Monitoring of high-power fiber laser welding based on principal component analysis of a molten pool configuration

There exists plenty of welding quality information on a molten pool during high-power fiber laser welding. An approach for monitoring the high-power fiber laser welding status based on the principal component analysis (PCA) of a molten pool configuration is investigated. An infrared-sensitive high-speed camera was used to capture the molten pool images during laser butt-joint welding of Type 304 austenitic stainless steel plates with a high-power (10 kW) continuous wave fiber laser. In order to study the relationship between the molten pool configuration and the welding status, a new method based on PCA is proposed to analyze the welding stability by comparing the situation when the laser beam spot moves along, and when it deviates from the weld seam. Image processing techniques were applied to process the molten pool images and extract five characteristic parameters. Moreover, the PCA method was used to extract a composite indicator which is the linear combination of the five original characteristics to analyze the different status during welding. Experimental results showed that the extracted composite indicator had a close relationship with the actual welding results and it could be used to evaluate the status of the high-power fiber laser welding, providing a theoretical basis for the monitoring of laser welding quality.

[1]  X. Chen,et al.  Characterization and differentiation of normal and abnormal spermatozoa via micro-Raman spectroscopy , 2013 .

[2]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[3]  F. Vollertsen,et al.  Numerical simulation of molten pool dynamics in high power disk laser welding , 2012 .

[4]  Joaquín A. Pacheco,et al.  Exact methods for variable selection in principal component analysis: Guide functions and pre-selection , 2013, Comput. Stat. Data Anal..

[5]  M. Rethmeier,et al.  Plume attenuation of laser radiation during high power fiber laser welding , 2011 .

[6]  Re Gonzalez,et al.  R.C. Eddins, Digital image processing using MATLAB, vol. Gatesmark Publishing Knoxville , 2009 .

[7]  Do-Chang Ahn,et al.  Coaxial monitoring of keyhole during Yb:YAG laser welding , 2012 .

[8]  Y. Jamil,et al.  Recent advancements in spectroscopy using tunable diode lasers , 2013 .

[9]  L. Pazart,et al.  Microsensors and image processing for single oocyte qualification: toward multiparametric determination of the best?time for fertilization , 2013 .

[10]  Nikola Pavesic,et al.  Finger-based personal authentication: a comparison of feature-extraction methods based on principal component analysis, most discriminant features and regularised-direct linear discriminant analysis , 2009 .

[11]  Eam Khwang Teoh,et al.  Facial feature extraction and image warping using PCA based statistic model , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[12]  M. Rethmeier,et al.  Vapor–plasma plume investigation during high-power fiber laser welding , 2012 .

[13]  J. Liang,et al.  Sharp feature extraction in point clouds , 2012 .

[14]  M. Wahba,et al.  Keyhole stability in disc laser welding of AZ31B and AZ61A magnesium alloys and weld metal properties , 2010 .

[15]  P. D. Thouin,et al.  Survey and comparative analysis of entropy and relative entropy thresholding techniques , 2006 .

[16]  Nickolai V. Kukhtarev,et al.  Recording holograms of micro-scale objects in real time , 2013 .

[17]  Desire L. Massart,et al.  Feature selection in principal component analysis of analytical data , 2002 .

[18]  Deyong You,et al.  Seam Tracking Monitoring Based on Adaptive Kalman Filter Embedded Elman Neural Network During High-Power Fiber Laser Welding , 2012, IEEE Transactions on Industrial Electronics.

[19]  J. W. Hines,et al.  Differentiating between expanded and fault conditions using principal component analysis , 2012, J. Intell. Manuf..

[20]  Seiji Katayama,et al.  Weld-pool image centroid algorithm for seam-tracking vision model in arc-welding process , 2011 .

[21]  W. L. Woo,et al.  Image-based facial recognition in the domain of high-order polynomial one-way mapping , 2008 .

[22]  Energy Coupling Rate in Aluminum Welding by CO2 Laser and Nd:YAG Laser. , 2003 .

[23]  Asit K. Datta,et al.  Generalized regression neural network trained preprocessing of frequency domain correlation filter for improved face recognition and its optical implementation , 2013 .

[24]  Arun Anand.  Tracing of interference fringes using average gray value and simultaneous row and column scan , 2003 .

[25]  I. Jolliffe.  Principal Component Analysis , 2002 .

[26]  A keyhole volumetric model for weld pool analysis in Nd:YAG pulsed laser welding , 2012 .

[27]  S. Na,et al.  Seam tracking based on estimation of weld position using Kalman filtering , 2005 .

[28]  Rong Chen,et al.  Near-infrared confocal micro-Raman spectroscopy combined with PCA–LDA multivariate analysis for detection of esophageal cancer , 2013 .

[29]  Igor Meglinski,et al.  Application of wavelet analysis in optical coherence tomography for obscured pattern recognition , 2009 .