Saint Petersburg Mining University, Saint Petersburg, Russia:

D. A. Kashin, Postgraduate Student of the Department of Process and Production Automation, e-mail: s185023@stud.spmi.ru
A. A. Kulchitskiy, Associate Professor at the Department of Process and Production Automation, Candidate of Technical Sciences, e-mail: doz-ku@rambler.ru

This paper examines the problem of monitoring the quality of briquetted charge for metallurgical industry. The authors analyze the existing techniques and systems that help detect contaminants in or improper shape of briquettes. The study revealed that the current practice is based on destructive spot tests only, while no automatic monitoring systems are available. So, the authors looked into the applicability of volume-weight technique for monitoring metallurgical briquettes. The study relied on digital images produced by machine vision cameras to analyze the geometry of briquettes, as well as their surface properties. The paper describes a possible combination of components for the proposed system. A method is proposed to estimate the volume of a briquette by considering the image shift in the calibration plane. A relationship was calculated of the relative error caused by faulty positioning when using the correction method and without using it. The paper also examines a technique that helps analyze the porosity of briquettes so that their true density and the concentration of contaminants in them could be further determined. TensorFlow software library and images of different objects were used to teach the neural network. The authors conducted a quality study to understand how accurately neural networks can identify the type of metal contained in a briquette. The performance of neural networks reached 94%. Analysis of samples conducted on a test bench showed that the described technique could be used to monitor the quality of metallurgical briquettes with a minimum 0.4 % accuracy of dimensional analysis. The latter is based on positioning error correction in relation to the calibration plane.

