USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Revista Árvore (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-67622016000500949 |
Resumo: | ABSTRACT This study aims to assess Artificial Neural Networks (ANN) in predicting particleboard quality based on its physical and mechanical properties. Particleboards were manufactured using eucalyptus (Eucalyptus grandis) and bonded with urea-formaldehyde and phenol-formaldehyde resins. To characterize quality, physical (density and water absorption and thickness swelling after 24-hour immersion) and mechanical (static bending strength and internal bond) properties were assessed. For predictions, adhesive type and particleboard density were adopted as ANN input variables. Networks of multilayer Perceptron (MLP) were adopted, training 100 networks for each assessed parameter. The results pointed out ANN as effective in predicting quality parameters of particleboards. With this technique, all the assessed properties presented models with adjustments higher than 0.90. |
id |
SIF-1_45e757066abfda91c7d2fb3283da21cf |
---|---|
oai_identifier_str |
oai:scielo:S0100-67622016000500949 |
network_acronym_str |
SIF-1 |
network_name_str |
Revista Árvore (Online) |
repository_id_str |
|
spelling |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERSArtificial intelligenceParticleboardsPhysico-mechanical propertiesABSTRACT This study aims to assess Artificial Neural Networks (ANN) in predicting particleboard quality based on its physical and mechanical properties. Particleboards were manufactured using eucalyptus (Eucalyptus grandis) and bonded with urea-formaldehyde and phenol-formaldehyde resins. To characterize quality, physical (density and water absorption and thickness swelling after 24-hour immersion) and mechanical (static bending strength and internal bond) properties were assessed. For predictions, adhesive type and particleboard density were adopted as ANN input variables. Networks of multilayer Perceptron (MLP) were adopted, training 100 networks for each assessed parameter. The results pointed out ANN as effective in predicting quality parameters of particleboards. With this technique, all the assessed properties presented models with adjustments higher than 0.90.Sociedade de Investigações Florestais2016-10-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-67622016000500949Revista Árvore v.40 n.5 2016reponame:Revista Árvore (Online)instname:Universidade Federal de Viçosa (UFV)instacron:SIF10.1590/0100-67622016000500019info:eu-repo/semantics/openAccessMelo,Rafael Rodolfo deMiguel,Eder Pereiraeng2016-11-30T00:00:00Zoai:scielo:S0100-67622016000500949Revistahttp://www.scielo.br/revistas/rarv/iaboutj.htmPUBhttps://old.scielo.br/oai/scielo-oai.php||r.arvore@ufv.br1806-90880100-6762opendoar:2016-11-30T00:00Revista Árvore (Online) - Universidade Federal de Viçosa (UFV)false |
dc.title.none.fl_str_mv |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS |
title |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS |
spellingShingle |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS Melo,Rafael Rodolfo de Artificial intelligence Particleboards Physico-mechanical properties |
title_short |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS |
title_full |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS |
title_fullStr |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS |
title_full_unstemmed |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS |
title_sort |
USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS |
author |
Melo,Rafael Rodolfo de |
author_facet |
Melo,Rafael Rodolfo de Miguel,Eder Pereira |
author_role |
author |
author2 |
Miguel,Eder Pereira |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Melo,Rafael Rodolfo de Miguel,Eder Pereira |
dc.subject.por.fl_str_mv |
Artificial intelligence Particleboards Physico-mechanical properties |
topic |
Artificial intelligence Particleboards Physico-mechanical properties |
description |
ABSTRACT This study aims to assess Artificial Neural Networks (ANN) in predicting particleboard quality based on its physical and mechanical properties. Particleboards were manufactured using eucalyptus (Eucalyptus grandis) and bonded with urea-formaldehyde and phenol-formaldehyde resins. To characterize quality, physical (density and water absorption and thickness swelling after 24-hour immersion) and mechanical (static bending strength and internal bond) properties were assessed. For predictions, adhesive type and particleboard density were adopted as ANN input variables. Networks of multilayer Perceptron (MLP) were adopted, training 100 networks for each assessed parameter. The results pointed out ANN as effective in predicting quality parameters of particleboards. With this technique, all the assessed properties presented models with adjustments higher than 0.90. |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016-10-01 |
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=S0100-67622016000500949 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-67622016000500949 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/0100-67622016000500019 |
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 |
Sociedade de Investigações Florestais |
publisher.none.fl_str_mv |
Sociedade de Investigações Florestais |
dc.source.none.fl_str_mv |
Revista Árvore v.40 n.5 2016 reponame:Revista Árvore (Online) instname:Universidade Federal de Viçosa (UFV) instacron:SIF |
instname_str |
Universidade Federal de Viçosa (UFV) |
instacron_str |
SIF |
institution |
SIF |
reponame_str |
Revista Árvore (Online) |
collection |
Revista Árvore (Online) |
repository.name.fl_str_mv |
Revista Árvore (Online) - Universidade Federal de Viçosa (UFV) |
repository.mail.fl_str_mv |
||r.arvore@ufv.br |
_version_ |
1750318002152144896 |