Genetic Algorithms in Hot Steel Rolling for Scale Defect Prediction

Authors: Jarno Haapamäki, Juha Röning

Abstract:

Scale defects are common surface defects in hot steel rolling. The modelling of such defects is problematic and their causes are not straightforward. In this study, we investigated genetic algorithms in search for a mathematical solution to scale formation. For this research, a high-dimensional data set from hot steel rolling process was gathered. The synchronisation of the variables as well as the allocation of the measurements made on the steel strip were solved before the modelling phase.

Keywords: Genetic algorithms, hot strip rolling, knowledge discovery, modeling.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1082861

References:

[1] P.H. Bolt, F. Friedel, H. Pircher, X. Cornet, S. Ehlers, and F. Steinert, "Investigation of the formation, constitution and properties of scale formed during the finishing rolling, cooling and coiling of thin hot strips," ECSC steel RTD project tech. rep.
[2] T. Fukagawa, H. Okada, and Y. Maehara, "Mechanism of red scale defect formation in Si-added hot-rolled steel sheets," Tetsu-to-Hagane (Iron and Steel Institute of Japan), vol. 34 no. 11, 1994, pp. 906-911.
[3] V. Ginzburg, Steel-rolling technology: theory and practice. Marcel Dekker Inc. New York ,1989.
[4] Surface defects in hot rolled flat steel products. Verlag Stahleisen Gmbh, 1996.
[5] J. Andorfer, D. Paesold, R. Puntigam, K. Rendl, J. Zeindl, D. Auzinger, G. Hubmer, "New achievements in quality control systems for hot band," METEC 2003, 6th international metallurgy trade fair.
[6] J.H. Holland, Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. The University of Michigan Press, Ann Arbor, 1975.
[7] R.Y. Chen, and W.Y.D. Yuen, "Effects of finishing and coiling temperatures on the scale structure and picklability of hot rolled strip," Iron and Steelmaker, vol. 27 no. 4, 2000, pp. 47-53.
[8] K.S. Tan, M. Krzyzanowski, and J.H. Beynon, "Effect of Steel Composition on Failure of Oxide Scales in Tension under Hot Rolling Conditions," Steel Research, vol. 72 no. 7, 2001, pp. 250-258.
[9] J. Haapam├ñki, S. Tamminen, and J. Röning, "Data mining methods in scale defect prediction for hot steel rolling," in Proc. 23rd IASTED Int. Conf. Artificial Intelligence and Applications, Feb. 2005 pp. 90-94
[10] Y. Bisseur, E.B. Martin, A.J. Morris, and P. Kitson, "Fault detection in hot steel rolling using neural networks and multivariate statistics," IEE Proc. Control Theory and Applications, 147(6), 2000, pp. 633-640.
[11] T. Kohonen, Self organizing maps. Springer, Berlin, 1995.
[12] E. Alhoniemi, J. Hollmén, O. Simula, and J. Vesanto, "Process monitoring and modeling using the self-organizing map," Integrated Computer-Aided Engineering, vol. 6 no. 1, 1999, pp. 3-14.
[13] L. Cser, A.S. Korhonen, J. Gulyás, P. Mäntylä, O. Simula, Gy. Reiss, and P. Ruha, "Data mining and state monitoring in hot rolling," Proc. of the 2nd Int. Conf. on Intelligent Processing and Manufacturing of Materials, Honolulu, Hawaii, July 10-15, 1999, Vol. 1, IEEE, pp. 529- 537.
[14] M. Krzyzanowski, and J.H. Beynon, "The tensile failure of mild steel oxides under hot rolling conditions," Steel Research vol. 70 no. 1, 1999, pp. 22-27.
[15] S. Haykin, Neural networks: a comprehensive foundation. Macmillan Publishing Company, 1994.
[16] Z. Michalewicz, Genetic algorithms + data structures = evolution programs. 3. ed. 1996 Springer-Verlag.
[17] M. Kotani, M. Ochi, S. Ozawa, and K. Akazawa, "Evolutionary discriminant functions using genetic algorithms with variable-length chromosome," Proc. Int. joint conference on Neural Networks, 2001, IJCNN pp. 761-766.
[18] J.R. Koza, Genetic programming: "A paradigm for genetically breeding populations of computer programs to solve problems," Stanford University, 1990. Available http://www.geneticprogramming. com/jkpdf/tr1314.pdf
[19] D.E. Goldberg, Genetic algorithms in search optimization and machine learning. Addison-Wesley, 1989.