Publication:
Prediction of PVT properties in crude oil systems using support vector machines

Simple item page
dc.citedby8
dc.contributor.authorNagi J.en_US
dc.contributor.authorKiong T.S.en_US
dc.contributor.authorAhmed S.K.en_US
dc.contributor.authorNagi F.en_US
dc.contributor.authorid25825455100en_US
dc.contributor.authorid15128307800en_US
dc.contributor.authorid25926812900en_US
dc.contributor.authorid56272534200en_US
dc.date.accessioned2023-12-29T07:52:41Z
dc.date.available2023-12-29T07:52:41Z
dc.date.issued2009
dc.description.abstractCalculation 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 ?-Support Vector Regression (?-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 ?-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 ?-SVR performance with ANNs, nonlinear regression, and different empirical correlation techniques. The results obtained reveal that the ?-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.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo5398681
dc.identifier.doi10.1109/ICEENVIRON.2009.5398681
dc.identifier.epage5
dc.identifier.scopus2-s2.0-77949584632
dc.identifier.spage1
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-77949584632&doi=10.1109%2fICEENVIRON.2009.5398681&partnerID=40&md5=190c3284d24e5862c183e62bc90bd28f
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/30758
dc.pagecount4
dc.sourceScopus
dc.sourcetitleICEE 2009 - Proceeding 2009 3rd International Conference on Energy and Environment: Advancement Towards Global Sustainability
dc.subjectBubble point pressue
dc.subjectOil formation volume factor
dc.subjectPVT properties
dc.subjectSupport vector machine
dc.subjectSupport vector regression
dc.subjectCrude oil
dc.subjectForecasting
dc.subjectGears
dc.subjectLearning algorithms
dc.subjectMathematical models
dc.subjectMultilayer neural networks
dc.subjectPetroleum analysis
dc.subjectPetroleum reservoir engineering
dc.subjectPetroleum reservoirs
dc.subjectRegression analysis
dc.subjectSupport vector machines
dc.subjectSustainable development
dc.subjectVectors
dc.subjectArtificial Neural Network
dc.subjectBubble point pressure
dc.subjectBubble points
dc.subjectComparative studies
dc.subjectCrude oil system
dc.subjectData sets
dc.subjectEmpirical correlations
dc.subjectGas oil ratios
dc.subjectInput features
dc.subjectMachine learning techniques
dc.subjectNon-linear regression
dc.subjectOil formation
dc.subjectOil gravity
dc.subjectOil reservoirs
dc.subjectPrediction model
dc.subjectPressure-volume-temperature properties
dc.subjectPVT properties
dc.subjectRelative density
dc.subjectReservoir temperatures
dc.subjectSupport vector regressions
dc.subjectTraining and testing
dc.subjectOil field development
dc.titlePrediction of PVT properties in crude oil systems using support vector machinesen_US
dc.typeConference paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS