Self-adaptive extraction method for geometrical characteristics of butt weld

Abstract

The invention relates to a welding image processing technology, in particular to a self-adaptive extraction method for geometrical characteristics of a butt weld. The method comprises the following steps of: acquiring a real-time image of the butt weld during welding by using a visual sensor; preprocessing the collected real-time image of the butt weld, and extracting an ROI region during welding; performing image processing on the extracted ROI region during welding, removing interference and smoothing the image; and extracting a laser center line from the image processed in the step 3 and calculating the center point position of the weld. According to the method, the collected real-time welding image can be effectively processed, the ROI region is accurately intercepted, position information such as a light strip center line and a weld center point is rapidly and accurately extracted, and then weld tracking is achieved. The method has the characteristics of high processing speed, high accuracy, high image quality and the like.

Description

technical field [0001] The invention belongs to the technical field of welding image processing, in particular to an adaptive extraction method of geometric features of butt welds. Background technique [0002] Welding is an important processing technology in the manufacturing industry. It is widely used in aerospace, energy equipment, automobile manufacturing and shipbuilding, but the working conditions are harsh, the workload is heavy and the quality requirements are high. With the continuous development of industrial automation and intelligence, the automation and intelligence of welding has become an inevitable trend in the development of welding technology. [0003] With the popularity of robot programming systems, when welding structural parts, the program is compiled offline according to the three-dimensional digital model of the part. There is a certain deviation between the actual workpiece shape and the theoretical digital model, and the absolute positioning accura...

AI Technical Summary

Problems solved by technology

[0003] With the popularity of robot programming systems, when welding structural parts, the program is compiled offline according to the three-dimensional digital model of the part. There is a certain deviation between the actual workpiece shape and the theoretical digital model, and the absolute positioning accuracy of the robot is low, and the error can reach 0.5 ~ 2mm. Lead to welding defects or even interference collisions; moreover, during the welding process, the parts are heated and restrained, forming significant residual stress and causing the parts to deform, making the actual weld position deviate from the theoretical track position, resulting in poor welding quality

Images