z-logo
Premium
Artificial neural network modeling for removal of azo dye from aqueous solutions by Ti anode coated with multiwall carbon nanotubes
Author(s) -
Nabizadeh Chianeh Farideh,
Basiri Parsa Jalal,
Rezaei Vahidian Hadi
Publication year - 2017
Publication title -
environmental progress and sustainable energy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.495
H-Index - 66
eISSN - 1944-7450
pISSN - 1944-7442
DOI - 10.1002/ep.12650
Subject(s) - anode , aqueous solution , materials science , electrochemistry , carbon nanotube , electrode , chemical engineering , electrophoretic deposition , current density , titanium , composite material , chemistry , coating , metallurgy , organic chemistry , physics , quantum mechanics , engineering
In this study, a titanium based electrode, coated with multiwall carbon nanotubes (MWCNTs/Ti) was applied as anode in a laboratory‐made electrochemical reactor. The MWCNTs/Ti electrode was prepared by the electrophoretic deposition (EPD) method in an aqueous solution and was characterized by field emission scanning electron microscopy. The prepared electrode was used as anode in decolorization of C.I. Acid Red 33 as typical target pollutant in aqueous solutions. Effect of pH, current density, and reaction time was evaluated on color removal efficiency. The experimental studies revealed that color removal efficiency and TOC removal efficiency were 90 and 15%, respectively, at optimum conditions: pH = 8, current density of 5.5 mA/cm 2 and reaction time of 60 min. Also, the electrochemical decolorization was modeled using a three‐layered feed‐forward back propagation artificial neural network (ANN), consisting of “trainbfg” as learning algorithm, “tansig” transfer function in the hidden layer with 10 neuron and “purelin” as output transfer function in order to predict the color removal efficiency. Comparison between the predicted values and selective experimental data showed that the developed ANN model has a high correlation coefficient ( R 2 ) of 0.995 and can predict decolorization efficiency with acceptable accuracy. © 2017 American Institute of Chemical Engineers Environ Prog, 36: 1778–1784, 2017

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here