Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks

In the Bayer process, the reaction of silica in bauxite with caustic soda causes the loss of great amount of NaOH. In this research, the bound-soda losses in Bayer process solid residue (red mud) are predicted using intelligent techniques. This method, based on the application of regression and arti...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Mahmoudian, A. Ghaemi, H. Hashemabadi
Format: Article
Language:English
Published: Iranian Association of Chemical Engineering (IAChE) 2016-04-01
Series:Iranian Journal of Chemical Engineering
Subjects:
Online Access:https://www.ijche.com/article_15372_adb8c99476d998d53bba15d9b470fafa.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714719121735680
author M. Mahmoudian
A. Ghaemi
H. Hashemabadi
author_facet M. Mahmoudian
A. Ghaemi
H. Hashemabadi
author_sort M. Mahmoudian
collection DOAJ
description In the Bayer process, the reaction of silica in bauxite with caustic soda causes the loss of great amount of NaOH. In this research, the bound-soda losses in Bayer process solid residue (red mud) are predicted using intelligent techniques. This method, based on the application of regression and artificial neural networks (AAN), has been used to predict red mud bound-soda losses in Iran Alumina Company. Multilayer perceptron (MLP), radial basis function (RBF) networks and multiple linear regressions (MLR) were applied. The results of three methodologies were compared for their predictive capabilities in terms of the correlation coefficient (R), mean square error (MSE) and the absolute average deviation (AAD) based on the experimental data set. The optimum MLP network was obtained with structure of two hidden layer including 13 and 15 neurons in each layer respectively. The results showed that the RBF model with 0.117, 5.909 and 0.82 in MSE, AAD and R, respectively, is extremely accurate in prediction as compared with MLP and MLR.
format Article
id doaj-art-9a15c82124b74429afb7de0e45d2b9fb
institution DOAJ
issn 1735-5397
2008-2355
language English
publishDate 2016-04-01
publisher Iranian Association of Chemical Engineering (IAChE)
record_format Article
series Iranian Journal of Chemical Engineering
spelling doaj-art-9a15c82124b74429afb7de0e45d2b9fb2025-08-20T03:13:38ZengIranian Association of Chemical Engineering (IAChE)Iranian Journal of Chemical Engineering1735-53972008-23552016-04-01132465615372Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural NetworksM. Mahmoudian0A. Ghaemi1H. Hashemabadi2Iran Alumina Complex, P.O. Box 944115-13114, Jajarm, Iran.School of Chemical Engineering, Iran University of Science and Technology, Tehran, P.O. Box 16765-163, IranIran Alumina Complex, P.O. Box 944115-13114, Jajarm, Iran.In the Bayer process, the reaction of silica in bauxite with caustic soda causes the loss of great amount of NaOH. In this research, the bound-soda losses in Bayer process solid residue (red mud) are predicted using intelligent techniques. This method, based on the application of regression and artificial neural networks (AAN), has been used to predict red mud bound-soda losses in Iran Alumina Company. Multilayer perceptron (MLP), radial basis function (RBF) networks and multiple linear regressions (MLR) were applied. The results of three methodologies were compared for their predictive capabilities in terms of the correlation coefficient (R), mean square error (MSE) and the absolute average deviation (AAD) based on the experimental data set. The optimum MLP network was obtained with structure of two hidden layer including 13 and 15 neurons in each layer respectively. The results showed that the RBF model with 0.117, 5.909 and 0.82 in MSE, AAD and R, respectively, is extremely accurate in prediction as compared with MLP and MLR.https://www.ijche.com/article_15372_adb8c99476d998d53bba15d9b470fafa.pdfneural networklinear regressionbound-sodared mudbayer process
spellingShingle M. Mahmoudian
A. Ghaemi
H. Hashemabadi
Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks
Iranian Journal of Chemical Engineering
neural network
linear regression
bound-soda
red mud
bayer process
title Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks
title_full Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks
title_fullStr Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks
title_full_unstemmed Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks
title_short Prediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks
title_sort prediction of red mud bound soda losses in bayer process using neural networks
topic neural network
linear regression
bound-soda
red mud
bayer process
url https://www.ijche.com/article_15372_adb8c99476d998d53bba15d9b470fafa.pdf
work_keys_str_mv AT mmahmoudian predictionofredmudboundsodalossesinbayerprocessusingneuralnetworks
AT aghaemi predictionofredmudboundsodalossesinbayerprocessusingneuralnetworks
AT hhashemabadi predictionofredmudboundsodalossesinbayerprocessusingneuralnetworks