Weld defect automatic detection method and device

Abstract

The invention discloses a welding seam defect automatic detection method which comprises the following steps: S1, acquiring a preset welding track and process parameters during welding operation of a welding robot and storing the preset welding track and process parameters in an additionally arranged server, and acquiring an actual welding track during welding operation of the welding robot and storing the actual welding track in the additionally arranged server; s2, a welding seam visual detection device and an ultrasonic flaw detector are used for scanning and detecting the welding seam along with the preset welding track, obtained in the step S1, of the welding robot, welding seam detection data are uploaded to a server to be stored, the welding seam visual detection device detects appearance parameters of the welding seam, and the ultrasonic flaw detector detects internal parameters of the welding seam; and S3, tabulating the preset welding track, the actual welding track, the process parameters and the welding seam detection data stored in the server during the welding operation of the welding robot according to the time latitude, and generating a flaw detection report. The invention further discloses an automatic weld defect detection device.

Description

technical field [0001] The invention relates to the technical field of weld detection, in particular to an automatic detection method and device for weld defects. Background technique [0002] Weld inspection is an important means to detect welding quality. At present, commonly used weld detection methods include visual detection, radiographic detection, and ultrasonic detection. Based on the above principles, there are currently a variety of weld detection equipment on the market. At present, in the field of welding, a large number of automatic equipment such as welding robots have participated in welding operations, which has greatly improved welding efficiency. The current market weld flaw detection method is to use a hand-held flaw detector, and this solution focuses on convenient operation. This scheme has greater versatility and universality, but it does not integrate the welding seam data with the welding robot data. Existing scheme has following deficiency and sho...

AI Technical Summary

Problems solved by technology

[0003] 1. Manual data collection, unable to add welding trajectory and process parameter modeling information of welding robot;

[0004] 2. Data edge computing cannot be performed, only simple data transmission can be performed, and data processing requirements cannot be met;

[0005] 3. Artificial intelligence algorithm intervention cannot be performed to compensate;

[0006] 4. The existing solution does not have the data storage function, and the collected data cannot be stored in the database;

[0007] 5. The existing system is not automated and cannot cope with future digital factory upgrades

[0009] 1. The flaw detection method belongs to manual operation, and the intelligence level of the equipment is not enough;

[0010] 2. It is difficult for flaw detectors to standardize data processing, which is not conducive to improving the welding process, so existing products basically do not have edge computing functions;

[0011] 3. In terms of comprehensive cost and benefit, the existing flaw detection system is designed with a scheme of one machine and one module, which does not meet the requirements of intelligent equipment;

[0012] 4. Existing flaw detection data cannot be integrated with various data indicators of welding robots, and it is impossible to trace back and analyze the causes of weld quality defects

Images