی تخمینگر ها از داده های خوشه بندی شده انتخاب شد. نتایج به‌دست‌آمده نشان داد که استفاده از داده های خوشه بندی شده، دقت تخمین را 13 درصد افزایش داده و میانگین دقت تخمینگرهای عناصر ژئوشیمیایی که در حالت استفاده از کل داده ها برابر 75 درصد بود به 88 درصد افزایش یافته است. عناصری با دقت های پایین در حالت استفاده از کل داده ها، در حالت استفاده از داده های خوشه بندی شده افزایش قابل ملاحظه ای از خود نشان داده و خطای تخمین (MSE) در حالت استفاده از داده های خوشه بندی به میزان قابل توجهی کاهش پیدا کرده است و میانگین خطا از مقدار 079/0 با کاهشی 3 برابری به 025/0 رسیده است.
Pattern recognition methods are able to identify the hidden relationships between exploration data, especially in the case of limited number of data. The geochemical distribution patterns of the elements are identified and generalized using these methods. Multilayer perceptron, MLP, is one of the pattern recognition methods which is used for the estimation of geochemical element concentrations in mineral deposit studies. In the current study, multilayer neural network was used to estimate the concentration of geochemical elements based on 1755 surface and borehole samples, analyzed by ICP. Fuzzy c-means, FCM, clustering algorithm was used to increase the neural network estimation accuracy. The optimal number of clusters in the dataset was identified by validation indices and was used to design estimator. The clustering data on average showed an increase of 13% accuracy compared to normal mode. The average accuracy was increased from 75 percent to 88 percent. Elements with the lowest estimation accuracy showed an acceptable increase on the estimation accuracy by using clustering data. Mean squared error was 0.079 using all data and decreased to 0.025 while using hybrid developed method.
محمدزاده، م. ناصری، آ و محمودیان، ا،. 1388. مقایسه روش¬های جداسازی جوامع سنگی و خوشه¬بندی فازی میان مرکز برای حذف اثر سینژنتیک در اکتشافات ناحیه¬ای رسوبات آبراهه¬ای قره چمن-آذربایجان شرقی. مجله مهندسی معدن، 4، 58-51.
Allahkarami, E., Salmani Nuri, O., Abdollahzadeh, A., Rezai, B. and Maghsoudi, B., 2017. Improving estimation accuracy of metallurgical performance of industrial flotation process by using hybrid genetic algorithm–artificial neural network (GA-ANN). Physicochemical Problems of Mineral Processing, 53.
Bensaid, A.M., Hall, L.O., Bezdek, J.C., Clarke, L.P., Silbiger, M.L., Arrington, J.A. and Murtagh, R.F., 1996. Validity-guided (re) clustering with applications to image segmentation. IEEE Transactions on fuzzy systems, 4,2,112-123.
Bezdek, J.C., 1981. Objective function clustering. In Pattern recognition with fuzzy objective function algorithms, 43-93, Springer, Boston, MA.
Carranza, E.J.M., 2008. Geochemical Anomaly and Mineral Prospectivity Mapping in Gis,11, Elsevier.
Cheng, Q., 2004. Application of weights of evidence method for assessment of flowing wells in the Greater Toronto area, Canada. Natural Resources Research, 13(2), 77-86.
Chiu, S.L., 1994. Fuzzy model identification based on cluster estimation. Journal of Intelligent & fuzzy systems, 2,3, 267-278.
Dunn, J.C., 1973. A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters.
Ghavami-Riabi, R., Seyedrahimi-Niaraq, M.M., Khalokakaie, R. and Hazareh, M.R., 2010. U-spatial statistic data modeled on a probability diagram for investigation of mineralization phases and exploration of shear zone gold deposits. Journal of Geochemical Exploration, 104,1-2, 27-33.
Goovaerts, P., 1997. Geostatistics for Natural Resources Evaluation. Oxford University Press on Demand.
Guo, W.W., 2010. A novel application of neural networks for instant iron-ore grade estimation. Expert Systems with Applications, 37,12, 8729-8735.
Halkidi, M., Batistakis, Y. and Vazirgiannis, M., 2001. On clustering validation techniques. Journal of intelligent information systems, 17,2-3, 107-145.
Hezarkhani, A., 2003. Exploration of Sonajil copper deposit. Iranian company of copper, northwestern report exploration.
Hornik, K., Stinchcombe, M. and White, H., 1989. Multilayer feedforward networks are universal approximators. Neural networks, 2,5, 359-366.
