Optimal features combination for pulsed eddy current NDT

This paper investigates current feature extraction techniques for pulsed eddy current NDT including peak value and peak time, spectral characteristics analysis, principal component analysis (PCA) projection coefficient and response shape curvature. Experimental study has been undertaken on samples with artificial surface and subsurface defects and metal thickness changes. Based on a comparative study of the feature extraction techniques, the most suitable features and their combination are discussed. The present study will provide a framework for future applications comprising the characterisation of real defects and stress profiles in engineering components.

[1]  Baback Moghaddam,et al.  Principal Manifolds and Probabilistic Subspaces for Visual Recognition , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[3]  Binfeng Yang,et al.  QUANTIFICATION AND CLASSIFICATION OF CRACKS IN AIRCRAFT MULTI-LAYERED STRUCTURE , 2006 .

[4]  James H. Rose,et al.  Scanned pulsed eddy current instrument for nondestructive inspection of aging aircraft , 1996, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[5]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Gui Yun Tian,et al.  Electromagnetic and Eddy Current NDT: A Review , 2001 .

[7]  Y. Bar-Cohen,et al.  Emerging NDT technologies and challenges at the beginning of the third millennium, Part 2 , 2000 .

[8]  V. Kshirsagar,et al.  Face recognition using Eigenfaces , 2011, 2011 3rd International Conference on Computer Research and Development.

[9]  Robert A. Smith,et al.  Transient eddy-current NDE for ageing aircraft - Capabilities and limitations. , 2001 .

[10]  Gui Yun Tian,et al.  Wavelet-based PCA defect classification and quantification for pulsed eddy current NDT , 2005 .

[11]  Gui Yun Tian,et al.  Comparison Of Pec And Sfec Nde Techniques , 2009 .

[12]  Gui Yun Tian,et al.  Feature extraction and selection for defect classification of pulsed eddy current NDT , 2008 .

[13]  J. Rudlin,et al.  Multiple sensors on pulsed eddy-current detection for 3-D subsurface crack assessment , 2005, IEEE Sensors Journal.

[14]  Gui Yun Tian,et al.  DEFECT CLASSIFICATION USING A NEW FEATURE FOR PULSED EDDY CURRENT SENSORS , 2005 .