Intelligent decision support system based on video recognition of the blast furnace tuyeres

An approach to creation of an intelligent system for predicting the state of a technological process in real time is presented. The approach is based on the analysis of a video sequence of images obtained as a result of streaming video by cameras installed on the tuyeres of a blast furnace. Algorithms for recognizing video images of tuyere foci, as well as scenario forecasting of the evolution of technological situations are proposed. A historical background regarding the development of methods for automatic control of the blast-furnace process, in particular, the use of artificial intelligence, is presented. The study is aimed at the ability of rapid analysis of the production situation (PS) and prediction of the PS evolution in the course of functioning of the blast furnace process, which will provide the possibility of timely decisions on adjusting control in an automatic or automated mode. Using the developed algorithm for analysis and prediction of the process dynamics and proceeding from the revealed regularities of the change in video data, a method for early detection of a tendency to the occurrence of certain events on tuyeres, including those leading to the destabilization of the blast furnace process, is proposed. The novelty of the presented approach lies in the fact that not only the state of the process at the next moment of time, but also the most probable chain of several subsequent states is predicted. Real-time forecasting algorithms are based on the construction and replenishment of the base of inductive knowledge — regularities revealed through the intellectual analysis of the revealed information — in the course of real functioning. Methods of studying Markov chains, machine learning and wavelet analysis are used for the associative search for patterns. The algorithms developed by the authors can be used in decision support systems for blast-furnace control. The results of practical research, confirming the effectiveness and viability of the proposed approach, are presented.

1. Sibagatullin S. K., Kharchenko A. S., Beginyuk V. A. Processing Solutions for Optimum Implementation of Blast Furnace Operation / Metallurgist. 2014. N 58(3 – 4). P. 285 – 293. DOI: 10.1007/s11015-014-9903-5

2. Grachev Yu. M., Kac M. D., Davidenko A. M. A new approach to solving the problem of increasing the efficiency of blast-furnace smelting at the same time in terms of specific coke consumption and productivity / Metallurg. Gornorud. Promyshl. 2008. N 5. P. 142 – 145 [in Russian].

3. Shcherbakov V. P. Blast-furnace production basics. — Vladimir: Metallurgiya, 1969. — 213 p. [in Russian].

4. Yusfin Yu. S. Iron metallurgy. — Moscow: Akademkniga, 2004. — 774 p. [in Russian].

5. Spirin Kh. A. Model systems of decision support in the automated process control system of blast-furnace smelting of metallurgy. — Yekaterinburg: UrFU, 2011. — 462 p. [in Russian].

6. Gulina I. G., Kornienko V. I., Gusev A. Yu., Makienko V. G. Identification, prediction and control of a complex multi-connected control object / Sist. Obrab. Inform. 2012. N 9(107). P. 31 – 35 [in Russian].

7. Salyga V. I., Karabutov N. N. Identification and control of processes in the iron and steel industry. — Moscow: Metallurgiya, 1986. — 192 p. [in Russian].

8. Spirin Kh. A. Blast-furnace smelting control problems and information-modeling systems / Cognition of the processes of blast-furnace smelting. Collective monograph // V. I. Bolshakova and I. G. Tovarovskiy, Eds. — Dnepropetrovsk: Porogi, 2006. P. 322 – 344 [in Russian].

9. Gulina I. G. Adaptive ACS for a complex multi-connected control object with intelligent forecasting / Sist. Obrab. Inform. 2011. N 8(98). P. 57 – 62 [in Russian].

10. Nelles O. Nonlinear System Identification: From Classical Approaches to Neural and Fuzzy Models. — Berlin: Springer, 2001. — 785 p.

11. Vegman E. F., Zherebin B. N., Pokhvisnev A. N. Iron metallurgy: a textbook for universities. — Moscow: Metallurgiya, 1978. — 480 p. [in Russian].

12. Sorokin V. A. Complex automation of blast furnaces. — Moscow: Metallurgizdat, 1963. — 279 p. [in Russian].

13. Kitaev B. I., Yaroshenko Yu. G., Lazarev B. L. Blast furnace heat transfer. — Moscow: Metallurgiya, 1966. — 356 p. [in Russian].

14. Kazantsev C. B., Spirin Kh. A. On the application of pattern recognition methods for predicting the composition of cast iron in a blast furnace / Proc. of the IV All-Russian sci.-pract. conf. «Automation systems in education, science and manufacturing». — Novokuznetsk, 2003. P. 359 – 361 [in Russian].

15. Aizerman M. A., Braverman E. M., Rozonoer L. I. Potential function method in machine learning theory. — Moscow: Nauka, 1970. — 384 p. [in Russian].

16. Rastrigin I. A., Érenshtein R. Kh. Collective recognition method. — Moscow: Énergiya, 1981. — 80 p. [in Russian].

17. Carmichael J., Tyrion K., Goffin R. The evolution of modern blast furnace production and the introduction of progressive engineering solutions / Stal’. 2006. N 12. P. 8 – 14.

