Online defect detection of Al alloy in arc welding based on feature extraction of arc spectroscopy signal

In this paper, a novel methodology for real-time nondestructive defect detection, particularly hydrogen-assisted porosity of an aluminum alloy welded using pulsed gas tungsten arc welding is presented based on the plasma spectroscopy signal of the welding arc. The emission lines of the hydrogen atom at 656.3 nm and argon atom at 641.63 nm were analyzed to extract multiple feature parameters, from which more sensitive features were then selected for monitoring by means of Fisher distance criteria. The threshold detection method based on the features selected from the spectrum was found to be feasible in detecting the welding defect, i.e., porosity in real-time. Furthermore, the established predicting model based on SVM-CV also successfully identified defect of porosity from normal welding with high accuracy.

[1]  J. E. Shea,et al.  Spectroscopic measurement of hydrogen contamination in weld arc plasmas , 1983 .

[2]  Yanling Xu,et al.  Arc spectral processing technique with its application to wire feed monitoring in Al–Mg alloy pulsed gas tungsten arc welding , 2013 .

[3]  Elijah Kannatey-Asibu,et al.  Tool Failure Monitoring in Turning by Pattern Recognition Analysis of AE Signals , 1988 .

[4]  Y. M. Zhang,et al.  Analysis of an arc light mechanism and its application in sensing of the GTAW process , 2000 .

[5]  Bernhard Schölkopf,et al.  Feature selection for support vector machines by means of genetic algorithm , 2003, Proceedings. 15th IEEE International Conference on Tools with Artificial Intelligence.

[6]  Elijah Kannatey-Asibu,et al.  Monitoring of laser weld penetration using sensor fusion , 2002 .

[7]  Giles M. Foody,et al.  Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification , 2004 .

[8]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[9]  Radovan Kovacevic,et al.  Development of a real-time laser-based machine vision system to monitor and control welding processes , 2012 .

[10]  Y. M. Zhang,et al.  Characterization of Three-Dimensional Weld Pool Surface in GTAW The width, length, and convexity of the 3D weld pool surface provided the optimal model for accurately predicting the backside bead width , 2012 .

[11]  Jing Wu,et al.  Intelligentized Methodology for Arc Welding Dynamical Processes , 2009, Lecture Notes in Electrical Engineering.

[12]  M. Węglowski,et al.  Monitoring of Arc Welding Process Based on Arc Light Emission , 2012 .

[13]  Huanwei Yu,et al.  Real-time defect detection in pulsed GTAW of Al alloys through on-line spectroscopy , 2013 .

[14]  Elijah Kannatey-Asibu,et al.  Sensor systems for real-time monitoring of laser weld quality , 1999 .

[15]  E. Kannatey-Asibu.  Principles of Laser Materials Processing , 2009 .

[16]  Radovan Kovacevic,et al.  Real-Time Image Processing for Monitoring of Free Weld Pool Surface , 1997 .

[17]  B. K. Christner.  DEVELOPING A GTAW PENETRATION CONTROL SYSTEM FOR THE TITAN IV PROGRAM , 1998 .

[18]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[19]  Shanben Chen,et al.  Passive vision based seam tracking system for pulse-MAG welding , 2013 .

[20]  Yu-Ming Zhang,et al.  Robust sensing of arc length , 2001, IEEE Trans. Instrum. Meas..

[21]  Adolfo Cobo,et al.  Real-time arc welding defect detection technique by means of plasma spectrum optical analysis , 2006 .