A novel feature extraction method of eddy current testing for defect detection based on machine learning

Abstract In eddy current testing, the trajectory of the impedance data due to a defect is presented as a Lissajous curve (LC) in the complex plane. This paper proposes a novel analytical model for describing a LC. Further, a new feature extraction method is implemented which automatically computes four geometric features (amplitude, width, angle and symmetry) from Lissajous figures. In addition, six machine learning-based classifiers are used for automatic defect identification based on these features. High detection rates are achieved for both the simulated and experimental data, which demonstrates the flexibility of the analytical model and the validity of the methodology.

[1]  Aouni A. Lakis,et al.  Application of time–frequency analysis for automatic hidden corrosion detection in a multilayer aluminum structure using pulsed eddy current , 2012 .

[2]  Luigi Ferrigno,et al.  Crack Shape Reconstruction in Eddy Current Testing Using Machine Learning Systems for Regression , 2008, IEEE Transactions on Instrumentation and Measurement.

[3]  E. Ruiz.  An algorithm for finding nearest neighbours in (approximately) constant average time , 1986 .

[4]  Peter Cawley,et al.  A review of non-destructive techniques for the detection of creep damage in power plant steels , 2010 .

[5]  Yoshiaki Nagaya,et al.  Identification of multiple cracks from eddy-current testing signals with noise sources by image processing and inverse analysis , 2004 .

[6]  Patrick Stalph.  Analysis and Design of Machine Learning Techniques , 2014 .

[7]  G. Betta,et al.  Fast 2D crack profile reconstruction by image processing for Eddy-Current Testing , 2015, 2015 IEEE Metrology for Aerospace (MetroAeroSpace).

[8]  Gianni D'Angelo,et al.  Fast Eddy Current Testing Defect Classification Using Lissajous Figures , 2018, IEEE Transactions on Instrumentation and Measurement.

[9]  David D. Lewis,et al.  Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval , 1998, ECML.

[10]  Gianni D'Angelo,et al.  Shape-based defect classification for non destructive testing , 2015, 2015 IEEE Metrology for Aerospace (MetroAeroSpace).

[11]  Maria Wrzuszczak,et al.  Eddy current flaw detection with neural network applications , 2005 .

[12]  Yifei Zhao,et al.  Sparse electromagnetic tomography based on matching pursuit algorithms , 2016, 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[13]  Wuliang Yin,et al.  A Very-Low-Frequency Electromagnetic Inductive Sensor System for Workpiece Recognition Using the Magnetic Polarizability Tensor , 2017, IEEE Sensors Journal.

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

[15]  Gianni D'Angelo,et al.  Automated Eddy Current non-destructive testing through low definition lissajous figures , 2016, 2016 IEEE Metrology for Aerospace (MetroAeroSpace).

[16]  Wuliang Yin,et al.  The Design of a Digital Magnetic Induction Tomography (MIT) System for Metallic Object Imaging Based on Half Cycle Demodulation , 2011, IEEE Sensors Journal.

[17]  Federico Girosi,et al.  Support Vector Machines: Training and Applications , 1997 .

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

[19]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[20]  Feilu Luo,et al.  Pulsed eddy current imaging and frequency spectrum analysis for hidden defect nondestructive testing and evaluation , 2011 .

[21]  L.A.N.M. Lopez,et al.  Removing Eddy-Current probe wobble noise from steam generator tubes testing using Wavelet Transform , 2008 .

[22]  Feilu Luo,et al.  PEC defect automated classification in aircraft multi-ply structures with interlayer gaps and lift-offs , 2013 .

[23]  Thomas W. Krause,et al.  Simultaneous Multiparameter Measurement in Pulsed Eddy Current Steam Generator Data Using Artificial Neural Networks , 2016, IEEE Transactions on Instrumentation and Measurement.

[24]  Hans-Martin Thomas,et al.  NDT techniques for railroad wheel and gauge corner inspection , 2004 .

[25]  Lior Rokach,et al.  Ensemble-based classifiers , 2010, Artificial Intelligence Review.

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

[27]  M. Bodruzzaman,et al.  Estimation of micro-crack lengths using eddy current C-scan images and neural-wavelet transform , 2008, IEEE SoutheastCon 2008.

[28]  T. Chady,et al.  Flaws Identification Using an Approximation Function and Artificial Neural Networks , 2007, IEEE Transactions on Magnetics.

[29]  Luis S. Rosado,et al.  Defect Characterization With Eddy Current Testing Using Nonlinear-Regression Feature Extraction and Artificial Neural Networks , 2013, IEEE Transactions on Instrumentation and Measurement.

[30]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.