Inderscience Publishers

Grade estimation of ore stockpiles by using Artificial Neural Networks: case study on Choghart Iron Mine in Iran

0
This paper investigates the application of the neural network in a run of mine ore stockpile in Choghart Iron Mine of Iran. While a significant amount of high grade stockpile at Choghart mine, near the open pit, is an environmental hazard, it is also potential source of high grade ores. For future exploitation, determination of stockpile resource tonnage and grade has become an important aspect of this study. In order to achieve this goal, Artificial Neural Networks was applied. Initially a Feed–forward Neural Network model was constructed to estimate the iron grade. In this model 52% of samples from stockpile were used for training, 25% for validation and the remaining as the test set. Finally optimal architecture for grade estimation was 3–19–1 and values of R and MSE were 0.8 and 2.36, respectively. The results showed that neural networks offer a valid alternate approach to the problem of stockpile grade estimation, while requiring considerably less knowledge and time.

Keywords: artificial neural networks, ANNs, multilayer perceptron, Choghart Iron Mine, ore stockpiles, mining, Iran, iron grade estimation

Customer comments

No comments were found for Grade estimation of ore stockpiles by using Artificial Neural Networks: case study on Choghart Iron Mine in Iran. Be the first to comment!