Steel structure welding crack defect detection method based on image processing technology

Abstract

The invention discloses a steel structure welding crack defect detection method based on an image processing technology, and relates to the field of artificial intelligence. The method mainly comprises the following steps: processing an acquired weld surface image to obtain a third image; performing PCA on each category obtained after clustering of the pixel points in the third image, so that the near-circle edge probability of each category is obtained, and the category with the near-circle edge probability smaller than a preset first threshold value is reserved; obtaining direction vectors corresponding to the reserved categories respectively, and combining the categories with the similarity larger than a preset second threshold value to obtain a welding seam area so as to obtain a crack area; and finally obtaining the difference degree of each crack region to determine the actual depth of the crack in the crack region. According to the embodiment of the invention, the weld crack defect detection process does not need human intervention, so that the tedious operation process is avoided, and the detection efficiency of the weld crack defect is improved.

Description

technical field [0001] This application relates to the field of artificial intelligence, in particular to a method for detecting welding crack defects in steel structures based on image processing technology. Background technique [0002] Welding defects refer to the defects formed during the welding process of the welded joints, mainly including welding cracks, incomplete penetration, slag inclusions, pores and weld appearance defects. These defects will reduce the weld area, cause stress concentration at the weld and cause cracks; reduce the fatigue strength of the weldment, and at the same time easily cause the weldment to crack and cause brittle fracture. Welding production is affected by many factors such as material, process, structure, etc., and improper operation in welding operations is prone to welding defects. [0003] One of the most common weld defects in actual welding construction is welding cracks. At present, the detection methods for welding cracks mainly ...

AI Technical Summary

Problems solved by technology

In the process of realizing the embodiment of the present invention, the inventor found at least the following defects in the background technology: the detection procedures of magnetic particle detection or penetrant detection are various, and the detection process requires human intervention, so that the detection efficiency is not high

Images