Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors

An unsupervised approach to classify surface defects in wire rod manufacturing is developed in this paper. The defects are extracted from an eddy current signal and classified using a clustering technique that uses the dynamic time warping distance as the dissimilarity measure. The new approach has...

Descripción completa

Detalles Bibliográficos
Autores principales: Saludes-Rodil, Sergio, Baeyens, Enrique, Rodríguez-Juan, Carlos P.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2015
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4482004/
https://www.ncbi.nlm.nih.gov/pubmed/25938201
http://dx.doi.org/10.3390/s150510100
_version_ 1782378365509959680
author Saludes-Rodil, Sergio
Baeyens, Enrique
Rodríguez-Juan, Carlos P.
author_facet Saludes-Rodil, Sergio
Baeyens, Enrique
Rodríguez-Juan, Carlos P.
author_sort Saludes-Rodil, Sergio
collection PubMed
description An unsupervised approach to classify surface defects in wire rod manufacturing is developed in this paper. The defects are extracted from an eddy current signal and classified using a clustering technique that uses the dynamic time warping distance as the dissimilarity measure. The new approach has been successfully tested using industrial data. It is shown that it outperforms other classification alternatives, such as the modified Fourier descriptors.
format Online
Article
Text
id pubmed-4482004
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-44820042015-06-29 Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors Saludes-Rodil, Sergio Baeyens, Enrique Rodríguez-Juan, Carlos P. Sensors (Basel) Article An unsupervised approach to classify surface defects in wire rod manufacturing is developed in this paper. The defects are extracted from an eddy current signal and classified using a clustering technique that uses the dynamic time warping distance as the dissimilarity measure. The new approach has been successfully tested using industrial data. It is shown that it outperforms other classification alternatives, such as the modified Fourier descriptors. MDPI 2015-04-29 /pmc/articles/PMC4482004/ /pubmed/25938201 http://dx.doi.org/10.3390/s150510100 Text en © 2015 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Saludes-Rodil, Sergio
Baeyens, Enrique
Rodríguez-Juan, Carlos P.
Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors
title Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors
title_full Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors
title_fullStr Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors
title_full_unstemmed Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors
title_short Unsupervised Classification of Surface Defects in Wire Rod Production Obtained by Eddy Current Sensors
title_sort unsupervised classification of surface defects in wire rod production obtained by eddy current sensors
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4482004/
https://www.ncbi.nlm.nih.gov/pubmed/25938201
http://dx.doi.org/10.3390/s150510100
work_keys_str_mv AT saludesrodilsergio unsupervisedclassificationofsurfacedefectsinwirerodproductionobtainedbyeddycurrentsensors
AT baeyensenrique unsupervisedclassificationofsurfacedefectsinwirerodproductionobtainedbyeddycurrentsensors
AT rodriguezjuancarlosp unsupervisedclassificationofsurfacedefectsinwirerodproductionobtainedbyeddycurrentsensors

Ejemplares similares