Application of Artificial Neural Network (ANN) for Modelling Chromium(VI) removal using Iron Oxide Nanoparticles
Nowadays, one of the most important environmental pollution is heavy metals industrial wastewater. Among the various types of heavy metals, chromium is one of the hazardous and toxic environmental pollutants. In order to prevent damage caused by chromium, it seems essential to prevent its entrance t...
Main Authors: | , |
---|---|
Format: | Article |
Language: | fas |
Published: |
Iranian Rainwater Catchment Systems Association
2017-03-01
|
Series: | محیط زیست و مهندسی آب |
Subjects: | |
Online Access: | http://www.jewe.ir/article_40978_8ceca06b17bb49a3ed443fcf8c273ef7.pdf |
_version_ | 1797783557813305344 |
---|---|
author | Elham Asrari Vahide Khosravi |
author_facet | Elham Asrari Vahide Khosravi |
author_sort | Elham Asrari |
collection | DOAJ |
description | Nowadays, one of the most important environmental pollution is heavy metals industrial wastewater. Among the various types of heavy metals, chromium is one of the hazardous and toxic environmental pollutants. In order to prevent damage caused by chromium, it seems essential to prevent its entrance to the environment. The purpose of this study was modelling chromium removal using iron oxide nanoparticles through artificial neural network model for estimating the best removal Cr(VI) model. The optimum conditions (more than 90% removal efficiency) achieved were at pH=3, initial concentration of Cr = 10 mg/L; dosage of Fe2O3 = 1 g/L; contact time = 60 minutes, and temperature =25 . After backpropagation (BP) training, the ANN model was able to predict adsorption efficiency with a tangent sigmoid transfer function (Tansig) at hidden layer with 11 neurons and a linear transfer function (Purelin) at out layer. The Levenberg-Marquardt algorithm (LMA) was applied, giving a minimum mean squared error (MSE) for training and cross validation at the ninth place of decimal. The high correlation coefficient (R2ANN = 0.996) between the model and its closeness to the experimental coefficient (R2Exp = 0.998) showed that the model is able to predict the removal of Cr(VI) from aqueous solutions by iron oxide nanoparticles. |
first_indexed | 2024-03-13T00:27:35Z |
format | Article |
id | doaj.art-ebfc33eda2c044e38856ee4b23c2a267 |
institution | Directory Open Access Journal |
issn | 2476-3683 |
language | fas |
last_indexed | 2024-03-13T00:27:35Z |
publishDate | 2017-03-01 |
publisher | Iranian Rainwater Catchment Systems Association |
record_format | Article |
series | محیط زیست و مهندسی آب |
spelling | doaj.art-ebfc33eda2c044e38856ee4b23c2a2672023-07-11T04:41:27ZfasIranian Rainwater Catchment Systems Associationمحیط زیست و مهندسی آب2476-36832017-03-0131303940978Application of Artificial Neural Network (ANN) for Modelling Chromium(VI) removal using Iron Oxide NanoparticlesElham Asrari0Vahide Khosravi1Associate Prof., Department of Engineering, Faculty of Civil Engineering, Payam-e-Noor University, Shiraz, IranM.Sc. Department of Civil Engineering (Environment), Faculty of Civil Engineering, Payam-e-Noor University, Shiraz, IranNowadays, one of the most important environmental pollution is heavy metals industrial wastewater. Among the various types of heavy metals, chromium is one of the hazardous and toxic environmental pollutants. In order to prevent damage caused by chromium, it seems essential to prevent its entrance to the environment. The purpose of this study was modelling chromium removal using iron oxide nanoparticles through artificial neural network model for estimating the best removal Cr(VI) model. The optimum conditions (more than 90% removal efficiency) achieved were at pH=3, initial concentration of Cr = 10 mg/L; dosage of Fe2O3 = 1 g/L; contact time = 60 minutes, and temperature =25 . After backpropagation (BP) training, the ANN model was able to predict adsorption efficiency with a tangent sigmoid transfer function (Tansig) at hidden layer with 11 neurons and a linear transfer function (Purelin) at out layer. The Levenberg-Marquardt algorithm (LMA) was applied, giving a minimum mean squared error (MSE) for training and cross validation at the ninth place of decimal. The high correlation coefficient (R2ANN = 0.996) between the model and its closeness to the experimental coefficient (R2Exp = 0.998) showed that the model is able to predict the removal of Cr(VI) from aqueous solutions by iron oxide nanoparticles.http://www.jewe.ir/article_40978_8ceca06b17bb49a3ed443fcf8c273ef7.pdfremovalchromiumiron oxide nanoparticlesaqueous solutionsneural network |
spellingShingle | Elham Asrari Vahide Khosravi Application of Artificial Neural Network (ANN) for Modelling Chromium(VI) removal using Iron Oxide Nanoparticles محیط زیست و مهندسی آب removal chromium iron oxide nanoparticles aqueous solutions neural network |
title | Application of Artificial Neural Network (ANN) for Modelling Chromium(VI) removal using Iron Oxide Nanoparticles |
title_full | Application of Artificial Neural Network (ANN) for Modelling Chromium(VI) removal using Iron Oxide Nanoparticles |
title_fullStr | Application of Artificial Neural Network (ANN) for Modelling Chromium(VI) removal using Iron Oxide Nanoparticles |
title_full_unstemmed | Application of Artificial Neural Network (ANN) for Modelling Chromium(VI) removal using Iron Oxide Nanoparticles |
title_short | Application of Artificial Neural Network (ANN) for Modelling Chromium(VI) removal using Iron Oxide Nanoparticles |
title_sort | application of artificial neural network ann for modelling chromium vi removal using iron oxide nanoparticles |
topic | removal chromium iron oxide nanoparticles aqueous solutions neural network |
url | http://www.jewe.ir/article_40978_8ceca06b17bb49a3ed443fcf8c273ef7.pdf |
work_keys_str_mv | AT elhamasrari applicationofartificialneuralnetworkannformodellingchromiumviremovalusingironoxidenanoparticles AT vahidekhosravi applicationofartificialneuralnetworkannformodellingchromiumviremovalusingironoxidenanoparticles |