Application of principal component analysis method (PCA) for fault detection in chemical plants
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Research, Society and Development |
Texto Completo: | https://rsdjournal.org/index.php/rsd/article/view/6335 |
Resumo: | Control systems are used in chemical industries to reduce the value of process variable deviations from the desired value known as setpoint. Even if conventional controllers contribute to reduce those errors, there is a possibility to occur system faults, which are a not allowed deviation due to some characteristic property or system parameters. Developing new fault detection techniques is the key to meet a demand growing complexity of industrial systems and their performances that aim to achieve better efficiency. This work aims to apply the Principal Component Analysis (PCA) method to detect faults in chemical plants. PCA collects historical process data and constructs a statistical model from them, besides allowing the order reduction of multivariable models to facilitate its implementation. Two case studies were performed involving CSTR (Continuously Stirred Tank Reactor) with heating jacket and a non-isothermic CSTR in order to verify the efficiency of the proposed method in detecting failures in monitored control systems. Both failures in sensors and systems submitted to step disturbances were assessed using PCA and T2 of Hotelling and Q statistics. The PCA proved to be an efficient method in fault detections involving the case studies presented, which indicates its potential to be applied in chemical industry controllers. |
id |
UNIFEI_b51b28a7e4cf0d1235146785adee865d |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/6335 |
network_acronym_str |
UNIFEI |
network_name_str |
Research, Society and Development |
repository_id_str |
|
spelling |
Application of principal component analysis method (PCA) for fault detection in chemical plantsAplicación del método de análisis de componentes principales (PCA) para la detección de fallas en plantas químicasAplicação do método de análise dos componentes principais (PCA) para detecção de falhas em plantas químicasSupervisiónDetección de fallasPCA.MonitoringFault detectionPCA.MonitoramentoDetecção de falhasPCA.Control systems are used in chemical industries to reduce the value of process variable deviations from the desired value known as setpoint. Even if conventional controllers contribute to reduce those errors, there is a possibility to occur system faults, which are a not allowed deviation due to some characteristic property or system parameters. Developing new fault detection techniques is the key to meet a demand growing complexity of industrial systems and their performances that aim to achieve better efficiency. This work aims to apply the Principal Component Analysis (PCA) method to detect faults in chemical plants. PCA collects historical process data and constructs a statistical model from them, besides allowing the order reduction of multivariable models to facilitate its implementation. Two case studies were performed involving CSTR (Continuously Stirred Tank Reactor) with heating jacket and a non-isothermic CSTR in order to verify the efficiency of the proposed method in detecting failures in monitored control systems. Both failures in sensors and systems submitted to step disturbances were assessed using PCA and T2 of Hotelling and Q statistics. The PCA proved to be an efficient method in fault detections involving the case studies presented, which indicates its potential to be applied in chemical industry controllers.Los sistemas de control se utilizan en las industrias químicas para reducir el valor de las desviaciones variables del proceso del valor deseado conocido como punto de ajuste. Incluso si los controladores convencionales contribuyen a reducir esos errores, existe la posibilidad de que ocurran fallas del sistema, que son una desviación no permitida debido a algunas propiedades características o parámetros del sistema. El desarrollo de nuevas técnicas de detección de fallas es la clave para satisfacer la creciente demanda de la complejidad de los sistemas industriales y sus rendimientos que apuntan a lograr una mayor eficiencia. Este trabajo tiene como objetivo aplicar el método de Análisis de Componentes Principales o PCA (Principal Component Analysis) para detectar fallas en plantas químicas. PCA recopila datos de procesos históricos y construye un modelo estadístico a partir de ellos, además de permitir la reducción del orden de modelos multivariables para facilitar su implementación. Se realizaron dos estudios de caso que involucraron CSTR con camisa de calentamiento y un CSTR no isotérmico para verificar la eficiencia del método propuesto en la detección de fallas en los sistemas de control monitoreados. Ambas fallas en sensores y sistemas sometidos a perturbaciones escalonadas se evaluaron utilizando PCA y T2 de las estadísticas de Hotelling y Q. El PCA demostró ser un método eficiente en la detección de fallas que involucra los estudios de caso presentados, lo que indica su potencial para ser aplicado en los controladores de la industria química.Sistemas de controle são usados na indústria química para reduzir o desvio do valor das variáveis de processo em relação ao valor desejado, conhecido como setpoint. Mesmo que os controladores convencionais ajudem a reduzir esses erros, ainda existe a possibilidade de ocorrerem falhas, que são um desvio não permitido devido a alguma propriedade característica ou parâmetros do sistema. O desenvolvimento de novas técnicas de detecção de falhas é fundamental para atender a demanda da crescente complexidade dos sistemas industriais e suas performances que visam atingir uma melhor eficiência. O objetivo desse trabalho foi aplicar o método de análise dos componentes principais ou PCA (Principal Component Analysis) para detectar falhas em plantas químicas. O PCA coleta os dados históricos do processo e constrói um modelo estatístico baseado neles, bem como permite a redução da ordem de modelos multivariável para facilitar sua implementação. Foram