Welding seam ultrasonic image defect identification method based on machine and depth vision fusion

Abstract

The invention discloses a machine and depth vision fusion-based weld ultrasonic image defect identification method. The method comprises the following steps of performing ultrasonic imaging on a to-be-detected object by utilizing ultrasonic detection equipment; a defect labeling model is used for automatically positioning a welding seam area of the ultrasonic detection image; obtaining texture feature data of a weld seam image in the defect labeling image by using an image recognition technology, and performing category recognition on the texture feature data through a collaborative algorithm; and outputting an identification result to a front-end interface, and automatically describing the shape of the weld joint by utilizing cartographic software to realize weld joint defect identification of the to-be-detected object. According to the method, the defect area can be automatically positioned, various weld defects can be identified, the weld defect identification quality can be effectively improved, the identification speed can be increased, the dependence on artificial experience can be effectively reduced, the labor cost can be reduced, the identification process can be visualized step by step, the identification quality can be improved, the identification process can be obviously accelerated, and the identification efficiency can be improved. And the robot welding process speed is met.

Description

technical field [0001] The present invention relates to the technical field of defect recognition, in particular to a defect recognition method of welding seam ultrasonic images based on the fusion of machine and depth vision. Background technique [0002] The welding process has long been an important part of industrial production applications. Today, welding robots have been widely used in industrial production. At the same time, it brings high-level control of welding quality and reliable quality traceability, etc. question. Due to various defects in welding construction, affected by the stability of various parameters in the welding process, various defects such as slag inclusions, cracks, and pores will inevitably appear in the weld seam. In order to ensure the quality of welded components, there are Detailed detection and reasonable evaluation of weld defects are necessary. Welding image recognition mainly has two levels of problems. The first level is to judge wheth...

AI Technical Summary

Problems solved by technology

Welding image recognition mainly has two levels of problems. The first level is to judge whether the current welding point is defective. Recognition errors will lead to serious product quality problems. The second level needs to identify which category the defect belongs to based on the defect. Recognition type errors will make quality retrospective and process improvement encounter great difficulties

[0003] At present, most enterprises use ultrasonic detection to image welding parts, but the images still need to rely on manual experience for cumbersome rule processing, and then carry out defect identification. This type of method cannot meet the needs of enterprises in terms of recognition quality and recognition speed.

Since enterprises basically adopt the method of manual identification, on the one hand, the manual identification steps are cumbersome and easy to cause false detection; The problem has gradually become the pain point of the enterprise

Images