Abstract
This paper describes a multi-sensor fusion system for monitoring disk laser welding process. During bead-on-plate disk laser welding of type 304 austenitic stainless steel plates, a multi-sensor fusion system was applied to monitor the welding process, which consisted of auxiliary illumination (AI) sensing, ultraviolet and visible (UVV) sensing, and photodiode sensing. The visual sensing based on auxiliary illumination was used to capture the dynamic behavior of a molten pool and keyhole. The ultraviolet and visible sensing was to capture the dynamic behavior of plume and spatter. Photodiode sensing was to monitor the visible light emission and laser reflection. The features that were extracted from the sensing signals were used for monitoring disk laser welding based on a backpropagation (BP) neural network. Experimental results showed that the integration of photodiode and visual sensing provided a more accurate estimation on the laser welding process.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
