Applying a Smart Technique for Accurate Determination of Flowing Oil-Water Pressure Gradient in Horizontal Pipelines

Mohammad Fazavi, Seyyed Mohsen Hosseini, Milad Arabloo, Amin Shokrollahi, Morteza Nouri-Taleghani, Mahmood Amani

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Two-phase flow of liquids in pipelines is crucial subject in many industries such as chemical and petroleum. Accurate prediction of pressure gradient will lead to a better design of an energy efficient transportation system. Although numerous studies for prediction of two-phase flowing pressure drop have been reported in the literature, the accurate prediction of this parameter has been a topic of debate in many research areas. In this article, a novel model based on least square support vector (LSSVM) was proposed for calculation of two-phase flowing pressure drop in horizontal pipes. The inputs of this model are oil and water superficial velocities, pipe diameter, pipe roughness, and oil viscosity. To develop and test the model, more than 700 experimental dataset from open literature were utilized. The results of proposed model were compared against the well-known empirical correlations. Statistical error analysis showed that the LSSVM model outperforms existing predictive models. Finally, an outlier diagnosis was performed to detect the doubtful experimental.

Original languageEnglish
Pages (from-to)882-888
Number of pages7
JournalJournal of Dispersion Science and Technology
Volume35
Issue number6
DOIs
Publication statusPublished - 2014

Fingerprint

water pressure
Pressure gradient
pressure gradients
Oils
Pipelines
oils
Water
Pipe
pressure drop
Pressure drop
predictions
Petroleum
error analysis
two phase flow
crude oil
Two phase flow
Error analysis
Flow of fluids
roughness
Crude oil

Keywords

  • Correlations
  • LSSVM
  • outlier
  • pressure gradient
  • two-phase flow

ASJC Scopus subject areas

  • Surfaces, Coatings and Films
  • Physical and Theoretical Chemistry
  • Polymers and Plastics

Cite this

Applying a Smart Technique for Accurate Determination of Flowing Oil-Water Pressure Gradient in Horizontal Pipelines. / Fazavi, Mohammad; Hosseini, Seyyed Mohsen; Arabloo, Milad; Shokrollahi, Amin; Nouri-Taleghani, Morteza; Amani, Mahmood.

In: Journal of Dispersion Science and Technology, Vol. 35, No. 6, 2014, p. 882-888.

Research output: Contribution to journalArticle

Fazavi, Mohammad ; Hosseini, Seyyed Mohsen ; Arabloo, Milad ; Shokrollahi, Amin ; Nouri-Taleghani, Morteza ; Amani, Mahmood. / Applying a Smart Technique for Accurate Determination of Flowing Oil-Water Pressure Gradient in Horizontal Pipelines. In: Journal of Dispersion Science and Technology. 2014 ; Vol. 35, No. 6. pp. 882-888.
@article{548891de9f984b8cb033f950ef125ece,
title = "Applying a Smart Technique for Accurate Determination of Flowing Oil-Water Pressure Gradient in Horizontal Pipelines",
abstract = "Two-phase flow of liquids in pipelines is crucial subject in many industries such as chemical and petroleum. Accurate prediction of pressure gradient will lead to a better design of an energy efficient transportation system. Although numerous studies for prediction of two-phase flowing pressure drop have been reported in the literature, the accurate prediction of this parameter has been a topic of debate in many research areas. In this article, a novel model based on least square support vector (LSSVM) was proposed for calculation of two-phase flowing pressure drop in horizontal pipes. The inputs of this model are oil and water superficial velocities, pipe diameter, pipe roughness, and oil viscosity. To develop and test the model, more than 700 experimental dataset from open literature were utilized. The results of proposed model were compared against the well-known empirical correlations. Statistical error analysis showed that the LSSVM model outperforms existing predictive models. Finally, an outlier diagnosis was performed to detect the doubtful experimental.",
keywords = "Correlations, LSSVM, outlier, pressure gradient, two-phase flow",
author = "Mohammad Fazavi and Hosseini, {Seyyed Mohsen} and Milad Arabloo and Amin Shokrollahi and Morteza Nouri-Taleghani and Mahmood Amani",
year = "2014",
doi = "10.1080/01932691.2013.805653",
language = "English",
volume = "35",
pages = "882--888",
journal = "Journal of Dispersion Science and Technology",
issn = "0193-2691",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

TY - JOUR

T1 - Applying a Smart Technique for Accurate Determination of Flowing Oil-Water Pressure Gradient in Horizontal Pipelines

AU - Fazavi, Mohammad

AU - Hosseini, Seyyed Mohsen

AU - Arabloo, Milad

AU - Shokrollahi, Amin

AU - Nouri-Taleghani, Morteza

AU - Amani, Mahmood

PY - 2014

Y1 - 2014

N2 - Two-phase flow of liquids in pipelines is crucial subject in many industries such as chemical and petroleum. Accurate prediction of pressure gradient will lead to a better design of an energy efficient transportation system. Although numerous studies for prediction of two-phase flowing pressure drop have been reported in the literature, the accurate prediction of this parameter has been a topic of debate in many research areas. In this article, a novel model based on least square support vector (LSSVM) was proposed for calculation of two-phase flowing pressure drop in horizontal pipes. The inputs of this model are oil and water superficial velocities, pipe diameter, pipe roughness, and oil viscosity. To develop and test the model, more than 700 experimental dataset from open literature were utilized. The results of proposed model were compared against the well-known empirical correlations. Statistical error analysis showed that the LSSVM model outperforms existing predictive models. Finally, an outlier diagnosis was performed to detect the doubtful experimental.

AB - Two-phase flow of liquids in pipelines is crucial subject in many industries such as chemical and petroleum. Accurate prediction of pressure gradient will lead to a better design of an energy efficient transportation system. Although numerous studies for prediction of two-phase flowing pressure drop have been reported in the literature, the accurate prediction of this parameter has been a topic of debate in many research areas. In this article, a novel model based on least square support vector (LSSVM) was proposed for calculation of two-phase flowing pressure drop in horizontal pipes. The inputs of this model are oil and water superficial velocities, pipe diameter, pipe roughness, and oil viscosity. To develop and test the model, more than 700 experimental dataset from open literature were utilized. The results of proposed model were compared against the well-known empirical correlations. Statistical error analysis showed that the LSSVM model outperforms existing predictive models. Finally, an outlier diagnosis was performed to detect the doubtful experimental.

KW - Correlations

KW - LSSVM

KW - outlier

KW - pressure gradient

KW - two-phase flow

UR - http://www.scopus.com/inward/record.url?scp=84901338025&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901338025&partnerID=8YFLogxK

U2 - 10.1080/01932691.2013.805653

DO - 10.1080/01932691.2013.805653

M3 - Article

VL - 35

SP - 882

EP - 888

JO - Journal of Dispersion Science and Technology

JF - Journal of Dispersion Science and Technology

SN - 0193-2691

IS - 6

ER -