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

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

doi:10.1016/j.ijmultiphaseflow.2010.06.002

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

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

Computer Science

Research output: Contribution to journal › Article › peer-review

20 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 language	English (US)
Pages (from-to)	793-797
Number of pages	5
Journal	International Journal of Multiphase Flow
Volume	36
Issue number	10
DOIs	https://doi.org/10.1016/j.ijmultiphaseflow.2010.06.002
State	Published - 2010

All Science Journal Classification (ASJC) codes

Mechanical Engineering
General Physics and Astronomy
Fluid Flow and Transfer Processes

Keywords

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

Access to Document

10.1016/j.ijmultiphaseflow.2010.06.002

Cite this

@article{0942de225096438abcb2272b4755e1d0,

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

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.",

keywords = "Local binary pattern, Neural network, Support vector machine, Two-phase flow regime",

author = "Wenyin Zhang and Shih, {Frank Y.} and Ningde Jin and Yinfeng Liu",

note = "Funding Information: This paper is supported by National Natural Science Foundation of China (ID: 50674070) and Post-Doctor Foundation of Ministry of Education of China (ID: 20070410757).",

year = "2010",

doi = "10.1016/j.ijmultiphaseflow.2010.06.002",

language = "English (US)",

volume = "36",

pages = "793--797",

journal = "International Journal of Multiphase Flow",

issn = "0301-9322",

publisher = "Elsevier B.V.",

number = "10",

}

TY - JOUR

T1 - Recognition of gas-liquid two-phase flow patterns based on improved local binary pattern operator

AU - Zhang, Wenyin

AU - Shih, Frank Y.

AU - Jin, Ningde

AU - Liu, Yinfeng

N1 - Funding Information: This paper is supported by National Natural Science Foundation of China (ID: 50674070) and Post-Doctor Foundation of Ministry of Education of China (ID: 20070410757).

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

KW - Local binary pattern

KW - Neural network

KW - Support vector machine

KW - Two-phase flow regime

UR - http://www.scopus.com/inward/record.url?scp=77955513895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955513895&partnerID=8YFLogxK

U2 - 10.1016/j.ijmultiphaseflow.2010.06.002

DO - 10.1016/j.ijmultiphaseflow.2010.06.002

M3 - Article

AN - SCOPUS:77955513895

SN - 0301-9322

VL - 36

SP - 793

EP - 797

JO - International Journal of Multiphase Flow

JF - International Journal of Multiphase Flow

IS - 10

ER -

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

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this