ARTIFICIAL NEURAL NETWORK APPROACH FOR MODELING OF Ni(II) ADSORPTION FROM AQUEOUS SOLUTION BY PEANUT SHELL

Abstract

In this study, ANN (artificial neural network) model was applied to estimate the Ni(II) removal efficiency of peanut shell based on batch adsorption tests. The effects of initial pH, metal concentrations, temperature, contact time and sorbent dosage were determined. Also, COD (chemical oxygen demand) was measured to evaluate the possible adverse effects of the sorbent during the tests performed with varying temperature, pH and sorbent dosage. COD was found as 96.21 mg/dm(3) at pH 2 and 54.72 mg/dm(3) at pH 7. Also, a significant increase in COD value was observed with increasing dosage of the used sorbent. COD was found as 12.48 mg/dm(3) after use of 0.05 g sorbent and as 282.78 mg/dm(3) after use of 1 g sorbent. During isotherm studies, the highest regression coefficient (R-2) value was obtained with Freundlich isotherm (R-2 = 0.97) for initial concentration and with Temkin isotherm for sorbent dosage. High pseudo-second order kinetic model regression constants were observed (R-2 = 0.95-0.99) during kinetic studies with varying pH values. In addition, Ni(II) ion adsorption on peanut shell was further defined with pseudo-second order kinetic model, since q(e) values in the second order kinetic equation were very close to the experimental values. The relation between the estimated results of the built ANN model and the experimental results were used to evaluate the success of ANN modeling. Consequently, experimental results of the study were found to be in good agreement with the estimated results of the model.