Journals →  Tsvetnye Metally →  2023 →  #4 →  Back

ArticleName Use of multifunctional crust breaker and machine vision system for acquisition and processing of aluminium reduction cell data
DOI 10.17580/tsm.2023.04.06
ArticleAuthor Petrov P. A., Shestakov A. K., Nikolaev M. Yu.

Saint Petersburg Mining University, Saint Petersburg, Russia:

P. A. Petrov, Dean of the Minerals Processing Faculty, Candidate of Technical Sciences, e-mail:
A. K. Shestakov, Postgraduate Student at the Department of Process and Plant Automation, e-mail:
M. Yu. Nikolaev, Master’s Student at the Department of Process and Plant Automation, e-mail:


The aluminium output control systems that are most commonly used in practice fail to ensure timely monitoring and adjustment of the key process parameters, such as electrolyte temperature, alumina concentration, cryolite ratio, metal and electrolyte levels. These parameters are measured manually, at a large interval (once a day). The difficulty of introducing automatic control systems comes down to the fact that most instruments and solutions are not practicable due to harsh process environment (i.e. high temperature, harmful emissions, alumina dusting, varying magnetic field). This paper describes a solution that enables to automatically collect electrolyte level values without compromising the tightness of the cell during measurement. The measurements are taken with a laser distance meter installed inside a crust breaker cylinder of the point feeding control system. Knowing the level of electrolyte in each feed cycle, one can define the smallest portion of alumina (the feeding interval) and add crushed bath automatically (if there is a hopper with a crushed bath feeding device). A neural network-based machine vision system developed for detecting visible emissions helps to quickly restore the cell cover in case of cryolite-alumina crust breakage or loss of cell tightness.

keywords Electrowinning of aluminium, electrolyte level monitoring, laser distance meter, automatic alumina feeding, TensorFlow, machine learning, convolutional neural network, object recognition, machine vision, emissions

