• Vol 6, No 3 (2015)
  • Industrial Engineering

Artificial Neural Network Modeling and Optimization of Hall-Heroult Process for Aluminum Production

Sepehr Sadighi, Reza Seif Mohaddecy, Yasser Arab Ameri

Corresponding email: sadighis@ripi.ir

Published at : 29 Jul 2015
IJtech : IJtech Vol 6, No 3 (2015)
DOI : https://doi.org/10.14716/ijtech.v6i3.887

Cite this article as:

Sadighi, S., Mohaddecy, R.S., Ameri, Y.A., 2015. Artificial Neural Network Modeling and Optimization of Hall-Heroult Process for Aluminum Production. International Journal of Technology. Volume 6(3), pp. 480-491

Sepehr Sadighi Catalytic Reaction Engineering Department, Catalysis Research Division, Research Institute of Petroleum Industry (RIPI), West Blvd., Azadi Sports Complex , P.O. Box 14665-137, Tehran , Iran
Reza Seif Mohaddecy Catalytic Reaction Engineering Department, Catalysis Research Division, Research Institute of Petroleum Industry (RIPI), West Blvd., Azadi Sports Complex , P.O. Box 14665-137, Tehran , Iran
Yasser Arab Ameri Faculties of Engineering, Shahrood branch, Islamic Azad University, Shahrood, Iran
Email to Corresponding Author


Experience in applying a hybrid artificial neural network (ANN)-genetic algorithm for modeling and optimizing the Hall-Heroult process for aluminum extraction is described in this study. During the stage of modeling, the most important and effective process variables including temperature and cell voltage, metal and bath heights, purity of CaF2 and Al2O3, and bath ratio are chosen as input variables whilst outputs of the model are product purity, ampere efficiency, and product rate. During three years of operation, 19 points were selected for building and training, 7 points for testing, and 7 data points for validating the model. Results show that a feed-forward Artificial Neural Network (ANN) model with 3 neurons in the hidden layer can acceptably simulate the mentioned output variables with the Mean Squared Error (MSE) of 0.002%, 0.108% and 0.407%, respectively. Utilizing the validated model and multi-objective genetic algorithms, aluminum purity and the rate of production are maximized by manipulating decision variables. Results show that setting these decision variables at the optimal values can increase approximately the metal purity, ampere efficiency, and product rate by 0.007%, 0.185%, and 20kg/h, respectively.

Aluminum production, Artificial neural network, Hall-Heroult process, Modeling, Optimization


Behbahani, R.M., Jazayeri-Rad, H., Hajmirzaee, S., 2009. Fault Detection and Diagnosis in a Sour Gas Absorption Column using Neural Networks. Chemical Engineering Technology, Volume 32, pp. 840-845

Bellos, G.D., Kallinikos, L.E., Gounaris, C.E., Papayannakos, N.G., 2005. Modeling of the Performance of Industrial HDS Reactors using a Hybrid Neural Network Approach. Chemical Engineering and Processing, Volume 44, pp. 505-515

Bhutani, N., Rangaiah, G.P., Ray, A., 2006. First-principles, Data-based and Hybrid Modeling and Optimization of an Industrial Hydrocracking Unit. Industrial and Engineering Chemical Research, Volume 45, pp. 7807-7816

Durici, I., Mihajlovici, I., Zivkovici, Z., Keselj, D., 2012. Artificial Neural Network Prediction of Aluminum Extraction from Bauxite in the Bayer Process. Journal of Serbian Chemical Society, Volume 76, pp. 1259-1271

Frost, F., Karri V., 2000. Productivity Improvements through Prediction of Electrolyte Temperature in Aluminum Reduction Cell using BP Neural Network. PRICAI 2000 Topics in Artificial Intelligence Lecture Notes in Computer Science, Volume 1886, pp. 490-499

Goldberg, D.E., 1989. Genetic Algorithms in Search Optimization and Machine Learning. Addison-Wesley, Reading, MA

Hagan, M.T., Demuth, H.B., Beale, M., 1995. Neural Network Design. PWS Publishing Company, Boston

Haupin, W.E., 1995. Principles of Aluminum Electrolysis. In: the Proceedings of the 124th TMS Annual Meeting, Las Vegas, pp. 195–203

Haykin, S., Hamilton, O., 1998. Neural Networks. Prentice Hall International, Inc., Upper Saddle River

Joshi, G., 2014. Review of Genetic Algorithm: An Optimization Technique. International Journal of Advanced Research in Computer Science and Software Engineering, Volume 4(4), pp. 802-805

Kalyanmoy, D., 2001. Multi-objective Optimization Using Evolutionary Algorithms. John Wiley & Sons

Keniry, J., 1994. Outline of the Reduction Process. In: Proc. Aluminum Smelting Fundamentals, Course 1, Comalco Aluminium Limited

Noor, R.A.M., Ahmad, Z., Don, M.M., Uzir, M.H., 2010. Modelling and Control of Different Types of Polymerization Processes using Neural Networks Technique: A Review. Canadian Journal of Chemical Engineering, Volume 88, pp. 1065-1084

Parisi, D.R., Chocron, M., Amadeo, N.E., Labrode, M.A., 2002. Approximation by Neural Network of the Effectiveness Factor in a Catalyst with Deactivation. Chemical Engineering Technology, Volume 25, pp. 1183-1186

Perazzini, H.F., Freire, B., Freire, J.T., 2013. Drying Kinetics Prediction of Solid Waste using Semi-empirical and Artificial Neural Network Models. Chemical Engineering Technology, Volume 36, pp.1-10

Prasad, A., 2000. Studies on the Hall-Heroult Aluminum Electrowinning Process. Journal of Brazilian Chemical Society, Volume 11, pp. 245-251

Sadighi, S., Mohaddecy, R.S., 2013. Predictive Modeling for an Industrial Naphtha Reforming Plant Using Artificial Neural Network. International Journal of Technology, Volume 4(2), pp. 102-111

Serra, J.M., Corma, A., Argente, E., Valero, S., Botti, S., 2003. Neural Networks for Modeling of Kinetic Reaction Data Applicable to Catalyst Scale Up and Process Control and Optimization in the Frame of Combinatorial Catalysis. Applied Catalysis: A-General, Volume 254, pp. 133-145