Jafrasteh, B. and Fathianpour, N., 2017. 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, 235, 217-227.
Jalloh, A.B., Kyuro, S., Jalloh, Y. and Barrie, A.K., 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.
Journel, A.G. and Huijbregts, C.J., 1978. Mining Geostatistics. London: Academic press, 600.
Jozanikohan, G., Norouzi, G.H., Sahabi, F., Memarian, H. and Moshiri, B., 2015. The application of multilayer perceptron neural network in volume of clay estimation: Case study of Shurijeh gas reservoir, Northeastern Iran. Journal of Natural Gas Science and Engineering, 22, 119-131.
Koike, K. and Matsuda, S., 2003. Characterizing content distributions of impurities in a limestone mine using a feedforward neural network. Natural resources research, 12,3, 209-222.
Mahmoudabadi, H., Izadi, M. and Menhaj, M.B., 2009. A hybrid method for grade estimation using genetic algorithm and neural networks. Computational Geosciences, 13,1, 91-101.
Moghadassi, A., Parvizian, F. and Hosseini, S., 2009. A new approach based on artificial neural networks for prediction of high pressure vapor-liquid equilibrium. Australian Journal of Basic and Applied Sciences, 3,3, 1851-1862.
Nakhaei, F. and Irannajad, M., 2013. Comparison between neural networks and multiple regression methods in metallurgical performance modeling of flotation column. Physicochemical Problems of Mineral Processing, 49.
Pal, A., Singh, J.P. and Dutta, P., 2015. Path length prediction in MANET under AODV routing: Comparative analysis of ARIMA and MLP model. Egyptian Informatics Journal, 16,1, 103-111.
Qiuming, C., 2008. Special Issue of Mathematical Geosciences for the 33rd IGC. Journal of China University of Geosciences, 19,4, 307-308.
Rendu, J.M., 1979. October. Kriging, logarithmic Kriging, and conditional expectation: comparison of theory with actual results. In Proc. 16th APCOM Symposium. Tucson, Arizona, 199-212.
Rooki, R., Ardejani, F.D., Aryafar, A. and Asadi, A.B., 2011. Prediction of heavy metals in acid mine drainage using artificial neural network from the Shur River of the Sarcheshmeh porphyry copper mine, Southeast Iran. Environmental earth sciences, 64,5, 1303-1316.
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.
Samanta, B., Bandopadhyay, S., Ganguli, R. and Dutta, S., 2005. A comparative study of the performance of single neural network vs. Adaboost algorithm based combination of multiple neural networks for mineral resource estimation. Journal of South African Institute of Mining and Metallurgy, 105,4, 237-246.
Strebelle, S., 2002. Conditional simulation of complex geological structures using multiple-point statistics. Mathematical geology, 34,1, 1-21.
Tahmasebi, P. and Hezarkhani, A., 2010a. Application of adaptive neuro-fuzzy inference system for grade estimation; case study, sarcheshmeh porphyry copper deposit, Kerman, Iran. Australian Journal of Basic and Applied Sciences, 4,3, 408-420.
Tahmasebi, P. and Hezarkhani, A., 2010b. Comparison of optimized neural network with fuzzy logic for ore grade estimation. Australian Journal of Basic and Applied Sciences, 4,5, 764-772.
Tahmasebi, P. and Hezarkhani, A., 2012. A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation. Computers & geosciences, 42, 18-27.
Tahmasebi, P., Hezarkhani, A. and Sahimi, M., 2012. Multiple-point geostatistical modeling based on the cross-correlation functions. Computational Geosciences, 16,3, 779-797.
Webb, A.R., 2003. Statistical Pattern Recognition. John Wiley and Sons.
Xiao-li, L., Yu-ling, X., Li-hong, L. and Qin-jin, G., 2009, October. A nonlinear grade estimation method based on Wavelet Neural Network. In Bio-Inspired Computing. BIC-TA'09. Fourth International Conference on, 1-5, IEEE.
Xie, X.L. and Beni, G., 1991. A validity measure for fuzzy clustering. IEEE Transactions on Pattern Analysis & Machine Intelligence, 8, 841-847.
Zhijing, W., Qiuming, C., Deyi, X. and Yaosong, D., 2008. Fractal modeling of sphalerite banding in Jinding Pb-Zn deposit, Yunnan, southwestern China. Journal of China University of Geosciences, 19,1,77-84.
