National University of Science and Technology (Moscow, Russia):

A. V. Kudrya, Dr. Eng., Prof., e-mail: AVKudrya@misis.ru
E. A. Sokolovskaya, Cand. Eng., Associate Prof.
D. F. Kodirov, Post-graduate Student
E. V. Bosov, Post-graduate Student

“Novye tekhnologii kachestva” (Moscow, Russia):
G. V. Kotishevskiy, Advisor of General Director

Several statistical restrictions, which are critically important for correct use of different Big Data procedures in metallurgy for attestation and management of quality of metal products are evaluated. Representative production control data stores for steel manufacturing technologies are used as the research object. This research covered wide grade and dimension range of steels: large forgings of heat treatable 38KhN3MFA-Sh steel, rolled products of 40KhMFA steel, sheet 17G1S-U, 09G2S and 15KhSND steels. Possible scale of variety of values distribution both for managing parameters and characteristics of strength, plasticity and toughness is shown using the coefficients of asymmetry and kurtosis. These characteristics are varied within the technological tolerance range. Accompanying risk during metal quality prediction and management, e.g. using the methods of parametric statistics, was evaluated for the case when this circumstance was not taken into account. The features of influence of a sample list volume on the results of statistical processing of large production control data stores and metallurgical product are revealed. It is shown how absence of common space of parameters restricts possibilities of classic statistics in metallurgy, makes non-effective the management “by disturbance” principle. In this connection, possibilities of non-parametric statistics, presented by Kolmogorov – Smirnov criterion, which is not depended on distribution of collection of analyzed sample lists, are evaluated. To provide objective selection of the areas with dominating type of relationship, it is necessary to take into account possibility of existence of different evolution scenarios for structure and defects along the technological chain (technological heredity) within the framework of rather wide tolerance range, as well as features of their appearance. Difference in the evolution mechanisms of structures and defects within the framework of separate technological trajectory is a cause of appearances of developed heterogeneity for nominal single-type structures which have, however, different scales, as well as accompanying quality dispersion (which is often essential). Taking this circumstance into account allows to find out the links in the system “managing parameters – final parameters of metal products”, which are not always evident during their search using generally accepted approaches. Development of the complex of rules for online management of metal products quality is possible on this base.

1. Steel on the threshold of centuries. Edited by Yu.S. Karabasov. Moscow. MISiS. 2001. Pp. 445-543.
2. Manwendra K.cTripathia, Randhir Kumarb, Rakesh Tripathib. Big-data driven approaches in materials science: A survey. Materials Today: Proceedings. 2020. Vol. 26. Part 2. pp. 1245-1249.
3. Shun Guo Jinxin Yu, Xingjun Liu, Cuiping Wang, Qingshan Jiang. A predicting model for properties of steel using the industrial big data based on machine learning. Computational Materials Science. 2019. Vol. 160. April. pp. 95-104.
4. Neuer M., Ebel A., Brandenburger J., Polzer J., Wolff A., Loos M., Holzknecht N., Peters H. Digital technologies in ferrous metallurgy. Chernye metally. 2019. No. 3. pp. 54-58.
5. Schuster R., Veugt N., Nath G., Louw N. Possibilities of digital technologies for transformation of value chains in metallurgy and metalworking. Chernye metally. 2019. No. 3. pp. 59-61.
6. Lindner Ch., Raschewski F., Weinberg M. New opportunities in quality control due to the progress in the control of technological parameters at HKM. Chernye metally. 2018. No. 1. pp. 63-69.

7. Cox I. J., Lewis R. W., Ransing R. S., Laxzczewski H., Berni G. Application of neural computing in basic oxygen steelmaking. J. Mat. Processing Technol. 2002. Jan. 15. pp. 310-315.
8. Dobrzanski L. A., Honysz R. Application of artificial neural networks in modeling of normalized structural steels mechanical properties. Journal of Achievements in Materials and Manufacturing Engineering. 2009. Vol. 32. Iss. 1. pp. 37–45.
9. Melnichenko A. S. Statistical analysis in metallurgy and materials science. A textbook. Moscow: Izdatelskiy dom “MISiS”. 2009. 268 p.
10. Gmurman V. E. Probability theory and mathematical statistics. A textbook for high schools. Moscow: Vysshaya shkola. 2003. 479 p.
11. Chubukova I. A. Data mining. Moscow. Binom. 2006. 384 p.
12. Shtremel M. A., Kudrya A. V., Ivashchenko A. V. Non-parametric discriminant analysis in quality management tasks. Zavodskaya laboratoriya. 2006. No. 5. p. 53.
13. Kudrya A. V., Shtremel M. A. On the reliability of data analysis in quality control. Metal Science and Heat Treatment. 2010. Vol. 52. No. 7-8. pp. 341-346.
14. Shtremel M. A. Information content of impact strength measurements. Metallovedenie i termicheskaya obrabotka metallov. 2008. No. 11. p. 37.
15. Chentsov N. N. Statistical decisive rules and optimal conclusions. Moscow. Nauka. 1972. 820 p.
16. Nikitin Ya. Yu. Asymptotic efficiency of non-parametric criteria. Moscow. Fizmatlit. 1995. 240 p.
17. Jia C. Self-adaptive flat control based on artificial intelligence. Gangtie Yanjiu Xuebao (J. of Iron and Steel Research). 2001. No. 13 (July-August). pp. 58-61.
18. Im Y.-T., Jung J.-Y. Fuzzy control algorithm for the prediction of tension variations in hot rolling. J. Mat. Processing Technol. 1999. pp. 163-172.
19. Honarmandi Р., Arróyave R. R. Uncertainty Quantification and Propagation in Computational Materials Science and Simulation-Assisted Materials Design. Integrating Materials and Manufacturing Innovation. 2020. Vol. 9. pp. 103-143.
20. Yong Liu, Jing-chuan Zhu, Yong Cao. Modeling effects of alloying elements and heat treatment parameters on mechanical properties of hot die steel with back-propagation artificial neural network. Journal of Iron and Steel Research International. 2017. Vol. 24. pp. 1254–1260.
21. Hastie, T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Chapter 15. Random Forests. 2^nd edition. Springer-Verlag. 2009. 746 p.
22. Kudrya A. V., Sokolovskaya E. A, Perezhogin V. Yu., Kodirov D. F. On Taking into Account the Statistical Nature of Objects in Structural Analysis in Metals Science. Russian Metallurgy (Metally). 2020. Vol. 12. pp. 1435–1438.