Defect detection for highly reflective rotary surfaces: an overview

Zhou, Aihui; Ai, Bobo; Pingge, Qu; Shao, Wei

doi:10.1088/1361-6501/abd579

Cited by 10 publications

(6 citation statements)

References 58 publications

(101 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the analysis, the surface of the metal strip divided into sections was lit from above. Since different parts of the metal strip reflect the light falling on them differently, the reflected rays have different intensities [18]. Owing to this, the image was obtained.…”

Section: Methodsmentioning

confidence: 99%

Influence of Uneven Lighting on Quantitative Indicators of Surface Defects

et al. 2022

View full text Add to dashboard Cite

The impact of the illumination level on the quantitative indicators of mechanical damage of the rolled strip is investigated. To do so, a physical model experiment was conducted in the laboratory. The obtained images of defects at light levels in the range of 2–800 lx were recognized by a neural network model based on the U-net architecture with a decoder based on ResNet152. Two levels of illumination were identified, at which the total area of recognized defects increased: 50 lx and 300 lx. A quantitative assessment of the overall accuracy of defect recognition was conducted on the basis of comparison with data from images marked by an expert. The best recognition result (with Dice similarity coefficient ) was obtained for the illumination of 300 lx. At lower light levels (less than 200 lx), some of the damage remained unrecognized. At high light levels (higher than 500 lx), a decrease in DSC was observed, mainly due to the fact that the surface objects are better visible and the recognized fragments become wider. In addition, more false-positives fragments were recognized. The obtained results are valuable for further adjustment of industrial systems for diagnosing technological defects on rolled metal strips.

show abstract

Section: Methodsmentioning

confidence: 99%

Influence of Uneven Lighting on Quantitative Indicators of Surface Defects

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In recent years, photoelectric technology has gradually become an important means of detection in the industrial field [15]. The detection methods of the tube inner surface based on photoelectric technology mainly include the closed circuit television method and the laser vision detection method [16]. In the closed circuit television method, a chargecoupled device (CCD) camera is installed on the tube climbing machine, and the defects of the tube's inner surface is inspected through the two-dimensional image captured by the CCD camera [17].…”

Section: Introductionmentioning

confidence: 99%

Tube inner wall defect detection method based on rotary scanning micro laser distance sensor

An,

Liu,

Pang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

In this paper, an inspection device which mainly consists of a micro laser distance sensor and a stepper motor is proposed to detect the inner wall defect of oil tubes. When the inspection device moves along the axial direction inside the tube, the stepper motor drives the micro laser distance sensor to rotate and scan the inner wall of the tube so that the coordinate data of 3D point cloud can be obtained. In order to obtain the pose transformation matrix for the laser distance sensor coordinate system with respect to the device flange coordinate system, particle swarm optimization (PSO) algorithm is innovatively introduced. Finally, experiments have been carried out in two actual oil tubes and point cloud data have been obtained which demonstrate 3D information of tubes inner wall. The measuring error of tube eccentric wear is within 0.2mm which verifies the effectiveness of the novel method.

show abstract

“…Note the above-mentioned surface defect inspection methods typically utilize a single light source to illuminate the target workpieces for image acquisition. They assume that the surface defects are visually observable local anomalies on single input images which cannot be well satisfied in many practical industrial inspection tasks particularly for products made of highly reflective materials [36][37][38].…”

Section: Introductionmentioning

confidence: 99%