Correlation for predicting bubble point pressure for 22.3≤°API≥45 crude oils: A white-box machine learning approach
Department of Petroleum Engineering, Faculty of Technology, University of Ibadan, Ibadan, Nigeria.
Research Article
International Journal of Frontiers in Engineering and Technology Research, 2022, 03(02), 015–027.
Article DOI: 10.53294/ijfetr.2022.3.2.0043
Publication history:
Received on 10 July 2022; revised on 25 October 2022; accepted on 28 October 2022
Abstract:
Bubble point pressure (BPP) is a key parameter for oil and gas reservoir identification, characterization, and management. An accurate correlation of this property with the evolving digital technology of machine learning, in the absence of experimental PVT analysis, serves as guidance in the development and recovery of reservoir fluids. In this study, a predictive BPP correlation was derived by intrinsically linearizing a nonlinear multiple regression, with the best coefficients (global minimum) extracted using White-box (Linear Regression, Ridge Regression, and Lasso Regression) Machine Learning models. The new correlation was developed, validated, and tested using 314 measured PVT data points from the Niger Delta Region. The data were subdivided into four classes: extra-light crude for API > 45, light crude for 31.1 < API ≤ 45, medium crude for 22.3 < API ≤ 31.1, and heavy crude for API ≤ 22.3. Statistical evaluation metrics such as root mean squared error, average absolute relative error, and average relative error were employed to compare the performance of the new correlation with the existing empirical ones. Results showed that the new BPP correlation developed by White-box Linear Regression outperformed the other White box (Ridge Regression and Lasso Regression) and other existing BPP empirical models. Taking advantage of emerging data-driven and machine learning as BPP predictive model is effective and efficient in reservoir fluids analysis.
Keywords:
Bubble point pressure; Crude oil; White-box machine learning; Predictive model
Full text article in PDF:
Copyright information:
Copyright © 2022 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0