Quality evaluation in small-scale resistance spot welding by electrode voltage recognition

This study focuses on weld quality evaluation by electrode voltage in small-scale resistance spot welding of titanium alloy. Voltage curve could be divided into four stages based on the variation characteristic. The single voltage peak was detected as combined effects of increasing bulk material resistivity and nugget size. Variations of voltage curve shape, voltage peak and failure load were more sensitive to welding current than electrode force. A generalised regression neural network was proposed to evaluate weld quality using features extracted from voltage signal. A discrete Hopfield neural network was also applied for electrode voltage recognition. The recognised voltage patterns were found effective in identifying different quality levels. A real-time and on-line quality monitoring system could be developed.

[1]  K. J. Ely,et al.  Microresistance spot welding of Kovar, steel, and nickel , 2001 .

[2]  Abderrazak El Ouafi,et al.  An On-Line ANN-Based Approach for Quality Estimation in Resistance Spot Welding , 2010 .

[3]  Michel Guillot,et al.  Dynamic Resistance Based Model for On-Line Resistance Spot Welding Quality Assessment , 2012 .

[4]  Yung-Chang Chen,et al.  Electrode Displacement and Dynamic Resistance During Small-Scale Resistance Spot Welding , 2012 .

[5]  Guoxiang Meng,et al.  Experimental study on electrode displacement fluctuation characteristics during resistance spot welding , 2011 .

[6]  D. W. Dickinson,et al.  Characterization of Spot Welding Behavior by Dynamic Electrical Parameter , 2013 .

[7]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[8]  M. Nishijima,et al.  Weldability of Zr50Cu30Al10Ni10 bulk glassy alloy by small-scale resistance spot welding , 2008 .

[9]  Sehun Rhee,et al.  New technology for measuring dynamic resistance and estimating strength in resistance spot welding , 2000 .

[10]  Dave F. Farson,et al.  Monitoring of expulsion in small scale resistance spot welding , 2003 .

[11]  Y. Zhou,et al.  A study of dynamic resistance during small scale resistance spot welding of thin Ni sheets , 2004 .

[12]  Y J Park,et al.  Quality evaluation by classification of electrode force patterns in the resistance spot welding process using neural networks , 2004 .

[13]  Fujun Wang,et al.  Quality assessment for resistance spot welding based on binary image of electrode displacement signal and probabilistic neural network , 2014 .

[14]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[15]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[16]  Primož Podržaj,et al.  Resistance spot weld strength estimation based on electrode tip displacement/velocity curve obtained by image processing , 2014 .

[17]  Kana Fujiwara,et al.  Small-scale resistance spot welding of austenitic stainless steels , 2008 .

[18]  S. Bhole,et al.  Expulsion monitoring in spot welded advanced high strength automotive steels , 2006 .

[19]  Yansong Zhang,et al.  Effect of variable electrode force on weld quality in resistance spot welding , 2007 .