feitos dois estudos de caso envolvendo reator tanque agitado contínuo ou CSTR (Continuously Stirred Tank Reactor) com jaqueta de aquecimento e CSTR não-isotérmico de modo a verificar a eficiência do método proposto na detecção de falhas em sistemas de controle monitorado. Avaliaram-se falhas em sensores e sistemas submetidos a perturbações tipo degrau, mediante o PCA e as estatísticas T2 de Hotelling e Q. O método PCA mostrou-se eficiente para detectar as falhas existentes nos estudos de caso apresentados, o que indica seu potencial para aplicação em controladores da indústria química.Research, Society and Development2020-08-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://rsdjournal.org/index.php/rsd/article/view/633510.33448/rsd-v9i8.6335Research, Society and Development; Vol. 9 No. 8; e957986335Research, Society and Development; Vol. 9 Núm. 8; e957986335Research, Society and Development; v. 9 n. 8; e9579863352525-3409reponame:Research, Society and Developmentinstname:Universidade Federal de Itajubá (UNIFEI)instacron:UNIFEIporhttps://rsdjournal.org/index.php/rsd/article/view/6335/6062Copyright (c) 2020 Thessa Fuzaro Corrêa, Davi Leonardo de Souzahttp://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessMendes, Thessa FuzaroSouza, Davi Leonardo de2020-08-20T18:00:17Zoai:ojs.pkp.sfu.ca:article/6335Revistahttps://rsdjournal.org/index.php/rsd/indexPUBhttps://rsdjournal.org/index.php/rsd/oairsd.articles@gmail.com2525-34092525-3409opendoar:2024-01-17T09:29:30.442460Research, Society and Development - Universidade Federal de Itajubá (UNIFEI)false |
dc.title.none.fl_str_mv |
Application of principal component analysis method (PCA) for fault detection in chemical plants Aplicación del método de análisis de componentes principales (PCA) para la detección de fallas en plantas químicas Aplicação do método de análise dos componentes principais (PCA) para detecção de falhas em plantas químicas |
title |
Application of principal component analysis method (PCA) for fault detection in chemical plants |
spellingShingle |
Application of principal component analysis method (PCA) for fault detection in chemical plants Mendes, Thessa Fuzaro Supervisión Detección de fallas PCA. Monitoring Fault detection PCA. Monitoramento Detecção de falhas PCA. |
title_short |
Application of principal component analysis method (PCA) for fault detection in chemical plants |
title_full |
Application of principal component analysis method (PCA) for fault detection in chemical plants |
title_fullStr |
Application of principal component analysis method (PCA) for fault detection in chemical plants |
title_full_unstemmed |
Application of principal component analysis method (PCA) for fault detection in chemical plants |
title_sort |
Application of principal component analysis method (PCA) for fault detection in chemical plants |
author |
Mendes, Thessa Fuzaro |
author_facet |
Mendes, Thessa Fuzaro Souza, Davi Leonardo de |
author_role |
author |
author2 |
Souza, Davi Leonardo de |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Mendes, Thessa Fuzaro Souza, Davi Leonardo de |
dc.subject.por.fl_str_mv |
Supervisión Detección de fallas PCA. Monitoring Fault detection PCA. Monitoramento Detecção de falhas PCA. |
topic |
Supervisión Detección de fallas PCA. Monitoring Fault detection PCA. Monitoramento Detecção de falhas PCA. |
description |
Control systems are used in chemical industries to reduce the value of process variable deviations from the desired value known as setpoint. Even if conventional controllers contribute to reduce those errors, there is a possibility to occur system faults, which are a not allowed deviation due to some characteristic property or system parameters. Developing new fault detection techniques is the key to meet a demand growing complexity of industrial systems and their performances that aim to achieve better efficiency. This work aims to apply the Principal Component Analysis (PCA) method to detect faults in chemical plants. PCA collects historical process data and constructs a statistical model from them, besides allowing the order reduction of multivariable models to facilitate its implementation. Two case studies were performed involving CSTR (Continuously Stirred Tank Reactor) with heating jacket and a non-isothermic CSTR in order to verify the efficiency of the proposed method in detecting failures in monitored control systems. Both failures in sensors and systems submitted to step disturbances were assessed using PCA and T2 of Hotelling and Q statistics. The PCA proved to be an efficient method in fault detections involving the case studies presented, which indicates its potential to be applied in chemical industry controllers. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-08-03 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/6335 10.33448/rsd-v9i8.6335 |
url |
https://rsdjournal.org/index.php/rsd/article/view/6335 |
identifier_str_mv |
10.33448/rsd-v9i8.6335 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/6335/6062 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2020 Thessa Fuzaro Corrêa, Davi Leonardo de Souza http://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2020 Thessa Fuzaro Corrêa, Davi Leonardo de Souza 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 |
Research, Society and Development |
publisher.none.fl_str_mv |
Research, Society and Development |
dc.source.none.fl_str_mv |
Research, Society and Development; Vol. 9 No. 8; e957986335 Research, Society and Development; Vol. 9 Núm. 8; e957986335 Research, Society and Development; v. 9 n. 8; e957986335 2525-3409 reponame:Research, Society and Development instname:Universidade Federal de Itajubá (UNIFEI) instacron:UNIFEI |
instname_str |
Universidade Federal de Itajubá (UNIFEI) |
instacron_str |
UNIFEI |
institution |
UNIFEI |
reponame_str |
Research, Society and Development |
collection |
Research, Society and Development |
repository.name.fl_str_mv |
Research, Society and Development - Universidade Federal de Itajubá (UNIFEI) |
repository.mail.fl_str_mv |
rsd.articles@gmail.com |
_version_ |
1797052830516772864 |