Prediction of azo dye decolorization by UV/H2O2 using artificial neural networks

Abstract:The commercially available nanoscale zerovalent zinc (nZVZ) was used as an adsorbent for the removal of malachite green (MG) from aqueous solutions. This material was characterized by X-ray diffraction and X-ray photoelectron spectroscopy. The advanced experimental design tools were adopted to study the effect of process parameters (viz. initial pH, temperature, contact time and initial concentration) and to reduce number of trials and cost. Response surface methodology and rapidly developing artificial intelligence technologies, i.e., artificial neural network coupled with particle swarm optimization (ANN-PSO) and artificial neural network coupled with genetic algorithm (ANN-GA) were employed for predicting the optimum process variables and obtaining the maximum removal efficiency of MG. The results showed that the removal efficiency predicted by ANN-GA (94.12%) was compatible with the experimental value (90.72%). Furthermore, the Langmuir isotherm was found to be the best model to describe the adsorption of MG onto nZVZ, while the maximum adsorption capacity was calculated to be 1000.00 mg/g. The kinetics for adsorption of MG onto nZVZ was found to follow the pseudo-second-order kinetic model. Thermodynamic parameters (∆G 0 , ∆H 0 and ∆S 0 ) were calculated from the Van't Hoff plot of lnKc vs. 1/T in order to discuss the removal mechanism of MG.

show abstract

“…The relative influence of the individual variable was calculated by the following Garson equation [35,36]:…”

Section: Back Propagation Artificial Neural Network (Bp-ann)mentioning

confidence: 99%

Modeling of Malachite Green Removal from Aqueous Solutions by Nanoscale Zerovalent Zinc Using Artificial Neural Network

Ruan

Shi

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…10. Comparison between predicted and measured decolorization (Aleboyeh et al, 2008) 4.5 Decolorization process modeling by neural network Guimarães et al (2008) developed an artificial neural network model for the prediction and simulation of photochemical decolorization of acid orange 52 dye solution by the UV/H 2 O 2 process. The input variables were dye concentration, pH, hydrogen peroxide concentration, temperature and time of operation.…”

Section: Wwwintechopencommentioning

confidence: 99%

“…The sensitivity analysis was conducted using two methods. The first one was based on the neural net weight matrix and Garson equation (Aleboyeh et al, 2008). Garson (1991) proposed an equation based on the partitioning of connection weights where, I j is the relative importance of the j th input variable on the output variable, N i and N h are the numbers of input and hidden neurons, respectively, Ws are connection weights, the superscripts 'i', 'h' and 'o' refer to input, hidden and output layers, respectively, and subscripts 'k', 'm' and 'n' refer to input, hidden and output neurons, respectively.…”

Section: Case Studiesmentioning

confidence: 99%

See 1 more Smart Citation

The Use of Artificial Neural Network (ANN) for Modelling, Simulation and Prediction of Advanced Oxidation Process Performance in Recalcitrant Wastewater Treatment

Elmolla¹,

Chaudhuri²

2011

Artificial Neural Networks - Application

View full text Add to dashboard Cite

“…The most effective ways of wastewater treatment from organic pollutants are the "advanced oxidation processes", in which the oxidation of organic substances is carried out by a highly active oxygen-containing particles or radicals generated from H 2 O 2 , O 2 and O 3 [3]. These technologies include Fenton and photo-Fenton Fe-peroxide systems (Fe 2+ /H 2 O 2 , Fe 3+ /H 2 O 2 , Fe 3+ /(H 2 O 2 ,UV)), with which deep oxidation of organic compounds occurs to carbon dioxide, water and inorganic ions [4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Catalytic Properties of Fe-containing Layered Aluminosilicates in Photo-oxidation of Dye “Methyl Green”

Shadrina

Dashinamzhilova

Khankhasaeva

2017

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Abstract. The iron-containing materials with an iron content of 40 mg/g and 52.5 mg/g, a specific surface area of 107 m 2 /g and 96 m 2 /g are developed on the basis of natural layered aluminosilicate (montmorillonite) and polyhydroxo complexes of iron. It is shown that the materials exhibit high catalytic activity in the photo-oxidation of dye "Methyl Green". The influence of physicochemical parameters (loading of the catalyst, a ratio of initial concentrations [H 2 O 2 ]/[MG] on the efficiency of the dye photo-oxidation was established. The optimum conditions, which made it possible to achieve high mineralization and 100 % the dye oxidation efficiency were determined: the catalyst loading equal to 1.0 g/l and the ratio of [H 2 O 2 ] and [MG] equal to stoichiometric ratio (55 mol/mol). The decrease of the total organic carbon content after photo-oxidation reaction was 56.5%. The average value of the quantum yield of the dye photo-oxidation was to 0.30 mol/Einstein. The results of the conducted research show that the developed iron-containing materials are the promising catalysts for photo-Fenton processes of oxidative degradation of organic compounds. The materials are of interest for use in wastewater treatment processes from toxic organic pollutants.

show abstract

Prediction of azo dye decolorization by UV/H2O2 using artificial neural networks

Cited by 204 publications

References 20 publications

Modeling of Malachite Green Removal from Aqueous Solutions by Nanoscale Zerovalent Zinc Using Artificial Neural Network

Modeling of Malachite Green Removal from Aqueous Solutions by Nanoscale Zerovalent Zinc Using Artificial Neural Network

The Use of Artificial Neural Network (ANN) for Modelling, Simulation and Prediction of Advanced Oxidation Process Performance in Recalcitrant Wastewater Treatment

Catalytic Properties of Fe-containing Layered Aluminosilicates in Photo-oxidation of Dye “Methyl Green”

Contact Info

Product

Resources

About