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

Sensors

Sergio Saludes-Rodil²  Enrique Baeyens³  Carlos P. Rodríguez-Juan¹ 

[1] ISEND S.A., Parque Tecnológico de Boecillo, Luis Proust 10, 47151 Boecillo, Valladolid, Spain; E-Mail:;Centro Tecnológico CARTIF, Parque Tecnológico de Boecillo 205, 47151 Boecillo, Valladolid, Spain;Instituto de las Tecnologías Avanzadas de la Producción, Universidad de Valladolid, Paseo del cauce 59, 47011 Valladolid, Spain; E-Mail:

关键词: dynamic time warping;    cluster analysis;    modified Fourier descriptors;    unsupervised classification;    wire rod manufacturing;    eddy current inspection;    nondestructive testing;   

DOI  :  10.3390/s150510100

来源: mdpi

【 摘 要 】

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.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.