Artificial neural network model for removal of copper ions from pollutant solutions by olives seeds powder

Abstract

Artificial Neural Network (ANNs) model was done to develop and to predict the Pollutant Removal Efficiency (PRE) of Copper Cu (II) ions from polluted solution by olives seeds powder. Five model variables as Adsorbent dosage, the initial concentration, initial pH, agitation speed, and contact time was studied to optimize the conditions for maximum removal efficiency of Cu (II) ions. Perceptron Multilayer Networks (PMN), with a back-propagation algorithm where the sigmoid axon transforms function for input and output layers is adopted. The PMN model is systematically trained with 425 data points and is validated with data points from the database. The optimum values of learning parameters that are giving encouraging and satisfactory with a correlation coefficient of about 0.983 at training and 0.987 at verification for variables used in this study. The model results showed that the major important parameter influencing on the removal efficiency is the initial copper concentration 37.3%, olive seeds dosage 23.53%, the agitation speed 21%, the pH 10.38%, and smallest influence has the contact time 7.77%. The results showed a good agreement between the ANN model result and the experimental result.