A neural network algorithm for density measurement of multiphase flow

Nabeel Al-Rawahi, Mahmoud Meribout, Ahmed Al-Naamany, Ali Al-Bimani, Adel Meribout

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Measurement of the density of multiphase flow is crucial in multiphase flow meters. While radioactive-based measuring methods are known to give good results, end users prefer nonradioactive devices for obvious reasons. This paper shows the capability of an online neural network algorithm, that uses the differential pressure along a vertical pipe and across a venturi meter, in predicting the average density of the multiphase flow. A multiphase flow loop was constructed to conduct the training and evaluating experiments needed for the algorithm. Experimental results performed on the multiphase flow loop demonstrate that the density measurement can be achieved with good accuracy for liquid and gas velocities for up to 4 and 25 m/s (at 30°C and 7 bars), respectively, while covering different complex flow regimes including annular flow, slug flow, and dispersed flow. The neural network algorithm that was developed for this purpose gave very good results in measuring the flow density.

Original languageEnglish
Pages (from-to)89-103
Number of pages15
JournalMultiphase Science and Technology
Volume24
Issue number2
DOIs
Publication statusPublished - 2012

Fingerprint

multiphase flow
Multiphase Flow
Multiphase flow
Network Algorithms
Neural Networks
Neural networks
annular flow
differential pressure
coverings
education
Covering
Vertical
Pipe
Liquid
Liquids
Experimental Results
liquids
Gases
gases
Demonstrate

Keywords

  • Density measurement
  • Multiphase flow loop
  • Neural network algorithm

ASJC Scopus subject areas

  • Modelling and Simulation
  • Condensed Matter Physics
  • Engineering(all)

Cite this

A neural network algorithm for density measurement of multiphase flow. / Al-Rawahi, Nabeel; Meribout, Mahmoud; Al-Naamany, Ahmed; Al-Bimani, Ali; Meribout, Adel.

In: Multiphase Science and Technology, Vol. 24, No. 2, 2012, p. 89-103.

Research output: Contribution to journalArticle

Al-Rawahi, Nabeel ; Meribout, Mahmoud ; Al-Naamany, Ahmed ; Al-Bimani, Ali ; Meribout, Adel. / A neural network algorithm for density measurement of multiphase flow. In: Multiphase Science and Technology. 2012 ; Vol. 24, No. 2. pp. 89-103.
@article{d7e0168ceab6491ab258697bc7ddb6da,
title = "A neural network algorithm for density measurement of multiphase flow",
abstract = "Measurement of the density of multiphase flow is crucial in multiphase flow meters. While radioactive-based measuring methods are known to give good results, end users prefer nonradioactive devices for obvious reasons. This paper shows the capability of an online neural network algorithm, that uses the differential pressure along a vertical pipe and across a venturi meter, in predicting the average density of the multiphase flow. A multiphase flow loop was constructed to conduct the training and evaluating experiments needed for the algorithm. Experimental results performed on the multiphase flow loop demonstrate that the density measurement can be achieved with good accuracy for liquid and gas velocities for up to 4 and 25 m/s (at 30°C and 7 bars), respectively, while covering different complex flow regimes including annular flow, slug flow, and dispersed flow. The neural network algorithm that was developed for this purpose gave very good results in measuring the flow density.",
keywords = "Density measurement, Multiphase flow loop, Neural network algorithm",
author = "Nabeel Al-Rawahi and Mahmoud Meribout and Ahmed Al-Naamany and Ali Al-Bimani and Adel Meribout",
year = "2012",
doi = "10.1615/MultScienTechn.v24.i2.10",
language = "English",
volume = "24",
pages = "89--103",
journal = "Multiphase Science and Technology",
issn = "0276-1459",
publisher = "Begell House Inc.",
number = "2",

}

TY - JOUR

T1 - A neural network algorithm for density measurement of multiphase flow

AU - Al-Rawahi, Nabeel

AU - Meribout, Mahmoud

AU - Al-Naamany, Ahmed

AU - Al-Bimani, Ali

AU - Meribout, Adel

PY - 2012

Y1 - 2012

N2 - Measurement of the density of multiphase flow is crucial in multiphase flow meters. While radioactive-based measuring methods are known to give good results, end users prefer nonradioactive devices for obvious reasons. This paper shows the capability of an online neural network algorithm, that uses the differential pressure along a vertical pipe and across a venturi meter, in predicting the average density of the multiphase flow. A multiphase flow loop was constructed to conduct the training and evaluating experiments needed for the algorithm. Experimental results performed on the multiphase flow loop demonstrate that the density measurement can be achieved with good accuracy for liquid and gas velocities for up to 4 and 25 m/s (at 30°C and 7 bars), respectively, while covering different complex flow regimes including annular flow, slug flow, and dispersed flow. The neural network algorithm that was developed for this purpose gave very good results in measuring the flow density.

AB - Measurement of the density of multiphase flow is crucial in multiphase flow meters. While radioactive-based measuring methods are known to give good results, end users prefer nonradioactive devices for obvious reasons. This paper shows the capability of an online neural network algorithm, that uses the differential pressure along a vertical pipe and across a venturi meter, in predicting the average density of the multiphase flow. A multiphase flow loop was constructed to conduct the training and evaluating experiments needed for the algorithm. Experimental results performed on the multiphase flow loop demonstrate that the density measurement can be achieved with good accuracy for liquid and gas velocities for up to 4 and 25 m/s (at 30°C and 7 bars), respectively, while covering different complex flow regimes including annular flow, slug flow, and dispersed flow. The neural network algorithm that was developed for this purpose gave very good results in measuring the flow density.

KW - Density measurement

KW - Multiphase flow loop

KW - Neural network algorithm

UR - http://www.scopus.com/inward/record.url?scp=84865217576&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865217576&partnerID=8YFLogxK

U2 - 10.1615/MultScienTechn.v24.i2.10

DO - 10.1615/MultScienTechn.v24.i2.10

M3 - Article

AN - SCOPUS:84865217576

VL - 24

SP - 89

EP - 103

JO - Multiphase Science and Technology

JF - Multiphase Science and Technology

SN - 0276-1459

IS - 2

ER -