Izvestiya vuzov. Yadernaya Energetika

The peer-reviewed scientific and technology journal. ISSN: 0204-3327

Methodology for Determining Parameters of a Two-Phase Medium Using Computer Vision Tools

9/17/2026 2026 - #03 Thermal physics and thermal hydraulics

Pavliukovski N.V. Tolokonski A.O. Kutsenko K.V. Maslov Yu.A. Savelev A.A.

DOI: https://doi.org/10.26583/npe.2026.3.08

UDC: 536.24: 004.89

Detection systems for two-phase flows are attracting increasing attention in the field of thermal physics and nuclear engineering. However, existing tools for identifying flow regime parameters often cannot be applied in practice due to the wide variety of flow structures, inherent complexity and high cost, as well as their invasive nature, which disturbs the flow under study. The primary goal of this work is to develop a straightforward, non-invasive system for determining the characteristics of a coolant two-phase flow utilizing computer vision methods. Data acquired by the parameter acquisition system, specifically the video stream, enabled the implementation of an algorithm for steam bubble detection based on a convolutional neural network (CNN). The developed system allows for the determination of key two-phase flow parameters, including the void fraction, steam bubble sizes, and their size distribution. An accuracy assessment of the detected bubble size classes was conducted, demonstrating a measurement error of less than 10%. The diagnostic system is fully integrated with a software and hardware complex for automated real-time data acquisition and parameter monitoring. The experimental data obtained using the created system are consistent with theoretical calculations, thereby validating the employed methods. For future work, it is proposed to investigate correlations between the identified two-phase flow parameters and the spectrum of wall superheat temperature fluctuations. This research direction aims to enhance the understanding of heat transfer mechanisms and could contribute to the development of advanced monitoring and predictive maintenance tools for thermal-hydraulic systems.

