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

Document Type: Full article

Authors

1 Iran Alumina Complex, P.O. Box 944115-13114, Jajarm, Iran.

2 School of Chemical Engineering, Iran University of Science and Technology, Tehran, P.O. Box 16765-163, Iran

Abstract

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.

Keywords


[1]   Barnes, M. C. Addai-Mensah, J. and Gerson, A.R., "The solubility of sodalite and cancrinite in synthetic spent Bayer liquor", Colloids Surf., 157, 101(1999b).

[2]   Sonthalia, R. Behara, P. Kumaresan, T. and Thakre, S., "Review on alumina trihydrate precipitation mechanisms and effect of Bayer impurities on hydrate particle growth rate", J. Miner. Proc. 125, 137 (2013).

[3]   Xiao, J. B. Jiang, X. Y. and Chen, X. Q., "Identification of Organic Acids in Bayer Liquors By GC–MS: A Comparison Using Butylation and Methylation", J. Chromatogr. Sci., 45, 183 (2007).

[4]   Barnes, M. C. Addai-Mensah, J. and Gerson, A.R., "The mechanism of the sodalite-to-cancrinite phase transformation in synthetic spent Bayer liquor", Microporous Mesoporous Mater., 31, 287 (1999a).

[5]   Xu, B. Wingate, C. and Smith, P., "The effect of surface area on the modelling of quartz dissolution under conditions relevant to the Bayer process", Hydrometallurgy, 98, 108 (2009).

[6]   Kumaresan, T. Thakre, S. S. Basu, B. Kaple, K. Gupta, H. P. Bandi, A. Chaturvedi, P. Roy, N. N. Gararia, S. N. Sapra, V. and Shah, R. P., "Performance improvement of alumina digestors". 7th International Conference on CFD in the Minerals and Process Industries CSIRO, Melbourne, Australia (2009).

[7]   Zhao, Q. J. Yang, Q. F. Chen, Q. Y. Yin, Z. L. Wu, Z. P. and Yin, Z. G., "Behavior of silicon-containing minerals during Bayer digestion", Trans. Nonferrous Met. Soc. China., 20, 1 (2010).

[8]   Leonard, J., "Proceeding of bauxite symposium". Published by SME Los angles, California, pp 656 (1984).

[9]   Ma, S. H. Wen, Z. G. Chen, J. N. and Zheng, S. L., "An environmentally friendly design for low-grade diasporic-bauxite processing", Miner. Eng., 22, 793 (2009).

[10]  Liu, W. Yang, J. and Xiao, B., "Review on treatment and utilization of bauxite residues in China", Int. J. Miner. Proc., 93, 220 (2009).

[11]  Xiao-bin, L. Wei, X. Wei, L, Gui-hua, L. Zhi-hong, P. Qiu-sheng, Z. and Tian-gui, Q., "Recovery of alumina and ferric oxide from Bayer red mud rich in iron by reduction sintering", Trans. Nonferrous Met. Soc. China., 19, 1342 (2009).

[12]  Liu, W., "The developing of red mud utilization in china", Zhengzhou Research Institute of CHALCO., 1 (2015).

[13]  Ghaemi, A. Shahhoseini, Sh. Ghannadi Marageh, M. and Farrokhi, M., "Prediction of Vapor-Liquid Equilibrium for Aqueous Solutions of Electrolytes Using Artificial Neural Networks", J. Appl. Sci., 8, 615 (2008).

[14]  Ganguly, S., "Prediction of VLE data using radial basis function network", Comput. Chem. Eng., 27, 1445 (2003).

[15]  Hemmat E, M. Afrand, M. Wongwises, S. Naderi, A. Asadi, A., Rostami, S. and Akbari, M., "Applications of feedforward multilayer perceptron artificial neural networks and empirical correlation for prediction of thermal conductivity of Mg(OH)2–EG using experimental data", Int. Commun. Heat and Mass Transfer, 67, 46 (2015).

[16]  Zhang, J. Feng, Q. Zhang, X. Zhang, X. Yuan, N.  Wen, S. Wang, S. and Zhang, A., "The use of an artificial neural network to estimate natural gas/water interfacial tension", Fuel., 157, 28 (2015).

[17]  Aish, A. M.  Zaqoot, H. A. and Abdeljawad, S. M., "Artificial neural network approach for predicting reverse osmosis desalination plants performance in the Gaza Strip", Desalination, 367, 240 (2015).

[18]  Chelgani, S. C. and Jorjani, E., "Artificial neural network prediction of Al2O3 leaching recovery in the Bayer process—Jajarm alumina plant (Iran)", Hydrometallurgy, 97, 105 (2009).

[19]  Duric, I. Mihajlovic, I. Zivkovic, Z. and Dragana, K., "Artificial neural network prediction of aluminum extraction from bauxite in the Bayer process", J. Serbian chem. Soc., 76, 1259 (2012).

[20]  Oludolapo, O. A. Jimoh, A. A. and Kholopane, P.A., "Comparing performance of MLP and RBF neural network models for predicting South Africa’s energy consumption", J. Energy South. Afr., 23, 40 (2012).

