Prediction of PVT properties in crude oil systems using support vector machines
Calculation of reserves in an oil reservoir and the determination of its performance and economics require good knowledge of its physical properties. Accurate determination of the pressure-volume-temperature (PVT) properties such as the bubble point pressure (Pb) and the oil formation volume factor...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference Paper |
Language: | English |
Published: |
2017
|
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uniten.dspace-5027 |
---|---|
record_format |
dspace |
spelling |
my.uniten.dspace-50272017-11-14T07:20:37Z Prediction of PVT properties in crude oil systems using support vector machines Nagi, J. Kiong, T.S. Ahmed, S.K. Nagi, F. Calculation of reserves in an oil reservoir and the determination of its performance and economics require good knowledge of its physical properties. Accurate determination of the pressure-volume-temperature (PVT) properties such as the bubble point pressure (Pb) and the oil formation volume factor (Bob) are important in the primary and subsequent development of an oil field. This paper proposes Support Vector Machines (SVMs) as a novel machine learning technique for predicting outputs in uncertain situations using the ε-Support Vector Regression (ε-SVR) method. The objective of this research is to investigate the capability of SVRs in modeling PVT properties of crude oil systems and solving existing Artificial Neural Network (ANN) drawbacks. Three datasets used for training and testing the SVR prediction model were collected from distinct published sources. The ε-SVR model incorporates four input features from the datasets: (1) solution gas-oil ratio, (2) reservoir temperature, (3) oil gravity and, (4) gas relative density. A comparative study is carried out to compare ε-SVR performance with ANNs, nonlinear regression, and different empirical correlation techniques. The results obtained reveal that the ε-SVR once successfully trained and optimized is more accurate, reliable, and outperforms the other existing approaches such as empirical correlation for estimating crude oil PVT properties. ©2009 IEEE. 2017-11-14T03:21:28Z 2017-11-14T03:21:28Z 2009 Conference Paper 10.1109/ICEENVIRON.2009.5398681 en ICEE 2009 - Proceeding 2009 3rd International Conference on Energy and Environment: Advancement Towards Global Sustainability 2009, Article number 5398681, Pages 1-5 |
institution |
Universiti Tenaga Nasional |
building |
UNITEN Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tenaga Nasional |
content_source |
UNITEN Institutional Repository |
url_provider |
http://dspace.uniten.edu.my/ |
language |
English |
description |
Calculation of reserves in an oil reservoir and the determination of its performance and economics require good knowledge of its physical properties. Accurate determination of the pressure-volume-temperature (PVT) properties such as the bubble point pressure (Pb) and the oil formation volume factor (Bob) are important in the primary and subsequent development of an oil field. This paper proposes Support Vector Machines (SVMs) as a novel machine learning technique for predicting outputs in uncertain situations using the ε-Support Vector Regression (ε-SVR) method. The objective of this research is to investigate the capability of SVRs in modeling PVT properties of crude oil systems and solving existing Artificial Neural Network (ANN) drawbacks. Three datasets used for training and testing the SVR prediction model were collected from distinct published sources. The ε-SVR model incorporates four input features from the datasets: (1) solution gas-oil ratio, (2) reservoir temperature, (3) oil gravity and, (4) gas relative density. A comparative study is carried out to compare ε-SVR performance with ANNs, nonlinear regression, and different empirical correlation techniques. The results obtained reveal that the ε-SVR once successfully trained and optimized is more accurate, reliable, and outperforms the other existing approaches such as empirical correlation for estimating crude oil PVT properties. ©2009 IEEE. |
format |
Conference Paper |
author |
Nagi, J. Kiong, T.S. Ahmed, S.K. Nagi, F. |
spellingShingle |
Nagi, J. Kiong, T.S. Ahmed, S.K. Nagi, F. Prediction of PVT properties in crude oil systems using support vector machines |
author_facet |
Nagi, J. Kiong, T.S. Ahmed, S.K. Nagi, F. |
author_sort |
Nagi, J. |
title |
Prediction of PVT properties in crude oil systems using support vector machines |
title_short |
Prediction of PVT properties in crude oil systems using support vector machines |
title_full |
Prediction of PVT properties in crude oil systems using support vector machines |
title_fullStr |
Prediction of PVT properties in crude oil systems using support vector machines |
title_full_unstemmed |
Prediction of PVT properties in crude oil systems using support vector machines |
title_sort |
prediction of pvt properties in crude oil systems using support vector machines |
publishDate |
2017 |
_version_ |
1644493594050953216 |
score |
13.18916 |