Pattern recognition for bubbly flows with vapor or gas-liquid interfaces using U-Net architecture

Alexander Seredkin, Ivan Plokhikh, Rustam Mullyadzhanov, Ivan Malakhov, Vladimir Serdyukov, Anton Surtaev, Alexander Chinak, Pavel Lobanov, Mikhail Tokarev

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5-8
Number of pages4
ISBN (Electronic)9780738131115
DOIs
Publication statusPublished - 14 Nov 2020
Event2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020 - Virtual, Novosibirsk, Russian Federation
Duration: 14 Nov 202015 Nov 2020

Publication series

NameProceedings - 2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020

Conference

Conference2020 Science and Artificial Intelligence Conference, S.A.I.ence 2020
CountryRussian Federation
CityVirtual, Novosibirsk
Period14.11.202015.11.2020

Keywords

  • bubbles
  • image processing
  • neural networks

Fingerprint

Dive into the research topics of 'Pattern recognition for bubbly flows with vapor or gas-liquid interfaces using U-Net architecture'. Together they form a unique fingerprint.

Cite this