Prediction model of weld width during high-power disk laser welding of 304 austenitic stainless steel

Morphology of molten pool is significantly associated with welding quality. In this study, an active vision system was designed to form the shadow of a molten pool to get its morphology information during high-power disk laser welding of Type 304 austenitic stainless steel. The shadow was segmented from the recorded images, and four features of the shadow were defined to describe the morphology of a molten pool. The BP (Back propagation) and RBF (Radial based function) neural networks were established to model the relation between the four features and the solid weld width which is the foremost characteristic of weld quality. The effectiveness of two models were compared and analyzed at different welding speeds, and it was found that the BP model had the better results than RBF. The study focuses on predicting the solid weld width by observing the morphology of a molten pool, and provides a necessary foundation for online monitoring and control of weld width during laser welding.

[1]  Y. Shin,et al.  Investigation of keyhole plume and molten pool based on a three-dimensional dynamic model with sharp interface formulation , 2013 .

[2]  Wang Yongsheng,et al.  Prediction of the chaotic time series from parameter-varying systems using artificial neural networks , 2008 .

[3]  P. V. Coveney,et al.  Prediction of the functional properties of ceramic materials from composition using artificial neural networks , 2007 .

[4]  Deyong You,et al.  Kalman Filtering Compensated by Radial Basis Function Neural Network for Seam Tracking of Laser Welding , 2013, IEEE Transactions on Control Systems Technology.

[5]  Michael Rethmeier,et al.  Numerical simulation of full-penetration laser beam welding of thick aluminium plates with inductive support , 2012 .

[6]  Tao Zhang,et al.  Image processing of weld pool and keyhole in Nd:YAG laser welding of stainless steel based on visual sensing , 2011 .

[7]  Koshun Iha,et al.  Artificial neural networks applied to epoxy composites reinforced with carbon and E-glass fibers: Analysis of the shear mechanical properties , 2007 .

[8]  Jong-Do Kim,et al.  Characteristics of butt-welded joints on AZ31 magnesium alloy using a Nd:YAG laser , 2010 .

[9]  Young Whan Park,et al.  Parameter optimization using a regression model and fitness function in laser welding of aluminum alloys for car bodies , 2011 .

[10]  Joerg Beersiek,et al.  A CMOS camera as a tool for process analysis not only for laser beam welding , 2001 .

[11]  Erkan Besdok,et al.  A Comparison of RBF Neural Network Training Algorithms for Inertial Sensor Based Terrain Classification , 2009, Sensors.

[12]  Tomonori Yamada,et al.  In-situ X-ray observation of molten pool depth during laser micro welding , 2012 .

[13]  F. Vollertsen,et al.  Numerical simulation of molten pool dynamics in high power disk laser welding , 2012 .

[14]  Zhi-Wei Chen,et al.  A study on fiber laser lap welding of thin stainless steel , 2013 .

[15]  Jae-Woong Kim,et al.  Design of a laser welded thin metal tube structure incorporating welding distortion and residual stress , 2010 .

[16]  Deyong You,et al.  Infrared image recognition for seam tracking monitoring during fiber laser welding , 2012 .

[17]  Deyong You,et al.  Seam Tracking Monitoring Based on Adaptive Kalman Filter Embedded Elman Neural Network During High-Power Fiber Laser Welding , 2012, IEEE Transactions on Industrial Electronics.

[18]  Yanxi Zhang,et al.  Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding , 2014 .

[19]  Ding Xuan-Tong,et al.  HL-2A tokamak disruption forecasting based on an artificial neural network , 2007 .

[20]  Gao Xiangdong,et al.  Monitoring of high-power fiber laser welding based on principal component analysis of a molten pool configuration , 2013 .