Spectral processing technique based on feature selection and artificial neural networks for arc-welding quality monitoring

The validity of a processing technique, based on feature selection and artificial neural networks, when applied to arc-welding on-line quality monitoring is analyzed. An optical fiber embedded within the welding torch captures the plasma radiation, which is delivered to a CCD spectrometer. In the proposed solution the spectral analysis is performed in two stages: dimensionality reduction is accomplished using a feature selection algorithm and, after that, an artificial neural network carries out the spectral identification task. The validity of the technique has been successfully demonstrated by means of several experimental welding tests.

[1]  A. Marotta,et al.  Determination of axial thermal plasma temperatures without Abel inversion , 1994 .

[2]  Elfed Lewis,et al.  Combining principal component analysis with an artificial neural network to perform online quality assessment of food as it cooks in a large-scale industrial oven , 2005 .

[3]  Adolfo Cobo,et al.  Embedded spectroscopic fiber sensor for on-line arc-welding analysis. , 2007, Applied optics.

[4]  Moshe Tur,et al.  Instrumentation for the monitoring of toxic pollutants in water resources by means of neural network analysis of absorption and fluorescence spectra , 2007 .

[5]  T. R. Anderson.  Control of electromagnetic interference from arc and electron beam welding by controlling the physical parameters in arc or electron beam theoretical model , 2000, IEEE International Symposium on Electromagnetic Compatibility. Symposium Record (Cat. No.00CH37016).

[6]  Pietro Mario Lugarà,et al.  Correlation analysis in laser welding plasma , 2005 .

[7]  G. Camps-Valls,et al.  Feature selection of hyperspectral data through local correlation and SFFS for crop classification , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[8]  Yaowen Wang,et al.  Noncontact acoustic analysis monitoring of plasma arc welding , 2001 .

[9]  Masao Ushio,et al.  Analysis of the TIG welding arc behavior , 1997 .

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

[11]  David Naso,et al.  A fuzzy-logic based optical sensor for online weld defect-detection , 2005, IEEE Transactions on Industrial Informatics.

[12]  A Cobo,et al.  Plasma spectroscopy analysis technique based on optimization algorithms and spectral synthesis for arc-welding quality assurance. , 2007, Optics express.

[13]  P. M. Lugarà,et al.  Optical Sensor for real-time Monitoring of CO(2) Laser Welding Process. , 2001, Applied optics.

[14]  M F Thornton,et al.  Spectroscopic determination of temperature distributions for a TIG arc , 1993 .

[15]  Rodney M. Forster,et al.  Imaging spectroscopy as a tool to study sediment characteristics on a tidal sandbank in the Westerschelde , 2006 .

[16]  Bryan A. Chin,et al.  Infrared sensing techniques for penetration depth control of the submerged arc welding process , 2001 .

[17]  Pietro Mario Lugarà,et al.  A sensing torch for on-line monitoring of the gas tungsten arc welding process of steel pipes , 2004 .

[18]  D. J. Brookfield,et al.  Plasma charge sensor for in-process, non-contact monitoring of the laser welding process , 1996 .

[19]  J. López-Higuera,et al.  Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks , 2007 .

[20]  H. Griem.  Principles of Plasma Spectroscopy , 1997 .

[21]  Vincenzo Spagnolo,et al.  Optical sensor for real-time weld defect detection , 2002, IS&T/SPIE Electronic Imaging.

[22]  Francesc J. Ferri,et al.  Comparative study of techniques for large-scale feature selection* *This work was suported by a SERC grant GR/E 97549. The first author was also supported by a FPI grant from the Spanish MEC, PF92 73546684 , 1994 .

[23]  Cesar Jauregui,et al.  Fast algorithm for spectral processing with application to on-line welding quality assurance , 2006 .