Advertisement

Transactions of the Indian Institute of Metals

, Volume 72, Issue 12, pp 3015–3025 | Cite as

Neural Network Modelling to Characterize Steel Continuous Casting Process Parameters and Prediction of Casting Defects

  • Sheuli HoreEmail author
  • Suchandan K. Das
  • Manoj M. Humane
  • Anil Kumar Peethala
Technical Paper
  • 56 Downloads

Abstract

The current work outlines application of a data-driven multilayer perceptron-based artificial neural network (ANN) model to characterize the influence of melt compositions, tundish temperature, tundish superheat, casting speed and mould oscillation frequency on the important processing parameters such as mould powder consumption rate, oscillation mark depth and metallurgical length during continuous casting process. A two-layer feedforward back-propagation neural network model has been developed for predicting the probability of occurrence of defect in the cast product. The network training architecture has been optimized using a gradient-based algorithm, namely the back-propagation algorithm. The neural network predictions are found to be in good agreement with regard to oscillation mark depth, mould powder consumption rate, metallurgical length and probability of occurrence of defect using data obtained from an operating Indian steel plant (Rashtriya Ispat Nigam Limited, Visakhapatnam). The ANN model prediction has been validated successfully with multiple linear regression analysis carried out on each data set.

Keywords

Artificial neural network Continuous casting Casting defects Metallurgical length Mould oscillation parameters Oscillation mark depth 

Notes

References

  1. 1.
    Continuous Casting of Steel 1985—A Second Study, Eds: International Iron and Steel Institute. Committee on Technology, International Iron and Steel Institute, Brussels (1986).Google Scholar
  2. 2.
    Brimacombe J K, and Sorimachi K, Metall Trans B8 (1977) 489.CrossRefGoogle Scholar
  3. 3.
    Maehara Y, Yasumoto K, Tomono H, Nagamichi T, and Ohmori Y, Mater Sci Technol6 (1990) 793.CrossRefGoogle Scholar
  4. 4.
    Harada S, Tanaka H, Misumi H, Mizoguchi S, and Horiguchi H, ISIJ Int30 (1990) 310.CrossRefGoogle Scholar
  5. 5.
    Patrick B, and Ludlow V, Rev Metall91 (1994) 1081.CrossRefGoogle Scholar
  6. 6.
    Thomas B G, Metall Mater Trans B33 (2002) 795.CrossRefGoogle Scholar
  7. 7.
    Thomas B G, Steel Res Int89 (2018) 1700312.CrossRefGoogle Scholar
  8. 8.
    Lally B, Biegler L, and Henein H, Metall Trans21 (1990) 761.CrossRefGoogle Scholar
  9. 9.
    Szekely J, and Stanek V, Metall Mater Trans1 (1970) 119.Google Scholar
  10. 10.
    Mishra P, Ajmani S K, Kumar A, and Shrivastava K K, Int J Eng Sci Technol4 (2012) 2234.CrossRefGoogle Scholar
  11. 11.
    Warzecha M, Merder T, and Warzecha P, ISIJ Int53 (2013) 1983.CrossRefGoogle Scholar
  12. 12.
    Cwudziński A, Jowsa J, and Przegrałek P, Arch Metall Mater61 (2016) 2013.CrossRefGoogle Scholar
  13. 13.
    Cwudziński A, Steel Res Int81 (2017) 123.CrossRefGoogle Scholar
  14. 14.
    Warzecha M, Merder T, Warzecha P, and Stradomski G, Metalurgija63 (2015) 462.Google Scholar
  15. 15.
    Merder T, and Warzecha M, Metall Mater Trans B43 (2012) 549.CrossRefGoogle Scholar
  16. 16.
    Tirian G O, Rusu-Anghel S, Panoiu M, and Bretotean C P, Proceedings of the 13th WSEAS International Conference on Computers (2009) 199.Google Scholar
  17. 17.
    Avila C, and Tsuji Y, Adaptive and Natural Computing Algorithms, Springer, Vienna (2005) p 92.CrossRefGoogle Scholar
  18. 18.
    Narendra K S, and Parthasarathy K, IEEE Trans Neural Netw1 (1990) 4.CrossRefGoogle Scholar
  19. 19.
    Sharafi S M, and Esmaeily H R, J Theor Appl Inf Technol20 (2005) 87.Google Scholar
  20. 20.
    Makvandi P, Jassbi J, and Khanmohammadi S, WSEAS Trans Syst4 (2005) 337.Google Scholar
  21. 21.
    Pivonka P, and Dohnal J, WSEAS Trans Syst3 (2004) 381.Google Scholar
  22. 22.
    Giakos G C, IEEE Trans Instrum Meas1 (1998) 16.CrossRefGoogle Scholar
  23. 23.
    Shi Z, and He L, Proceedings of the Second International Symposium on Networking and Network Security (ISNNS’10) Jinggangshan, People’s Republic of China (2010) 23.Google Scholar
  24. 24.
    Torkkola K, and Kokkonen M, Proceedings of the IEEE ICASSP (1991).Google Scholar
  25. 25.
    Dumortier C, and Lehert P, ISIJ Int39 (1999) 980.CrossRefGoogle Scholar
  26. 26.
    Xudong W, Man Y, and Xingfu C, ISIJ Int46 (2006) 1047.CrossRefGoogle Scholar
  27. 27.
    Mugwagwa L, Nyanga L, and Mhlanga S, Int J Eng Adv Technol2 (2012) 380.Google Scholar
  28. 28.
    Gresovnik I, Kodelja T, Vertnik R, and Sarler B, Proceedings of the IASTED International Conference and Soft Computing (ASC 2012) 249.Google Scholar
  29. 29.
    Jancikova Z, Zimny O, Kvicala M, Kostial P, and Meca R, in Metal 2013, 22nd International Conference on Metallurgy and Materials, Ostrava, Tanger (2013) 1932.Google Scholar
  30. 30.
    Steeluniversity.org, “Continuous casting User Manual”. https://moodle2.units.it/pluginfile.php/68243/mod_resource/content/1/Colata_continua_2.pdf.
  31. 31.
    Mazumdar S, Ray S K, Sadhna26 (2001) 179.CrossRefGoogle Scholar

Copyright information

© The Indian Institute of Metals - IIM 2019

Authors and Affiliations

  1. 1.CSIR-National Metallurgical LaboratoryJamshedpurIndia
  2. 2.Visakhapatnam Steel Plant (RINL)VisakhapatnamIndia

Personalised recommendations