Modeling the degradation of Sunset Yellow FCF azo dye by Fe2O3/Bentonite catalyst using artificial neural networks

Subject Areas : Journal of Nanoanalysis

Mohammad Ehsan Mosayebian ¹ , Reza Moradi ² , Kazem Mahanpoor ³

1 - Department of Chemistry, Tuyserkan Branch, Islamic Azad University, Tuyserkan, Iran Department of Electrical Engineering, Tuyserkan Branch, Islamic Azad University, Tuyserkan, Iran
2 - Department of Chemistry, Tuyserkan Branch, Islamic Azad University, Tuyserkan, Iran.
3 - Department of Chemistry, Arak Branch, Islamic Azad University, Arak, Iran

Received: 2021-10-19 Accepted : 2021-10-19 Published : 2021-09-01

Keywords: Artificial Neural Network, Photocatalyst, Fe2O3/Bentonite, Sunset Yellow FCF,

Abstract :

In this paper, the precipitation method has been used to stabilize Fe2O3 particleson Bentonite zeolite (BEN). Fe2O3/BEN catalysts have been characterized byscanning electron microscopy (SEM), X-ray diffraction (XRD), and Brunauer-Emmett-Teller (BET) surface area analysis. Artificial neural network (ANN)was used for modeling the photocatalytic degradation of Sunset Yellow FCF(SYF) azo dye in aqueous solution under irradiation in the batch photoreactor.The parameters including pH, catalyst amount, dye concentration and H2O2concentration was applied as input; the output of the network was degradationpercentage. Modeling the results of the photocatalytic degradation of dye using afeed-forward, backpropagation three-layer network, topology (4:7:1) with fourneurons in the input layer, seven neurons in the hidden layer, and one neuron inthe output layer was used. Comparison between data obtained from ANN andexperimental data indicated that the proposed ANN model provides reasonablepredictive performance. The optimum conditions were as follows: pH= 4, catalystamount=60 mg/L, dye concentration =50 ppm and H2O2 concentration =32ppm. The chemical oxygen demand (COD) analysis of the dye under optimumconditions showed a 91% reduction in 80 min period.