Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks

In the Bayer process, the reaction of silica in bauxite with caustic soda causes the loss of a great amount of NaOH. In this research, the bound-soda losses in Iran Alumina Complex solid residue (red mud) are predicted using intelligent techniques. This method, based on the application of regression and artificial neural networks (AAN), has been used to predict red mud bound-soda losses in Iran Alumina Company. Multilayer perceptron (MLP), radial basis function (RBF) networks and multiple linear regressions (MLR) were applied. The results of three methodologies were compared for their predictive capabilities in terms of the correlation coefficient (R), mean square error (MSE) and the absolute average deviation (AAD) based on the experimental data set. The optimum MLP network was obtained with structure of two hidden layers including 13 and 15 neurons in each layer respectively. The results showed that the RBF model with 0.117, 5.909 and 0.82 in MSE, AAD and R, respectively, is extremely accurate in prediction as compared with MLP and MLR.