Neural tool condition estimation in the grinding of advanced ceramics

Detalhes bibliográficos
Autor(a) principal: Nakai, M. E. [UNESP]
Data de Publicação: 2015
Outros Autores: Junior, H. G. [UNESP], Aguiar, P. R. [UNESP], Bianchi, E. C. [UNESP], Spatti, D. H. [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1109/TLA.2015.7040629
http://hdl.handle.net/11449/171785
Resumo: Ceramic parts are increasingly replacing metal parts due to their excellent physical, chemical and mechanical properties, however they also make them difficult to manufacture by traditional machining methods. The developments carried out in this work are used to estimate tool wear during the grinding of advanced ceramics. The learning process was fed with data collected from a surface grinding machine with tangential diamond wheel and alumina ceramic test specimens, in three cutting configurations: with depths of cut of 120μm, 70μm and 20μm. The grinding wheel speed was 35m/s and the table speed 2.3m/s. Four neural models were evaluated, namely: Multilayer Perceptron, Radial Basis Function, Generalized Regression Neural Networks and the Adaptive Neuro-Fuzzy Inference System. The models' performance evaluation routines were executed automatically, testing all the possible combinations of inputs, number of neurons, number of layers, and spreading. The computational results reveal that the neural models were highly successful in estimating tool wear, since the errors were lower than 4%.
id UNSP_3ddb2d8a7e9f6c891619ea263f962e23
oai_identifier_str oai:repositorio.unesp.br:11449/171785
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Neural tool condition estimation in the grinding of advanced ceramicsadvanced ceramicsANFISCeramic grindingGRNNRBFCeramic parts are increasingly replacing metal parts due to their excellent physical, chemical and mechanical properties, however they also make them difficult to manufacture by traditional machining methods. The developments carried out in this work are used to estimate tool wear during the grinding of advanced ceramics. The learning process was fed with data collected from a surface grinding machine with tangential diamond wheel and alumina ceramic test specimens, in three cutting configurations: with depths of cut of 120μm, 70μm and 20μm. The grinding wheel speed was 35m/s and the table speed 2.3m/s. Four neural models were evaluated, namely: Multilayer Perceptron, Radial Basis Function, Generalized Regression Neural Networks and the Adaptive Neuro-Fuzzy Inference System. The models' performance evaluation routines were executed automatically, testing all the possible combinations of inputs, number of neurons, number of layers, and spreading. The computational results reveal that the neural models were highly successful in estimating tool wear, since the errors were lower than 4%.Departamento de Engenharia Elétrica da Faculdade de Engenharia de Bauru, UNESPDepartamento de Engenharia Elétrica da Faculdade de Engenharia de Bauru, UNESPUniversidade Estadual Paulista (Unesp)Nakai, M. E. [UNESP]Junior, H. G. [UNESP]Aguiar, P. R. [UNESP]Bianchi, E. C. [UNESP]Spatti, D. H. [UNESP]2018-12-11T16:57:09Z2018-12-11T16:57:09Z2015-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article62-68application/pdfhttp://dx.doi.org/10.1109/TLA.2015.7040629IEEE Latin America Transactions, v. 13, n. 1, p. 62-68, 2015.1548-0992http://hdl.handle.net/11449/17178510.1109/TLA.2015.70406292-s2.0-849231991082-s2.0-84923199108.pdf14554003096600810000-0002-9934-4465Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIEEE Latin America Transactions0,253info:eu-repo/semantics/openAccess2024-06-28T13:34:08Zoai:repositorio.unesp.br:11449/171785Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T13:45:18.721401Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Neural tool condition estimation in the grinding of advanced ceramics
title Neural tool condition estimation in the grinding of advanced ceramics
spellingShingle Neural tool condition estimation in the grinding of advanced ceramics
Nakai, M. E. [UNESP]
advanced ceramics
ANFIS
Ceramic grinding
GRNN
RBF
title_short Neural tool condition estimation in the grinding of advanced ceramics
title_full Neural tool condition estimation in the grinding of advanced ceramics
title_fullStr Neural tool condition estimation in the grinding of advanced ceramics
title_full_unstemmed Neural tool condition estimation in the grinding of advanced ceramics
title_sort Neural tool condition estimation in the grinding of advanced ceramics
author Nakai, M. E. [UNESP]
author_facet Nakai, M. E. [UNESP]
Junior, H. G. [UNESP]
Aguiar, P. R. [UNESP]
Bianchi, E. C. [UNESP]
Spatti, D. H. [UNESP]
author_role author
author2 Junior, H. G. [UNESP]
Aguiar, P. R. [UNESP]
Bianchi, E. C. [UNESP]
Spatti, D. H. [UNESP]
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Nakai, M. E. [UNESP]
Junior, H. G. [UNESP]
Aguiar, P. R. [UNESP]
Bianchi, E. C. [UNESP]
Spatti, D. H. [UNESP]
dc.subject.por.fl_str_mv advanced ceramics
ANFIS
Ceramic grinding
GRNN
RBF
topic advanced ceramics
ANFIS
Ceramic grinding
GRNN
RBF
description Ceramic parts are increasingly replacing metal parts due to their excellent physical, chemical and mechanical properties, however they also make them difficult to manufacture by traditional machining methods. The developments carried out in this work are used to estimate tool wear during the grinding of advanced ceramics. The learning process was fed with data collected from a surface grinding machine with tangential diamond wheel and alumina ceramic test specimens, in three cutting configurations: with depths of cut of 120μm, 70μm and 20μm. The grinding wheel speed was 35m/s and the table speed 2.3m/s. Four neural models were evaluated, namely: Multilayer Perceptron, Radial Basis Function, Generalized Regression Neural Networks and the Adaptive Neuro-Fuzzy Inference System. The models' performance evaluation routines were executed automatically, testing all the possible combinations of inputs, number of neurons, number of layers, and spreading. The computational results reveal that the neural models were highly successful in estimating tool wear, since the errors were lower than 4%.
publishDate 2015
dc.date.none.fl_str_mv 2015-01-01
2018-12-11T16:57:09Z
2018-12-11T16:57:09Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1109/TLA.2015.7040629
IEEE Latin America Transactions, v. 13, n. 1, p. 62-68, 2015.
1548-0992
http://hdl.handle.net/11449/171785
10.1109/TLA.2015.7040629
2-s2.0-84923199108
2-s2.0-84923199108.pdf
1455400309660081
0000-0002-9934-4465
url http://dx.doi.org/10.1109/TLA.2015.7040629
http://hdl.handle.net/11449/171785
identifier_str_mv IEEE Latin America Transactions, v. 13, n. 1, p. 62-68, 2015.
1548-0992
10.1109/TLA.2015.7040629
2-s2.0-84923199108
2-s2.0-84923199108.pdf
1455400309660081
0000-0002-9934-4465
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv IEEE Latin America Transactions
0,253
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 62-68
application/pdf
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808128272004808704