An Artificial Neural Network Approach for the Prediction of Extraction Performance of Emulsion Liquid Membrane

Abstract

This paper reports the use of artificial neural networks (ANN) approach to predict nickel concentration in external phase during emulsion liquid membrane extraction process. Experimental data from laboratory batch analysis of nickel extraction have been used to train, validate and test the back-propagation ANN model. The input neurons correspond to, external phase pH, stripping phase concentration, stirring speed, carrier concentration, surfactant concentration, treatment ratio (volume ratio of emulsion to external phase), phase ratio (volume ratio of membrane to stripping phase), initial external phase nickel(II) concentration, and time. A tree -layer network with different hidden neurons and different learning algorithms such as LM, SCG, and BR were examined. The network with six hidden neurons and Bayesian regularization (BR) algorithm showed good performance. The predicted values of solute concentration in external phase are found to be in good agreement with the experimental results, with average absolute deviation (ADD%) of 0.2664% and correlation coefficient R 2 of 0.977. The results of this study show that the ANN model trained on experimental measurements can be successfully applied to the rapid prediction of external phase concentration