Description of Lead Removal from Aqueous Solution Onto Eggshell Using Artificial Neural Network

Abstract

A 130 batch experiments were conducted for prediction the uptake of Pb(II) from simulated aqueous solutions onto chicken eggshell using artificial neural network model. Many operational conditions are considered in this process such as contact time (10-240 min), initial pH of the solution (3-7), initial lead concentration (50-300 mg/l), eggshell dosage (0.1-4 g/100 ml), and agitation speed (0-300 rpm). The best values of these parameters that achieved the maximum uptake (=90 %) of Pb(II) were 60 min, 5, 50 mg/l, 2 g/100 ml, and 200 rpm respectively at room temperature (=25 ºC). The artificial neural network model was able to predict sorption efficiency with a tangent sigmoid transfer function at hidden layer and a linear transfer function at output layer based on10 neurons. The linear regression between the outputs of the model and the corresponding targets were acceptable with a correlation coefficient of 0.99738 for adopted variables.