2026-04-26T22:07:27Zhttps://uvadoc.uva.es/oai/request

oai:uvadoc.uva.es:10324/578232022-12-19T20:00:38Zcom_10324_966com_10324_952com_10324_894col_10324_967

Saludes Rodil, Sergio Baeyens Lázaro, Enrique Rodríguez Juan, Carlos 2022-12-19T10:41:37Z 2022-12-19T10:41:37Z 2015 Sensors, 2015, vol. 18, n. 5, p. 10100-10117 1424-8220 https://uvadoc.uva.es/handle/10324/57823 10.3390/s150510100 10100 5 10117 Sensors 15 1424-8220 Producción Científica 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. Ministerio de Economía y Competitividad through the INNPACTO program (project IPT–2012–0755–420000) application/pdf eng MDPI info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/4.0/ © 2015 The Author(s) Atribución 4.0 Internacional Dynamic time warping Cluster analysis Modified Fourier descriptors Eddy current inspection 33 Ciencias Tecnológicas Unsupervised classification of surface defects in wire rod production obtained by Eddy current sensors info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://www.mdpi.com/1424-8220/15/5/10100 SI