Image detection method for weld seam surface defects of laser welded plates of unequal thickness

Abstract

The invention relates to an image detection method for weld seam surface defects of laser welded plates of unequal thickness, which comprises the following steps of: firstly, acquiring a physical image of laser stripes which is formed on a weld seam surface by using a linear laser generator for irradiating the weld seam surface through a CCD (Charge Coupled Device) camera, and converting the physical image of laser stripes into a digital image of laser stripes through an image acquisition card; processing the digital image of laser stripes by using a margin-variable Gaussian fitting method and extracting a centerline image of laser stripes which has sub-pixel accuracy; furthermore, fitting three intersecting characteristic straight lines of the centerline image of laser stripes through a least square method and solving the point of intersection of the three intersecting characteristic straight lines so as to obtain accurate position coordinates of weld seam endpoints; and finally, calculating the defects, i.e. a concavity value and a convexity value of the weld seam surface according to the position coordinates of the weld seam endpoints. The method can realize the fast and accurate detection of the weld seam surface defects of the laser welded plates of unequal thickness, so that an important basis which is used for judging whether the quality of laser welded weld seams of plates of unequal thickness is qualified or not is provided.

Description

technical field [0001] The invention relates to the technical field of laser welding seam quality inspection, in particular to an image detection method for surface defects of laser welding seams of unequal thickness plates based on structured light vision and data fitting processing. Background technique [0002] Laser welding has obvious advantages such as fast welding speed, high weld strength and beautiful weld seam. However, during the welding process, the quality of the weld seam will also be affected by parameters such as laser power, beam characteristics, defocus, auxiliary blowing and welding speed. Volatility is affected. Therefore, it is very important to study the surface defect detection technology of laser welding seam quality. There are three main methods of laser welding quality inspection: non-destructive testing means to detect defects such as weld stress concentration and internal gas milk after welding; monitoring various optical and electromagnetic sign...

AI Technical Summary

Problems solved by technology

[0003] After searching the existing technical literature, it was found that Xu Min and others published "Image Processing Method for Welding Seam Quality Inspection of Unequal Thickness Tailored Welded Blank" in "Welding Technology" (2010, vol39, No4: 56-59), Aiming at various noise interferences in the laser tailoring welding process, this paper studies the region of interest by adding windows in the image preprocessing process, uses median filtering to remove image noise, and uses the template method in the process of extracting the centerline of structured light stripes. The boundary of the fringe is obtained and the center line of the fringe is extracted by the geometric center method, and the feature points are detected based on the sudden change of the weld gray level and the fitting line method, but the disadvantage is that the structured light center extracted by the template method and the geometric center method The line position accuracy is low, and the straight line fitting method only fits the straight lines at both ends of the weld end profile, but does not perform straight line fitting on the ideal straight line of the weld end profile, so the accuracy of the weld feature points obtained is poor. And there is no detection method for weld surface defects such as concavity and convexity, which is difficult to apply to actual engineering

In "Instrument Technology and Sensors" (2010, Vol9, No.9: 84-87), Zhang Wanjiang et al. published "Research on the quality detection method of the back side of laser tailor welding seam based on structured light vision", and proposed a new The template method is used to obtain the stripe boundary, and the geometric center method is used to extract the stripe center line, and the slope analysis method is introduced into the stripe center line feature point detection to extract a series of feature points, and then calculate the geometry at different positions of the back weld through the image sequence of the back weld. parameters and defects, but the centerline extraction accuracy is only at the pixel level and cannot reach the sub-pixel level, and misjudgment is prone to occur in feature point extraction, which reduces the accuracy of detection results

Images