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

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

Bibliographic Details
Published in:Petroleum Science and Technology
Main Author: Rushd S.; Rahman M.; Arifuzzaman M.; Ali S.A.; Shalabi F.; Aktaruzzaman M.
Format: Article
Language:English
Published: Taylor and Francis Ltd. 2021
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115717461&doi=10.1080%2f10916466.2021.1980012&partnerID=40&md5=e49af5c174986d6efc76595b08c03f78
id 2-s2.0-85115717461
spelling 2-s2.0-85115717461
Rushd S.; Rahman M.; Arifuzzaman M.; Ali S.A.; Shalabi F.; Aktaruzzaman M.
Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning
2021
Petroleum Science and Technology
39
21-22
10.1080/10916466.2021.1980012
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115717461&doi=10.1080%2f10916466.2021.1980012&partnerID=40&md5=e49af5c174986d6efc76595b08c03f78
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 (R2) of 0.99 and mean squared error (MSE) of 0.009. © 2021 Taylor & Francis Group, LLC.
Taylor and Francis Ltd.
10916466
English
Article
author Rushd S.; Rahman M.; Arifuzzaman M.; Ali S.A.; Shalabi F.; Aktaruzzaman M.
spellingShingle Rushd S.; Rahman M.; Arifuzzaman M.; Ali S.A.; Shalabi F.; Aktaruzzaman M.
Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning
author_facet Rushd S.; Rahman M.; Arifuzzaman M.; Ali S.A.; Shalabi F.; Aktaruzzaman M.
author_sort Rushd S.; Rahman M.; Arifuzzaman M.; Ali S.A.; Shalabi F.; Aktaruzzaman M.
title Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning
title_short Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning
title_full Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning
title_fullStr Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning
title_full_unstemmed Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning
title_sort Predicting pressure losses in the water-assisted flow of unconventional crude with machine learning
publishDate 2021
container_title Petroleum Science and Technology
container_volume 39
container_issue 21-22
doi_str_mv 10.1080/10916466.2021.1980012
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115717461&doi=10.1080%2f10916466.2021.1980012&partnerID=40&md5=e49af5c174986d6efc76595b08c03f78
description 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 (R2) of 0.99 and mean squared error (MSE) of 0.009. © 2021 Taylor & Francis Group, LLC.
publisher Taylor and Francis Ltd.
issn 10916466
language English
format Article
accesstype
record_format scopus
collection Scopus
_version_ 1809677895159775232

Similar Items