An artificial neural network for the prediction of immiscible flood performance

Ridha Gharbi, Mansour Karkoub, Ali Elkamel

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Despite several decades of artificial neural network reserach in other engineering disciplines, only recently work has been reported on its use as a prediction tool in petroleum engineering applications. Existing methods for the prediction of fluid flow in porous medium include numerical simulation techniques and laboratory core flood experiments. Both of these methods are generally expensive and time consuming. However, neural networks, once successfully trained, can be used to predict reservoir performance in a short time with a personal computer. An artificial neural network was developed using data obtained from fine-mesh numerical simulation to predict the breakthrough oil recovery of immiscible displacement of oil by water in a two-dimensional vertical cross section. The network is able to predict the results of the fine-mesh numerical simulations without actually performing these simulation runs. Various neural network connections were investigated using the back-propagation with momentum algorithm for error minimization. This paper describes the design, development, and testing of the neural network.

Original languageEnglish
Pages (from-to)894-900
Number of pages7
JournalEnergy and Fuels
Volume9
Issue number5
Publication statusPublished - 1995
Externally publishedYes

Fingerprint

Neural networks
Computer simulation
Oils
Petroleum engineering
Backpropagation
Personal computers
Porous materials
Flow of fluids
Momentum
Recovery
Water
Testing
Experiments

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Energy Engineering and Power Technology
  • Fuel Technology

Cite this

An artificial neural network for the prediction of immiscible flood performance. / Gharbi, Ridha; Karkoub, Mansour; Elkamel, Ali.

In: Energy and Fuels, Vol. 9, No. 5, 1995, p. 894-900.

Research output: Contribution to journalArticle

@article{22a187f12b5548ad8e115610418835e9,
title = "An artificial neural network for the prediction of immiscible flood performance",
abstract = "Despite several decades of artificial neural network reserach in other engineering disciplines, only recently work has been reported on its use as a prediction tool in petroleum engineering applications. Existing methods for the prediction of fluid flow in porous medium include numerical simulation techniques and laboratory core flood experiments. Both of these methods are generally expensive and time consuming. However, neural networks, once successfully trained, can be used to predict reservoir performance in a short time with a personal computer. An artificial neural network was developed using data obtained from fine-mesh numerical simulation to predict the breakthrough oil recovery of immiscible displacement of oil by water in a two-dimensional vertical cross section. The network is able to predict the results of the fine-mesh numerical simulations without actually performing these simulation runs. Various neural network connections were investigated using the back-propagation with momentum algorithm for error minimization. This paper describes the design, development, and testing of the neural network.",
author = "Ridha Gharbi and Mansour Karkoub and Ali Elkamel",
year = "1995",
language = "English",
volume = "9",
pages = "894--900",
journal = "Energy and Fuels",
issn = "0887-0624",
publisher = "American Chemical Society",
number = "5",

}

TY - JOUR

T1 - An artificial neural network for the prediction of immiscible flood performance

AU - Gharbi, Ridha

AU - Karkoub, Mansour

AU - Elkamel, Ali

PY - 1995

Y1 - 1995

N2 - Despite several decades of artificial neural network reserach in other engineering disciplines, only recently work has been reported on its use as a prediction tool in petroleum engineering applications. Existing methods for the prediction of fluid flow in porous medium include numerical simulation techniques and laboratory core flood experiments. Both of these methods are generally expensive and time consuming. However, neural networks, once successfully trained, can be used to predict reservoir performance in a short time with a personal computer. An artificial neural network was developed using data obtained from fine-mesh numerical simulation to predict the breakthrough oil recovery of immiscible displacement of oil by water in a two-dimensional vertical cross section. The network is able to predict the results of the fine-mesh numerical simulations without actually performing these simulation runs. Various neural network connections were investigated using the back-propagation with momentum algorithm for error minimization. This paper describes the design, development, and testing of the neural network.

AB - Despite several decades of artificial neural network reserach in other engineering disciplines, only recently work has been reported on its use as a prediction tool in petroleum engineering applications. Existing methods for the prediction of fluid flow in porous medium include numerical simulation techniques and laboratory core flood experiments. Both of these methods are generally expensive and time consuming. However, neural networks, once successfully trained, can be used to predict reservoir performance in a short time with a personal computer. An artificial neural network was developed using data obtained from fine-mesh numerical simulation to predict the breakthrough oil recovery of immiscible displacement of oil by water in a two-dimensional vertical cross section. The network is able to predict the results of the fine-mesh numerical simulations without actually performing these simulation runs. Various neural network connections were investigated using the back-propagation with momentum algorithm for error minimization. This paper describes the design, development, and testing of the neural network.

UR - http://www.scopus.com/inward/record.url?scp=0029367444&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029367444&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0029367444

VL - 9

SP - 894

EP - 900

JO - Energy and Fuels

JF - Energy and Fuels

SN - 0887-0624

IS - 5

ER -