Linear array camera-based gapless welding seam identification method and system

Abstract

The invention discloses a gapless weld joint recognition method and system based on a linear array camera. The gapless weld joint recognition method comprises the following steps of: acquiring the image information of a weldment through the linear array camera; performing noise reduction processing on the image information to obtain preprocessed information; screening the preprocessed information to obtain candidate information; removing the error position information in the candidate information to obtain welding seam information; welding seam information is spliced, a welding seam track is obtained, and a welding gun is controlled to conduct welding operation according to the welding seam track. The image information is subjected to noise reduction and screening processing, so that the information amount of the image information can be effectively reduced, a large amount of information redundancy is avoided, a large amount of data operation is further reduced, and the processing speed is improved; meanwhile, by removing the wrong position information in the candidate information, the wrong position information in the candidate information can be quickly deleted, and the accuracy of gapless welding seam recognition is ensured.

Description

technical field [0001] The invention relates to the field of welding technology, in particular to a method and system for identifying a gapless weld seam based on a line array camera. Background technique [0002] As a non-contact sensor, the visual sensor has the advantages of high sensitivity, good real-time performance, and less susceptible to interference. Therefore, the visual sensor is widely used in weld seam recognition and other fields. Most of the existing vision-based weld recognition methods use laser vision to identify welds. This method requires linear laser stripes to irradiate the surface of the workpiece and deform, and the computer converts the deformation of the laser stripes into the surface of the weldment. height information, and then identify the weld position. But for butt welds without gaps, the surface of the workpiece will not be significantly deformed when the line laser stripes are irradiated, so the laser vision method cannot identify extremely...

AI Technical Summary

Problems solved by technology

But for butt welds without gaps, the line laser stripes irradiate the surface of the workpiece without obvious deformation, so the laser vision method cannot identify extremely narrow gaps and gapless welds

[0003] In addition, part of the existing weld recognition system uses an area array camera to collect the surface image information of the weldment. Although the collected pictures contain a lot of information, most of them are useless information, resulting in a large amount of data redundancy. lead to lower processing efficiency

Images