1. Sizyakov V. M., Polyakov P. V., Bazhin V. Yu. Current trends and strategic objectives in the production of aluminum and its alloys in Russia. Tsvetnye Metally. 2022. No. 7. pp. 16–23.
2. Tarabarinova T. A., Golovina E. I. Capitalization of mineral resources as an innovation ecological strategy. Geology and Mineral Resources of Siberia. 2021. Vol. 4. pp. 86–96. DOI: 10.20403/2078-0575-2021-4-86-96
3. Savchenkov S., Beloglazov I. Features of the process obtaining of Mg – Zn – Y master alloy by the metallothermic recovery method of yttrium fluoride melt. Crystals. 2022. Vol. 12. p. 771. DOI: 10.3390/cryst12060771
4. Bolobov V. I., Chupin S. A., Bochkov V. S., Akhmerov E. V., Plaschinskiy V. A. The Effect of finely divided martensite of austenitic high manganese steel on the wear resistance of the excavator buckets teeth. Key Engineering Materials. 2020. Vol. 854. pp. 3–9. DOI: 10.4028/
5. Ojeda Pardo F. R., Sánchez Figueredo R. P., Belette Fuentes O., Quiroz Cabascango V. E. et al. Metallographic properties evaluation of the specimens obtained by the vibratory method (cast iron ISO 400-12). Journal of Physics: Conference Series. 2022. Vol. 2388. p. 012058. DOI: 10.1088/1742-6596/ 2388/1/012058
6. Zakirova G., Pshenin V., Tashbulatov R., Rozanova L. Modern bitumen oil mixture models in ashalchinsky field with low-viscosity solvent at various temperatures and solvent concentrations. Energies. 2023. Vol. 16. p. 395. DOI: 10.3390/EN16010395
7. Bolshunov A. V., Vasilev D. A., Ignatiev S. A., Dmitriev A. N., Vasilev N. I. Mechanical drilling of glaciers with bottom-hole scavenging with compressed air. Ice and Snow. 2022. Vol. 62. pp. 35–46. DOI: 10.31857/S2076673422010114
8. Kozyrev B. A., Sizyakov V. M., Arsentyev V. A. Principles of rational processing of red mud with the use of carboxylic acids. Non-Ferrous Metals. 2022. Vol. 53. pp. 30–34. DOI: 10.17580/nfm.2022.02.05
9. Fedorova E., Pupysheva E., Morgunov V. Modelling of red-mud particlesolid distribution in the feeder cup of a thickener using the combined CFDDPM approach. Symmetry. 2022. Vol. 14. p. 2314. DOI: 10.3390/sym14112314
10. Gorlanov E. S., Kawalla R., Polyakov A. A. Electrolytic production of aluminium. Review. Part 2. Development prospects. Tsvetnye Metally. 2020. No. 10. pp. 42–49. DOI: 10.17580/tsm.2020.10.06
11. Martynov S. A., Masko O. N., Fedorov S. N. Innovative ore-thermal furnace control systems. Tsvetnye Metally. 2022. No. 4. pp. 87–94. DOI: 10.17580/tsm.2022.04.11
12. The Program for improving the environmental efficiency of the branch office PJSC RUSAL Bratsk in Shelekhov. 2019. (n.d.).
13. Dubovikov O. A., Beloglazov I. I., Alekseev A. A. Specific features of the use of pulverized coal fuel in combined chemical processing. Obogashchenie Rud. 2022. No. 6. pp. 32–38. DOI: 10.17580/or.2022.06.06
14. Litvinova T., Kashurin R., Zhadovskiy I., Gerasev S. The kinetic aspects of the dissolution of slightly soluble lanthanoid carbonates. Metals. 2021. Vol. 11. p. 1793. DOI: 10.3390/met11111793
15. Kashurin R. R., Gerasev S. A., Litvinova T. E., Zhadovskiy I. T. Prospective recovery of rare earth elements from waste. Journal of Physics: Conference Series. 2020. Vol. 1679, Iss. 5. p. 052070. DOI: 10.1088/1742-6596/1679/5/052070
16. Boduen A. Ya., Petrov G. V., Kobylyansky A. A., Bulaev A. G. Sulfide leaching of high-grade arsenic copper concentrates. Obogashchenie Rud. 2022. No. 1. pp. 14–20. DOI: 10.17580/or.2022.01.03
17. Awrejcewicz J., Oikonomou V. K., Boikov A., Payor V. The present issues of control automation for levitation metal melting. Symmetry. 2022. Vol. 14. p. 1968. DOI: 10.3390/sym14101968
18. Cabascango V. E. Q., Bazhin V. Y., Martynov S. A., Pardo F. R. O. Automatic control system for thermal state of reverberatory furnaces in production of nickel alloys. Metallurgist. 2022. Vol. 66. pp. 104–116. DOI: 10.1007/S11015-022-01304-3
19. Nguyen H. H., Bazhin V. Y. Optimization of control system for electrolytic copper refining with digital twin during dendritic precipitation. Metallurg. 2023. No. 1. pp. 49–56. DOI: 10.52351/00260827_2023_01_49
20. Potocnik V., Reverdy M. History of computer control of aluminum reduction cells. Minerals, Metals and Materials Series. 2021. Vol. 6. pp. 591–599. DOI: 10.1007/978-3-030-65396-5_81/cover
21. Nozhko S. I., Grishaev I. I., Puzanov I. I., Zheleznyak Ya. M., Belotelov A. Yu. Usage of the new method of estimation of metal and electrolyte levels on aluminium electrolyzers for improving approximation of measurements. Tsvetnye Metally. 2010. No. 9. pp. 48–51.
22. Wang X., Hosler B., Tarcy G. Alcoa STARprobeTM. Essential Readings in Light Metals. 2016. Vol. 2. pp. 844–850. DOI: 10.1007/978-3-319-48156-2_126
23. Wang X., Tarcy G., Batista E., Wood G. Active pot control using alcoa STARprobeTM. Light Metals. 2011. pp. 491–496. DOI: 10.1002/9781118061992.ch87
24. Wang X. Alcoa STARprobeTM – update in further development for measuring cryolite properties. Light Metals. 2016. pp. 395–402. DOI: 10.1002/9781119274780.ch65
25. Fardeau S., Mattel A., Marcellin P., Richard P. Statistical evaluation and modeling of the link between anode effects and bath height, and implications for the ALPSYS pot control system. TMS Light Metals. 2014. pp. 845–850. DOI: 10.1007/978-3-319-48144-9_142/cover
26. Verreault J., Desgroseilliers B., Gariépy R., Simard C., Simard S. et al. Retrofit of a combined breaker feeder with a chisel bath contact detection system to reduce anode effect frequency in a potroom. Light Metals. 2011. pp. 467–470. DOI: 10.1007/978-3-319-48160-9_83
27. Nikandrov K., Zarouni A., Akhmetov S., Ahli N. Evolution of crust breaker control for DX+ and DX+ Ultra Technologies. Light Metals. 2016. pp. 511–514. DOI: 10.1002/9781119274780.ch84
28. Zhang H., Li T., Li J., Yang S., Zou Z. Progress in aluminum electrolysis control and future direction for smart aluminum electrolysis plant. JOM. 2017. Vol. 69. pp. 292–300. DOI: 10.1007/S11837-016-2150-4
29. Mulder A., Gao Y., Zhou D., Wong D. S., Ming L. et al. New generation control for daily aluminium smelter improvement generation 3 process control for potlines. Light Metals. 2014. pp. 835–840. DOI: 10.1002/9781118888438.ch140
30. Viumdal H., Mylvaganam S. Beyond the dip stick: Level measurements in aluminum electrolysis. JOM. 2010. Vol. 62. pp. 18–25. DOI: 10.1007/S11837-010-0161-0
31. Mann V., Buzunov V., Pingin V., Zherdev A., Grigoriev V. Environmental aspects of UC Rusal’s aluminum smelters sustainable development. Light Metals. 2019. pp. 553–563. DOI: 10.1007/978-3-030-05864-7_70
32. Zherdev A., Svoevskiy A., Pingin V., Shakhmatov V., Shtefanyuk Y. Environmental enhancement of potroom processes by using a machine vision system. Light Metals. 2022. pp. 979–984. DOI: 10.1007/978-3-030-92529-1_127
33. RUSAL Sustainability Report 2020. Available at: (Accessed: 6.04.2023).
34. Bazhin V., Masko O. Monitoring of the behaviour and state of nanoscale particles in a gas cleaning system of an ore-thermal furnace. Symmetry. 2022. Vol. 14. pp. 923. DOI: 10.3390/sym14050923
35. Shklyarskiy Y. E., Batueva D. E. Operation mode selection algorithm development of a wind-diesel power plant supply complex. Journal of Mining Institute. 2022. Vol. 253. pp. 115–126. DOI: 10.31897/pmi.2022.7

