Deep learning segmentation to analyze bubble dynamics and heat transfer during boiling at various pressures. (May 2023)

• Record Type: Journal Article
• Authors: Malakhov, Ivan; Seredkin, Aleksandr; Chernyavskiy, Andrey; Serdyukov, Vladimir; Mullyadzanov, Rustam; Surtaev, Anton
• Is Part Of: International journal of multiphase flow. Volume 162(2023)
• Publication Date: 2023-05
• Subjects: Boiling -- Bubble dynamics -- Heat transfer -- Subatmospheric pressures -- Optical diagnostics -- Neural networks; CFD computational fluid dynamics -- CNN convolutional neural network -- CHF critical heat flux -- HSV high speed visualization -- MLP multilayer perceptron -- NSD nucleation site density (1/m2) -- IR infrared -- DC direct current -- ITO indium tin oxide; Multiphase flow -- Periodicals; Écoulement polyphasique -- Périodiques; Multiphase flow; Periodicals; 620.1064
• DOI: 10.1016/j.ijmultiphaseflow.2023.104402
• Languages: English
• ISSNs: 0301-9322

Abstract

Highlights: U-net and Mask R-CNN were used to detect and segment bubbles at boiling on transparent heater. General local boiling characteristics on heat flux were determined in pressure range 40–102 kPa. The applicability of various heat flux partitioning approaches for boiling heat transfer simulation was demonstrated. Abstract: 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.