A detection method for on-line recognition of the surface quality of continuous laser welded seams of metal workpieces

Abstract

The invention provides a detection method for identifying the surface quality of a continuous laser seam of a metal workpiece online, wherein the method comprises the following steps: using a high resolution color area array camera, a high magnification micro lens and double LED illuminating systems to acquire an image of the surface of the seam; afterwards, when dividing a seam region and calculating the characteristic value, translating or rotating the workpiece to shoot an image for other positions of the seam, continuously shooting the image of the seam and completing real-time calculation until reaching a seam welding end or an overlapping point; finally integrating the calculation results of the images, and completing online judgement on the size, the position and the surface defect of the continuous seam. The method is used to complete online detection of the quality of a laser straight welded joint, a curve welding seam or a space welding seam of various ferrous metals and nonferrous metals, and belongs to the category of non-contact visual inspection; a device is simple and compact, high in response speed and strong in anti-jamming capability, has the characteristics of stability, reliability and convenience, and can be widely applied to the field of laser welding of metal materials.

Description

technical field [0001] The invention relates to the technical field of laser welding, in particular to a detection method for online recognition of the surface quality of continuous laser welds of metal workpieces. Background technique [0002] Laser welding technology has been widely used in the connection of metal parts, especially for thin plates with a thickness of less than 3mm. Laser welding has the advantages of small deformation, high degree of automation, and narrow welding heat-affected zone. However, in mass welding production, the process stability control of laser welding and the online quality monitoring of laser welds have always been the key factors in determining product quality. Fluctuations in beam quality, assembly clearance, workpiece surface state and other factors will interfere with the welding process, resulting in weld defects such as welding deviation, holes, and weld penetration. Due to the high energy density of the laser beam, which is invisibl...

AI Technical Summary

Problems solved by technology

This method only relies on the weld height information, and there are fewer types of weld defects that can be identified, and the surface of the weld is usually rough, and disturbances such as scum, spatter, and dust on the surface seriously affect the accuracy of height measurement

In addition, the line scanning method is time-consuming and has limitations in the field of continuous long weld detection

[0006] 3) The paper "Structured Light Visual Inspection of Weld Defects in Laser Welding of Unequal Thick Plates" ("Laser Technology" Vol. 35 No. 4, 2011) uses the structured light active visual inspection method to calculate the height information of the weld surface, but the The method can only obtain the concavity or convexity state of the weld, and cannot detect the surface defects of the weld and the location of the weld

[0007] 4) The paper "Weld Surface Defect Detection System Based on Line Laser Scanning" ("Welding" 2016 No. 2) uses line laser to scan the weld surface, and uses the method of single contour fitting and multi-contour combination to judge the weld surface defects, but this method can only be applied to arc welding seams with larger widths, and is not suitable for narrow and thin welds (such as laser welding seams, electron beam welding seams, etc.) with smaller weld seam width and defect size , the incident laser light will easily lead to measurement failure due to problems such as beam reflection, refraction, and diffraction at small-scale mutations, so that the detection of the surface state cannot be completed

[0008] It can be seen that the current identification of weld surface defects mainly adopts the line scanning method, and the state judgment is based on the height data of the weld surface, which has limitations in the field of narrow and thin weld detection, and the line laser scanning method is also difficult in terms of detection speed. Meet the actual production needs; on the other hand, the detection method based on the two-dimensional image of the weld is still in the optimization of the weld extraction algorithm, and there is no report on the detection of weld surface defects, let alone a systematic method for automatic detection of weld surface defects

In short, there is still a lack of effective and adaptable detection methods for weld surface quality inspection, which cannot meet the needs of large-scale automated welding production, and even cause serious safety hazards

Images