OPTIMIZATION OF HEMATITE AND QUARTZ BIOFLOTATION BY AN ARTIFICIAL NEURAL NETWROK (ANN)

摘要

Mineral flotation using microorganisms and/or their derived products is called “Bioflotation”, this is a promising process due to their low environmental impact; however, it is also a very complicated process, due to their multidisciplinary character, involving: mineralogy, chemistry and biology. So, the optimization of this process is a relevant task. This study examined the implementation of the artificial neural network (ANN) for the optimization of hematite and quartz recovery floatability. The flotation process was carried out using a biosurfactant extracted from the R. erythropolis bacteria. The multilayered feed-forward networks were trained based on backpropagation algorithm, using the software MATLAB R2017a. The topologies of neural networks were 2 neurons in the input layer, 1 neuron in the output layer in both models and the hidden layer varied according to the performance of the model. The results showed that the ANN model can predict the experimental results with good agreement, for the hematite model was reached R2 = 0.998 and sum squared error (SSE) = 0.26 and for the quartz model R~2 = 0.998 and SSE=0.37. The sensitivity analysis showed that studied variables (pH and biosurfactant concentration) have an effect on the mineral recovery