Automated seam tracking system based on passive monocular vision for automated linear robotic welding process

摘要

Welding is a very important process in the industrial scenario, especially in the shipbuilding industry. Many researches employ robots to automate different welding process. This paper proposes a system for automated seam tracking, based on passive vision, to act as a data feedback to the automated robotic welding system, with quality and productivity gains in the process. Different cameras arrangements are presented and tested as the vision acquisition system in a commercial linear welding robot. A physical method and an algorithm to remove visual noises from images, produced by the GMAW welding process, are presented and the results discussed.