Thirteenth international conference on computerization of welding

The development of a novel sensing method coupled with a pattern recognition system is presented as a non-destructive evaluation (NDE) technique for inertia friction welding. The complex nature of sohd-state welding processes, and, in particular, inertia friction welding, prevents a system from incorporating a simple model (e.g., upset) to separate acceptable from unacceptable welds when subtle process variations occur. This work presents the application of an array of non-contact, acoustic emission sensors for determining bond integrity. The sensor data is explored through a variety of feature descriptors (RMS, energy, attack and decay, and power spectrum) and, in some cases, fused with the machine data (speed, pressure, and upset) in an attempt to develop a robust, in-situ NDE technique. The results are presented for bar-to-bar inertia friction welding of copper to stainless steel which exhibits only marginal weldability and, therefore, is ideally suited for validating the capabilities of this new sensing technique.

[1]  John Lancaster,et al.  The Physics of Welding , 1984 .

[2]  K. Hiraoka,et al.  GMA Welding Process with Periodically Controlling Shielding Gas Composition. Development of Ultra-Narrow Gap GMA Welding Process. Report 3. , 2002 .

[3]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[4]  Gerhard Pahl,et al.  Konstrucktionslehre : Methoden und Anwendung , 1993 .

[5]  J. S. Hunter,et al.  Statistics for Experimenters: An Introduction to Design, Data Analysis, and Model Building. , 1979 .

[6]  P. Sink.  A Comprehensive Guide to Industrial Networks, Part 2: Embedded Networking 101-The Nuts and Bolts of Hardware and Software Design , 2001 .

[7]  Joseph R. Davis,et al.  Welding, brazing, and soldering , 1993 .

[8]  M. Ashby,et al.  Engineering Materials 2: An Introduction to Microstructures, Processing and Design , 1986 .

[9]  K. Hiraoka,et al.  Wire Melting Behavior by Non-Steady Heat Conduction Numerical Analysis in Gas Metal Arc Welding. Development of Ultra-Narrow Gap GMA Welding Process. Report 2. , 2002 .

[10]  Jeong-ick Lee,et al.  A comparison in a back-bead prediction of gas metal arc welding using multiple regression analysis and artificial neural network , 2000 .

[11]  V. Malin.  Monograph on Narrow-Gap Welding Technology , 1987 .

[12]  H. P. Seow,et al.  Effect of increasing deposition rate on the bead geometry of submerged arc welds , 1997 .

[13]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[14]  T. Quinn,et al.  Arc sensing for defects in constant-voltage gas metal arc welding , 1999 .

[15]  Malcolm Bibby,et al.  Modelling Gas Metal Arc Weld Geometry Using Artificial Neural Network Technology , 1999 .

[16]  Yukio Ueda,et al.  Weldability analysis of spot welding on aluminum using FEM , 1995 .

[17]  C. Shiga.  Systematic approach to solution of welding problems in STX21 project: aiming for remarkable advances in welded joints , 2000 .

[18]  Alvin M. Strauss,et al.  Dynamic model for electrode melting rate in gas metal arc welding process , 2001 .

[19]  Jamil A. Khan,et al.  Prediction of nugget development during resistance spot welding using coupled thermal–electrical–mechanical model , 1999 .

[20]  Alvin M. Strauss,et al.  Statistical process control application to weld process , 1997 .

[21]  Xin Sun,et al.  Analysis of aluminum resistance spot welding processes using coupled finite element procedures , 2000 .

[22]  T G Lim,et al.  Estimation of Weld Pool Sizes in GMA Welding Process Using Neural Networks , 1993 .

[23]  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,.

[24]  S. B. Chen,et al.  Intelligent methodology for sensing, modeling and control of pulsed GTAW : Part 2: Butt joint welding , 2000 .

[25]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[26]  V. R. Dave,et al.  Nondestructive, in-process inspection of inertia friction welding : an investigation into a new sensing technique. , 2002 .