Prediction of ionic Cr (VI) extraction efficiency in flat sheet supported liquid membrane using artificial neural networks (ANNs)

Artificial neural networks (ANNs) are computer techniques that attempt to simulate the func-tionality and decision-making processes of the human brain. In the past few decades, artificial neural networks (ANNs) have been extensively used in a wide range of engineering applications. There are only a few applica-tions in liquid membrane process. The objective of this research was to develop artificial neural networks (ANNs) model to estimate Cr (VI) extraction efficiency in feed phase.Data set (413 experiment records) were obtained from a laboratory scale experimental study. Various combinations of experimental data, namely % (w/w) extractant Alamine 336 concentration in membrane phase, stirring speed in feed and stripping phase, flat sheet support type, stripping phase NaOH concentration, feed phase pH, diluents type, % (w/w) diluents concentration, polymer support type, extractant type, and time are used as inputs into the ANN so as to evaluate the degree of effect of each of these variables on Cr (VI) extraction efficiency in feed phase. The results of the ANN model is compared with multiple linear regression model (MLR). Mean square error (MSE), average absolute relative error (AARE) and coefficient of determination (R² ) statistics are used as comparison criteria for the evaluation of the model performances. Based on the comparisons, it was found that the ANN model could be employed successfully in estimating the Cr (VI) extraction efficiency.

Keywords
Artificial neural networks, multiple linear regression models, supported liquid membrane, chromium (VI) extraction, solvent extraction