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.


Cameras used in top surface inspection.
© Copyright Policy
Related In: Results  -  Collection

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

f2-sensors-12-10788: Cameras used in top surface inspection.

Mentions: There are several studies about the development of vision-based sensor systems for industrial use, such as inspection tasks [2] or defect detection tasks in many different fields, like satin glass [3], welds [4], bearings [5] or ship hulls [6]. Depending on each case, the design of the vision system (cameras, lenses, lighting, etc.) is different. It is critical to build the most suitable vision system in each case in order to obtain satisfactory results [7]. In the particular case studied here, the sensing tasks are carried out using several cameras, which take images of both surfaces of the material to be inspected. The areas inspected by the cameras are overlapped in order to ensure complete coverage, as shown in Figure 2. These images are used by a software system to perform other typical tasks of these systems, namely fault detection, characterization of defects, feature extraction and classification [8]. Using an inspection system that performs these tasks, the technicians responsible for quality control can obtain information about the position and class (or type) of each defect present in the produced material. Some of these systems are able to determine whether a surface defect is a roll mark or not, based on its features. Thus, a technician can find out that at least one roll is defective. In production lines in which only one roll can generate defects, this information may be sufficient. However, in more complicated cases, where several rolls can be the source of such defects, more information about the periodical defects generated is required to determine which roll must be replaced.


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

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

Cameras used in top surface inspection.
© Copyright Policy
Related In: Results  -  Collection

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

f2-sensors-12-10788: Cameras used in top surface inspection.
Mentions: There are several studies about the development of vision-based sensor systems for industrial use, such as inspection tasks [2] or defect detection tasks in many different fields, like satin glass [3], welds [4], bearings [5] or ship hulls [6]. Depending on each case, the design of the vision system (cameras, lenses, lighting, etc.) is different. It is critical to build the most suitable vision system in each case in order to obtain satisfactory results [7]. In the particular case studied here, the sensing tasks are carried out using several cameras, which take images of both surfaces of the material to be inspected. The areas inspected by the cameras are overlapped in order to ensure complete coverage, as shown in Figure 2. These images are used by a software system to perform other typical tasks of these systems, namely fault detection, characterization of defects, feature extraction and classification [8]. Using an inspection system that performs these tasks, the technicians responsible for quality control can obtain information about the position and class (or type) of each defect present in the produced material. Some of these systems are able to determine whether a surface defect is a roll mark or not, based on its features. Thus, a technician can find out that at least one roll is defective. In production lines in which only one roll can generate defects, this information may be sufficient. However, in more complicated cases, where several rolls can be the source of such defects, more information about the periodical defects generated is required to determine which roll must be replaced.

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.