Vision-Based Sensor for Early Detection of Periodical Defects in Web Materials

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.

Automated Visual Defect Detection for Flat Steel Surface: A Survey

“…Based on the similarity among image pixels, clustering method is specialized in mining information implicitly existing in texture images, then defect detection can be achieved by the multiple-class defect classification. Real-time and anti-noise capability are always the basic requirements of industrial defect detection, Bulnes et al [24] detected the defects occurring periodically by clustering the characteristics (i.e., position, type) of each defect. This method can timely detect periodical defects even in noisy environment.…”

Research Progress of Visual Inspection Technology of Steel Products—A Review

“…Guo et al [61] used the Sobel gradient edge detection operator combined with the Fisher discriminant to detect defects on steel surfaces. Spatial filtering methods are also discussed in the literature [25,34,35,45,46,[62][63][64] for the defect detection of various steel products. For the optical properties of highly reflective surfaces of cold-rolled strip, Zhao et al [36] adopted a kind of homomorphic filtering algorithm based on a partial differential equation (PDE).…”

“…For the optical properties of highly reflective surfaces of cold-rolled strip, Zhao et al [36] adopted a kind of homomorphic filtering algorithm based on a partial differential equation (PDE). Recently, the application of filter banks has been expressed in Bulnes [46], Liu [65], Li [47], and particularly in Li [47], which used mean filtering combined with a local annular contrast (LAC) detection method, which led to better performance.…”

Surface Defect Detection Method Using Saliency Linear Scanning Morphology for Silicon Steel Strip under Oil Pollution Interference

“…For instance, Yun et al 4) developed the univariate dynamic encoding algorithm for searches (uDEAS) to detect the cracks, and Pan et al 5) exploited an engineering-driven rule-based detection (ERD) method for bleed detection in visual images which lie in the low signal-to-noise ratio. In addition, Landström et al 6) focused on automated detection of longitudinal cracks in steel slabs based on morphology theory, and Bulnes et al 7) introduced the clustering method to detect periodical defects. These four studies mentioned above focus on locating the positions of the defects while some studies focus on defect features extraction such as gabor filters, 8) wavelet filters, 9) and multi-scale geometric analysis (MGA).…”