Mixed logical dynamical model for back bead width prediction of pulsed GTAW process with misalignment

The purpose of this paper is to propose a kind of mixed logical dynamical (MLD) model to predict the back bead width of pulsed GTAW process with misalignment. Misalignment is considered as discrete input and the nonlinear welding process is approximated using piecewise linear models. A MLD model is then established and gives a good prediction quality of the back bead width of pulsed GTAW process with misalignment. The stability and reliability of the MLD model are tested by a closed loop control experiment. This study shows that the MLD framework is a good modeling method for pulsed GTAW process. Thus, a solid foundation for penetration control of welding process is established based on the MLD model.

[1]  Lin Li,et al.  Adaptive control of full penetration gas tungsten arc welding , 1996, IEEE Trans. Control. Syst. Technol..

[2]  Weimin Zhang,et al.  On-line predication of underwater welding penetration depth based on multi-sensor data fusion , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[3]  W. Duley,et al.  The effect of surface condition on acoustic emission during welding of aluminium with CO2 laser radiation , 1994 .

[4]  I. C. Ume,et al.  Measuring on-line and off-line noncontact ultrasound time of flight weld penetration depth , 2007 .

[5]  Alberto Bemporad,et al.  HYSDEL-a tool for generating computational hybrid models for analysis and synthesis problems , 2004, IEEE Transactions on Control Systems Technology.

[6]  Chiung-Hsin Tsai,et al.  Fuzzy control of pulsed GTA welds by using real-time root bead image feedback , 2006 .

[7]  Ario Sunar Baskoro,et al.  An application of genetic algorithm for edge detection of molten pool in fixed pipe welding , 2009 .

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

[9]  Satoshi Yamane,et al.  Neural Network Model of Weld Pool in Pulsed MIG Welding , 2003 .

[10]  林涛,et al.  A Generalized Rough Set Modeling Method for Welding Process , 2007 .

[11]  Dongbin Zhao,et al.  Intelligent methodology for sensing, modeling and control of pulsed GTAW : Part 1 : Bead-on-plate welding , 2000 .

[12]  Shanben Chen,et al.  SVM-based fuzzy modeling for the arc welding process , 2006 .

[13]  Jay F. Tu,et al.  On-Line Estimation of Laser Weld Penetration , 1997 .

[14]  Alberto Bemporad,et al.  Control of systems integrating logic, dynamics, and constraints , 1999, Autom..

[15]  Shanben Chen,et al.  Visual sensing and penetration control in aluminum alloy pulsed GTA welding , 2009 .

[16]  G. Karsai,et al.  Artificial neural networks applied to arc welding process modeling and control , 1989, Conference Record of the IEEE Industry Applications Society Annual Meeting,.