Journals →  Tsvetnye Metally →  2023 →  #4 →  Back

ArticleName Machine vision system for monitoring the process of levitation melting of non-ferrous metals
DOI 10.17580/tsm.2023.04.11
ArticleAuthor Boykov A. V., Payor V. A.

Saint Petersburg Mining University, Saint Petersburg, Russia:

A. V. Boykov, Project Supervisor at the Research and Training Centre for Digital Technology, Associate Professor, Candidate of Technical Science, e-mail:
V. A. Payor, Postgraduate Student of the Department of Process and Plant Automation, e-mail:


Machine vision-based optical non-destructive monitoring systems are widely used in different industries. Optical systems are able to measure a variety of parameters at high speed and at a distance (in a contactless manner), and all this makes them efficient. Due to the development of computer hardware, optical monitoring techniques can be automated and integrated into process control systems utilized by non-ferrous metals producers. This paper describes a machine vision system that can be used to monitor the melt in the coil of an electromagnetic levitation furnace. Using a case study of levitation melting of aluminium test pieces, the authors describe the result of testing an algorithm designed to track the melt moving in the coil.
Support for this research was provided under Grant No. 22-71-00029 by the Russian Science Foundation,

keywords Machine vision, levitation melting, automation, metallurgy, electromagnetism, induction, electromagnetic field, melt, coil, non-ferrous metals

