A method for detecting surface defects of laser brazing welds based on envelope recognition

Abstract

The invention discloses a method for detecting surface defects of laser brazing welding seam based on envelope recognition. After obtaining the welding seam surface contour data, the actual contour curve is fitted with a weighted cubic spline curve in real time to obtain a standard contour, The standard contour is translated up and down by the fluctuation distance to obtain the welding seam grid interval; the actual contour curve is compared with the welding seam reasonable interval: when the actual contour curve is all within the welding seam reasonable interval, the welding seam has no defects; When the curve is higher than the upper contour line or lower than the lower contour line, and the area of ​​the excess part is greater than or equal to the threshold value, the weld contour is unqualified; when the number of unqualified weld contours continuously reaches the critical size of the weld defect, it is judged There are defects in the weld; and on this basis, the defects are classified and the corresponding eigenvalues ​​are calculated. The welding seam surface defect detection method of the invention can quickly and accurately detect the welding seam defects, and is insensitive to the interference caused by the environment, sensors and the like.

Description

technical field [0001] The invention belongs to the technical field of welding seam defect detection, and more particularly relates to a method for detecting surface defects of laser brazing welding seam based on envelope identification. Background technique [0002] The quality of the weld determines whether the mechanical product is qualified and meets the requirements. The poor quality of the weld reduces the strength of the weldment, which is prone to breakage during use, causing accidents, causing economic losses and threatening personal safety. Various inspections are carried out on the weld to make the weldment meet the standard of use. Among them, laser brazing welds have high requirements on surface quality, especially when the outer surface of parts is processed in automobile manufacturing, the surface quality of welds is directly related to whether the parts are qualified or not. The complex splicing joint form of laser brazing brings many challenges to the inspe...

AI Technical Summary

Problems solved by technology

However, the accuracy of this detection method is strictly affected by the degree of color difference, and it is difficult to achieve a good trade-off between sensitivity and accuracy

Moreover, it is difficult to achieve good detection results in the strong noise environment of laser brazed joints

In addition, the types of defects detected in the above patents do not involve welding spatter, and as one of the defects that seriously affect the quality of the welding surface, this patent proposes a detection method for welding spatter

Images