No Access

Prediction of Mechanical Properties of Seamless Steel Tubes Using Artificial Neural Networks

Department of Electronic Engineering, Federal University of Minas Gerais, Av. Pres. Antonio Carlos, 6627, Pampulha, Belo Horizonte, MG, 31.270-901, Brazil

Search for more papers by this author

Patricia Teixeira Sampaio

Federal Institute of Norte de Minas Gerais, R. Prof. Monteiro Fonseca, 216, Vila Brasilia, Montes Claros, MG, 39.400-149, Brazil

Search for more papers by this author

Rafael Utsch Braga

Vallourec Tubular Solutions Brazil, Barreiro Unit, Av. Olinto Meireles, 65, Barreiro de Baixo, Belo Horizonte, 30.640-010, Minas Gerais, Brazil

Search for more papers by this author

Victor Alberto Lambertucci

Vallourec Tubular Solutions Brazil, Barreiro Unit, Av. Olinto Meireles, 65, Barreiro de Baixo, Belo Horizonte, 30.640-010, Minas Gerais, Brazil

Search for more papers by this author

Gustavo Matheus Almeida

Department of Chemical Engineering, Federal University of Minas Gerais, Av. Pres. Antonio Carlos, 6627, Pampulha, Belo Horizonte, MG, 31.270-901, Brazil

Search for more papers by this author

, and

Antonio Padua Braga

Department of Electronic Engineering, Federal University of Minas Gerais, Av. Pres. Antonio Carlos, 6627, Pampulha, Belo Horizonte, MG, 31.270-901, Brazil

E-mail Address: apbraga@ufmg.br

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S1469026820500285Cited by:1 (Source: Crossref)

Abstract

A bottleneck of laboratory analysis in process industries including steelmaking plants is the low sampling rate. Inference models using only variables measured online have then been used to made such information available in advance. This study develops predictive models for key mechanical properties of seamless steel tubes, by strength, ultimate tensile strength and hardness. A plant in Brazil was used as the case study. The sample sizes of some steel tube families given namely, yield a particular property are discrepant and sometimes very small. To overcome this sample imbalance and lack of representativeness, committees of predictive neural network models based on bagging predictors, a type of ensemble method, were adopted. As a result, all steel families for all properties have been satisfactorily described showing the correlations between targets and model estimates close to 99%. These results were compared to multiple linear regression, support vector machine and a simpler neural network. Such information available in advance favors corrective actions before complete tube production mitigating rework costs in general.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

