Abstract

In automatic welding of thin plates, it is well known that the application of an arc sensing system for the recognition of a weld line is relatively difficult. Therefore, an intelligent welding robot with a visual sensing system has been recently sought. However, it is not always easy to recognize the weld line clearly, because the weld line is sometimes very fine and the machined surfaces of steel plates have irregular brightness distribution. Therefore, a basic Cartesian-coordinate welding robot system with a visual sensor was constructed in order to investigate the recognition and automatic tracking of the weld line of machined steel plates. In this study, the effects of surface conditions of plates and the image processing of brightness distributions on the recognition of weld line were discussed, and moreover the effectiveness of the processes was experimentally confirmed.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call