Application of artificial neural networks to predict pyrite oxidation in a coal washing refuse pile

This paper presents a neural network model to predict the pyrite oxidation in the spoil of the Alborz Sharghi coal washing refuse pile, northeast Iran. Spoil depth, annual precipitation, effective diffusion coefficient and initial amount of pyrite in the spoil particles were used as inputs to the network. The output of the network was the amount of pyrite remained in the spoils at different depths. Feed-forward artificial neural network with back-propagation learning algorithm with 4-7-4-1 arrangement was found capable to predict the rate of pyrite oxidation. The network was used to predict the amount of pyrite remained at different depths of three trenches over the refuse pile. Simulated values obtained by the network were very close to the experimental results. The correlation coefficient (R) value was 0.99821 for training set, and in testing stage the R value was 0.99007, 0.9958 and 0.99898 for trench 1, trench 2 and trench 3 respectively which shows the model prediction was quite satisfactory.