Evaluate the performance of Fenton process for the removal of Methylene Blue from aqueous solution: experimental, neural network modeling and optimization

In this article, degradation of Methylene Blue by Fenton's oxidation process was investigated. The effect of, Fe²⁺ and H₂O₂ concentrations and reaction time in initial concentration of the dye = 10 mg/L, pH = 3 and lab temperature on the dye removal was studied. Also, Artificial Neural Networks (ANN) was applied to model the dye removal data obtained by Fenton oxidation process. A network consisting of two layers of eight neurons in the hidden layer was considered. Very low root mean squared error (RMSE) of 1.262 and high determination of coefficient (R²) of 0.995 in the network calculation verified validity of the acquired network for further analysis and optimization. © 2018 American Institute of Chemical Engineers Environ Prog, 2018