Limits...
Unsupervised classification of surface defects in wire rod production obtained by eddy current sensors.

Saludes-Rodil S, Baeyens E, Rodríguez-Juan CP - Sensors (Basel) (2015)

Bottom Line: 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.It is shown that it outperforms other classification alternatives, such as the modified Fourier descriptors.

View Article: PubMed Central - PubMed

Affiliation: Centro Tecnológico CARTIF, Parque Tecnológico de Boecillo 205, 47151 Boecillo, Valladolid, Spain. sersal@cartif.es.

ABSTRACT
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.

No MeSH data available.


Related in: MedlinePlus

Confusion matrix for MFD and ESOM-based clustering.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4482004&req=5

f5-sensors-15-10100: Confusion matrix for MFD and ESOM-based clustering.

Mentions: The confusion matrix shown in Figure 5 summarizes the results. Seven clusters have been found, but two of them are negligible, because they contain only one element. Defects in Classes A and B are mainly assigned to Clusters C1 and C2, respectively. Defects in Class C are assigned to Cluster C4. Most of the defects in Class D are also assigned to Cluster C4. Only five defects from this class are assigned to Cluster C5. The value of the silhouette index is = 0.348.


Unsupervised classification of surface defects in wire rod production obtained by eddy current sensors.

Saludes-Rodil S, Baeyens E, Rodríguez-Juan CP - Sensors (Basel) (2015)

Confusion matrix for MFD and ESOM-based clustering.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4482004&req=5

f5-sensors-15-10100: Confusion matrix for MFD and ESOM-based clustering.
Mentions: The confusion matrix shown in Figure 5 summarizes the results. Seven clusters have been found, but two of them are negligible, because they contain only one element. Defects in Classes A and B are mainly assigned to Clusters C1 and C2, respectively. Defects in Class C are assigned to Cluster C4. Most of the defects in Class D are also assigned to Cluster C4. Only five defects from this class are assigned to Cluster C5. The value of the silhouette index is = 0.348.

Bottom Line: 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.It is shown that it outperforms other classification alternatives, such as the modified Fourier descriptors.

View Article: PubMed Central - PubMed

Affiliation: Centro Tecnológico CARTIF, Parque Tecnológico de Boecillo 205, 47151 Boecillo, Valladolid, Spain. sersal@cartif.es.

ABSTRACT
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.

No MeSH data available.


Related in: MedlinePlus