References

  1. Wongsaroj W., Hamdani A., Thong-un N., Takahashi H., Kikura H. Ultrasonic measurement of velocity profile on bubbly flow using fast Fourier transform (FFT) technique. IOP Conference Series: Materials Science and Engineering. 2017;249(1):012011. DOI: https://doi.org/10.1088/1757-899x/249/1/012011
  2. Cui X., He Y., Li M., Cao W., Gao Z. Complex network-based framework for flow pattern identification in vertical upward oil–water two-phase flow. Physica A: Statistical Mechanics and its Applications. 2025;662:130351. DOI: https://doi.org/10.1016/j.physa.2025.130351
  3. Zhang K.P., Ku H.C., He X.G., Lu H.L., Zhang M., Guo C.B. Measurement of gas and liquid flow rates in two-phase pipe flows with distributed acoustic sensing. Measurement. 2025;250:117137. DOI: https://doi.org/10.1016/j.measurement.2025.117137
  4. Jha D.K., Ray A., Mukherjee K., Chakraborty S. Classification of two-phase flow patterns by ultrasonic sensing. Journal of Dynamic Systems, Measurement and Control. 2013;135(2):024503. DOI: https://doi.org/10.1115/1.4007555
  5. Poelma C. Measurement in opaque flows: a review of measurement techniques for dispersed multiphase flows. Acta Mechanica. 2020;231(6):2089–2111. DOI: https://doi.org/10.1007/s00707-020-02683-x
  6. Di Nunno F., Alves Pereira F., de Marinis G., Di Felice F., Gargano R., Miozzi M., Granata F. Deformation of air bubbles near a plunging jet using a machine learning approach. Applied Sciences. 2020;10(11):3879. DOI: https://doi.org/10.3390/app10113879
  7. Condriuc I., Kipping R., Maestri R., Kryk H., Schleicher E., Hampel U. Gas flow rate measurement in two-phase flows using an optical channel body flow sensor. Design and validation of the single-channel prototype. Flow Measurement and Instrumentation. 2025;104:102901. DOI: https://doi.org/10.1016/j.flowmeasinst.2025.102901
  8. Shi Y., Sun Y., Wang M., Zhang S., Yang Z. Flow pattern recognition for horizontal gas-liquid two-phase flow with a hybrid deep-learning model. Flow Measurement and Instrumentation. 2025;102:102829. DOI: https://doi.org/10.1016/j.flowmeasinst.2025.102829
  9. Suh Y., Bostanabad R., Won Y. Deep learning predicts boiling heat transfer. Scientific reports. 2021;11(1):5622. DOI: https://doi.org/10.1038/s41598-021-85150-4
  10. Paz C., Cabarcos A., Concheiro M., Conde-Fontenla M. Classification of boiling regimes, fluids, and heating surfaces through deep learning algorithms and image analysis. International Journal of Heat and Mass Transfer. 2025;242:126829. DOI: https://doi.org/10.1016/j.ijheatmasstransfer.2025.126829
  11. Lauar Sufian, Delov M.I., Litvintsova Yu.E., Kuzmenkov D.M., Muradyan K.Yu., Navasardyan M.V., Kutsenko K.V. A thermohydraulic flow loop for developing novel solutions in the field of using digital twins for nuclear power facilities. Izvestiya vuzov. Yadernaya Energetika. 2020;2:122–134. DOI: https://doi.org/10.26583/npe.2020.2.11 (in Russian).
  12. Lykov A.V. Theory of Heat Conduction. Moscow, Vysshaya Shkola Publ., 1967, 599 p. URL: https://djvu.online/file/xgw6k0PwkBfEk (accessed 02.11.2025) (in Russian).
  13. Liu W., Wang Z., Liu X., Zeng N., Liu Y., Alsaadi F.E. A survey of deep neural network architectures and their applications. Neurocomputing. 2017;234:11–26. DOI: https://doi.org/10.1016/j.neucom.2016.12.038
  14. Ultralytics Home. Ultralytics YOLO Docs. URL: https://docs.ultralytics.com/ (accessed 02.11.2025).
  15. Jiang P., Ergu D., Liu F., Cai Y., Ma B. A Review of Yolo algorithm developments. Procedia computer science. 2022;199:1066–1073. DOI: https://doi.org/10.1016/j.procs.2022.01.135
  16. Srivastava S., Divekar A.V., Anilkumar C., Naik I., Kulkarni V., Pattabiraman V. Comparative analysis of deep learning image detection algorithms. Journal of Big data. 2021;8(1):66. DOI: https://doi.org/10.1186/s40537-021-00434-w
  17. Lazakovich N.V., Stashulenok S.P., Yablonskii O.L. Kurs teorii veroyatnostei. Minsk, Elektronnaya kniga BGU, 2003. URL: https://dl.libcats.org/genesis/32000/548250e754e0e74d6f4331c38c592829/_as/[Lazakovich_N.V.,_Stashulenok_S.P.,_YAblonsky_O.L.(libcats.org).pdf (accessed 02.11.2025) (in Russian).
  18. Balakin B.V., Delov M.I., Kosinska A., Kutsenko K.V., Lavrukhin A.A. Heat transfer during transition to nucleate boiling. International Journal of Heat and Mass Transfer. 2015;91:1101–1105. DOI: https://doi.org/10.1016/j.ijheatmasstransfer.2015.08.026
  19. Labuncov D.A., Yagov V.V. Mechanics of two-phase systems. Moscow, MEI Publ., 2016, 384 p. ISBN 978-5-383-00964-2. URL: https://techlibrary.ru/b2/2t1a1b1u1o1x1p1c_2l.2h.,_3n1d1p1c_2j.2j._2u1f1w1a1o1j1l1a_1e1c1u1w1v1a1i1o2c1w_1s1j1s1t1f1n._2016.pdf (accessed 02.11.2025) (in Russian).
  20. Nesis E.I. On the mechanism of bubble detachment from a non-wettable horizontal plane. Dokl. Academy of Sciences. Russian Academy of Sciences. 1965,165(4):871–873. URL: https://www.mathnet.ru/links/8142f906003ca3f43bcd9e4bf455814e/dan31905.pdf (accessed 02.11.2025) (in Russian).
  21. Islamova A.G., Feoktistov D.V., Orlova E.G. Influence of the copper and steel surfaces’ roughness on surface energy and wettability. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy. 2021;7(1(25)):60–78. DOI: https://doi.org/10.21684/2411-7978-2021-7-1-60-78 (in Russian).
  22. Zuber N. The dynamics of vapor bubbles in nonuniform temperature fields. International Journal of Heat and Mass Transfer. 1961;2(1–2):83–98. DOI: https://doi.org/10.1016/0017-9310(61)90016-3

two-phase flow void fraction boiling computer vision two-phase medium parameters

Link for citing the article: Pavliukovski N.V., Tolokonski A.O., Kutsenko K.V., Maslov Yu.A., Savelev A.A. Methodology for Determining Parameters of a Two-Phase Medium Using Computer Vision Tools. Izvestiya vuzov. Yadernaya Energetika. 2026, no. 3, pp. 111-122; DOI: https://doi.org/10.26583/npe.2026.3.08 (in Russian).

Open PDF file