Artificial neural networks in skin-pass mill modeling

an empirical analysis of architecture and hyperparameters

Authors

DOI:

https://doi.org/10.47385/cadunifoa.v18.n53.4672

Keywords:

Artificial Neural Network, System Identification, Data-driven Modelling, Skin Pass Mill, Steel Making

Abstract

To ensure industrial competitiveness, including the steel market, it is necessary to streamline expenses and increase productivity. Therefore, avoiding incidents involving automation and equipment maintenance is a key factor in ensuring uninterrupted production. Additionally, material loss should be minimized. In this context, there is an opportunity to incorporate improvements in the control of a skin pass mill, ensuring that the mechanical tension applied to the steel sheet remains within specifications. To achieve efficient control, it is necessary for the controller to send the appropriate signal to the plant. This article explores different architectures of artificial neural networks to model this plant. A moderate improvement was observed in the model, and the neural model allows for continuous training to adapt to the real phenomenon.

Downloads

Download data is not yet available.

Author Biographies

Italo Pinto Rodrigues, Instituto Nacional de Pesquisas Espaciais

PhD candidate in the Space Engineering and Technology program at the National Institute for Space Research - INPE.

Faculty member in the Engineering program at Centro Universitário de Volta Redonda - UniFOA

Gabriel Alberto Rodrigues, Centro Universitário de Volta Redonda - UniFOA

Student of the Engineering program at Centro Universitário de Volta Redonda - UniFOA

Bruno Lima Dos Santos, Centro Universitário de Volta Redonda - UniFOA

Student of the Engineering program at Centro Universitário de Volta Redonda - UniFOA

References

AGUIRRE, L. A. Introdução à identificação de sistemas: técnicas lineares e não-lineares aplicadas a sistemas reais. 3 ed ed. Belo Horizonte: UFMG, 2007.

ALVES, P. G.; CASTRO, J. A. DE; MOREIRA, L. P.; HEMERLY, E. M. Modeling, simulation and identification for control of tandem cold metal rolling. Materials Research, v. 15, n. 6, p. 928-936, 2012. DOI: https://doi.org/10.1590/S1516-14392012005000137

BISHOP, CHRISTOPHER M. Pattern Recognition and Machine Learning. 1. ed. New York: Springer-Verlag, 2006.

COLLA, V. A big step ahead in Metal Science and Technology through the application of Artificial Intelligence. IFAC-PapersOnLine, v. 55, n. 21, p. 1-6, 2022. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S2405896322014641>. DOI: https://doi.org/10.1016/j.ifacol.2022.09.234

ESCRIBANO, R.; LOSTADO, R.; MARTÍNEZ-DE-PISÓN, F. J.; PERNÍA, A.; VERGARA, E. Modelling a Skin-Pass Rolling Process by Means of Data Mining Techniques and Finite Element Method. Journal of Iron and Steel Research International, v. 19, n. 5, p. 43-49, 2012. Disponível em: <http://link.springer.com/10.1016/S1006-706X(12)60098-3>. DOI: https://doi.org/10.1016/S1006-706X(12)60098-3

HAYKIN, S. Neural Networks and Learning Machines. 3. ed. Bookman, 2009.

HE, HAI-TAO; LIU, HONG-MIN. The research on integrated neural networks in rolling load prediction system for temper mill. 2005 International Conference on Machine Learning and Cybernetics. Anais... . p.4089-4093. v. 7, 2005. IEEE. Disponível em: <http://ieeexplore.ieee.org/document/1527653/>. DOI: https://doi.org/10.1109/ICMLC.2005.1527653

LEVENBERG, K. A METHOD FOR THE SOLUTION OF CERTAIN NON-LINEAR PROBLEMS IN LEAST SQUARES. Quarterly of Applied Mathematics, p. 164-168, 1944. Disponível em: <https://www.jstor.org/stable/43633451>. Acesso em: 26/8/2023. DOI: https://doi.org/10.1090/qam/10666

MAIER, H. R.; GALELLI, S.; RAZAVI, S.; et al. Exploding the myths: An introduction to artificial neural networks for prediction and forecasting. Environmental Modelling & Software, v. 167, p. 105776, 2023. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S1364815223001627>. DOI: https://doi.org/10.1016/j.envsoft.2023.105776

MARQUARDT, D. W. An Algorithm for Least-Squares Estimation of Nonlinear Parameters. Journal of the Society for Industrial and Applied Mathematics, v. 11, n. 2, p. 431-441, 1963. Disponível em: <https://www.jstor.org/stable/2098941>. Acesso em: 26/8/2023. DOI: https://doi.org/10.1137/0111030

PICAN, N.; ALEXANDRE, F.; BRESSON, P. Artificial neural networks for the presetting of a steel temper mill. IEEE Expert, v. 11, n. 1, p. 22–27, 1996. Disponível em: <http://ieeexplore.ieee.org/document/482953/>. DOI: https://doi.org/10.1109/64.482953