18. Druckenthaner H., Schurz B., Schaler M. Vairon blast furnace optimization / Steel Times. 2000. N 8. P. 290 – 293.

19. Expert control systems for blast-furnace smelting. https://www.researchgate.net/publication/326160639_Ekspertnye_sistemy_upravlenia_domennoj_plavkoj (accessed 22.08.2021).

20. Kazarinov L. S., Barbasova T. A. Identification Method of Blast-Furnace Process Parameters / Proc. of Int. Conf. for young scientists «High Technology: Research and Applications 2015 (HTRA 2015)», Key Engineering Materials. 2016. Vol. 685. P. 137 – 141.

21. RF Pat. N 2368853. Method for automatic control of the upper level of the slag phase and the interface between the slag and metal phases in a metallurgical furnace bath / Salikhov Z. G., Afanas’ev A. G., Ishmet’ev E. N., Salikhov K. Z., Oreshkin S. A.; applicant and owner Scientific and Ecological Enterprise Ltd. — N 2007119099/02; appl. 23.05.2007; publ. 27.09.2009. Byull. N 27 [in Russian].

22. Bakhtadze N., Lototsky V. Knowledge-Based Models of Nonlinear Systems Based on Inductive Learning / New Frontiers in Information and Production Systems Modelling and Analysis Incentive Mechanisms, Competence Management, Knowledge-based Production. — Heidelberg: Springer, 2016. P. 85 – 104.

23. Zhang C. N., Li Y. R. Optimization Analysis based on intelligent controlof the process of the plast furnace / Metallurgia. Zagreb. Chroatia. 2019. N 58. P. 7 – 10.

24. Matsuzaki S., Ito M., Motita A. Development of Blast Furnace Operation Data Visualization and Analysis Technology / Nippon steel technical report. 2020. N 123. P. 100 – 109. https://www.nipponsteel.com/en/tech/report/pdf/123-15.pdf

25. Kumar D. Optimization of blast furnace parameters using artificial neural network. National Institute of Technology Rourkela, India. 2015. — 44 p. https://core.ac.uk/download/pdf/80147603.pdf

26. Zhang Y., Sukhram M., Cameron I., Bolen J., Rozo A. / AISTech Conference Proceedings Industrial Perspective of Digital Twin Development and Applications for Iron and Steel Processes. 2020.

27. Agrawal R. and Suresh R. P. Improving Blast Furnace Operations Through Advanced Analytics / Springer Proceedings in Business and Economics, Applied Advanced Analytics // Arnab Kumar Laha, Ed. — Springer, 2021. P. 115 – 123.

28. Pan D., Jiang Z., Chen Z., Gui W., Xie Y., and Yang C. Temperature Measurement and Compensation Method of Blast Furnace Molten Iron Based on Infrared Computer Vision / IEEE Trans. Instr. Meas. 2019. Vol. 68. N 10. P. 3576 – 3588. DOI: 10.1109/TIM.2018.2880061

29. Lay-Ekuakille M. A., Ugwiri J., Okitadiowo, D., Chiffi C., Pietrosanto A. Computer Vision for Sensed Images Approach in Extremely Harsh Environments: Blast Furnace Chute Wear Characterization / IEEE Sens. J. 2021. Vol. 2021. DOI: 10.1109/JSEN.2021.3063264

30. Puttinger S., Stocker H. Improving Blast Furnace Raceway Blockage Detection. Part 3: Visual Detection Based on Tuyere Camera Images J-STAGE — an electronic journal platform managed by the Japan Science and Technology Agency (JST). 2019 Vol. 59. Issue 3. P. 481 – 488. ISIJ INT-2018 – 532. DOI: 10.2355/isijinternational

31. Salikhov Z. G., Ishmet’ev E. N. Automatic diagnostics of the operational state of dangerous (tuyere) zones of a pyrometallurgical unit / Izv. Vuzov. Cher. Met. 2010. N 11. P. 60 – 64 [in Russian].

32. Bakhtadze N. N., Salikhov Z. G., Donchan D. M. Predicting the state of processes based on video content analysis / Information technology and mathematical modeling of systems. — Moscow: Planeta+, 2018. P. 84 – 86 [in Russian].

33. Vapnik V. N. Statistical Learning Theory. — New York: John Wiley, 1998.

34. Jain A. Hough Transform. Fundamentals of Digital Image Processing. — Prentice-Hall, 1989. Chapter 9. https://homepages.inf.ed.ac.uk/rbf/HIPR2/hough.htm

35. Ghanem R., Romeo F. A wavelet-based approach for the identification of linear time-varying dynamical systems / J. Sound Vibration. 2000. Vol. 234. P. 555 – 576.