Skip to main navigation Skip to search Skip to main content

Wet gas metering using a venturi-meter and neural networks

  • Lijun Xu*
  • , Hui Li
  • , Shaliang Tang
  • , Cheng Tan
  • , Bo Hu
  • *Corresponding author for this work
  • Beihang University
  • Fudan University

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

Abstract

In this paper, a novel approach is presented to the measurement of wet gas flows using a venturi meter and neural network technique. Results obtained on a laboratory test rig suggest that the flowrate of wet gas flowing in a throat-extended Venturi meter is related to the characteristic features of the differential pressures across the converging section and the extended throat section, the static pressure and temperature signals within the Venturi-meter. The relation between the signal features and gas/liquid flowrates of wet gas is established through the use of back-propagation (BP) neural networks. The experimental test carried out within static pressure range of 0. 3-0.8MPa, gas flowrate range of 50-160 m3/d and oil flowrate range of 1.1-5.3 m3/h suggested that it is a simple and viable method to solve the problem of wet gas metering by combining a revised Venturi meter and neural networks techniques.

Original languageEnglish
Title of host publication2008 IEEE International Instrumentation and Measurement Technology Conference Proceedings, I2MTC
Pages761-764
Number of pages4
DOIs
StatePublished - 2008
Event2008 IEEE International Instrumentation and Measurement Technology Conference, I2MTC - Victoria, BC, Canada
Duration: 12 May 200815 May 2008

Publication series

NameConference Record - IEEE Instrumentation and Measurement Technology Conference
ISSN (Print)1091-5281

Conference

Conference2008 IEEE International Instrumentation and Measurement Technology Conference, I2MTC
Country/TerritoryCanada
CityVictoria, BC
Period12/05/0815/05/08

Keywords

  • Gas/liquid two-phase flow
  • Neural networks
  • Venturi meters
  • Wet gas metering

Fingerprint

Dive into the research topics of 'Wet gas metering using a venturi-meter and neural networks'. Together they form a unique fingerprint.

Cite this