Application of artificial neural network (ANN) for modeling of dyes decolorization by Sn/Zn-TiO2nanoparticles

Abstract

This study examined the implementation of artificial neural network (ANN) for the prediction and modeling of methylene blue (MB) and methyl orange (MO) dyes decolorization in aqueous solution using Sn/Zn-TiO2 nanoparticles prepared by sol–gel method. Operational parameters such as amount of catalyst, concentration of dye, reaction time, and temperature of solution were employed as inputs to the network and dye decolorization efficiency was the output of the network. ANN predicted results are in good agreement with the experimental results data with a correlation coefficient (R2) of 0.9839 and 0.9887 for MB and MO dyes, respectively. The sensitivity analysis investigated that studied parameters have different effect on dyes decolorization. For both dyes, reaction time is the most influential parameter and the temperature of solution is the less influential variable in the removal efficiency of both dyes. The results indicated that neural network modeling could effectively predict and model the photocatalytic activity of the prepared Sn/Zn-TiO2 nanoparticles.