Skip to main content

Advertisement

SpringerLink
Log in

Automatic System for Detecting Visible Emissions in a Potroom of Aluminum Plant Based on Technical Vision and a Neural Network

  • Published:
Metallurgist Aims and scope

Electrolysis of a cryolite-alumina melt is accompanied by emission of harmful pollutants into the atmosphere: hydrogen fluorides, perfluorocarbons, fluorine (gaseous and solid), tarry matters, benzopyrene. Workers of the potroom receive the highest dose of harmful emissions, which leads to a multiple risk of developing serious occupational diseases, including lung cancer. For these reasons, ensuring the environmental safety of production is an important and relevant task, which also corresponds to the goals of sustainable development of the aluminium production industry.

The appearance of smoke in the potroom signals a malfunction of the gas treatment system, depressurization of aluminum reduction cell, disruptions of the anode carbon or occurrence of the anode effect. Such situations require immediate actions of the staff. The objective of the research is to improve the monitoring quality and reduce the emissions of pollutants into the environment, which are generated as a result of the cryolite-alumina melt electrolysis. To improve the emissions detection rate, an automatic system for monitoring the visible emissions of pollutants in the atmosphere of the potroom has been developed. The development is a vision system based on a convolutional neural network. The neural network was trained using the TensorFlow machine learning software and a dataset of labeled photographs of the model of the aluminum reduction cell with different smoke variations. The results of neural network testing show that the overall accuracy of the trained model was 94.75%. It proves that the model can be used to detect smoke and visible emissions of pollutants. The developed automatic monitoring system allows increasing the detection rate of an emergency situation by 2 times compared to traditional systems based on gas sensors, reducing the time for aluminium reduction cells depressurization and, consequently, reducing emissions of pollutants into the environment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.
Fig. 10.
Fig. 11.

Similar content being viewed by others

References

  1. V. Mann, V. Buzunov, V. Pingin, et al., “Environmental aspects of UC RUSAL’s aluminum smelters sustainable development,” in: Light Metals, Springer, Cham (2019).

  2. RUSAL Sustainability Report 2020 (2020); https://rusal.ru/sustainability/report/.

  3. Yu. A. Sychev, M. E. Aladin, and V. A. Serikov, “Developing a hybrid filter structure and a control algorithm for hybrid power supply,” Int. J. Power Elec. Dr., 13, No. 3, 1625–1634 (2022).

    Google Scholar 

  4. Byuro NDT, Best Available Techniques (BAT) Reference Document for the Non-Ferrous Metals Industries. Aluminum Production in Russian Federation [in Russian]; http://burondt.ru/NDT/NDTDocsDetail.php?UrlId=616&etkstructure_id=1872&UrlLang=ru (2019).

  5. Program for Improving the Environmental Efficiency of the Branch Office RUSAL Bratsk PJSC in Shelekhov (2019).

  6. T. A. Tarabarinova and E. I. Golovina, “Capitalization of mineral resources as an innovation ecological strategy,” Geol. Miner. Res. Sib., 4, 86–96 (2021).

    Google Scholar 

  7. R. Y. Feshchenko, E. A. Feschenko, R. N. Eremin, et al., “Analysis of the anode paste charge composition,” Metallurgist, 64, No. 7, 615–622 (2020).

    Article  CAS  Google Scholar 

  8. F. Y. Sharikov, Y. V. Sharikov, and K. A. Krylov, “Selection of key parameters for green coke calcination in a tubular rotary kiln to produce anode petcoke,” ARPN J. Eng. Appl. Sci., 15, 2904–2912 (2020).

    CAS  Google Scholar 

  9. Y. V. Sharikov and V. E. Quiroz Cabascango, “Mathematical modeling of mass, heat and fluid flow in a reverberatory furnace for melting nickel-containing raw materials,” J. Phys. Conf. Ser., 1753, No. 1, 012064 (2021).

  10. E. S. Gorlanov, R. Kawalla, and A. A. Polyakov, “Electrolytic production of aluminum. Review. Part 2. Development prospects,” Tsvetn. Metall., No. 10, 42–49 (2020).

  11. A. Zherdev, A. Svoevskiy, V. Pingin, et al., “Environmental enhancement of potroom processes by using a machine vision system,” in: Light Metals, Springer, Cham (2022).

  12. S. A. Martynov, O. N. Masko, and S. N. Fedorov, “Innovative ore-thermal furnace control systems,” Tsvetn. Metall., No. 4, 87–94 (2022).

  13. V. E. Q. Cabascango, V. Y. Bazhin, S. A. Martynov, and F. R. O. Pardo, “Automatic control system for thermal state of reverberatory furnaces in production of nickel alloys,” Metallurgist, 66, No. 1, 104–116 (2022).

    Article  Google Scholar 

  14. V. Bazhin and O. Masko, “Monitoring of the behavior and state of nanoscale particles in a gas cleaning system of an ore-thermal furnace,” Symmetry, 14, No. 5, 923–936 (2022).

