Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach

Detalhes bibliográficos
Autor(a) principal: Junior, Pedro [UNESP]
Data de Publicação: 2018
Outros Autores: D’Addona, Doriana M., Aguiar, Paulo [UNESP], Teti, Roberto
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.3390/s18124453
http://hdl.handle.net/11449/188509
Resumo: This paper presents an approach for impedance-based sensor monitoring of dressing tool condition in grinding by using the electromechanical impedance (EMI) technique. This method was introduced in Part 1 of this work and the purpose of this paper (Part 2) is to achieve an optimal selection of the excitation frequency band based on multi-layer neural networks (MLNN) and k-nearest neighbor classifier (k-NN). The proposed approach was validated on the basis of dressing tool condition information obtained from the monitoring of experimental dressing tests with two industrial stationary single-point dressing tools. Moreover, representative damage indices for diverse damage cases, obtained from impedance signatures at different frequency bands, were taken into account for MLNN data processing. The intelligent system was able to select the most damage-sensitive features based on optimal frequency band. The best models showed a general overall error lower than 2%, thus robustly contributing to the efficient automation of grinding and dressing operations. The promising results of this study foster the EMI-based sensor monitoring approach to fault diagnosis in dressing operations and its effective implementation for industrial grinding process automation.
id UNSP_64b7c41de29be60da3e2ce2c4bab9c08
oai_identifier_str oai:repositorio.unesp.br:11449/188509
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approachDressingElectromechanical impedanceGrinding processk-NNMLNNNeural networksPiezoelectric sensorsSensor monitoringTool condition monitoringThis paper presents an approach for impedance-based sensor monitoring of dressing tool condition in grinding by using the electromechanical impedance (EMI) technique. This method was introduced in Part 1 of this work and the purpose of this paper (Part 2) is to achieve an optimal selection of the excitation frequency band based on multi-layer neural networks (MLNN) and k-nearest neighbor classifier (k-NN). The proposed approach was validated on the basis of dressing tool condition information obtained from the monitoring of experimental dressing tests with two industrial stationary single-point dressing tools. Moreover, representative damage indices for diverse damage cases, obtained from impedance signatures at different frequency bands, were taken into account for MLNN data processing. The intelligent system was able to select the most damage-sensitive features based on optimal frequency band. The best models showed a general overall error lower than 2%, thus robustly contributing to the efficient automation of grinding and dressing operations. The promising results of this study foster the EMI-based sensor monitoring approach to fault diagnosis in dressing operations and its effective implementation for industrial grinding process automation.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Faculdade de Engenharia UNESP-University Estadual Paulista Bauru Departamento de Engenharia Elétrica, Av. Eng. Luiz Edmundo C. Coube 14-01Dipartimento di Ingegneria Chimica Università degli Studi di Napoli Federico II dei Materiali e della Produzione IndustrialeFaculdade de Engenharia UNESP-University Estadual Paulista Bauru Departamento de Engenharia Elétrica, Av. Eng. Luiz Edmundo C. Coube 14-01FAPESP: 2016/02831-5FAPESP: 2017/16921-9Universidade Estadual Paulista (Unesp)dei Materiali e della Produzione IndustrialeJunior, Pedro [UNESP]D’Addona, Doriana M.Aguiar, Paulo [UNESP]Teti, Roberto2019-10-06T16:10:28Z2019-10-06T16:10:28Z2018-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/s18124453Sensors (Switzerland), v. 18, n. 12, 2018.1424-8220http://hdl.handle.net/11449/18850910.3390/s181244532-s2.0-85058646437Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengSensors (Switzerland)info:eu-repo/semantics/openAccess2024-06-28T13:34:24Zoai:repositorio.unesp.br:11449/188509Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T20:34:40.395769Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach
title Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach
spellingShingle Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach
Junior, Pedro [UNESP]
Dressing
Electromechanical impedance
Grinding process
k-NN
MLNN
Neural networks
Piezoelectric sensors
Sensor monitoring
Tool condition monitoring
title_short Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach
title_full Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach
title_fullStr Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach
title_full_unstemmed Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach
title_sort Dressing tool condition monitoring through impedance-based sensors: Part 2—neural networks and K-nearest neighbor classifier approach
author Junior, Pedro [UNESP]
author_facet Junior, Pedro [UNESP]
D’Addona, Doriana M.
Aguiar, Paulo [UNESP]
Teti, Roberto
author_role author
author2 D’Addona, Doriana M.
Aguiar, Paulo [UNESP]
Teti, Roberto
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dei Materiali e della Produzione Industriale
dc.contributor.author.fl_str_mv Junior, Pedro [UNESP]
D’Addona, Doriana M.
Aguiar, Paulo [UNESP]
Teti, Roberto
dc.subject.por.fl_str_mv Dressing
Electromechanical impedance
Grinding process
k-NN
MLNN
Neural networks
Piezoelectric sensors
Sensor monitoring
Tool condition monitoring
topic Dressing
Electromechanical impedance
Grinding process
k-NN
MLNN
Neural networks
Piezoelectric sensors
Sensor monitoring
Tool condition monitoring
description This paper presents an approach for impedance-based sensor monitoring of dressing tool condition in grinding by using the electromechanical impedance (EMI) technique. This method was introduced in Part 1 of this work and the purpose of this paper (Part 2) is to achieve an optimal selection of the excitation frequency band based on multi-layer neural networks (MLNN) and k-nearest neighbor classifier (k-NN). The proposed approach was validated on the basis of dressing tool condition information obtained from the monitoring of experimental dressing tests with two industrial stationary single-point dressing tools. Moreover, representative damage indices for diverse damage cases, obtained from impedance signatures at different frequency bands, were taken into account for MLNN data processing. The intelligent system was able to select the most damage-sensitive features based on optimal frequency band. The best models showed a general overall error lower than 2%, thus robustly contributing to the efficient automation of grinding and dressing operations. The promising results of this study foster the EMI-based sensor monitoring approach to fault diagnosis in dressing operations and its effective implementation for industrial grinding process automation.
publishDate 2018
dc.date.none.fl_str_mv 2018-12-01
2019-10-06T16:10:28Z
2019-10-06T16:10:28Z
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/10.3390/s18124453
Sensors (Switzerland), v. 18, n. 12, 2018.
1424-8220
http://hdl.handle.net/11449/188509
10.3390/s18124453
2-s2.0-85058646437
url http://dx.doi.org/10.3390/s18124453
http://hdl.handle.net/11449/188509
identifier_str_mv Sensors (Switzerland), v. 18, n. 12, 2018.
1424-8220
10.3390/s18124453
2-s2.0-85058646437
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Sensors (Switzerland)
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
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_ 1808129223000326144