REN, X.-Y.; GAO, H.-M.; XU, H.-W.; HUANG, H.-G.; SUN, J.-N. Identification and Control of Elongation System of Skin Passing Mill Based on Intelligent Algorithm. Journal of Physics: Conference Series, v. 1820, n. 1, p. 012154, 2021. Disponível em: <https://iopscience.iop.org/article/10.1088/1742-6596/1820/1/012154>. DOI: https://doi.org/10.1088/1742-6596/1820/1/012154

RODRIGUES, I. P.; JORGE, J. M.; OLIVEIRA, K. F. DE. Identificação e controle de um laminador de encruamento em malha fechada através de métodos de subespaços, dez. 2013. Trabalho de Conclusão de Curso, Volta Redonda: Centro Universitário de Volta Redonda.

RODRIGUES, I. P.; OLIVEIRA, P. A. S.; AMBROSIO, A. M.; CHAGAS, R. A. J. Modeling satellite battery aging for an operational satellite simulator. Advances in Space Research, v. 67, n. 6, p. 1981-1999, 2021. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0273117720309042>. DOI: https://doi.org/10.1016/j.asr.2020.12.031

ROSENBLATT, F. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, v. 65, n. 6, p. 386-408, 1958. DOI: https://doi.org/10.1037/h0042519

RUMELHART, D. E.; MCCLELLAND, J. L. Learning Internal Representations by Error Propagation. Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations. p.318-362, 1986. MITP. Disponível em: <https://ieeexplore.ieee.org/document/6302929>. Acesso em: 26/8/2023.

SANTOS, B. C. DOS; BARCELOS, A. F. Aplicação da rede neural artificial como ferramenta de diagnóstico e controle do sistema de tensão de um laminador de tiras a frio. XVII - Simpósio de Excelência em Gestão e Tecnologia. Anais... , 2020. Resende: Centro Universitário Dom Bosco do Rio de Janeiro.

SEO, M.; BAN, J.; KOO, B. Y.; KIM, S. W. Static Model Identification for Sendzimir Rolling Mill Using Noise Corrupted Operation Data. IEEE Access, v. 8, p. 150685-150695, 2020. Disponível em: <https://ieeexplore.ieee.org/document/9169645/>. DOI: https://doi.org/10.1109/ACCESS.2020.3017025

SHEN, S.; GUYE, D.; MA, X.; YUE, S.; ARMANFARD, N. Multistep networks for roll force prediction in hot strip rolling mill. Machine Learning with Applications, v. 7, p. 100245, 2022. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S2666827021001237>. DOI: https://doi.org/10.1016/j.mlwa.2021.100245

SHI, P.; GAO, H.; YU, Y.; XU, X.; HAN, D. Intelligent fault diagnosis of rolling mills based on dual attention-guided deep learning method under imbalanced data conditions. Measurement, v. 204, p. 111993, 2022. DOI: https://doi.org/10.1016/j.measurement.2022.111993

SHI, P.; YU, Y.; GAO, H.; HUA, C. A novel multi-source sensing data fusion driven method for detecting rolling mill health states under imbalanced and limited datasets. Mechanical Systems and Signal Processing, v. 171, p. 108903, 2022. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0888327022000905>. DOI: https://doi.org/10.1016/j.ymssp.2022.108903

SVOZIL, D.; KVASNICKA, V.; POSPICHAL, J. Introduction to multi-layer feed-forward neural networks. Chemometrics and Intelligent Laboratory Systems, v. 39, n. 1, p. 43-62, 1997. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0169743997000610>. DOI: https://doi.org/10.1016/S0169-7439(97)00061-0

WERBOS, P. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Science, 1974. Harvard University.

WIKLUND, O.; SANDBERG, F. Modelling and Control of Temper Rolling and Skin Pass Rolling. Metal Forming Science and Practice. p.313-343, 2002. Elsevier. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/B9780080440248500151>. DOI: https://doi.org/10.1016/B978-008044024-8/50015-1

ZHANG, G.; EDDY PATUWO, B.; Y. HU, M. Forecasting with artificial neural networks: International Journal of Forecasting, v. 14, n. 1, p. 35-62, 1998. Disponível em: <https://linkinghub.elsevier.com/retrieve/pii/S0169207097000447>. DOI: https://doi.org/10.1016/S0169-2070(97)00044-7

Downloads

Published

2023-12-07

How to Cite

RODRIGUES, Italo Pinto; RODRIGUES, Gabriel Alberto; DOS SANTOS, Bruno Lima. Artificial neural networks in skin-pass mill modeling: an empirical analysis of architecture and hyperparameters. Cadernos UniFOA, Volta Redonda, v. 18, n. 53, p. 1–12, 2023. DOI: 10.47385/cadunifoa.v18.n53.4672. Disponível em: https://unifoa.emnuvens.com.br/cadernos/article/view/4672. Acesso em: 23 nov. 2024.

Issue

Section

Tecnologia e Engenharias