Plate-strip surface quality detection system and method

Abstract

The invention discloses a plate-strip surface quality detection system, the plate-strip surface quality detection system and a plate-strip production line are in on-line running, the plate-strip surface quality detection system is characterized by comprising an image sampling device, a processing device and a control device; the image sampling device is used for real-time acquisition of plate-strip surface optical features from the plate-strip production line to obtain plate-strip images; the processing device is used for extracting plate-strip image defect information, packing the image defect information and processing position tag to obtain defect treatment results; and the control device is used for plate-strip surface quality evaluation according to the defect treatment results. The detection system collects the plate-strip surface optical features on the basis of machine vision technology to obtain the plate-strip images, the treatment results are obtained by feature information extraction and the subsequent processing, the defect is determined according to the treatment results, the missing inspection rate can be reduced, labor cost can be reduced, the normal plate-strip processing may not be affected in the detection process, alarms of unqualified products are issued, the unqualified products are removed, and the detection accuracy and the rate of qualified products can be improved.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a strip surface quality detection system and method. Background technique [0002] During the production process of alloy strips (take aluminum strips as an example), due to factors such as equipment wear, production raw materials, environmental pollution, and process operations, some appearance defects will inevitably occur, such as: roll scratches, crushed / guide rolls Injury, guide roller bag, air channel, double roller printing, sticking roller printing, knife printing, cloud flower color difference, etc. The quality defects on the surface of these strips need to be detected in time, and the strips that do not meet the production requirements should be removed. [0003] In the prior art, the method of manual sampling inspection is generally used to detect the surface of the strip. However, due to the limitations of strong subjectivity, inability to achieve comprehensiv...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the method of manual sampling inspection is generally used to detect the surface of the strip. However, due to the limitations of strong subjectivity, inability to achieve comprehensive detection, and low detection efficiency, manual sampling inspection has b

Images