РУС
ENG
DEVELOPMENT OF MACHINE LEARNING MODEL OF PREDICTION HIGH-TEMPERATURE METALLURGICAL PROPERTIES OF COKE
Goals and sphere
Founder and publisher
Editorial Board
Licensing conditions
Confidentiality
Attitude towards plagiarism
Publication ethics
Archiving Policy
Subscription
Instructions for authors
The review process
Copyright
Agreement on the transfer of rights
Editorial fees
All issues
Search
Contacts
Kovalchik Roman Vladislavovich
Candidate of Technical Sciences, Head of the Department of Computer Science and Computer Engineering
Priazovsky State Technical University, Russian Federation, DPR, Mariupol.
Research interests: system analysis, mathematical modeling, artificial intelligence, automation of technological processes in ferrous metallurgy.
UDC 004.932.2:004.622
DOI 10.24412/2413-7383-68-78
Language: Russian
Annotation:
The results of coke high-temperature metallurgical properties prediction models developed by the author are presented. The optimal model of machine learning was selected, which allowed to achieve the highest accuracy of prediction of the target index, as which the coke reactivity index CRI is used. The peculiarity of the models is the use of coal charge grade composition as input values. The proposed approach does not require additional laboratory studies of physicochemical properties of coal charge for coke production.
Keywords: machine learning, neural networks, optimizers, metallurgical coke, forecasting.
References:
1 Improvement of blast furnace coke quality by means of special reagents / V.A.Tamko, I.V.Zolotarev, E.I.Zbykovsky et al. // Uglekhimicheskiy Zhurnal. - 2009 - № 5 - С. 13-20.
2. Blast-furnace coke quality estimation / A.S. Afanasyev, Yu.V. Konovalova, S.G. Gagarin et al. https://www.researchgate.net/publication/293525211_Estimation_of_metallurgical_coke_quality
3. Kovalchik, R.V. Variation of the blast furnace smelting intensity when using coke with different hot strength (in Russian) / R.V. Kovalchik, A.A. Tomash, Yu.A. Zinchenko // Metal and casting of Ukraine. - 2008 - № 7-8. - С. 27-30.
4. Doroganov, V. S.; Sukhanova, E. Yu. Forecasting of the coke characteristics on the basis of the charge indicators (in Russian) // Proceedings of the All-Russian youth school-seminar “Analysis, geometry and topology”. Barnaul: AltSU, 2013 С. 46 - 50
5. Stankevich A. S., Gilyazetdinov R. R. R., Popova N. K., Koshkarov D. A. Model for prediction of coke CSR and CRI indicators on the basis of chemical and petrographic parameters of coal charge and conditions of their coking // Coke and Chemistry. 2008 № 9 С. 37 - 44
6. Influence of reactivity and “hot” strength of coke on technical and economic indicators of blast furnace melting in conditions of JSC “AZOVSTAL IRON & STEEL WORKS” / A.A. Tomash, V.P. Tarasov, R.V. Kovalchik [et al.] // Bulletin of Priazov State Technical University. - 2007 - № 17 - С. 9-13.
7. Kovalchik, R.V.; Tomash, A.A. Theoretical evaluation of the influence of hot strength of coke CSR on its specific consumption in blast furnace melting (in Russian) // Vestnik of Priazov State Technical University. Series: Technical sciences. - 2008 - № 18 - С. 15-18.
8. Afanasyev V. V. Probability theory in questions and tasks. Access mode: http://cito-web.yspu.org/link1/metod/theory/node42.html, free.
Release: 1(36)'2025
Chapter: SYSTEM ANALYSIS, INFORMATION MANAGEMENT AND PROCESSING, STATISTICS
How to quote:
R. V. Kovalchik. DEVELOPMENT OF MACHINE LEARNING MODEL OF PREDICTION HIGH-TEMPERATURE METALLURGICAL PROPERTIES OF COKE // Problems of artificial intelligence. 2025. №1.
