Development and Application of a Data-Driven System for Sensor Fault Diagnosis in an Oil Processing Plant
Predictive analytics is usually cited as one of the most important pillars of the digital transformation. For the oil industry, specifically, it is a common belief that issues like integrity and maintenance could benefit from predictive analytics. This paper presents the development and the applicat...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-07-01
|
Series: | Processes |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9717/7/7/436 |
id |
doaj-9f85e66bc9304459b57343820e530874 |
---|---|
record_format |
Article |
spelling |
doaj-9f85e66bc9304459b57343820e5308742020-11-24T21:36:42ZengMDPI AGProcesses2227-97172019-07-017743610.3390/pr7070436pr7070436Development and Application of a Data-Driven System for Sensor Fault Diagnosis in an Oil Processing PlantNayher Clavijo0Afrânio Melo1Maurício M. Câmara2Thiago Feital3Thiago K. Anzai4Fabio C. Diehl5Pedro H. Thompson6José Carlos Pinto7Programa de Engenharia Química/COPPE, Universidade Federal do Rio de Janeiro, Cidade Universitária, CP 68502, CEP 21941-972 Rio de Janeiro, BrazilPrograma de Engenharia Química/COPPE, Universidade Federal do Rio de Janeiro, Cidade Universitária, CP 68502, CEP 21941-972 Rio de Janeiro, BrazilPrograma de Engenharia Química/COPPE, Universidade Federal do Rio de Janeiro, Cidade Universitária, CP 68502, CEP 21941-972 Rio de Janeiro, BrazilPrograma de Engenharia Química/COPPE, Universidade Federal do Rio de Janeiro, Cidade Universitária, CP 68502, CEP 21941-972 Rio de Janeiro, BrazilCentro de Pesquisas Leopoldo Americo Miguez de Mello—CENPES, Petrobras—Petróleo Brasileiro SA, CEP 21941-915, Rio de Janeiro, BrazilCentro de Pesquisas Leopoldo Americo Miguez de Mello—CENPES, Petrobras—Petróleo Brasileiro SA, CEP 21941-915, Rio de Janeiro, BrazilCentro de Pesquisas Leopoldo Americo Miguez de Mello—CENPES, Petrobras—Petróleo Brasileiro SA, CEP 21941-915, Rio de Janeiro, BrazilPrograma de Engenharia Química/COPPE, Universidade Federal do Rio de Janeiro, Cidade Universitária, CP 68502, CEP 21941-972 Rio de Janeiro, BrazilPredictive analytics is usually cited as one of the most important pillars of the digital transformation. For the oil industry, specifically, it is a common belief that issues like integrity and maintenance could benefit from predictive analytics. This paper presents the development and the application of a process-monitoring tool in a real process facility. The PMA (Predictive Maintenance Application) system is a data-driven application that uses a multivariate analysis in order to predict the system behavior. Results show that the use of a multivariate approach for process monitoring could not only detect an early failure at a metering system days before the operation crew, but could also successfully identify, among hundreds of variables, the root cause of the abnormal situation. By applying such an approach, a better performance of the monitored equipment is expected, decreasing its downtime.https://www.mdpi.com/2227-9717/7/7/436fault diagnosisconditional-based maintenancecanonical variate analysisfiscal metersreal oil and gas processing facility |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Nayher Clavijo Afrânio Melo Maurício M. Câmara Thiago Feital Thiago K. Anzai Fabio C. Diehl Pedro H. Thompson José Carlos Pinto |
spellingShingle |
Nayher Clavijo Afrânio Melo Maurício M. Câmara Thiago Feital Thiago K. Anzai Fabio C. Diehl Pedro H. Thompson José Carlos Pinto Development and Application of a Data-Driven System for Sensor Fault Diagnosis in an Oil Processing Plant Processes fault diagnosis conditional-based maintenance canonical variate analysis fiscal meters real oil and gas processing facility |
author_facet |
Nayher Clavijo Afrânio Melo Maurício M. Câmara Thiago Feital Thiago K. Anzai Fabio C. Diehl Pedro H. Thompson José Carlos Pinto |
author_sort |
Nayher Clavijo |
title |
Development and Application of a Data-Driven System for Sensor Fault Diagnosis in an Oil Processing Plant |
title_short |
Development and Application of a Data-Driven System for Sensor Fault Diagnosis in an Oil Processing Plant |
title_full |
Development and Application of a Data-Driven System for Sensor Fault Diagnosis in an Oil Processing Plant |
title_fullStr |
Development and Application of a Data-Driven System for Sensor Fault Diagnosis in an Oil Processing Plant |
title_full_unstemmed |
Development and Application of a Data-Driven System for Sensor Fault Diagnosis in an Oil Processing Plant |
title_sort |
development and application of a data-driven system for sensor fault diagnosis in an oil processing plant |
publisher |
MDPI AG |
series |
Processes |
issn |
2227-9717 |
publishDate |
2019-07-01 |
description |
Predictive analytics is usually cited as one of the most important pillars of the digital transformation. For the oil industry, specifically, it is a common belief that issues like integrity and maintenance could benefit from predictive analytics. This paper presents the development and the application of a process-monitoring tool in a real process facility. The PMA (Predictive Maintenance Application) system is a data-driven application that uses a multivariate analysis in order to predict the system behavior. Results show that the use of a multivariate approach for process monitoring could not only detect an early failure at a metering system days before the operation crew, but could also successfully identify, among hundreds of variables, the root cause of the abnormal situation. By applying such an approach, a better performance of the monitored equipment is expected, decreasing its downtime. |
topic |
fault diagnosis conditional-based maintenance canonical variate analysis fiscal meters real oil and gas processing facility |
url |
https://www.mdpi.com/2227-9717/7/7/436 |
work_keys_str_mv |
AT nayherclavijo developmentandapplicationofadatadrivensystemforsensorfaultdiagnosisinanoilprocessingplant AT afraniomelo developmentandapplicationofadatadrivensystemforsensorfaultdiagnosisinanoilprocessingplant AT mauriciomcamara developmentandapplicationofadatadrivensystemforsensorfaultdiagnosisinanoilprocessingplant AT thiagofeital developmentandapplicationofadatadrivensystemforsensorfaultdiagnosisinanoilprocessingplant AT thiagokanzai developmentandapplicationofadatadrivensystemforsensorfaultdiagnosisinanoilprocessingplant AT fabiocdiehl developmentandapplicationofadatadrivensystemforsensorfaultdiagnosisinanoilprocessingplant AT pedrohthompson developmentandapplicationofadatadrivensystemforsensorfaultdiagnosisinanoilprocessingplant AT josecarlospinto developmentandapplicationofadatadrivensystemforsensorfaultdiagnosisinanoilprocessingplant |
_version_ |
1725939877293326336 |