Steel Property and Process Models for Quality Control and Optimization

Abstract:

High quality and low variability in the properties of the products are the main goals in manufacturing. The quality of the product is verified by testing different properties. It can be improved with models developed for event prediction. This paper presents with application examples the modelling steps required for effective process modelling. First, the pre-processing and feature extraction phase are illustrated. The modelling phase concentrates especially on the heteroscedasticity problem that is commonly present in industrial applications. The process monitoring and control parameter optimization based on these models is presented, as well as the solution for the lack of observations for the dependent variable. Many of the developed models are in daily use in different process states in steel industry. They enable the design of new products and the analysis of the effects of different process parameters on variability reduction. The proposed methods are application independent.

• Periodical: Materials Science Forum (Volume 762)
• Pages: 301-306
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.762.301
• Online since: July 2013
• Authors: Satu Tamminen, Henna Tiensuu, Ilmari Juutilainen, Juha Röning
• Keywords: Data Mining (DM), Process Modelling, Quality Control, Variability Reduction

References

[1] P. Laurinen and J. Röning: J. Mater. Process. Tech. Vol. 168(3) (2005), pp.423-430

[2] H. Koskimäki, P. Laurinen, E. Haapalainen, L. Tuovinen and J. Röning: IEEE T. Ind. Electron. Vol. 54(5) (2007), pp.2823-2830

[3] U. Elsilä and J. Röning, in: The minerals, metals & materials society 2006, edited by C-A. Candin & M. Bellet, USA (2006), pp.767-774

[4] H. Tiensuu, I. Juutilainen and J. Röning, in: Proc. 14th International Conference on Discovery Science, Vol. 6926 (2011), pp.351-364

[5] I. Juutilainen: Modelling of Conditional Variance and Uncertainty Using Industrial Process Data, University of Oulu, Finland (2006)

[6] I. Juutilainen and J. Röning: Mater. Manuf. Process. Vol. 21(4) (2006), pp.367-373

[7] S. Tamminen, I. Juutilainen and J. Röning, in: Proc. International Joint Conference on Neural Networks, Hong Kong, (2008), pp.990-993

[8] I. Juutilainen, S. Tamminen and J. Röning, in: Computational Methods for Optimizing Manufacturing Technology, edited by J.P. Davim, chapter, A, IGI Global (2012), pp.368-399

[9] I. Juutilainen, L. Tuovinen, P. Laurinen, H. Koskimäki and J. Röning: J. Comp. Inform. Tech. Vol. 19(3) (2011), pp.71-82

[10] P. Laurinen and L. Tuovinen and J. Röning, in: Proc. 5th International Conference on Intelligent Systems Design and Applications, Wroclaw, Poland, (2005), pp.20-26

[11] T. Kohonen: Self-Organizing Maps (Springer, 1997)

[12] J. Friedman: Comput. Stat. Data An. Vol. 38 (2002), pp.367-378

[13] L. Breiman: Mach. Learn. Vol. 45 (2001), pp.241-248

[14] T. Hastie, R. Tibshirani and J. Friedman: Elements of Statistical Learning (Springer, 2001)

[15] S. Tamminen, I. Juutilainen and J. Röning: Ironmak. Steelmak. Vol. 37(1) (2010), pp.35-40

[16] S. Tamminen, I. Juutilainen and J. Röning, in: Proc. 10th Industrial Conference on Data Mining, Berlin, Germany, (2010), pp.263-276

[17] I. Juutilainen, S. Tamminen and J. Röning: J. Stat. Theor. Pract. Vol. 6(3) (2012), pp.452-467