Artificial neural networks applied to the aluminum industry
DOI:
https://doi.org/10.62059/LatArXiv.preprints.154Keywords:
Aluminum, Machine learning, Artificial intelligence, Artificial neural networksAbstract
Artificial neural networks (ANN) are used in the aluminum industry to optimize production processes, improve product quality and predict equipment failures. For example, in aluminum smelting, ANNs can be used to monitor the temperature of the smelting furnace, monitor the solidification process, and predict when preventive maintenance is needed on machinery. Likewise, in the detection of defects in products, in the quality control of sheets. ANNs can also predict mechanical properties such as strength, hardness or ductility of laminated materials. For example, ANNs can be trained to predict the microstructure resulting from a rolling process based on parameters such as temperature, rolling speed, and applied pressure. They can also be used to predict properties of the electrolytic bath, anodic properties, in general everything related to the electrolytic process.
References
X. Basogain, Redes Neuronales Artificiales y ssus Aplicaciones. Departamento de Ingeniería de Sistemas y Automática, Escuela Superior de Bilbao. UPV-EHU.
J. A. Escobar, “Introducción a las Redes Neuronales,” [Online]. Available: https://www.halweb.uc3m.es/esp/personal/personas/jmmarin/esp/DM/tema3dm.pdf
“Componentes de una Red Neuronal.” [Online]. Available: https://www.datasmarts.net/componentes-de-una-red-neuronal/
“Redes Neuronales.” https://www.thepower.education/blog/redes-neuronales
“Que es una Red Neuronal.” https://www.thedataschools.com/que-es-una-red-neuronal/
J. Vorobioff, S. Cerrotta, N. Morel, and A. Amadio, “Inteligencia Artificial y Redes Neuronales Fundamentos, Ejercicios y Aplicaciones,” 2022. doi: ISBN 9789874998828.
A. Zaknich, “Characterization of Aluminum Hydroxide Particles from the Bayer Process Using Neural Network and Bayesian Classifiers,” IEEE Trans. Neural Netw., vol. 8, no. 4, 1997.
C. Chelgani and E. Jorjani, “Artificial Neural Network Prediction of Al2O3 Leaching Recovery in the Bayer Process-Jajarm Alumina Plant (Iran),” J. Hydrometall., vol. 97, no. 1–2, pp. 105–110, 2009, doi: 10.1016/j.hydromet.2009.01.008.
I. Milosevic, I. Mihajlovic, and Z. Zivkovic, “Artificial Neural Network Prediction of Aluminum Extraction from Bauxitein the Bayer Process,” J. Serbian Chem. Soc., vol. 77, no. 9, pp. 1259–1271, 2012, doi: 10.2298/JSC110526193D.
F. Suárez, P. Sucre, and G. Almeida, “Inteligencia Artificial en el Proceso de Obtención de Alúmina,”
Universidad, Cienc. y Tecnol., vol. 22, no. 88, pp. 48–56, 2018.
M. Mahmoudian, A. Ghaemi, H. Hashemabadi, and S. Shahhosseini, “Comparing the Capability of Various Models for Predicting the Bayer Process Parameters,” J. Adv. Mater. Process., vol. 6, no. 1, pp. 71–86, 2018.
L. Dion, C. Lagace, L. Kiss, and S. Poncsak, “Using Artificial Neural Network To Predict Low Voltage Anode Effect PFCS At The Duct End Of An Electrolysis Cell,” in Light Metals 2016, 2016.
D. Bhattacharyay, D. Kocaefe, Y. Kocaefe, B. Morais, and M. Gagnon, “Application of the Artificial Neural Network (ANN) in Predicting Anode Properties,” in Light Metals 2013, 2013.
D. Kocaefe, A. Sarkar, Y. Lu, D. Bhattacharyay, Y. Kocaefe, and B. Morais, “Utilization of Artificial Neural Network to Analyze and Predict the Influence of Different Parameters on Anode Properties,” in 11th Australasian Aluminium Smelting Technology Conference, United Arab Emirates, 2014.
P. Chermont, F. Soares, and R. Oliveira, “Simulations on the Bath Chemistry Variables Using Neural Networks,” in Light Metalas 2016, 2016.
D. Bhattacharyay, D. Kocaefe, Y. Kocaefe, and B. Morais, “An Artificial Neural Network Model for Predicting the CO2 Reactivity of Carbon Anodes Used in the Primary Aluminum Production,” Neural Comput. Appl., vol. 28, pp. 553–563, 2017, doi: 10.1007/s00521-015-2093-7.
A. Fernandez et al., “Soft Sensors in the Primary Aluminum Production Process Based on Neural Networks Using Clustering Methods,” Sensors, 2019. https://www.mdpi.com/journal/sensors
A. Saracibar, R. López, B. Ducoeur, M. Chiumenti, and B. Meester, “Un Modelo Numérico Para la Simulación de Disolución de Precipitados en Aleaciones de Aluminio con Endurecimiento Utilizando Redes Neuronales,” Rev. Int. Métodos Numéricos para Cálculo y Diseño en Ing., vol. 29, no. 1, pp. 29–37, 2013, doi: 10.1016/j.rimni.2012.02.003.
M. Jimenez, M. Alfaro, and C. Muñoz, “Design of an Aluminum Alloy Using a Neural Network Based Model,” Metals (Basel)., vol. 12, 2022, doi: 10.3390/met12101587.
M. Bagheripoor and H. Bisadi, “Application of Artificial Neural Network for the Prediction of Roll Force and Roll Torque in Hot Rolling Process,” Appl. Math. Model., vol. 37, pp. 4593–4607, 2013, doi: 10.1016/j.apm.2012.09.070.
P. Barat and P. Withers, “Neural Network Modeling for the Prediction of Texture Evolution of Hot Deformed Aluminum Alloys,” J. Mater. Eng. Perform., vol. 12, no. 6, pp. 623–628, 2003, doi: 10.1361/105994903322692402.
Downloads
Downloads
Posted
Categories
Data Availability Statement
Revisando las referencias o comunicandose con el autor
License
Copyright (c) 2024 Rafael Tosta (Autor/a)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This preprint contains the reported license and associated copyright. Once published in an associated journal or other publisher, the published version assumes the publisher's terms and conditions.
