Universal neural-network-based model for estimating the PVT properties of crude oil systems

Ridha B. Gharbi, Adel M. Elsharkawy, Mansour Karkoub

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

This study presents a universal neural-network-based model for the prediction of PVT properties of crude oil samples obtained from all over the world. The data, on which the network was trained, contains 5200 experimentally obtained PVT data sets of different crude oil and gas mixtures from all over the world. They were collected from major-producing oil fields in North and South America, the North Sea, Southeast Asia, the Middle East, and Africa. This represents the largest data set ever collected to be used in developing PVT models. An additional 234 PVT data sets were used to investigate the effectiveness of the neural-network models to predict outputs from inputs that were not used during the training process. The neural network model is able to predict the solution gas-oil ratio and the oil formation volume factor as a function of the bubble-point pressure, the gas relative density, the oil specific gravity, and the reservoir temperature. The neural-network models were developed using back-propagation with momentum for error minimization to obtain the most accurate PVT models. A detailed comparison between the results predicted by the neural-network models and those predicted by other correlations are presented for these crude oil samples. This study shows that artificial neural networks, once successfully trained, are excellent reliable predictive tools for estimating crude oil PVT properties better than available correlations. These neural-network PVT models can be easily incorporated into reservoir simulators and production optimization software.

Original languageEnglish
Pages (from-to)454-458
Number of pages5
JournalEnergy and Fuels
Volume13
Issue number2
DOIs
Publication statusPublished - Mar 1999
Externally publishedYes

Fingerprint

Petroleum
Crude oil
Neural networks
Density (specific gravity)
Oils
Oil fields
Gas oils
Backpropagation
Gas mixtures
Momentum
Simulators
Gases

ASJC Scopus subject areas

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

Cite this

Universal neural-network-based model for estimating the PVT properties of crude oil systems. / Gharbi, Ridha B.; Elsharkawy, Adel M.; Karkoub, Mansour.

In: Energy and Fuels, Vol. 13, No. 2, 03.1999, p. 454-458.

Research output: Contribution to journalArticle

Gharbi, Ridha B. ; Elsharkawy, Adel M. ; Karkoub, Mansour. / Universal neural-network-based model for estimating the PVT properties of crude oil systems. In: Energy and Fuels. 1999 ; Vol. 13, No. 2. pp. 454-458.
@article{b44f2a3c046846868a9931ae72f0cac4,
title = "Universal neural-network-based model for estimating the PVT properties of crude oil systems",
abstract = "This study presents a universal neural-network-based model for the prediction of PVT properties of crude oil samples obtained from all over the world. The data, on which the network was trained, contains 5200 experimentally obtained PVT data sets of different crude oil and gas mixtures from all over the world. They were collected from major-producing oil fields in North and South America, the North Sea, Southeast Asia, the Middle East, and Africa. This represents the largest data set ever collected to be used in developing PVT models. An additional 234 PVT data sets were used to investigate the effectiveness of the neural-network models to predict outputs from inputs that were not used during the training process. The neural network model is able to predict the solution gas-oil ratio and the oil formation volume factor as a function of the bubble-point pressure, the gas relative density, the oil specific gravity, and the reservoir temperature. The neural-network models were developed using back-propagation with momentum for error minimization to obtain the most accurate PVT models. A detailed comparison between the results predicted by the neural-network models and those predicted by other correlations are presented for these crude oil samples. This study shows that artificial neural networks, once successfully trained, are excellent reliable predictive tools for estimating crude oil PVT properties better than available correlations. These neural-network PVT models can be easily incorporated into reservoir simulators and production optimization software.",
author = "Gharbi, {Ridha B.} and Elsharkawy, {Adel M.} and Mansour Karkoub",
year = "1999",
month = "3",
doi = "10.1021/ef980143v",
language = "English",
volume = "13",
pages = "454--458",
journal = "Energy and Fuels",
issn = "0887-0624",
publisher = "American Chemical Society",
number = "2",

}

TY - JOUR

T1 - Universal neural-network-based model for estimating the PVT properties of crude oil systems

AU - Gharbi, Ridha B.

AU - Elsharkawy, Adel M.

AU - Karkoub, Mansour

PY - 1999/3

Y1 - 1999/3

N2 - This study presents a universal neural-network-based model for the prediction of PVT properties of crude oil samples obtained from all over the world. The data, on which the network was trained, contains 5200 experimentally obtained PVT data sets of different crude oil and gas mixtures from all over the world. They were collected from major-producing oil fields in North and South America, the North Sea, Southeast Asia, the Middle East, and Africa. This represents the largest data set ever collected to be used in developing PVT models. An additional 234 PVT data sets were used to investigate the effectiveness of the neural-network models to predict outputs from inputs that were not used during the training process. The neural network model is able to predict the solution gas-oil ratio and the oil formation volume factor as a function of the bubble-point pressure, the gas relative density, the oil specific gravity, and the reservoir temperature. The neural-network models were developed using back-propagation with momentum for error minimization to obtain the most accurate PVT models. A detailed comparison between the results predicted by the neural-network models and those predicted by other correlations are presented for these crude oil samples. This study shows that artificial neural networks, once successfully trained, are excellent reliable predictive tools for estimating crude oil PVT properties better than available correlations. These neural-network PVT models can be easily incorporated into reservoir simulators and production optimization software.

AB - This study presents a universal neural-network-based model for the prediction of PVT properties of crude oil samples obtained from all over the world. The data, on which the network was trained, contains 5200 experimentally obtained PVT data sets of different crude oil and gas mixtures from all over the world. They were collected from major-producing oil fields in North and South America, the North Sea, Southeast Asia, the Middle East, and Africa. This represents the largest data set ever collected to be used in developing PVT models. An additional 234 PVT data sets were used to investigate the effectiveness of the neural-network models to predict outputs from inputs that were not used during the training process. The neural network model is able to predict the solution gas-oil ratio and the oil formation volume factor as a function of the bubble-point pressure, the gas relative density, the oil specific gravity, and the reservoir temperature. The neural-network models were developed using back-propagation with momentum for error minimization to obtain the most accurate PVT models. A detailed comparison between the results predicted by the neural-network models and those predicted by other correlations are presented for these crude oil samples. This study shows that artificial neural networks, once successfully trained, are excellent reliable predictive tools for estimating crude oil PVT properties better than available correlations. These neural-network PVT models can be easily incorporated into reservoir simulators and production optimization software.

UR - http://www.scopus.com/inward/record.url?scp=0033097846&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033097846&partnerID=8YFLogxK

U2 - 10.1021/ef980143v

DO - 10.1021/ef980143v

M3 - Article

AN - SCOPUS:0033097846

VL - 13

SP - 454

EP - 458

JO - Energy and Fuels

JF - Energy and Fuels

SN - 0887-0624

IS - 2

ER -