Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Brazilian Journal of Operations & Production Management (Online) |
Texto Completo: | https://bjopm.org.br/bjopm/article/view/1952 |
Resumo: | Goal: This study aims to use artificial intelligence, specifically a random forest model, to predict the annual corrosion rate on FPSO offshore platforms in the oil and gas industry. Corrosion is a significant cause of equipment failure, leading to costly replacements. The random forest model, a machine learning technique, was developed using climatic and other relevant data to forecast corrosion trends based on selected variables. Design/methodology/approach: The methodology involved four steps: identifying influential factors affecting corrosion, selecting factors based on reliability and accessibility of measurements, applying the machine learning model to predict annual corrosion progression, and comparing the random forest model with other ML models. Results - The results showed that the random forest regression model successfully predicted corrosion rates, indicating an average yearly increase of 2.43% on the analyzed platforms. The main factors influencing this increase were wind speed, percentage of measured corrosion, and platform operating time. Regions with higher incidence of these factors are likely to experience higher corrosion rates, necessitating more frequent maintenance. Limitations of the investigation - The research sample consisted exclusively of 4 platforms located in the offshore region of Rio de Janeiro, Brazil. Thus, the results obtained must be interpreted as representative of these platforms and respective climate conditions. Practical implications – The use of data science tools to improve corrosion management allows managers to have knowledge of which areas has a greater or lesser tendency to corrode, helping to prioritize maintenance activities over time. Originality/value - This study aims to fill gaps regarding the use of random forest techniques for regression focused on predicting the rate of increase in corrosion. It offers a novel approach to assist decision-making in maintenance planning, providing insights into influential corrosion factors and facilitating more effective painting plans to preserve industrial unit integrity. |
id |
ABEPRO_81416d306174bb2c9f9bd39860db8f2a |
---|---|
oai_identifier_str |
oai:ojs.bjopm.org.br:article/1952 |
network_acronym_str |
ABEPRO |
network_name_str |
Brazilian Journal of Operations & Production Management (Online) |
repository_id_str |
|
spelling |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approachCorrosionMaintenance PlanRandom Forest Regressor Corrosion rateGoal: This study aims to use artificial intelligence, specifically a random forest model, to predict the annual corrosion rate on FPSO offshore platforms in the oil and gas industry. Corrosion is a significant cause of equipment failure, leading to costly replacements. The random forest model, a machine learning technique, was developed using climatic and other relevant data to forecast corrosion trends based on selected variables. Design/methodology/approach: The methodology involved four steps: identifying influential factors affecting corrosion, selecting factors based on reliability and accessibility of measurements, applying the machine learning model to predict annual corrosion progression, and comparing the random forest model with other ML models. Results - The results showed that the random forest regression model successfully predicted corrosion rates, indicating an average yearly increase of 2.43% on the analyzed platforms. The main factors influencing this increase were wind speed, percentage of measured corrosion, and platform operating time. Regions with higher incidence of these factors are likely to experience higher corrosion rates, necessitating more frequent maintenance. Limitations of the investigation - The research sample consisted exclusively of 4 platforms located in the offshore region of Rio de Janeiro, Brazil. Thus, the results obtained must be interpreted as representative of these platforms and respective climate conditions. Practical implications – The use of data science tools to improve corrosion management allows managers to have knowledge of which areas has a greater or lesser tendency to corrode, helping to prioritize maintenance activities over time. Originality/value - This study aims to fill gaps regarding the use of random forest techniques for regression focused on predicting the rate of increase in corrosion. It offers a novel approach to assist decision-making in maintenance planning, providing insights into influential corrosion factors and facilitating more effective painting plans to preserve industrial unit integrity.Brazilian Association for Industrial Engineering and Operations Management (ABEPRO)2023-09-22info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionResearch paperapplication/pdfhttps://bjopm.org.br/bjopm/article/view/195210.14488/BJOPM.1952.2023Brazilian Journal of Operations & Production Management; Vol. 20 No. 3 (2023): Special edition; 19522237-8960reponame:Brazilian Journal of Operations & Production Management (Online)instname:Associação Brasileira de Engenharia de Produção (ABEPRO)instacron:ABEPROenghttps://bjopm.org.br/bjopm/article/view/1952/1050Copyright (c) 2023 Fernanda Ramos Elmas, Marina Polonia Rios, Eduardo Rocha de Almeida Lima, Rodrigo Goyannes Gusmão caiado, Renan Silva Santoshttp://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessElmas, Fernanda RamosRios, Marina PoloniaLima, Eduardo Rocha de Almeidacaiado, Rodrigo Goyannes GusmãoSantos, Renan Silva2023-10-31T14:29:18Zoai:ojs.bjopm.org.br:article/1952Revistahttps://bjopm.org.br/bjopmONGhttps://bjopm.org.br/bjopm/oaibjopm.journal@gmail.com2237-89601679-8171opendoar:2023-10-31T14:29:18Brazilian Journal of Operations & Production Management (Online) - Associação Brasileira de Engenharia de Produção (ABEPRO)false |