[21]  Mata J., "Interpretation of concrete dam behavior with artificial neural network and multiple linear regression models", Eng. Struct., 33, 903 (2011).

[22]  Labiosa, A. A., "Dynamic simulation of red mud washers used in aluminum industries". Msc thesis, School of civil, Environmental and chemical engineering RMIT university victoria, 3000, Australia (2010).

[23]  Almeida, L. B., "Multilayer perceptrons. Handbook of Neural Computation". Publishing Ltd and Oxford University Press, C1.2, 1 (1997).

[24]  Memarian, H. and Balasundram, S. K., "Comparison between Multi-Layer Perceptron and Radial Basis Function Networks for Sediment Load Estimation in a Tropical Watershed", J. Water Res. Prot., 4, 870 (2012).

[25]  Salarian, T. Zare, M. and Mahmoudi, M., "Evaluation of shallow landslides hazard using artificial neural network of Multi-Layer Perceptron method in Subalpine Grassland (Case study: Glandrood watershed - Mazandaran)", Int. J. Agriculture Crop Sci., 7, 795 (2014).

[26]  Firoozi, S. Sheikhdavoodi, M. J. and Sami, M., "Evaluation the Ability of Different Artificial Intelligence-Based Modeling Techniques in Prediction of Yield Using Energy Inputs Data of Farms", J. Life Sci. Biomed., 4, 305 (2014).

[27]  Lasota, T. Makos, M. and Trawinski, B., "Comparative Analysis of Neural Network Models for Premises Valuation Using SAS Enterprise Miner", New Challenges Comput. Collective Int., 244, 337 (2009).

[28]  Russo, A. Raischel, F. and Lind P. G., "Air quality prediction using optimal neural networks with stochastic variables", Atmos. Environ., 79, 822 (2013).

[29]  Amato, F. Lopez, A. Peña-Méndez, E.M. Vaňhara, P. Hampl, A. and Havel, J., "Artificial neural networks in medical diagnosis", J. Appl. Biomed., 11, 47 (2013).

[30]  Nogay, H. S. Akinci, T. C. and Eidukeviciute, M., "Application of artificial neural networks for short term wind speed forecasting in Mardin, Turkey", J. Energy South. Afra., 23, 1 (2012).

[31]  Omurlu, I. K. Ture, M. Unubol, M. Katranci, M. and Guney, E., "Comparing Performances of Logistic Regression, Classification & Regression Trees and Artificial Neural Networks for Predicting Albuminuria in Type 2 Diabetes Mellitus", Int. J. Sci. Basic and Appl. Res., 16, 173 (2014).

[32]  Vali, A. A. Ramesht, M. H. and Mokarram, M., "The Comparison of RBF and MLP Neural Networks Performance for the Estimation of Land Suitability", J. Environ., 2, 74 (2013).

[33]  Benghanem, M. and Mellit, A., "Radial Basis Function Network-based prediction of global solar radiation data: Application for sizing of a standalone photovoltaic system at Al-Madinah, Saudi Arabia", Energy, 35, 3751 (2010).

[34]  Mellit, A. and Kalogirou, S., "Artificial intelligence techniques for photovoltaic applications: a review", Prog. Energy Comb. Sci., 34, 574 (2008).

[35]  Abu Bakar, N. M. and Tahir, I. M., "Applying Multiple Linear Regression and Neural Network to Predict Bank Performance", Int. Bus. Res., 2, 176 (2009).

[36]  Mustafar, I. B. and Razali, R., "A Study on Prediction of Output in Oilfield Using Multiple Linear Regression", Int. J. Appl. Sci. Technol., 1, 107 (2011).

[37]  Olaniyi, S. A. S. Kayode, S, A. and Jimoh, R. G., "Stock Trend Prediction Using Regression Analysis – A Data Mining Approach", ARPN J. Sys. Softwr., 1, 154 (2011).

[38]  Abyaneh, H. Z., "Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters", J.
Environ. Health Sci. Eng.,
12, 1(2014).

[39]  Razi, M. A. and Athappilly, K., "A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models", Expert. Syst. Appl., 29, 65 (2005).

[40]  Anyaeche, C. O. and Ighravwe D. E., "Predicting performance measures using linear regression and neural network: A comparison", Afr. J. Eng. Res., 1, 84 (2013).

[41]  Ghaffari Moghaddam, M. Ahmad, F. B. H. Basri, M. and Abdul Rahman, M. B., "Artificial neural network modeling studies to predict the yield of enzymatic synthesis of betulinic acid ester", Electr. J. Biotech., 13, 1 (2010).

[42]  Bas, D. and Boyac, I. H., "Modeling and optimization II: Comparison of estimation capabilities of response surface methodology with artificial neural networks in a biochemical reaction", J. Food Eng., 78, 846 (2007).

[43]  Kia, E. Emadi, A. R. and Fazlola, R., "Investigation and Evaluation of Artificial Neural Networks in Babolroud River Suspended Load Estimation", J. Civil Eng. Urbanism, 3, 183 (2013).

[44]  Xu, B. Smith, P. Wingate, C. and Silva, L. D., "The effect of calcium and temperature on the transformation of sodalite to cancrinite in Bayer digestion", Hydrometallurgy, 105, 75 (2010).