Monitoring of the seam quality gains significance for the industrial practice of the laser welding process. Due to the complexity of the process an extensive evaluation of the processing results depends on the concurrent monitoring of various sensor signals. In order to detect deviations in the process behavior state of the art process monitoring systems use predetermined reference data curves for the comparison with the measured signal. As a result of a statistical analysis the probability for an over-all defect is calculated. A new approach for the determination of defect classes using the combination of different sensor signals is presented. Based on a system for fast multi-channel signal acquisition and flexible data processing, different strategies were implemented for the combination of sensor signals and the interpretation of the resulting data. Experimental results show the suitability of the approach for the online determination of defect classes during laser beam welding.
Online detection of defect classes for laser beam welding
J. Ortmann, E. W. Kreutz, C. Maier, T. Wehner, M. Kogel-Hollacher, S. Kaierle, R. Poprawe; October 14–18, 2018. "Online detection of defect classes for laser beam welding." Proceedings of the International Congress on Applications of Lasers & Electro-Optics. ICALEO® 2003: 22nd International Congress on Laser Materials Processing and Laser Microfabrication. Orlando, FL, USA. (pp. 1301). ASME. https://doi.org/10.2351/1.5059994
Download citation file: