Welding quality analysis device based on infrared vision and analysis method thereof

Abstract

The invention discloses a welding quality analysis device based on infrared vision and an analysis method thereof. The analysis device comprises an infrared vision collecting system that is adjustably and fixedly connected to a welding facility, a vision processing system, in which welding defect intelligent recognition algorithm is embedded, and a feed control system, which can evaluate the welding quality, give an alarm, and adjust the parameters of the welding facility. The analysis method comprises the following steps: (1) collecting the infrared vision information of a molten pool or an area near a molten pool in real time through infrared sensing; (2) processing the infrared vision information by the welding defect intelligent recognition algorithm so as to obtain the weld seam positions and welding defect characteristics; (3) evaluating the welding quality in real time, and controlling the welding facility and giving an alarm aiming at different welding defects. According to the provided intelligent analysis device and intelligent analysis method, the welding process can be monitored in real time, the welding defects can be recognized, the welding seam position can be traced, the welding quality can be evaluated, the welding loss can be reduced, and the finished product yield rate can be increased.

Description

technical field [0001] The invention belongs to the field of infrared vision monitoring welding devices, and more specifically relates to a welding quality analysis device and analysis method based on infrared vision. Background technique [0002] With the improvement of traditional industrial level requirements, in the field of welding (such as TIG welding, MIG welding, CO 2 Gas-shielded welding, manual arc welding, high-frequency resistance welding, laser welding, etc.), in order to ensure that the mechanical properties, performance and safety performance of the welded parts meet the standards, the welding quality requirements are also constantly strict. Affected by factors such as the environment, materials, and equipment, welding defects are unavoidable, which makes important welded parts go through quality inspections to ensure they are qualified. According to the survey, in the field of welded pipes, the annual output of welded steel pipes in my country has reached 50...

AI Technical Summary

Problems solved by technology

Another example is a patent application with the patent application number 201310133509: "Robot welding quality visual inspection device and its inspection method", which connects the vision gun to the welding arm to follow the movement of the welding gun head, and compares the scanned pictures with the data in the database. Comparison and feedback control have a certain effect, but the vision gun in this patent uses an ordinary vision gun, and the fixing method only mentions that it is connected to the welding arm. It is difficult to satisfy manual welding or other situations without welding arms. In terms of image processing It is more biased towards comparison with the original database, not real-time intelligent recognition, lack of judgment on defects that are not in the original database, and its feedback control system is relatively vague

Another example is the patent document: "Narrow Gap Welding Monitoring and Weld Deviation Detection Method Based on Infrared Vision Sensing", which uses infrared vision, but its application is limited to narrow gap welding, and the monitoring of the welding process is only for welding Monitoring of seam deviation without consideration of monitoring of other welding defects

On the other hand, there is also a device that uses the current-voltage method to analyze the welding quality. Due to the influence of materials, environment, and human factors in the welding process, the data cannot fully reflect the changes in welding quality, so the analysis results have low accuracy. Disadvantages such as poor reliability and large randomness

Images