PSO-SVM model for gas/liquid two-phase flow regime recognition

Author

Dong, Feng ; Fu, Chun

Author_Institution

Sch. of Electr. Eng. & Autom., Tianjin Univ., Tianjin, China

fYear

2011

fDate

15-17 April 2011

Firstpage

4350

Lastpage

4353

Abstract

The correct identification of two-phase flow regime is the basis for the accurate measurement of other flow parameters in two-phase flow measurement. A PSO-SVM(Particle Swarm Optimization and Support Vector Machine) model, which can overcome selecting parameters needed in SVM model, was developed to identify the flow regime. The application of PSO SVM improves the accuracy of flow regime recognition for gas/liquid two-phase flow. The results show that the PSO-SVM model, which can identify the flow regime correctly, is an effective approach.

Keywords

flow measurement; particle swarm optimisation; support vector machines; two-phase flow; PSO-SVM model; flow parameter measurement; gas liquid two phase flow regime recognition; particle swarm optimization; support vector machine; two phase flow measurement; two phase flow regime identification; Artificial neural networks; Fluid flow; Forecasting; Genetic algorithms; Particle swarm optimization; Rocks; Support vector machines; accuracy; flow regime recognition; gas/liquid two-phase flow; particle swarm optimization; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Electric Information and Control Engineering (ICEICE), 2011 International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-8036-4

Type

conf

DOI

10.1109/ICEICE.2011.5777428

Filename

5777428