Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning

Machine learning (ML) is recognized as an efficient prediction tool. However, very few attempts have been made to apply it to model pressure losses in the water-assisted pipeline transportation of unconventional crudes. The performances of conventional ML algorithms for predictions were analyzed in...

Full description

Saved in:
Bibliographic Details
Published inPetroleum science and technology Vol. 39; no. 21-22; pp. 926 - 943
Main Authors Rushd, Sayeed, Rahman, Moklesur, Arifuzzaman, Md, Ali, Sherif Abdulbari, Shalabi, Faisal, Aktaruzzaman, Md
Format Journal Article
LanguageEnglish
Published Abingdon Taylor & Francis 17.11.2021
Taylor & Francis Ltd
Subjects
Algorithms
artificial intelligence
artificial neural network
Artificial neural networks
Core-annular flow
Data points
friction
heavy oil
Machine learning
Moisture content
pipeline transportation
Pressure loss
support vector machine
viscosity
Online AccessGet full text

Cover

More Information
Summary:Machine learning (ML) is recognized as an efficient prediction tool. However, very few attempts have been made to apply it to model pressure losses in the water-assisted pipeline transportation of unconventional crudes. The performances of conventional ML algorithms for predictions were analyzed in the current study based on a dataset comprised of 225 data points and seven input parameters: pipe diameter, average velocity, densities of oil and water, viscosities of oil and water, and water content. Among the algorithms tested, the artificial neural network demonstrated the most promising performance with the coefficient of determination (R 2 ) of 0.99 and mean squared error (MSE) of 0.009.
ISSN:1091-6466
1532-2459
DOI:10.1080/10916466.2021.1980012