    Article  CAS  Google Scholar 

  15. D. A. Kashin and A. A. Kulchitskiy, “Image-based quality monitoring of metallurgical briquettes,” Tsvetn. Metall., No. 9, 92–98 (2022).

  16. A. A. Kul’chitskii and D. A. Kashin, “The choice of a method for non-contact assessment of the composition of briquetted charge materials,” J. Phys. Conf. Ser., 1399, No. 4, 044108 (2019).

  17. V. I. Bolobov, S. A. Chupin, V. S. Bochkov, et al., “The effect of finely divided martensite of austenitic high manganese steel on the wear resistance of the excavator buckets teeth,” Key Eng. Mat., 854, 3–9 (2020).

    Article  Google Scholar 

  18. V. Y. Bazhin, A. A. Kulchitskiy, and D. N. Kadrov, “Complex control of the state of steel pins in soderberg electrolytic cells by using computer vision systems,” Tsvetn. Metall., No. 3, 27–32 (2018).

  19. N. V. Vasilyeva, A. V. Boikov, O. O. Erokhina, and A. Y. Trifonov, “Automated digitization of radial charts,” J. Min. Inst., 247, 82–87 (2021).

    Article  Google Scholar 

  20. L. C. Chen, G. Papandreou, I. Kokkinos, et al., “DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs,” IEEE T. Pattern Anal., 40, No. 4, 834–848 (2018).

    Article  Google Scholar 

  21. A. Boikov, V. Payor, R. Savelev, and A. Kolesnikov, “Synthetic data generation for steel defect detection and classification using deep learning,” Symmetry, 13, No. 7, 1176–1186 (2021).

    Article  CAS  Google Scholar 

  22. C. Chen, Q. Chen, J. Xu, and V. Koltun, “Learning to see in the dark,” Proc. CVPR IEEE, 3291–3300 (2018).

  23. D. R. Yakupov, P. V. Ivanova, and S. L. Ivanov, “Physical simulation of load displacement resistance of peat land surface on test bench,” Min. Inform. Anal. B., No. 5-1, 117–129 (2021).

  24. D. R. Iakupov, P. V. Ivanova, and S. L. Ivanov, “Estimate of parameters of retreat cutting equipment components for peatlands,” Min. Inform. Anal. B., No. 10, 88–103 (2022).

  25. A. V. Bolshunov, D. A. Vasilev, S. A. Ignatiev, et al., “Mechanical drilling of glaciers with bottom-hole scavenging with compressed air,” Ice Snow, 62, No. 1, 35–46 (2022).

    Google Scholar 

  26. L. Q. Phuc, P. N. Dmitriev, T. V. Duy, and L. Yunpeng, “Influence of the main roof on the parameters of the abutment pressure zone in the selvedge of the seam,” Min. Inform. Anal. B., No. 6-1, 68–82 (2022).

  27. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. CVPR IEEE, 770–778 (2016).

  28. S. A. Lavrenko and D. I. Shishlyannikov, “Performance evaluation of heading-and-winning machines in the conditions of potash mines,” Appl. Sci., 11, No. 8, 3444–3454 (2021).

    Article  CAS  Google Scholar 

  29. S. Zhao, Y. Xie, W. Yue, and X. Chen, “A machine learning method for state identification of superheat degree with flame interference,” in: 10th International Symposium on High-Temperature Metallurgical Processing, Springer, Cham (2019).

  30. B. U. Toreyin and A. E. Cetin, “Online detection of fire in video,” Proc. CVPR IEEE, 1–5 (2007).

  31. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, 60, No. 6, 84–90 (2017).

    Article  Google Scholar 

  32. A. Paszke, S. Gross, F. Massa, et al., “PyTorch: An imperative style, high-performance deep learning library,” Adv. Neur. In., 32, 8024–8035 (2019).

    Google Scholar 

  33. NVIDIA Developer, Jetson Benchmarks; https://developer.nvidia.com/embedded/jetson-benchmarks (2022).

  34. N. Vasilyeva, E. Fedorova, and A. Kolesnikov, “Big data as a tool for building a predictive model of mill roll wear,” Symmetry, 13, No. 5, 859–869 (2021).

    Article  CAS  Google Scholar 

  35. I. Beloglazov and K. Krylov, “An interval-simplex approach to determine technological parameters from experimental data,” Mathematics, 10, No. 16, 2959 (2022).

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. St. Petersburg Mining University, St. Petersburg, Russia

    A. K. Shestakov, P. A. Petrov & M. Yu. Nikolaev

Authors
  1. A. K. Shestakov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. P. A. Petrov
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. Yu. Nikolaev
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. K. Shestakov.

Additional information

Translated from Metallurg, Vol. 66, No. 10, pp. 105–112, October, 2022. Russian https://doi.org/10.52351/00260827_2022_10_105.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shestakov, A.K., Petrov, P.A. & Nikolaev, M.Y. Automatic System for Detecting Visible Emissions in a Potroom of Aluminum Plant Based on Technical Vision and a Neural Network. Metallurgist 66, 1308–1319 (2023). https://doi.org/10.1007/s11015-023-01445-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11015-023-01445-z

Keywords

Search

Navigation