dc.title.none.fl_str_mv |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach |
title |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach |
spellingShingle |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach Elmas, Fernanda Ramos Corrosion Maintenance Plan Random Forest Regressor Corrosion rate |
title_short |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach |
title_full |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach |
title_fullStr |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach |
title_full_unstemmed |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach |
title_sort |
Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach |
author |
Elmas, Fernanda Ramos |
author_facet |
Elmas, Fernanda Ramos Rios, Marina Polonia Lima, Eduardo Rocha de Almeida caiado, Rodrigo Goyannes Gusmão Santos, Renan Silva |
author_role |
author |
author2 |
Rios, Marina Polonia Lima, Eduardo Rocha de Almeida caiado, Rodrigo Goyannes Gusmão Santos, Renan Silva |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Elmas, Fernanda Ramos Rios, Marina Polonia Lima, Eduardo Rocha de Almeida caiado, Rodrigo Goyannes Gusmão Santos, Renan Silva |
dc.subject.por.fl_str_mv |
Corrosion Maintenance Plan Random Forest Regressor Corrosion rate |
topic |
Corrosion Maintenance Plan Random Forest Regressor Corrosion rate |
description |
Goal: This study aims to use artificial intelligence, specifically a random forest model, to predict the annual corrosion rate on FPSO offshore platforms in the oil and gas industry. Corrosion is a significant cause of equipment failure, leading to costly replacements. The random forest model, a machine learning technique, was developed using climatic and other relevant data to forecast corrosion trends based on selected variables. Design/methodology/approach: The methodology involved four steps: identifying influential factors affecting corrosion, selecting factors based on reliability and accessibility of measurements, applying the machine learning model to predict annual corrosion progression, and comparing the random forest model with other ML models. Results - The results showed that the random forest regression model successfully predicted corrosion rates, indicating an average yearly increase of 2.43% on the analyzed platforms. The main factors influencing this increase were wind speed, percentage of measured corrosion, and platform operating time. Regions with higher incidence of these factors are likely to experience higher corrosion rates, necessitating more frequent maintenance. Limitations of the investigation - The research sample consisted exclusively of 4 platforms located in the offshore region of Rio de Janeiro, Brazil. Thus, the results obtained must be interpreted as representative of these platforms and respective climate conditions. Practical implications – The use of data science tools to improve corrosion management allows managers to have knowledge of which areas has a greater or lesser tendency to corrode, helping to prioritize maintenance activities over time. Originality/value - This study aims to fill gaps regarding the use of random forest techniques for regression focused on predicting the rate of increase in corrosion. It offers a novel approach to assist decision-making in maintenance planning, providing insights into influential corrosion factors and facilitating more effective painting plans to preserve industrial unit integrity. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-09-22 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Research paper |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://bjopm.org.br/bjopm/article/view/1952 10.14488/BJOPM.1952.2023 |
url |
https://bjopm.org.br/bjopm/article/view/1952 |
identifier_str_mv |
10.14488/BJOPM.1952.2023 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://bjopm.org.br/bjopm/article/view/1952/1050 |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Brazilian Association for Industrial Engineering and Operations Management (ABEPRO) |
publisher.none.fl_str_mv |
Brazilian Association for Industrial Engineering and Operations Management (ABEPRO) |
dc.source.none.fl_str_mv |
Brazilian Journal of Operations & Production Management; Vol. 20 No. 3 (2023): Special edition; 1952 2237-8960 reponame:Brazilian Journal of Operations & Production Management (Online) instname:Associação Brasileira de Engenharia de Produção (ABEPRO) instacron:ABEPRO |
instname_str |
Associação Brasileira de Engenharia de Produção (ABEPRO) |
instacron_str |
ABEPRO |
institution |
ABEPRO |
reponame_str |
Brazilian Journal of Operations & Production Management (Online) |
collection |
Brazilian Journal of Operations & Production Management (Online) |
repository.name.fl_str_mv |
Brazilian Journal of Operations & Production Management (Online) - Associação Brasileira de Engenharia de Produção (ABEPRO) |
repository.mail.fl_str_mv |
bjopm.journal@gmail.com |
_version_ |
1797051459492118528 |