Limits...
Vision-based sensor for early detection of periodical defects in web materials.

Bulnes FG, Usamentiaga R, García DF, Molleda J - Sensors (Basel) (2012)

Bottom Line: For this reason, it is necessary to have a system that can detect these situations as soon as possible.A total of 36 strips produced in ArcelorMittal Avilés factory were used for this purpose, 18 to determine the optimal configuration of the proposed sensor using a full-factorial experimental design and the other 18 to verify the validity of the results.Next, they were compared with those provided by a commercial system used worldwide, showing a clear improvement.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science, University of Oviedo, Campus de Viesques, Gijón 33204, Spain. bulnes@uniovi.es

ABSTRACT
During the production of web materials such as plastic, textiles or metal, where there are rolls involved in the production process, periodically generated defects may occur. If one of these rolls has some kind of flaw, it can generate a defect on the material surface each time it completes a full turn. This can cause the generation of a large number of surface defects, greatly degrading the product quality. For this reason, it is necessary to have a system that can detect these situations as soon as possible. This paper presents a vision-based sensor for the early detection of this kind of defects. It can be adapted to be used in the inspection of any web material, even when the input data are very noisy. To assess its performance, the sensor system was used to detect periodical defects in hot steel strips. A total of 36 strips produced in ArcelorMittal Avilés factory were used for this purpose, 18 to determine the optimal configuration of the proposed sensor using a full-factorial experimental design and the other 18 to verify the validity of the results. Next, they were compared with those provided by a commercial system used worldwide, showing a clear improvement.

No MeSH data available.


Clustering algorithm.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3472857&req=5

f5-sensors-12-10788: Clustering algorithm.

Mentions: The amount of time available for detection may be limited. Thus, the search should examine the transversal coordinates most likely to have periodical defects first (the position of an individual defect is defined by its longitudinal and transversal coordinates, but the position of a periodical defect is defined by its transversal position only). To do this, a histogram representing the number of individual defects located at each transversal position is calculated, as shown in Figure 5. The transversal position containing the maximum of the histogram is chosen to start the search. In order to start a search at that transversal position, a periodical defect is created. Its tuple is initialized including an individual defect located at the transversal position in which periodical defects are being sought (any of them). In addition, before starting the search, the theoretical period length (tpl) of the periodical defects to be detected should be established (the theoretical period length of a roll could be defined as the period of the periodical defects generated by it). Generally, the theoretical period length of a roll is its perimeter, but this depends on the production process of each material. If multiple rolls are used in the production process, a search should be performed for each one of them (using their theoretical period lengths). Thus, the initial values of the features of the periodical defect are those shown in Equation (10).


Vision-based sensor for early detection of periodical defects in web materials.

Bulnes FG, Usamentiaga R, García DF, Molleda J - Sensors (Basel) (2012)

Clustering algorithm.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3472857&req=5

f5-sensors-12-10788: Clustering algorithm.
Mentions: The amount of time available for detection may be limited. Thus, the search should examine the transversal coordinates most likely to have periodical defects first (the position of an individual defect is defined by its longitudinal and transversal coordinates, but the position of a periodical defect is defined by its transversal position only). To do this, a histogram representing the number of individual defects located at each transversal position is calculated, as shown in Figure 5. The transversal position containing the maximum of the histogram is chosen to start the search. In order to start a search at that transversal position, a periodical defect is created. Its tuple is initialized including an individual defect located at the transversal position in which periodical defects are being sought (any of them). In addition, before starting the search, the theoretical period length (tpl) of the periodical defects to be detected should be established (the theoretical period length of a roll could be defined as the period of the periodical defects generated by it). Generally, the theoretical period length of a roll is its perimeter, but this depends on the production process of each material. If multiple rolls are used in the production process, a search should be performed for each one of them (using their theoretical period lengths). Thus, the initial values of the features of the periodical defect are those shown in Equation (10).

Bottom Line: For this reason, it is necessary to have a system that can detect these situations as soon as possible.A total of 36 strips produced in ArcelorMittal Avilés factory were used for this purpose, 18 to determine the optimal configuration of the proposed sensor using a full-factorial experimental design and the other 18 to verify the validity of the results.Next, they were compared with those provided by a commercial system used worldwide, showing a clear improvement.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science, University of Oviedo, Campus de Viesques, Gijón 33204, Spain. bulnes@uniovi.es

ABSTRACT
During the production of web materials such as plastic, textiles or metal, where there are rolls involved in the production process, periodically generated defects may occur. If one of these rolls has some kind of flaw, it can generate a defect on the material surface each time it completes a full turn. This can cause the generation of a large number of surface defects, greatly degrading the product quality. For this reason, it is necessary to have a system that can detect these situations as soon as possible. This paper presents a vision-based sensor for the early detection of this kind of defects. It can be adapted to be used in the inspection of any web material, even when the input data are very noisy. To assess its performance, the sensor system was used to detect periodical defects in hot steel strips. A total of 36 strips produced in ArcelorMittal Avilés factory were used for this purpose, 18 to determine the optimal configuration of the proposed sensor using a full-factorial experimental design and the other 18 to verify the validity of the results. Next, they were compared with those provided by a commercial system used worldwide, showing a clear improvement.

No MeSH data available.