Fusion penetration control method for fillet joints based on near-infrared binocular vision recognition

Abstract

A method for controlling penetration of fillet joints based on near-infrared binocular vision recognition, which involves a visual detection method for characteristic parameters of a weld pool and a detection method for reverse fusion width. The invention utilizes the method of combining front and back near-infrared scanning CCD camera devices with a computer image processing system and a control system to control the penetration of corner joints. First, select a suitable near-infrared scanning CCD camera device based on the principle of near-infrared; then acquire the melt pool image, including the melt pool characteristic parameters acquired by the near-infrared vision sensor on the front and the reverse side acquired by the near-infrared vision sensor on the back Welding width, and then image processing and analysis are performed on the obtained molten pool and its characteristic parameters, as well as the molten width on the reverse side, to obtain weld penetration information; finally, the penetration control is carried out by establishing a model through the obtained parameters. The present invention does not need to deduce the fusion width of the opposite surface. The use of the characteristic size parameters and characteristic shape parameters of the front melt pool image to characterize the fusion is avoided.

Description

technical field [0001] The invention relates to the technical fields of machine vision and additive forming, and in particular to a method for controlling penetration of corner joints based on near-infrared binocular vision recognition. Background technique [0002] At present, most of the penetration control in the industry is still using monocular vision to collect images, using the characteristic information of the front molten pool captured by the camera, after image processing, extracting the characteristics of the front molten pool, and finally using the established relationship The model deduces the reverse fusion width. The image captured in this way will be strongly disturbed by the arc light, which will affect the deduced reverse fusion width and easily cause large errors. At the same time, there are relatively few researches on penetration control of fillet welds. The present invention combines the method of measuring the temperature field with near-infrared meth...

AI Technical Summary

Problems solved by technology

The image captured in this way will be strongly disturbed by the arc light, which will affect the deduced reverse melting width and easily cause large errors

Images