1. Galevskiy G. V., Kulagin N. M., Mintsis M. Ya. Ecology and waste disposal in aluminium industry. Novosibirsk : Nauka, Sibirskoe predpriyatie RAN, 1996. 146 p.
2. Beloglazov I. I., Morenov V. A., Leusheva E. L. Flow modeling of high-viscosity fluids in pipeline infrastructure of oil and gas enterprises. Egyptian Journal of Petroleum. No. 11. pp. 1–9. DOI: 10.1016/j.ejpe.2021.11.001.
3. Bushuev A. B., Boikov V. I., Mansurova O. K., Bystrov S. V. et al. Synthesis of optimal information and energy schemes of measuring and converting devices. Mekhatronika, Avtomatizatsiya, Upravlenie. 2021. Vol. 22, Iss. 10. pp. 518–526.
4. Khalifa A. A., Bazhin V. Yu., Ustinova Ya. V., Shalabi M. E. Kh. Understanding the kinetics behind red mud pelletizing in hydrogen flow. Zapiski Gornogo instituta. 2022. Vol. 254. DOI: 10.31897/PMI.2022.18.
5. Ozhogin V. V. Briquetting of ground metallurgical raw material: Basic theory and process. Monograph. Mariupol : PGTU, 2010. 442 p.
6. GOST R 54565–2011. Scrap and waste of non-ferrous metals and alloys. Terms and definitions. Introduced: 01.01.2013.
7. Gonik I. L., Lsmyakin V. P., Novitskiy N. A. Application of briquetted ironbearing waste. Metallurg. 2011. No. 5. pp. 25–27.
8. Meyer H. J. Use of regenerative heating technologies at aluminium melting and aluminium recycling furnaces. Heat Processing. Essen. 2012. pp. 78–90.
9. Spencer D. B. The high-speed identification and sorting of nonferrous scrap. JOM. 2005. Vol. 57, Iss. 4. pp. 46–51.
10. Pugacheva N. B., Babaylov N. A., Bykova T. M., Loginov Yu. N. The structure, phase composition and micromechanical properties of briquetted aluminium. Obrabotka Metallov / Metal Working and Material Science. 2020. Vol. 22, No. 3. pp. 82–94. DOI: 10.17212/1994-6309-2020-22.3-82-94.
11. GOST 1639–2009. Non-ferrous metals and alloys scrap and waste. General specifications. Introduced: 01.01.2011.
12. Non-destructive testing and diagnostics: Reference book. Ed. by V. V. Klyuev. Moscow : Mashinostroenie, 2005. 679 p.
13. Kulchitskii А. А, Kashin D. A. The choice of a method for non-contact assessment of the composition of briquetted charge materials. Journal of Physics: Conference Series. 2019. No. 1399. pp. 1–6.
14. Ignatova A. M., Ignatov M. N. Contactless analysis of nickel foam porosity by 3D X-ray tomography. Izvestiya vuzov. Poroshkovaya metallurgiya i funktsionalnye pokrytiya. 2015. No. 3. pp. 36–43.
15. Fandeev V. P., Samokhina K. S. Porous structure study techniques. Internetzhurnal Naukovedenie. 2015. No. 4. p. 101.
16. E. A. Artemiev, A. A. Artemiev, E. V. Tsarenko. Method of continuous weighing of materials carried by belt conveyors, system to this end and belt conveyor roller support. Patent RF, No. 2401994C1. Published: 20.10.2010.
17. Jakubovicová L. et al. Technical solution of the modern conveyor system. IOP Conference Series: Materials Science and Engineering. 2021. Vol. 1199, No. 1. 012031.
18. Potapov A. I., Kulchitskii A. A., Smirnov A. G., Smorodinskii Y. G. Evaluating the error of a system for monitoring the geometry of anode posts in electrolytic cells with self-baking anode. Russian Journal of Nondestructive Testing. 2020. Vol. 56, Iss. 3. pp. 268–274.
19. Kashin D. A., Kulchitskiy A. A., Fedorova E. R. A computer programme for size and shape analysis of briquetted materials on the basis of their digital images. Certificate of State Registration of Computer Software No. 2020615959. State registration in the Computer Software Register. 5.06.2020.
20. Kashin D. A., Kulchitskiy A. A., Smirnov A. G. A computer programme for size control of axisymmetric parts that is capable of correcting perspective errors of a single-channel optical system. Certificate of State Registration of Computer Software No. 2020615959. State registration in the Computer Software Register. 25.10.2020.
21. Marrion C. C., Mullan N. J. Detecting object presence on a target surface. Patent US, No. 2016253793A1. Published: 01.09.2016.
22. Wang Zhou. Multi-face imaging measurement device. Patent CN, No. 102243185A. Published: 2011.11.16.
23. Wang Xue, Shan Bingzheng, Yang Kaige, Yang Huan. Screen appearance defect online detection device. Patent CN, No. 211528226U. Published: 2020.09.18.
24. Makhov V. E., Repin O. S., Potapov A. I. Dimensions measured by machine vision systems in coherent light. Kontrol. Diagnostika. 2014. No. 4. pp. 12–19. DOI: 10.14489/td.2014.04.pp.012-019.
25. Potapov A. I., Kulchitskiy A. A., Smorodinskii Ya. G., Smirnov A. G. Evaluating the error of a system for monitoring the geometry of anode posts in electrolytic cells with self-baking anode. Russian Journal of Nondestructive Testing. 2020. Vol. 56, Iss. 3. pp. 268–274.
26. Official website of Basler. https://www.baslerweb.com/ru/ (Accessed: 12.06.2022)
27. Gutorov M. M. Fundamentals of lighting engineering and light sources. Moscow, 1983.
28. Relf C. G. Image acquisition and processing with Lab VIEW. CRC Press LLC. 2004.
29. Schreder G., Treiber H. Optical engineering. Moscow : Tekhnosfera, 2006. 424 p.
30. Fedosov V. P., Nesterenko A. K. Digital processing of signals in LabVIEW: Learner’s guide. Ed. by V. P. Fedosov. Moscow : DMK Press, 2007. 456 p.
31. Beloglazov I. I., Sabinin D. S., Nikolaev M. Yu. Modeling the disintegration process for ball mills using dem. Mining Informational and Analytical Bulletin. 2022. No. 6-2. pp. 268–282. DOI: 10.25018/0236_1493_2022_62_0_268.
32. Boikov A., Payor V., Savelev R., Kolesnikov A. Synthetic data generation for steel defect detection and classification using deep learning. Symmetry. 2021. Vol. 13. p. 1176. DOI: 10.3390/sym13071176.
33. Vasilyeva N. V., Boikov A. V., Erokhina O. O., Trifonov A. Y. Automated digitization of radial charts. Journal of Mining Institute. 2021. Vol. 247. pp. 82–87. DOI: 10.31897/PMI.2021.1.9.
34. Vasilyeva N., Fedorova E., Kolesnikov A. Big data as a tool for building a predictive model of mill roll wear. Symmetry. 2021. Vol. 13. p. 859. DOI: 10.3390/sym13050859.
35. Vasilyeva N. V., Boikov A. V., Erokhina O. O. et al. Automated digitization of radial charts. Journal of Mining Institute. 2021. Vol. 247. pp. 82–87. DOI: 10.31897/PMI.2021.1.9.
36. Krizhevsky A., Sutskever I., Hinton G. E. ImageNet classification with deep convolutional neural networks. Communications of the ACM. Association for Computing Machinery. 2017. Vol. 60, No. 6. pp. 84–90. DOI: 10.1145/3065386.
37. Paszke A., Gross S., Massa F., Lerer A. et al. Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems. 2019. Vol. 32.