Artificial neural networks applied to iron ore grinding process combined with empirical models
DOI:
https://doi.org/10.33448/rsd-v11i13.32329Keywords:
Grinding Mill; Artificial Neural Networks; Machine Learning; Mineral processing; Iron ore; Process control.Abstract
Step by step, the technologies provided by Industry 4.0 are being inserted in the mining processes and one of the opportunities to be explored is the use of Big Data and Advanced Analytics tools. In iron ore beneficiation plants, in the milling processes, the potential gains from machine learning tools tend to be amplified when combined with mathematical models derived from process knowledge, whether empirical or phenomenological. This article presents the application of artificial neural networks for the prediction of the main product quality parameter of a milling plant, combined with empirical equations that describe the milling process, to establish whether such equations can contribute to a better performance of the predictive models.
References
Mariscal, G., Marban, O. & Fernandez, C. (2010). A survey of data mining and knowledge discovery process models and methodologies. The Knowledge Engineering Review, 25(2), 137-166.
IBM (2022) Introduction to CRISP-DM. <https://www.ibm.com/docs/en/spss-modeler/18.2.0?topic=guide-introduction-crisp-dm>
Shearer, C. (2000). The CRISP-DM Model: The New Blueprint for Data Mining. Journal of Data Warehousing, 5, 13-22.
Google (2022) Machine Learning Crash Course. < https://developers.google.com/machine-learning/crash-course/>
Pessoa, A. D. ., Sousa, G. C. L. de ., Araujo, R. C. & Anjos, G. J. M. (2021). Modelo de rede neural artificial para previsão da capacidade de carga de estacas cravadas. Research, Society and Development, 10(1), e12210111526. https://doi.org/10.33448/rsd-v10i1.11526
Donda, J. D., Galinari C. M. & Rabelo, P. J. B. (1999). O Controle da Eficiência Energética nos Circuitos de Pré-moagem e Moagem Primária da Samarco Mineração. In: II Simpósio Brasileiro de Minério de Ferro - ABM, Ouro Preto, p. 144-150.
Donda, J. D. (2003). Um método para prever o consumo específico de energia na (re)moagem de concentrados de minério de ferro em moinhos de bolas. Belo Horizonte, Tese (doutorado), CPGEM, Universidade Federal de Minas Gerais.
Donda, J. D. & Rosa, A. C. (2014). A lei de Moagem – Comprovação para minério de ferro. Livraria e Editora Graphar. Brasil.
Figueira, H. V. O., Almeida, S. L. M., Luz, A. B. (2004). Tratamento de Minérios, Rio de Janeiro: Centro de Tecnologia Mineral CETEM. Editora CETEM. Brasil.
Delboni, H. J. (2007). Tendências Tecnológicas Brasil 2015, Rio de Janeiro: Centro de Tecnologia Mineral CETEM. Editora CETEM. Brasil.
Napier-Munn, T. J., Morrel, S., Morrison, R. D., Kojovic, T. (1999). Mineral Comminution Circuits, Their Operation and Optimisation. Julius Kruttschnitt Mineral Research Center. Austrália.
Serpa, A. (2019). Modelagem do Teor de Sílica no Produto da Flotação de Minério de Ferro baseada em Redes Neurais. Trabalho de conclusão de curso de graduação. Curso de Graduação em Engenharia de Controle e Automação, Escola de Engenharia da UFMG. Belo Horizonte, Brasil:
Souza, E. S. (2014). Controle Automático de Circuitos de Moagem. Tese de Doutorado em Engenharia de Produção, Porto Alegre: Escola de Engenharia da UFRGS.
Oliveira K P. S. (2000). Aplicação das técnicas de redes neurais e de análise de componentes principais na modelagem de uma lagoa aerada da Ripasa SA. Tese de Mestrado, Faculdade de Engenharia Química, Unicamp.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press. EUA.
Chollet, François and others (2022). Keras API <https://keras.io/api/>
Labach, A., Salehinejad, H. & Valaee, S. (2019). Survey of dropout methods for deep neural networks. <https://doi.org/10.48550/arXiv.1904.13310>
Hinton G. Krizhevsky A. et al Srivastava, N. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(56):1929−1958, 2014.
Pedregosa et al.,(2011). Scikit-learn: Machine Learning in Python, Journal of Machine Learning Research, Journal of Machine Learning Research, 12, pp. 2825-2830.
Minsky, M., & Papert, S. (1969). Perceptrons. M.I.T. Press. EUA.
McCulloch, W.S. & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5, 115–133.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Daniel Henrique Cordeiro Silva; Vladmir Kronemberger Alves ; Ernandes Savio
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
