A study on the prediction of bead geometry in the robotic welding system

The gas metal are (GMA) welding is one of the most widely-used processes in metal joining process that involves the melting and solidification of the joined materials. To solve this problem, we have carried out the sequential experiment based on a Taguchi method and identified the various problems that result from the robotic GMA welding process to characterize the GMA welding process and establish guidelines for the most effective joint design. Also using multiple regression analysis with the help of a standard statistical package program, SPSS, on an IBM-compatible PC, three empirical models (linear, interaction, quadratic model) have been developed for off-line control which studies the influence of welding parameters on bead width and compares their influences on the bead width to check which process parameter is most affecting. These models developed have been employed for the prediction of optimal welding parameters and assisted in the generation of process control algorithms.

[1]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[2]  C. Y. Liu,et al.  The deflection of a simply supported plate induced by piezoelectric actuators , 2007 .

[3]  A. El-Azim,et al.  Accelerated aging processes in SiC-7020 aluminium composite , 1998 .

[4]  Prasad K. Yarlagadda,et al.  A study on the quality improvement of robotic GMA welding process , 2003 .

[5]  J.-Y. Jeng,et al.  Prediction of laser butt joint welding parameters using back propagation and learning vector quantization networks , 2000 .

[6]  D. K. Feder.  Computers in Welding Technology — A Look at Applications and Potentials , 1988 .

[7]  Dynamic mechanical properties of photo resist thin films , 2007 .

[8]  Y. S. Tarng,et al.  A comparison between the back-propagation and counter-propagation networks in the modeling of the TIG welding process , 1998 .

[9]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[10]  D. S. Nagesh,et al.  Prediction of weld bead geometry and penetration in shielded metal-arc welding using artificial neural networks , 2002 .

[11]  Y. S Tarng,et al.  Modeling, optimization and classification of weld quality in tungsten inert gas welding , 1999 .

[12]  James P. Ignizio,et al.  A practical overview of neural networks , 1997, J. Intell. Manuf..

[13]  Ill-Soo Kim,et al.  An investigation into an intelligent system for predicting bead geometry in GMA welding process , 2005 .