PREDICTION OF ADSORPTION EFFICIENCY FOR THE REMOVAL OF NICKEL (II) IONS BY ZEOLITE USING ARTIFICIAL NEURAL NETWORK (ANN) APPROACH

Abstract

This paper presents the development of an artificial neural network (ANN) model for the prediction of the adsorption efficiency (AE %) of nickel (II) ions from aqueous solution by zeolite based on 120 experimental data sets obtained in a bench scale experiments. The ANN models developed in this study used three input variables including initial concentration of Ni (II) ions, adsorbent dosage, and contact time for predicting corresponding AE %. The performance of the ANN models were assessed through root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R(2)), and T statistics. The ANN model was able to predict AE % of Ni (II) ions with a tangent sigmoid transfer function (tansig) in hidden layer with 12 neurons and a linear transfer function (purelin) in output layer and the BFGS quasi-Newton algorithm (trainbfg) was found as the best training algorithm with a minimum RMSE of 0.0222. The modeling results indicated that there was an excellent agreement between the experimental data and predicted values.