Development of automation and monitoring methods for narrow-gap hot-wire laser welding using camera images

In this study, an image-based method was developed for hot-wire laser narrow gap welding. The welding process was monitored based on image information processed using semantic segmentation, a method of classifying images by pixel. To control the welding position, an experimental system was configured that automatically follows the welding position by recognizing the position of the welding groove from the image during welding. In monitoring weld defects, a method was developed to predict the lack of fusion occurring on the wall surface using brightness information near the wall surface. For the lack of fusion occurring at the bottom of the groove, a defect detection method was developed by monitoring the molten pool shape using semantic segmentation. Defects were generated by intentionally reducing the laser power, and the defects were monitored from images taken during processing. In the unstable state where the laser power was reduced, the shape in front of the molten pool became unstable, and the occurrence of defects was monitored by capturing the shape change. In conclusion, this research made it possible to control and monitor the welding process with a single camera.