TY - JOUR

T1 - Bubble patterns recognition using neural networks: Application to the analysis of a two-phase bubbly jet

AU - Poletaev, Igor

AU - Tokarev, Mikhail P.

AU - Pervunin, Konstantin S.

N1 - Publisher Copyright: © 2019 Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/5

Y1 - 2020/5

N2 - Gas-liquid two-phase bubbly flows are found in different areas of science and technology such as nuclear energy, chemical industry, or piping systems. Optical diagnostics of two-phase bubbly flows with modern panoramic techniques makes it possible to capture simultaneously instantaneous characteristics of both continuous and dispersed phases with a high spatial resolution. In this paper, we introduce a novel approach based on neural networks to recognize bubble patterns in images and identify their geometric parameters. The originality of the proposed method consists in training of a neural network ensemble using synthetic images that resemble real photographs gathered in experiment. The use of neural networks in combination with automatically generated data allowed us to detect overlapping, blurred, and non-spherical bubbles in a broad range of volume gas fractions. Experiments on a turbulent bubbly jet proved that the implemented method increases the identification accuracy, reducing errors of various kinds, and lowers the processing time compared to conventional recognition methods. Furthermore, utilizing the new method of bubbles recognition, the primary physical parameters of a dispersed phase, such as bubble size distribution and local gas content, were calculated in a near-to-nozzle region of the bubbly jet. The obtained results and integral experimental parameters, especially volume gas fraction, are in good agreement with each other.

AB - Gas-liquid two-phase bubbly flows are found in different areas of science and technology such as nuclear energy, chemical industry, or piping systems. Optical diagnostics of two-phase bubbly flows with modern panoramic techniques makes it possible to capture simultaneously instantaneous characteristics of both continuous and dispersed phases with a high spatial resolution. In this paper, we introduce a novel approach based on neural networks to recognize bubble patterns in images and identify their geometric parameters. The originality of the proposed method consists in training of a neural network ensemble using synthetic images that resemble real photographs gathered in experiment. The use of neural networks in combination with automatically generated data allowed us to detect overlapping, blurred, and non-spherical bubbles in a broad range of volume gas fractions. Experiments on a turbulent bubbly jet proved that the implemented method increases the identification accuracy, reducing errors of various kinds, and lowers the processing time compared to conventional recognition methods. Furthermore, utilizing the new method of bubbles recognition, the primary physical parameters of a dispersed phase, such as bubble size distribution and local gas content, were calculated in a near-to-nozzle region of the bubbly jet. The obtained results and integral experimental parameters, especially volume gas fraction, are in good agreement with each other.

KW - Bubbles recognition

KW - Computer vision

KW - Machine learning

KW - Neural networks

KW - Planar Fluorescence for Bubbles Imaging (PFBI)

KW - Two-phase bubbly jet

KW - ALGORITHM

KW - SIZE DISTRIBUTION

KW - FLOW

UR - http://www.scopus.com/inward/record.url?scp=85079560188&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/a9210c13-f5e5-3883-8e7c-2ba4a0a8ff66/

U2 - 10.1016/j.ijmultiphaseflow.2019.103194

DO - 10.1016/j.ijmultiphaseflow.2019.103194

M3 - Article

AN - SCOPUS:85079560188

VL - 126

JO - International Journal of Multiphase Flow

JF - International Journal of Multiphase Flow

SN - 0301-9322

M1 - 103194

ER -