Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
Pattern recognition for bubbly flows with vapor or gas-liquid interfaces using U-Net architecture. / Seredkin, Alexander; Plokhikh, Ivan; Mullyadzhanov, Rustam et al.
Proceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 5-8 9303175 (Proceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
}
TY - GEN
T1 - Pattern recognition for bubbly flows with vapor or gas-liquid interfaces using U-Net architecture
AU - Seredkin, Alexander
AU - Plokhikh, Ivan
AU - Mullyadzhanov, Rustam
AU - Malakhov, Ivan
AU - Serdyukov, Vladimir
AU - Surtaev, Anton
AU - Chinak, Alexander
AU - Lobanov, Pavel
AU - Tokarev, Mikhail
N1 - Funding Information: Funded by the RFBR grants No. 20-08-01093, 20-58-46008 and within the state contract with IT SB RAS Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2020/11/14
Y1 - 2020/11/14
N2 - We apply deep learning algorithms to tackle the bubble recognition task relying on the experimental video recordings of the vapor cavities growing during the water pool boiling due to the heated bottom and an isothermal multiphase flow in a channel. As a basic network architecture we use U-Net with ResNet 34 and ResNet 50 encoders depending on the complexity of the image background. Three classes have been introduced, i.e. the background, bubble and its boundary allowing to post-process some geometric characteristics in a straightforward manner. We demonstrate the capabilities by tracking the growth of an ensemble of vapor bubbles attached to the heater and studying the size distribution of bubbles in a channel.
AB - We apply deep learning algorithms to tackle the bubble recognition task relying on the experimental video recordings of the vapor cavities growing during the water pool boiling due to the heated bottom and an isothermal multiphase flow in a channel. As a basic network architecture we use U-Net with ResNet 34 and ResNet 50 encoders depending on the complexity of the image background. Three classes have been introduced, i.e. the background, bubble and its boundary allowing to post-process some geometric characteristics in a straightforward manner. We demonstrate the capabilities by tracking the growth of an ensemble of vapor bubbles attached to the heater and studying the size distribution of bubbles in a channel.
KW - bubbles
KW - image processing
KW - neural networks
UR - http://www.scopus.com/inward/record.url?scp=85099552474&partnerID=8YFLogxK
U2 - 10.1109/S.A.I.ence50533.2020.9303175
DO - 10.1109/S.A.I.ence50533.2020.9303175
M3 - Conference contribution
AN - SCOPUS:85099552474
T3 - Proceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
SP - 5
EP - 8
BT - Proceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
Y2 - 14 November 2020 through 15 November 2020
ER -
ID: 27590117