عنوان مقاله [English]
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.