Weld quality detection method based on images

Abstract

The invention discloses a weld quality detection method based on images. The method comprises the following steps: adopting a camera, a line laser and a computer, correspondingly fixing the camera andthe line laser beside a workpiece respectively, enabling the line laser to be aligned to a weld formed by welding the workpiece, continuously collecting n weld images by the camera, transmitting theimages to the computer to be analyzed and processed, obtaining an edge graph S, and judging whether the weld is normal or not according to the number of pixel points in the edge graph S. Compared withthe prior art, the weld quality detection method disclosed by the invention has the advantages that weld quality detection is realized through image processing, the cost is low, and the welding quality of products and the benefits of enterprises are improved; only the camera, the line laser and the computer are adopted as detection systems, and the structure is simple, so that operation and application are relatively convenient; and during detection, the weld images are continuously collected by the camera and are analyzed and processed by the computer, the response speed is higher, and the detection accuracy is higher.

Description

technical field [0001] The invention relates to the technical field of weld quality detection, in particular to an image-based weld quality detection method. Background technique [0002] During the welding process of the welding robot, due to the influence of environmental factors, such as: strong arc radiation, high temperature, smoke, dust, splash, groove condition, processing error, fixture clamping accuracy, surface state and workpiece thermal deformation, etc., the actual welding conditions change Often causes the torch to deviate from the weld. The existence of weld defects will weaken the force-bearing area of ​​the weld, cause stress concentration at the defect, and have adverse effects on the strength, impact toughness and cold bending performance of the connection, and will seriously affect the quality of the product. Welding quality inspection at the same time as welding can ensure the construction quality in real time and adjust the optimal construction paramet...

AI Technical Summary

Problems solved by technology

[0003] At present, the commonly used non-destructive weld quality detection methods include X-ray and ultrasonic flaw detection, but their high cost makes the entire detection system expensive and reduces the production efficiency of enterprises.

Images