The technique of seam tracking based on vision sensing is one of the first-class techniques in the field of seam tracking in the recent years. Because of large information, high reliability, broad applicability etc., it has a huge potential for research and application.On the basis of pre-researches, the advantage of vision sensing was further studied in the thesis. According to the requirement of the manufacture, a passive vision sensing system composed of CCD (Charge Couple Device) camera, image grabber, industry computer, etc. was designed and optimized. What's more, it was used to capture the image information in real time during the welding process.The image processing algorithm is the key technique in the seam tracking. This thesis investigates the images of GTAW welded pool for the 6mm thickness LD10 aluminum alloys with grooves and put forward two different algorithms for extracting the center of seam and projection of tungsten-pole center, and the algorithms can satisfy the requirement for expeditiousness.
|