LOGIT MODEL AND PREDICTION QUALITY OF CONTINUOUSLY CAST SLABS

1 FRANĚK Zdeněk
Co-authors:
2 PYSZKO René
Institutions:
1 Silesian University in Opava, School of Business Administration, Karvina, Czech Republic, EU, franek@opf.slu.cz
2 VŠB - Technical University, Faculty of Materials Science and Technology, Ostrava, Czech Republic, EU, rene.pyszko@vsb.cz
Conference:
29th International Conference on Metallurgy and Materials, Brno, Czech Republic, EU, May 20 - 22, 2020
Proceedings:
Proceedings 29th International Conference on Metallurgy and Materials
Pages:
1232-1237
ISBN:
978-80-87294-97-0
ISSN:
2694-9296
Published:
27th July 2020
Proceedings of the conference were published in Web of Science and Scopus.
Metrics:
558 views / 323 downloads
Abstract

In the paper there are summarized basic analytical and empirical pieces of knowledge on searching dependences of the influence of thermal process during steel casting in the continuous casting of semi-finished products – slabs, on their quality assessment and as well the influence of thermal processes on the quality of final products rolled of slabs. The course of thermal processes at continuous steel casting has the significant impact on the quality of slabs. The assessment of the quality of slabs during continuous steel casting is an inseparable part of the information system of a metallurgical plant. This assessment works on the data collection and storing the necessary data for an effective assessment between measured and qualitative quantities. The paper describes the proposal of the concept of quality slab prediction. There are statistical methods used for this purpose, especially association rules and logistic regression. On the basis of use of the system for monitoring the casting parameters and the application of statistical methods, association rules for prediction of quality of continuously cast slabs were determined.

Keywords: Metallurgy, continuous casting of steel, slab, association rules, logistic regression

© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Scroll to Top