Modeling and optimization of biosorptive removal of Zn (II) ions process using hybrid Artificial Neural Network and Genetic Algorithm
Volume Title: 1
1Tafresh university Department of chemical Engineering
2Tafresh university Department of Chemical Engineering
3Department of Chemical Engineering, Tafresh University
Zn (II) is one of the common pollutants among heavy metals found in industrial effluents. Removal of pollutant from industrial effluents like water can be accomplished by various techniques. The absorption process is an attractive method for wastewater treatment because it is economically feasible. In the last two decades, the use of artificial neural networks (ANN) is welcome by many researchers due to their acceptable accuracy for modeling purposes. Indeed, the ANN modeling technique has many favorable features such as efficiency, generalization, and simplicity, which make it an attractive tool for modeling of complex systems, such as wastewater treatment processes. In the present study, ANN-model has been effectively employed to predict the uptake rate of Zn (II) ions from industrial effluents. A multilayer perceptron (MLP) ANN and genetic algorithm (GA) have been used to predict Zn (II) uptake rate and optimize operating conditions of the process. Four independent variables including PH, initial concentration of Zn (II) ions, temperature and dosage of biosorbent were selected as the input variables of the model. The results indicated that the ANN-model was successfully predicted the uptake rate of Zn (II) ions with acceptable accuracy, with the relative error as 12.12%. At the optimal conditions, the biosorption capacity was 75.172 (mg/g).