TY - JOUR

T1 - Deep learning segmentation to analyze bubble dynamics and heat transfer during boiling at various pressures

AU - Malakhov, Ivan

AU - Seredkin, Aleksandr

AU - Chernyavskiy, Andrey

AU - Serdyukov, Vladimir

AU - Mullyadzanov, Rustam

AU - Surtaev, Anton

N1 - The work was supported by the Russian Science Foundation (Grant No. 22-19-00581 ). The training procedure, performance evaluation and code development for U-Net was supported by the grant for the implementation of the strategic academic leadership program “Priority 2030” in Novosibirsk State University. The boiling experiments were carried out within the framework of the state assignment of the IT SB RAS (No. 121031800216-1).

PY - 2023/5

Y1 - 2023/5

N2 - Today, neural networks have increasingly gained the attention of researchers and become an effective instrument for a wide range of scientific applications, including issues related to the boiling. However, there are no universal tools in the literature that would allow detecting the life cycle of individual vapor bubbles and automatically measure a wide range of main boiling characteristics based on the high-speed visualization data. In this study, the U-net and Mask R-CNN convolutional neural networks were used to detect and segment bubbles obtained by visualization from the bottom side of a transparent heater during water boiling at various subatmospheric pressures. The key feature of the trained CNN architectures is the ability to detect bubbles located on a heated wall, while ignoring the bubbles that lift-off, and to determine the moment of their departure. The verification of various neural networks demonstrated that the Mask R-CNN architecture is more preferable to measure dynamic boiling characteristics. Through trained convolutional neural networks, a wide array of data on local boiling characteristics, including the nucleation site density, bubbles growth rate, life-time and departure diameters, waiting time between moments of bubbles departure and nucleation frequencies were automatically obtained for water boiling at various heat fluxes and pressures in the range of 42–103 kPa. Based on the parameters obtained, heat transfer simulation was carried out using various heat flux partitioning approaches and the ranges of their applicability were demonstrated.

AB - Today, neural networks have increasingly gained the attention of researchers and become an effective instrument for a wide range of scientific applications, including issues related to the boiling. However, there are no universal tools in the literature that would allow detecting the life cycle of individual vapor bubbles and automatically measure a wide range of main boiling characteristics based on the high-speed visualization data. In this study, the U-net and Mask R-CNN convolutional neural networks were used to detect and segment bubbles obtained by visualization from the bottom side of a transparent heater during water boiling at various subatmospheric pressures. The key feature of the trained CNN architectures is the ability to detect bubbles located on a heated wall, while ignoring the bubbles that lift-off, and to determine the moment of their departure. The verification of various neural networks demonstrated that the Mask R-CNN architecture is more preferable to measure dynamic boiling characteristics. Through trained convolutional neural networks, a wide array of data on local boiling characteristics, including the nucleation site density, bubbles growth rate, life-time and departure diameters, waiting time between moments of bubbles departure and nucleation frequencies were automatically obtained for water boiling at various heat fluxes and pressures in the range of 42–103 kPa. Based on the parameters obtained, heat transfer simulation was carried out using various heat flux partitioning approaches and the ranges of their applicability were demonstrated.

KW - Boiling

KW - Bubble dynamics

KW - Heat transfer

KW - Neural networks

KW - Optical diagnostics

KW - Subatmospheric pressures

UR - https://www.scopus.com/inward/record.url?eid=2-s2.0-85147592262&partnerID=40&md5=856ebaae636dc8c606b796e1d037ccf9

UR - https://www.mendeley.com/catalogue/21536139-61a0-34ff-8462-ee66f199e230/

U2 - 10.1016/j.ijmultiphaseflow.2023.104402

DO - 10.1016/j.ijmultiphaseflow.2023.104402

M3 - Article

VL - 162

JO - International Journal of Multiphase Flow

JF - International Journal of Multiphase Flow

SN - 0301-9322

M1 - 104402

ER -