1. R. N. Lima and G. M. de Almeida, A. P. Braga and M. Cardoso, Trend modelling with artificial neural networks. Case study: Operating zones identification for higher SO3 incorporation in cement clinker, Eng. Appl. Artif. Intell. 54 (2016) 17–25. Crossref, Google Scholar
2. F. A. A. Souza, R. Araujo and J. Mendes, Review of soft sensor methods for regression applications, Chemometr. Intell. Lab. 152(15) (2016) 69–79. Crossref, Google Scholar
3. P. Kadlec, R. Grbic and B. Gabrys, Review of adaptation mechanisms for data-driven soft sensors, Comput. Chem. Eng. 35(1) (2011) 1–24. Crossref, Google Scholar
4. X. Wang and H. Liu, Soft sensor based on stacked auto-encoder deep neural network for air preheater rotor deformation prediction, Adv. Eng. Inf. 36 (2018) 112–119. Crossref, Google Scholar
5. M. Zhang and X. Liu, A soft sensor based on adaptive fuzzy neural network and support vector regression for industrial melt index prediction, Chemometr. Intell. Lab. 126(15) (2013) 83–90. Crossref, Google Scholar
6. W. Xu, L. Zhang and X. Gu, Soft sensor for ammonia concentration at the ammonia converter outlet based on an improved particle swarm optimization and BP neural network, Chem. Eng. Res. Des. 89(10) (2011) 2102–2109. Crossref, Google Scholar
7. Y. Wang, X. Wu, X. Li, Z. Xie, R. Liu, W. Liu, Y. Zhang, Y. Xu and C. Liu, Prediction and analysis of tensile properties of austenitic stainless steel using artificial neural network, Metals 10(234) (2020) 1–16. Google Scholar
8. N. Sandhya, V. Sowmya, C. R. Bandaru and G. Raghu Babu, Prediction of mechanical properties of steel using data science techniques, Int. J. Recent. Technol. Eng. 8(3) (2019) 2277–3878. Google Scholar
9. H. Fazilat, M. Ghatarband, S. Mazinani, Z. A. Asadi, M. E. Shiri and M. R. Kalaee, Predicting the mechanical properties of glass fiber reinforced polymers via artificial neural network and adaptive neuro-fuzzy inference system, Comput. Mater. Sci. 58 (2012) 31–37. Crossref, Google Scholar
10. Y. F. Han, W. D. Zeng, Y. Shu, Y. G. Zhou and H. Q. Yu, Prediction of the mechanical properties of forged Ti–10V–2Fe–3Al titanium alloy using FNN, Comput. Mater. Sci. 50(3) (2011) 1009–1015. Crossref, Google Scholar
11. R. M. Hussein, N. J. Hammadi and Q. A. Rishaq, Prediction of yield strength of low/medium crmo ferritic steels using artificial neural networks, Iraqi J. Mech. Mater. Eng. 11(4) (2011) 649–662. Google Scholar
12. A. Khan, M. H. Shamsi and T. S. Choi, Correlating dynamical mechanical properties with temperature and clay composition of polymer-clay nanocomposites, Comput. Mater. Sci. 45(2) (2009) 257–265. Crossref, Google Scholar
13. N. S. Koksal, Prediction of mechanical properties in magnesia based refractory materials using ANN, Comput. Mater. Sci. 47(1) (2009) 86–92. Crossref, Google Scholar
14. L. Sun, C. Zhang, Q. Wang, M. Wang and Z. Yan, Prediction of mechanical properties of 25CrMo48V seamless tube using neural network model, Int. J. Mod. Phys. B 23(6–7) (2009) 1074–1079. Link, Google Scholar
15. I. B. Topcu and M. Saridemir, Prediction of mechanical properties of recycled aggregate concretes containing silica fume using artificial neural networks and fuzzy logic, Comput. Mater. Sci. 42(1) (2008) 74–82. Crossref, Google Scholar
16. J. F. Hollomon and L. D. Jaffe, Time-Temperature relations tempering steel, Trans. AIME 162 (1945) 223–249. Google Scholar
17. M. Chen and D. A. Linkens, Hybrid fuzzy modelling using simulated annealing and application to materials property prediction, in Proc. 2nd IEEE Int. Conf. Intelligent Processing and Manufacturing of Materials, Honolulu, August, 1999, pp. 395–400. Google Scholar
18. D. M. Jones, J. Watton and K. J. Brown, Comparison of hot rolled steel mechanical property prediction models using linear multiple regression, non-linear multiple regression and non-linear artificial neural networks, Ironmak. Steelmak. 32(5) (2013) 435–442. Crossref, Google Scholar
19. S. Haykin, Neural Networks: A Comprehensive Foundation (Prentice Hall, New York, 1999) Google Scholar
20. S. Kirkpatrick, D. C. Gellat and M. P. Vecchi, Optimization by simulated annealing, Science 220(5) (1983) 671–680. Crossref, Google Scholar
21. D. Chen and M. T. Hagan, Optimal use of regularization and cross-validation in neural network modeling, in Proc. IEEE Int. Joint Conf. Neural Networks, Washington, DC, July, 1999, pp. 1275–1280. Google Scholar
22. L. Breiman, Bagging predictors, Technical Report, University of California (1994). Google Scholar
23. D. C. Montgomery, E. A. Peck and G. G. Vining, Introduction to Linear Regression Analysis (Wiley-Blackwell, New York, 2012). Google Scholar
24. C. Cortes and V. Vapnik, Support-vector networks, Mach. Learn. 20 (1995) 273–297. Crossref, Google Scholar
25. G. E. Totten and M. A. H. Howes, Steel Heat Treatment Handbook (CRC Press, New York, 1997). Google Scholar
26. C. Gomes, A. L. Kaiser, J. P. Bas, A. Aissaoui and M. Piette, Predicting the mechanical properties of a quenched and tempered steel thanks to a tempering parameter, Rev. Metall. 107(7,8) (2010) 293–302. Crossref, Google Scholar
27. Y. Y. Yang and D. A. Linkens, Steel yield strength prediction using ensemble model: Performance improvement over single neural network model, in Intelligence in a Materials World – Selected Papers from IPMM–2001 (The Third Int. Conf. on Intelligent Processing and Manufacturing of Materials), (eds.) J. A. Meech, M. M. Veiga, Y. Kawazoe, S. R. LeClair, 1st ed. (CRC Press, 2002), pp. 335–346. Source: https://www.amazon.com/Intelligent-Applications-Material-Select-IPMM-2001/dp/0849314933. Google Scholar
28. D. W. Scott, Multivariate Density Estimation: Theory, Practice, and Visualization (Wiley, New York, 1992). Crossref, Google Scholar