DAILY PLANNING AND OPTIMIZATION OF RAW MATERIAL FLOWS IN FERROUS METALLURGY

Since 2017, EVRAZ ZSMK JSC has been developing and operating a mathematical model covering all processing stages from ore extraction to final products – SMM Forecast. The model is used to calculate technical cases, plans, and market prices for iron ore and coal, and its use brought more than 200 million rubles of economic effect in 2020 alone. The use of a universal mathematical model made it possible to begin the development of a module for daily optimization of the agglomeration factory and blast furnace production in 2023. The article discusses the experience of EVRAZ ZSMK JSC in the development and implementation of a daily planning system based on the monthly planning model of SMM Forecast. The SMM Forecast system was originally designed for end-to-end scenario calculation of the main raw materials processing from ore and coal to finished products in a volumetric monthly planning. The system uses optimization algorithms to search for a global objective function to maximize margin income within specified limits. The mathematical model of processingt uses the norms and technology specified in the company's regulatory documents. At the same time, the model is universal, and the transfer of algorithms from monthly to daily mode was carried out with minimal modifications. The article also discusses the difficulties encountered and methods of solving these problems. The first problem faced by the developers was the low speed of optimization of the model in daily dynamics due to the strong complication of the optimization load. The calculation time increased significantly, and to solve the problem, it took optimizing the speed of solving equations, setting the boundaries of variables, determining starting points, as a result of which the calculation speed for 30 days decreased to 40 minutes. The second problem was the need to develop a complex algorithm for managing the supply of raw materials. An important aspect was to maintain the usability of the system at the same level for the end user. The result of the implementation of the proposed solutions is a working tool that brings additional income to the enterprise.

1. Lisienko V.G., Solov'eva N.V., Trofimova O.G. Alternative metallurgy: the problem of alloying, model efficiency estimates. Moscow : Izd. Teplotekhnik. 2007:440. (In Russ.).

2. Protopopov E.V., Kalinogorskii A.N., Ganzer A.A. Steel production: current range and directions of development. In: "Metallurgy: technologies, innovations, quality: TR. Overseas. learned.- practical. conf. H. 1 / Е.V. Protopopov ed. Novokuznetsk: ITs SibGIU. 2019:9–14. EDN: MAPRGL. (In Russ.).

3. Johansen S.T. Mathematical modeling of metallurgical processes. In: Third International Conference on CFD in the Minerals and Process Industries CSIRO, Melbourne, Australia 10-12 December 2003. Norway. 2003.

4. Svatos J., Gargulak Z. Set of Models for Planning Iron and Steel Production. IFAC Proceedings Volumes. 1983;16(15):55–62.

5. https://doi.org/10.1016/S1474-6670(17)64256-3

6. Mitterlehner J., Loeffler G., Winter F., Hofbauer H., Schmid H., Zwittag E., Buergler T. H., Pammer O., Stiasny H. Modeling and Simulation of Heat Front Propagation in the Iron Ore Sintering Process. ISIJ International. 2004;44(11):11–20. https://doi.org/10.2355/isijinternational.44.11

7. Yang W., Changkook R., Choi S., Lee D., Huh W. Modeling of Combustion and Heat Transfer in an Iron Ore Sintering Bed with Considerations of Multiple Solid. ISIJ International. 2004;44(3):492–499. https://doi.org/10.2355/isijinternational.44.492

8. Fernández-González D., Martín-Duarte R., Ruiz-Bustinza Í., Mochón J., González-Gasca C., Verdeja L. F. Optimization of Sinter Plant Operating Conditions Using Advanced Multivariate Statistics: Intelligent Data Processing. The Minerals, Metals & Materials Society. 2016;68(8):2089–2095. https://doi.org/10.1007/s11837-016-2002-2

9. Shi Z., Lv W., & Mei G. A novel soft sensing modelling approach for sulphur content estimation in hot metal pretreatment process. Ironmaking & Steelmaking: Processes, Products and Applications. 2024;51.

