Increasing power plant efficiency with clustering methods and Variable Importance Index assessment
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/232126 |
Resumo: | Power plant performance can decrease along with its life span, and move away from the design and commissioning targets. Maintenance issues, operational practices, market restrictions, and financial objectives may lead to that behavior, and the knowledge of appropriate actions could support the system to retake its original operational performance. This paper applies unsupervised machine learning techniques to identify operating patterns based on the power plant’s historical data which leads to the identification of appropriate steam generator efficiency conditions. The selected operational variables are evaluated in respect to their impact on the system performance, quantified by the Variable Importance Index. That metric is proposed to identify the variables among a much wide set of monitored data whose variation impacts the overall power plant operation, and should be controlled with more attention. Principal Component Analysis (PCA) and k-means++ clustering techniques are used to identify suitable operational conditions from a one-year-long data set with 27 recorded variables from a steam generator of a 360MW thermal power plant. The adequate number of clusters is identified by the average Silhouette coefficient and the Variable Importance Index sorts nine variables as the most relevant ones, to finally group recommended settings to achieve the target conditions. Results show performance gains in respect to the average historical values of 73.5% and the lowest efficiency condition records of 68%, to the target steam generator efficiency of 76%. |
id |
UFRGS-2_1ffcb52a11564aad47e892a6f999a1d6 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/232126 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Duarte, JéssicaVieira, Lara WernckeMarques, Augusto DelavaldSchneider, Paulo SmithPumi, GuilhermePrass, Taiane Schaedler2021-11-25T04:35:52Z20212666-5468http://hdl.handle.net/10183/232126001132625Power plant performance can decrease along with its life span, and move away from the design and commissioning targets. Maintenance issues, operational practices, market restrictions, and financial objectives may lead to that behavior, and the knowledge of appropriate actions could support the system to retake its original operational performance. This paper applies unsupervised machine learning techniques to identify operating patterns based on the power plant’s historical data which leads to the identification of appropriate steam generator efficiency conditions. The selected operational variables are evaluated in respect to their impact on the system performance, quantified by the Variable Importance Index. That metric is proposed to identify the variables among a much wide set of monitored data whose variation impacts the overall power plant operation, and should be controlled with more attention. Principal Component Analysis (PCA) and k-means++ clustering techniques are used to identify suitable operational conditions from a one-year-long data set with 27 recorded variables from a steam generator of a 360MW thermal power plant. The adequate number of clusters is identified by the average Silhouette coefficient and the Variable Importance Index sorts nine variables as the most relevant ones, to finally group recommended settings to achieve the target conditions. Results show performance gains in respect to the average historical values of 73.5% and the lowest efficiency condition records of 68%, to the target steam generator efficiency of 76%.application/pdfengEnergy and AI. Oxford. Vol. 5 (2021), Art.100084Usina termelétricaClusterAnálise de componente principalThermal power plant performance enhancementOperating patterns identificationK-means clusteringPrincipal component analysisUnsupervised machine learningIncreasing power plant efficiency with clustering methods and Variable Importance Index assessmentEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001132625.pdf.txt001132625.pdf.txtExtracted Texttext/plain41064http://www.lume.ufrgs.br/bitstream/10183/232126/2/001132625.pdf.txt9fc4e97cfc06b9a32edbb14a7fedb963MD52ORIGINAL001132625.pdfTexto completo (inglês)application/pdf1594262http://www.lume.ufrgs.br/bitstream/10183/232126/1/001132625.pdf36a49442ea8164c2da5d76511f65dec5MD5110183/2321262021-12-06 05:33:34.089652oai:www.lume.ufrgs.br:10183/232126Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2021-12-06T07:33:34Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Increasing power plant efficiency with clustering methods and Variable Importance Index assessment |
title |
Increasing power plant efficiency with clustering methods and Variable Importance Index assessment |
spellingShingle |
Increasing power plant efficiency with clustering methods and Variable Importance Index assessment Duarte, Jéssica Usina termelétrica Cluster Análise de componente principal Thermal power plant performance enhancement Operating patterns identification K-means clustering Principal component analysis Unsupervised machine learning |
title_short |
Increasing power plant efficiency with clustering methods and Variable Importance Index assessment |
title_full |
Increasing power plant efficiency with clustering methods and Variable Importance Index assessment |
title_fullStr |
Increasing power plant efficiency with clustering methods and Variable Importance Index assessment |
title_full_unstemmed |
Increasing power plant efficiency with clustering methods and Variable Importance Index assessment |
title_sort |
Increasing power plant efficiency with clustering methods and Variable Importance Index assessment |
author |
Duarte, Jéssica |
author_facet |
Duarte, Jéssica Vieira, Lara Werncke Marques, Augusto Delavald Schneider, Paulo Smith Pumi, Guilherme Prass, Taiane Schaedler |
author_role |
author |
author2 |
Vieira, Lara Werncke Marques, Augusto Delavald Schneider, Paulo Smith Pumi, Guilherme Prass, Taiane Schaedler |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Duarte, Jéssica Vieira, Lara Werncke Marques, Augusto Delavald Schneider, Paulo Smith Pumi, Guilherme Prass, Taiane Schaedler |
dc.subject.por.fl_str_mv |
Usina termelétrica Cluster Análise de componente principal |
topic |
Usina termelétrica Cluster Análise de componente principal Thermal power plant performance enhancement Operating patterns identification K-means clustering Principal component analysis Unsupervised machine learning |
dc.subject.eng.fl_str_mv |
Thermal power plant performance enhancement Operating patterns identification K-means clustering Principal component analysis Unsupervised machine learning |
description |
Power plant performance can decrease along with its life span, and move away from the design and commissioning targets. Maintenance issues, operational practices, market restrictions, and financial objectives may lead to that behavior, and the knowledge of appropriate actions could support the system to retake its original operational performance. This paper applies unsupervised machine learning techniques to identify operating patterns based on the power plant’s historical data which leads to the identification of appropriate steam generator efficiency conditions. The selected operational variables are evaluated in respect to their impact on the system performance, quantified by the Variable Importance Index. That metric is proposed to identify the variables among a much wide set of monitored data whose variation impacts the overall power plant operation, and should be controlled with more attention. Principal Component Analysis (PCA) and k-means++ clustering techniques are used to identify suitable operational conditions from a one-year-long data set with 27 recorded variables from a steam generator of a 360MW thermal power plant. The adequate number of clusters is identified by the average Silhouette coefficient and the Variable Importance Index sorts nine variables as the most relevant ones, to finally group recommended settings to achieve the target conditions. Results show performance gains in respect to the average historical values of 73.5% and the lowest efficiency condition records of 68%, to the target steam generator efficiency of 76%. |
publishDate |
2021 |
dc.date.accessioned.fl_str_mv |
2021-11-25T04:35:52Z |
dc.date.issued.fl_str_mv |
2021 |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/232126 |
dc.identifier.issn.pt_BR.fl_str_mv |
2666-5468 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001132625 |
identifier_str_mv |
2666-5468 001132625 |
url |
http://hdl.handle.net/10183/232126 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Energy and AI. Oxford. Vol. 5 (2021), Art.100084 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/232126/2/001132625.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/232126/1/001132625.pdf |
bitstream.checksum.fl_str_mv |
9fc4e97cfc06b9a32edbb14a7fedb963 36a49442ea8164c2da5d76511f65dec5 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801225043414351872 |