Application of Regression Trees in Optimization of Metal Forming Process

Abstract:

Application of sensitivity analysis in optimization of process parameters of production processes for innovative materials, e.g. dual phase steel, requires deterministic model of thermomechanical processes and large datasets that covers whole surface of results. Difficulties in optimization of process parameters correspond with large number of control variables, which should be considered in the technology design. Furthermore, conduction of such analysis takes the great computational cost. Presented work concerns possibility of application of regression trees, especially CART model, in preliminary analysis for sensitivity analysis. Use of data mining algorithms enables acquiring of preliminary, rough results: relationships among parameters of the hot rolling process of dual phase steel strips and rules of optimization of this process, it also does not require any apriori knowledge about thermomechanical processes.

• Periodical: Key Engineering Materials (Volumes 622-623)
• Pages: 749-755
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.622-623.749
• Online since: September 2014
• Authors: Krzysztof Regulski, Danuta Szeliga*, Jan Kusiak
• Keywords: Data Mining (DM), Dual Phase Steel, Hot Rolling, Regression Trees, Sensitivity Analysis

References

[1] D. Szeliga, J. Kusiak, Ł. Rauch, Sensitivity analysis as Support for Design of Hot Rolling Technology of Dual Phase Steel Strips, Metal Forming 2012: proceedings of the 14th international conference on Metal Forming: September 16–19, 2012, Krakow, Poland, eds. Jan Kusiak, Janusz Majta, Danuta Szeliga. — Weinheim: Wiley-VCH Verlag GmbH & Co. KGaA, cop. 2012. (Steel Research International ; spec. ed. ), p.1275.

DOI: 10.1063/1.4806901

[2] K. Myczkowska, D. Szeliga, J. Kusiak, Sensitivity analysis of the cooling cycle for the DP steels, Rudy i Metale Nieżelazne, 56 (2011), pp.692-696, (in Polish).

[3] L. Breinman, J.H. Friedman, R.A. Olshen, and C.J. Stone, Classification and regression trees, Chapman and Hall, (1993).

[4] J.R. Quinlan, Induction on Decision Trees, Machine Learning, Kluwer Academic Publishers, Boston, (1986).

[5] T. Hill, P. Lewicki, STATISTICS Methods and Applications. StatSoft, Tulsa, OK, 2007, WEB: http: /www. statsoft. com/textbook/stathome. html.

[6] G.V. Kass, An exploratory technique for investigatin large quantities of categorical data, Applied Statistics, 29, 1980, pp.119-127.

DOI: 10.2307/2986296

[7] K. Regulski, G. Rojek, M. Skóra, J. Kusiak, Data exploration approach in control of metal forming manufacturing chain : example of fasteners production, Metal Forming 2012 : proceedings of the 14th international conference on Metal Forming : September 16–19, 2012, Krakow, Poland, eds. Jan Kusiak, Janusz Majta, Danuta Szeliga. — Weinheim : Wiley-VCH Verlag GmbH & Co. KGaA, cop. 2012. — (Steel Research International ; spec. ed. ). — p.1319.

DOI: 10.1533/9780857096340.1.35

[8] K. Regulski, S. Kluska-Nawarecka, Knowledge integration computer tools and algorithms in the improvement of the production processes of cast-steel castings, Artificial Intelligence in the Knowledge and Information Systems, Instytut Odlewnictwa, Kraków, (2012).

[9] K. Regulski, Aspects of knowledge management in the production processes control in the context of the application of data mining, e-mentor ; ISSN 1731-6758. — 2012 nr 5 p.63–71.

[10] S. Kluska-Nawarecka, Z. Górny, B. Mrzygłód, D. Wilk-Kołodziejczyk, K. Regulski, Methods of development fuzzy logic driven decision-support models in copper alloys processing, Achieves of Foundry Engineering, Polish Academy of Sciences, No. 10 (2010).

DOI: 10.1515/afe-2015-0064