1. Demidovich V. B., Rastvorova I. I. A combined method of simulation of an electric circuit and field problems in the theory of induction heating. Russian Electrical Engineering. 2014. Vol. 85, Iss. 8. pp. 536–540.
2. Boikov A. V., Payor V. A. The Present issues of control automation for levitation metal melting. Symmetry. 2022. Vol. 14, Iss. 10. 1968. DOI: 10.3390/sym14101968
3. Darhovsky Y. et al. A novel contactless, feedbackless and sensorless power delivery link to electromagnetic levitation melting system residing in sealed compartment. Energy. 2021. Vol. 231, Iss. 1. 120789.
4. Gendler S. G., Prokhorova E. A. Assessment of the cumulative impact of occupational injuries and diseases on the state of labor protection in the coal industry. Mining Informational Analytical Bulletin. 2022. No. 10-2. pp. 105–116. DOI: 10.25018/0236_1493_2022_102_0_105
5. Chamorro X. et al. Induction skull melting of Ti – 6Al – 4V: Process control and efficiency optimization. Metals. 2019. Vol. 9, Iss. 5. 539.
6. Seidel A., Soellner W., Stenzel C. EML – An electromagnetic levitator for the International Space Station. Journal of Physics: Conference Series. 2011. Vol. 327, Iss. 1. pp. 1–14.
7. Lohofer G. Theory of an electromagnetically levitated metal sphere I: absorbed power. SIAM Journal on Applied Mathematics. 1989. Vol. 49, Iss. 2. DOI: 10.1137/0149032
8. Spitans S. et al. Large-scale levitation melting and casting of titanium alloys. Magnetohydrodynamics. 2017. Vol. 53, Iss. 4. P. 633–641.
9. Bauer W., Baranowski J. Fractional PIλD controller design for a magnetic levitation system. Electronics. 2020. Vol. 9, Iss. 12. 2135.
10. Zhukovskiy Y., Batueva D., Buldysko A. et al. Motivation towards energy saving by means of IoT personal energy manager platform. Journal of Physics: Conference Series. 2019. Vol. 1333, Iss. 6. DOI: 10.1088/1742-6596/1333/6/062033
11. Baake A., Shpenst V. A. Latest research in the area of electrothermal treatment of metals. Journal of Mining Institute. 2019. Vol. 240. pp. 660–668.
12. Takahashi K. et al. Materials processing in magnetic levitation furnaces. Science and Technology of Advanced Materials. 2006. Vol. 7, Iss. 4. pp. 346–349.
13. Risheh A. et al. Infrared computer vision in non-destructive imaging: Sharp delineation of subsurface defect boundaries in enhanced truncated correlation photothermal coherence tomography images using K-means clustering. NDT and E International. 2022. Vol. 125, Iss. 2. 102568.
14. Ma Y. et al. Real-time detection and spatial localization of insulators for uav inspection based on binocular stereo vision. Remote Sensing. 2021. Vol. 13, Iss. 2. pp. 1–23.
15. David J. et al. Usage of real time machine vision in rolling mill. Sustainability. 2021. Vol. 13, Iss. 7. 3851.
16. Islamov S. et al. Research risk factors in monitoring well drilling – a case study using machine learning methods. Symmetry. 2021. Vol. 13, Iss. 7. 1293.
17. Ilyushin Y., Afanaseva O. Spatial distributed control system of temperature field: synthesis and modeling. ARPN Journal of Engineering and Applied Sciences. 2021. Vol. 16, Iss. 14. pp. 1491–1506.
18. Shestakov A. K., Petrov P. A., Nikolaev M. Yu. Automatic system for detecting visible emissions in a potroom of aluminum plant based on technical vision and a neural network. Metallurgist. 2023. Vol. 66, No. 9-10. pp. 1308–1319.
19. Guo M. H. et al. Attention mechanisms in computer vision: A survey. Computational Visual Media. 2022. Vol. 8, Iss. 11. pp. 331–368.
20. Feng X. et al. Computer vision algorithms and hardware implementations: A survey. Integration. 2019. Vol. 69. pp. 309–320.
21. Romashev A. O., Nikolaeva N. V., Gatiatullin B. L. An adaptive approach built on the basis of machine vision used for determining concentrate precipitation parameters. Journal of Mining Institute. 2022. Vol. 256. pp. 677–685.
22. Gupta K. K., Beg M. R., Niranjan J. K. A novel approach to fast image filtering algorithm of infrared images based on intro sort algorithm. International Journal of Computer Science Issues. 2011. Vol. 8, Iss. 6. pp. 235–241.
23. Zhang Y., Li D., Zhu W. Infrared and visible image fusion with hybrid image filtering. Mathematical Problems in Engineering. 2020. Vol. 2020. 1757214.
24. Deng H. et al. SS symmetry industrial laser welding defect detection and image defect. Symmetry. 2021. Vol. 13, Iss. 9. 1731.
25. Romachev A., Kuznetsov V., Ivanov E., Benndorf J. Flotation froth feature analysis using computer vision technology. Journal of Mining Institute. 2020. Vol. 192. 02022. DOI: 10.1051/e3sconf/202019202022
26. Ghahfarokhi P. S. et al. Thermal analysis of electromagnetic levitation coil. Proceedings 2016 17th International Scientific Conference on Electric Power Engineering, EPE 2016. 2016. pp. 1–5.
27. Park H. An RGB-NIR image fusion method for improving feature matching. International Journal of Engineering and Technology Innovation. 2020. Vol. 10, Iss. 3. pp. 225–234.
28. Long J., Shelhamer E., Darrell T. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2015. pp. 1–10.
29. Despotovic M. et al. Poster abstract: predicting heating energy demand by computer vision. Computer Science – Research and Development. 2018. Vol. 33, Iss. 1-2. pp. 231, 232.
30. Hyers R. W., Trapaga G., Abedian B. Laminar-turbulent transition in an electromagnetically levitated droplet. Metallurgical and Materials Transactions B: Process Metallurgy and Materials Processing Science. 2003. Vol. 34, Iss. 1. pp. 29–36.
31. Kashin D. A., Kulchitskiy A. A. Image-based quality monitoring of metallurgical briquettes. Tsvetnye Metally. 2022. No. 9. pp. 92–98. DOI: 10.17580/tsm.2022.09.13
32. Kulchitskiy A. A., Mansurova O. K., Nikolaev M. Yu. Recognition of defects in hoisting ropes of metallurgical equipment by an optical method using neural networks. Chernye Metally. 2023. № 3. P. 81–88. DOI: 10.17580/chm.2023.03.13
33. Simakov A. S., Trifonova M. E., Gorlenkov D. V. Virtual analyzer of the voltage and current spectrum of the electric arc in electric arc furnaces. Russian Metallurgy (Metally). 2021. Vol. 2021, Iss. 6. pp. 713–719.
34. Pan D. et al. Temperature measurement and compensation method of blast furnace molten iron based on infrared computer vision. IEEE Tran sactions on Instrumentation and Measurement. 2019. Vol. 68, Iss. 10. Р. 3576–3588. DOI: 10.1109/TIM.2018.2880061
35. Liu E. et al. Numerical simulation of effect of magnetizer on magnetic field of induction melting furnace. 3D Research. 2019. Vol. 10, Iss. 1. 9.

Language of full-text russian
Full content Buy