CRUDE Oil PVT Characterisation using Ensemble Systems

Oloso, Munirudeen, Hassan Sayed, Mohamed, Bader-El-Den, Mohamed and Buick, James (2016) CRUDE Oil PVT Characterisation using Ensemble Systems. Applied Soft Computing.

Abstract

In reservoir engineering, there is always a need to estimate crude oil pressure-volume-temperature properties for many critical calculations and decisions such as reserve estimate, material balance design and oil recovery strategy, among others. Empirical correlation are still often used instead of the costly laboratory experiments to estimate these properties, while the adoption of machine learning approaches is increasingly getting necessary attention for the industrial applications. However, these correlations may not always give sufficient or consistent accuracy. This paper develops ensemble support vector regression and ensemble regression tree models to predict two important crude oil PVT properties: bubblepoint pressure and oil formation volume factor at bubblepoint. Two different experimental works were carried out to train the ensemble models using different datasets. The developed ensemble models are compared with standalone support vector machine (SVM) and regression tree models, and commonly used empirical correlations. Consistency and reliability of the models are explored by testing on three different additional datasets. Training the ensemble models with bigger data set improves their performances. The ensemble regression trees model gives the best overall result, consistency and resilience to the variability of the datasets in testing.

This record has no associated files available for download.

Contributors

Author: Mohamed Hassan Sayed

Download statistics