K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Brazilian Journal of Chemical Engineering |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322019000100409 |
Resumo: | ABSTRACT Y-rank can present faults when dealing with non-linear problems. A methodology is proposed to improve the selection of data in situations where y-rank is fragile. The proposed alternative, called k-rank, consists of splitting the data set into clusters using the k-means algorithm, and then apply y-rank to the generated clusters. Models were calibrated and tested with subsets split by y-rank and k-rank. For the Heating Tank case study, in 59% of the simulations, models calibrated with k-rank subsets achieved better results. For the Propylene / Propane Separation Unit case, when dealing with a small number of sample points, the y-rank models had errors almost three times higher than the k-rank models for the test subset, meaning that the fitted model could not deal properly with new unseen data. The proposed methodology was successful in splitting the data, especially in cases with a limited amount of samples. |
id |
ABEQ-1_718a9a5ffc80531e0b8e2e49efaca755 |
---|---|
oai_identifier_str |
oai:scielo:S0104-66322019000100409 |
network_acronym_str |
ABEQ-1 |
network_name_str |
Brazilian Journal of Chemical Engineering |
repository_id_str |
|
spelling |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEMSplitting dataK-meansSystematic samplingMultiple solutionsABSTRACT Y-rank can present faults when dealing with non-linear problems. A methodology is proposed to improve the selection of data in situations where y-rank is fragile. The proposed alternative, called k-rank, consists of splitting the data set into clusters using the k-means algorithm, and then apply y-rank to the generated clusters. Models were calibrated and tested with subsets split by y-rank and k-rank. For the Heating Tank case study, in 59% of the simulations, models calibrated with k-rank subsets achieved better results. For the Propylene / Propane Separation Unit case, when dealing with a small number of sample points, the y-rank models had errors almost three times higher than the k-rank models for the test subset, meaning that the fitted model could not deal properly with new unseen data. The proposed methodology was successful in splitting the data, especially in cases with a limited amount of samples.Brazilian Society of Chemical Engineering2019-03-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322019000100409Brazilian Journal of Chemical Engineering v.36 n.1 2019reponame:Brazilian Journal of Chemical Engineeringinstname:Associação Brasileira de Engenharia Química (ABEQ)instacron:ABEQ10.1590/0104-6632.20190361s20170455info:eu-repo/semantics/openAccessSantos,Pedro V. J. L.Ranzan,LucasFarenzena,MarceloTrierweiler,Jorge O.eng2019-07-10T00:00:00Zoai:scielo:S0104-66322019000100409Revistahttps://www.scielo.br/j/bjce/https://old.scielo.br/oai/scielo-oai.phprgiudici@usp.br||rgiudici@usp.br1678-43830104-6632opendoar:2019-07-10T00:00Brazilian Journal of Chemical Engineering - Associação Brasileira de Engenharia Química (ABEQ)false |
dc.title.none.fl_str_mv |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM |
title |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM |
spellingShingle |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM Santos,Pedro V. J. L. Splitting data K-means Systematic sampling Multiple solutions |
title_short |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM |
title_full |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM |
title_fullStr |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM |
title_full_unstemmed |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM |
title_sort |
K-RANK: AN EVOLUTION OF Y-RANK FOR MULTIPLE SOLUTIONS PROBLEM |
author |
Santos,Pedro V. J. L. |
author_facet |
Santos,Pedro V. J. L. Ranzan,Lucas Farenzena,Marcelo Trierweiler,Jorge O. |
author_role |
author |
author2 |
Ranzan,Lucas Farenzena,Marcelo Trierweiler,Jorge O. |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Santos,Pedro V. J. L. Ranzan,Lucas Farenzena,Marcelo Trierweiler,Jorge O. |
dc.subject.por.fl_str_mv |
Splitting data K-means Systematic sampling Multiple solutions |
topic |
Splitting data K-means Systematic sampling Multiple solutions |
description |
ABSTRACT Y-rank can present faults when dealing with non-linear problems. A methodology is proposed to improve the selection of data in situations where y-rank is fragile. The proposed alternative, called k-rank, consists of splitting the data set into clusters using the k-means algorithm, and then apply y-rank to the generated clusters. Models were calibrated and tested with subsets split by y-rank and k-rank. For the Heating Tank case study, in 59% of the simulations, models calibrated with k-rank subsets achieved better results. For the Propylene / Propane Separation Unit case, when dealing with a small number of sample points, the y-rank models had errors almost three times higher than the k-rank models for the test subset, meaning that the fitted model could not deal properly with new unseen data. The proposed methodology was successful in splitting the data, especially in cases with a limited amount of samples. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-03-01 |
dc.type.driver.fl_str_mv |
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://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322019000100409 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322019000100409 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/0104-6632.20190361s20170455 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Brazilian Society of Chemical Engineering |
publisher.none.fl_str_mv |
Brazilian Society of Chemical Engineering |
dc.source.none.fl_str_mv |
Brazilian Journal of Chemical Engineering v.36 n.1 2019 reponame:Brazilian Journal of Chemical Engineering instname:Associação Brasileira de Engenharia Química (ABEQ) instacron:ABEQ |
instname_str |
Associação Brasileira de Engenharia Química (ABEQ) |
instacron_str |
ABEQ |
institution |
ABEQ |
reponame_str |
Brazilian Journal of Chemical Engineering |
collection |
Brazilian Journal of Chemical Engineering |
repository.name.fl_str_mv |
Brazilian Journal of Chemical Engineering - Associação Brasileira de Engenharia Química (ABEQ) |
repository.mail.fl_str_mv |
rgiudici@usp.br||rgiudici@usp.br |
_version_ |
1754213176349556736 |