Recognition of gas-liquid two-phase flow patterns based on improved local binary pattern operator

Wenyin Zhang, Frank Y. Shih, Ningde Jin, Yinfeng Liu

Research output: Contribution to journalArticlepeer-review

16 Scopus citations

Abstract

A new method to pattern recognition of gas-liquid two-phase flow regimes based on improved local binary pattern (LBP) operator is proposed in this paper. Five statistic features are computed using the texture pattern matrix obtained from the improved LBP. The support vector machine and back-propagation neural network are trained to flow pattern recognition of five typical gas-liquid flow regimes. Experimental results demonstrate that the proposed method has achieved better recognition accuracy rates than others. It can provide reliable reference for other indirect measurement used to analyze flow patterns by its physical objectivity.

Original languageEnglish (US)
Pages (from-to)793-797
Number of pages5
JournalInternational Journal of Multiphase Flow
Volume36
Issue number10
DOIs
StatePublished - 2010

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering
  • Physics and Astronomy(all)
  • Fluid Flow and Transfer Processes

Keywords

  • Local binary pattern
  • Neural network
  • Support vector machine
  • Two-phase flow regime

Fingerprint Dive into the research topics of 'Recognition of gas-liquid two-phase flow patterns based on improved local binary pattern operator'. Together they form a unique fingerprint.

Cite this