36. Isaeva L. A., Mikhalev Y. G., Zharinova N. Y. Dynamics of formation and properties of cryolite-aluminous crusts. Tsvetnye Metally. 2020. No. 8. pp. 56–61. DOI: 10.17580/tsm.2020.08.07
37. Non-destructive testing systems: how they help to produce products in continuous machine operation. Available at: (Accessed: 15.01.2023).
38. Gusberti V., Severo D. S., Welch B. J., Skyllas-Kazacos M. Modelling the aluminium smelting cell mass and energy balance – a tool based on the 1st law of thermodynamics.
39. 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
40. Chen L. C., Papandreou G., Kokkinos I., Murphy K., Yuille A. L. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018. Vol. 40. pp. 834–848. DOI: 10.1109/tpami.2017.2699184
41. Zakharov L., Martyushev D., Ponomareva I. N. Predicting dynamic formation pressure using artificial intelligence methods. Journal of Mining Institute. 2022. Vol. 253. pp. 23–32. DOI: 10.31897/pmi.2022.11
42. Boikov A., Payor V., Savelev R., Kolesnikov A. Synthetic data generation for steel defect detection and classification using deep learning. Symmetry. 2021. Vol. 13. DOI: 10.3390/sym13071176
43. 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
44. Pshenin V., Liagova A., Razin A., Skorobogatov A., Komarovsky M. Robot Crawler for surveying pipelines and metal structures of complex spatial configuration. Infrastructures. 2022. Vol. 7. p. 75. DOI: 10.3390/infrastructures7060075
45. Chen C., Chen Q., Xu J., Koltun V. Learning to See in the Dark. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2018. pp. 3291–3300. DOI: 10.1109/cvpr.2018.00347
46. He K., Zhang X., Ren S., Sun J. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2016. pp. 770–778. DOI: 10.1109/cvpr.2016.90
47. Zhao S., Xie Y., Yue W., Chen X. A machine learning method for state identification of superheat degree with flame interference. Minerals, Metals and Materials Series. 2019. pp. 199–208. DOI: 10.1007/978-3-030-05955-2_19
48. Toreyin B. U., Çetin A. E. Online detection of fire in video. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2007. DOI: 10.1109/cvpr.2007.383442
49. Krizhevsky A., Sutskever I., Hinton G. E. ImageNet classification with deep convol utional neural networks. Communications of the ACM. 2017. Vol. 60. pp. 84–90. DOI: 10.1145/3065386
50. Paszke A., Gross S., Massa F., Lerer A., Bradbury J. et al. An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems. 2019. Vol. 32. pp. 8024–8035.

Language of full-text russian
Full content Buy