Investigation Of Detecting Weld Seam Deviation Based On Infrared Sensing During High-power Fiber Laser Welding

Laser welding technology originated from the United States in 1970. With the development of laser, laser power changed from small to large, quality and stability of laser beam improved, laser welding technology has been widely used in various industry fields. As a special welding process, the main advantage of the advanced laser welding is its large weld energy density in per unit length, high welding speed, small weld heat affected zone, small deformation, high mechanical properties of joints and weld profile dimensions do not subject to restrictions. We could get a large penetration depth used high power laser welding.Weld seam tracking is a key technology in the welding process, precise control of laser beam to align the weld position accurately is the premise to ensure the welding quality. In recent years, machine vision becomes the primary method of seam detecting, however, the traditional machine vision inspection method collected weld image is mainly through visual sensors, then weld information was captured by applied the image edge detection algorithm, the welding process was often susceptible to noise interference, it's difficult to obtain clear images. Aiming at investigating the high-power fiber laser welding of type 304 austenitic stainless steel plate butt welding (the gap is not greater than 0.1mm), an infrared sensitive high speed camera arranged off-axis orientation of laser beam was used to capture the dynamic thermal images of a molten pool. The characteristics of thermal distribution and infrared radiation of the molten pool when the laser beam focus deviated from the welding seam center was analyzed. Parameters called the keyhole shape parameter, the heat accumulation effect parameter and keyhole centroid were defined as the eigenvalues of seam tracking offset to determine the offset between the laser beam focus and the desired welding seam. Also, the image processing techniques were applied to analyze the infrared images of the molten pool, which indicated the presence of mathematic correlation between the defined parameters and the seam tracking offset. The welding experiments confirmed that the offset between the laser beam focus and the welding seam could be estimated by the keyhole shape parameters, the heat accumulation effect parameter and keyhole centroid effectively. Through methods of regression analysis, BP neural network and RBF network modeling, the mathematical correlation between the seam bias and the characteristic parameters was studied. Laser welding experiment results show that there must be some relationship between the keyhole shape parameters, heat accumulation effect parameter, keyhole centroid and the seam tracking offset, with the laser beam deviating from the weld position gradually, the characteristic parameters show an increasing trend. A model of the relationship between the parameters and seam tracking offset was established, it provides a new method for real-time controlling welding laser beam in actual industrial, and has theoretical and practical significance.