Real-time spatter detection in laser welding with beam oscillation

Abstract Spatter formation is a longstanding issue in laser welding. This research addresses this topic and proposes a machine vision algorithm executed on a graphics processing unit to detect spatters in real time. Using this approach, a control system detecting spatter at a rate of 1 kHz and with a resolution of 900 x 900 pixels was implemented. Based on an experimental series, it is shown that the variation of the process parameters has a significant influence on the formation of spatter. It was also possible to quantify the variance of the spatter formation for a given set of process parameters.

[1]  Luigi Maria Galantucci,et al.  A Quality Evaluation Method for Laser Welding of Al Alloys Through Neural Networks , 2000 .

[2]  Seiji Katayama,et al.  Relationship between spatter formation and dynamic molten pool during high-power deep-penetration laser welding , 2014 .

[3]  Michael F. Zaeh,et al.  Analysis of spatters in laser welding with beam oscillation: A machine vision approach , 2016 .

[4]  A. Kaplan,et al.  Spatter in laser welding , 2011 .

[5]  Michael F. Zaeh,et al.  Validation of a spatter detection algorithm for remote laser welding applications , 2017 .

[6]  Bopaya Bidanda,et al.  Development of a spatter index for automated welding inspection using computer vision , 1989 .

[7]  Til Aach,et al.  Robust High-Speed Melt Pool Measurements for Laser Welding with Sputter Detection Capability , 2007, DAGM-Symposium.

[8]  Fang Li,et al.  Understanding of spatter formation in fiber laser welding of 5083 aluminum alloy , 2017 .

[9]  Baohua Chang,et al.  Studies on the spatter behaviour when welding AA5083 with a Yb-fibre laser , 2016 .

[10]  Genyu Chen,et al.  Observation of spatter formation mechanisms in high-power fiber laser welding of thick plate , 2013 .

[11]  Antti Salminen,et al.  Monitoring and Adaptive Control of Laser Processes , 2014 .

[12]  Yang Cao,et al.  Numerical study of spatter formation during fiber laser welding of aluminum alloy , 2018 .

[13]  Xiangdong Gao,et al.  Neural network of plume and spatter for monitoring high-power disk laser welding , 2014 .

[14]  Deyong You,et al.  Visual-based spatter detection during high-power disk laser welding , 2014 .

[15]  Deyong You,et al.  Monitoring of high-power laser welding using high-speed photographing and image processing , 2014 .

[16]  Yu Huang,et al.  Influence of steady magnetic field on dynamic behavior mechanism in full penetration laser beam welding , 2017 .