10. http://dx.doi.org/10.1051/metal/2023073

11. Shao H., Yi Z., Chen Z., Zhou Z., Deng Z. Application of artificial neural networks for prediction of sinter quality based on process parameters control. Transactions of the Institute of Measurement and Control. 2019:42(3):1–18. https://doi.org/10.1177/0142331219883501

12. Mallicka A, Dhara S., Rath S. Application of machine learning algorithms for prediction of sinter machine productivity. Machine Learning with Applications. 2021;6:100186.

13. http://dx.doi.org/10.1016/j.mlwa.2021.100186

14. Song L., Qing L., Xiaojie L., Yanqin S. Syn-thetically predicting the quality index of sinter using machine learning model. Ironmaking & Steelmaking Processes, Products and Applications. 2020;47(7):828–836.

15. https://doi.org/10.1080/03019233.2019.1617573

16. Mohanan S., Mohapatra P., Kumar A.C., Adepu R.K., Koranne V.M., Prasad Y.G.S., Reddy A.S., Ramna R.V. Prediction and Optimization of Internal Return Fines Generation in Iron Ore Sintering Using Machine Learning. Advances in Materials. 2021;10(3):42–46. https://doi.org/10.11648/j.am.20211003.12

17. Metzger M., Sieber A., Stirmer U. Mathematical model for a metallurgical plant, and method for optimizing the operation of a metallurgical plant using a model Pat. US 7,720,653 B2 USA Patent. 2010.

18. Lian X., Wu D., Lu S., Liu C., Wang H., Wang J. Optimal scheduling of multi-energy medium in steel enterprises based on improved genetic simulated annealing algorithm. Proceedings of the 2024 Chinese Control and Decision Conference (CCDC). 2024:2632‒2637.

19. https://doi.org/10.1109/CCDC62350.2024.10587574

20. Liu Q., Shao X., Yang J.–P., Zhang J.–S. Multiscale modeling and collaborative manufacturing for steelmaking plants. Chinese Journal of Engineering. 2012;12:1698–1712.

21. https://doi.org/10.13374/j.issn2095-9389.2021.09.27.010

22. Zhang J., Liu Y., Liu Q. Metallurgical Process Simulation and Optimization Metallurgical Process Simulation and Optimization. Materials. 2022;15(23):8421.

23. https://doi.org/10.3390/ma15238421

24. Leont'ev A.S., Rybenko I.A. Experience in the development and application of the mathematical modeling system at EVRAZ ZSMK. In: Modeling and high-tech information technologies in technical and socio-economic systems: proceedings of the V International Scientific and Practical Conference with international participation / I.A. Rybenko, T.V. Kiseleva ed. Novokuznetsk: ITs SibGIU. 2021:250–255. EDN: ATSSJP. (In Russ.).

25. Leont'ev А.S., Rybenko I.А. Mathematical modelling system for metallurgical enterprise: Operation and usability enhancement. Izvestiya. Ferrous Metallurgy. 2023;66(1):119–126. https://doi.org/10.17073/0368-0797-2023-1-119-126

26. Leont'ev A.S., Rybenko I.A. Experience in implementing machine learning for calculating the quality and production of agglomerate at EVRAZ ZSMK. In: Metallurgy: technologies, innovations, quality: tr. XXII international scientific and practical conference / A.B. Yuriev ed. Novokuznetsk: ITs SibGIU. 2021:82–87. EDN: HRRSAU.

27. Information about EVRAZ ZSMK JSC // EVRAZ Company website. Available at URL:https://www.kommersant.ru/doc/3502550 (Accessed 16.09.2024).

28. Analytical platform platform fore-cast//Website of the Foresight company. Available at URL: https://www.fsight.ru/ (Accessed 16.09.2024). (In Russ.).

29. GAMS. Available at URL: https://www.gams. com/latest/docs/UG_ExecErrPerformance.html (Accessed 19.10.2023). (In Russ.).