The use of robotic laser welding is increasing among industrial applications, because of its ability to weld objects in three dimensions. Robotic laser welding involves three sub-processes: seam detection and tracking, welding process control, and weld seam inspection. Usually, for each sub-process, a separate sensory system is required. The use of separate sensory systems leads to heavy and bulky tools, in contrast to compact and light sensory systems that are needed to reach sufficient accuracy and accessibility. In the solution presented in this paper all three subprocesses are integrated in one compact multipurpose welding head. This multipurpose tool is under development and consists of a laser welding head, with integrated sensors for seam detection and inspection, while also carrying interfaces for process control. It can provide the relative position of the tool and the work piece in three-dimensional space. Additionally, it can cope with the occurrence of sharp corners along a three-dimensional weld path, which are difficult to detect and weld with conventional equipment due to measurement errors and robot dynamics. In this paper the process of seam detection will be mainly elaborated.
A compact, lightweight, and multifunctional head for robotic laser welding applications has been equipped with a camera to provide a real time image stream of the work piece for seam teaching, tracking, and inspection purposes [D. Iakovou, R. G. K. M. Aarts, and J. Meijer, “Integrated sensors for robotic laser welding,” in Proceedings of the Third International WLT Conference on Lasers in Manufacturing, Munich, Germany (AT-Fachverlag GmBH, Stuttgart, 2005), pp. 121–126; D. Iakovou, R. G. K. M. Aarts, and J. Meijer “Sensor integration for robotic laser welding processes,” (paper No. 2301), in Proceedings of the International Congress on Applications of Lasers and Electro-Optics (ICALEO), Miami, 2005 (unpublished)]. The camera uses part of the laser focusing optics. Research has been done to identify and correct for positioning errors introduced by the optical system. A robust camera and lens calibration method has been developed. Calibration and seam detection experiments have been performed and the results were used for seam tracking.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.