Pulsed Eddy Current Data Analysis for the Characterization of the Second-Layer Discontinuities

Pulsed eddy current (PEC) technique has been applied as a viable method to detect hidden discontinuities in metallic structures. Conventionally, selected time-domain features are employed to characterize the PEC data, such as peak value, lift-off point of intersection, rising point, crossing time, and differential time to peak. The research presented in this paper continues the effort in a previous study on detecting the radial cracks starting from the fastener hole in second layer of a two-layer mock-up aircraft structure. A large diameter excitation coil with ferrite core is used to induce a strong pulse, and the magnetic field generated by eddy current is detected by Hall sensors. Instead of analyzing the limited time-domain features, we propose using machine learning methods to interpret the raw data without feature extraction. Thus, the second-layer discontinuities can be characterized presumably with all the information contained in a waveform. An automated detection framework is proposed in this paper and the experimental results demonstrate the effectiveness of the proposed method.

[1]  José Augusto Baranauskas,et al.  How Many Trees in a Random Forest? , 2012, MLDM.

[2]  Xinjun Wu,et al.  Assessment of wall thinning in insulated ferromagnetic pipes using the time-to-peak of differential pulsed eddy-current testing signals , 2012 .

[3]  Mustafa Neamah Jebur,et al.  Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS , 2014 .

[4]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[5]  Vladimir Vapnik,et al.  Support-vector networks , 2004, Machine Learning.

[6]  Mengchun Pan,et al.  Support vector machine and optimised feature extraction in integrated eddy current instrument , 2013 .

[7]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[8]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[9]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

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

[11]  Yunze He,et al.  Pulsed eddy current technique for defect detection in aircraft riveted structures , 2010 .

[12]  Zheng Liu,et al.  Pedestrian detection in thermal images using adaptive fuzzy C-means clustering and convolutional neural networks , 2015, 2015 14th IAPR International Conference on Machine Vision Applications (MVA).

[13]  R. W. Baines,et al.  The research of inhomogeneity in eddy current sensors , 1998 .

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  Yong Li,et al.  Generalized Analytical Expressions of Liftoff Intersection in PEC and a Liftoff-Intersection-Based Fast Inverse Model , 2011, IEEE Transactions on Magnetics.

[16]  Sang Won Yoon,et al.  Breast cancer diagnosis based on feature extraction using a hybrid of K-means and support vector machine algorithms , 2014, Expert Syst. Appl..

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

[18]  Gui Yun Tian,et al.  Pulsed Eddy Current Non-destructive Testing and Evaluation: A Review , 2017 .

[19]  Zheng Liu,et al.  Pulsed Eddy Current Inspections of Aircraft Structures in Support of Holistic Damage Tolerance , 2003 .

[20]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[21]  Gábor Vértesy,et al.  Detection of the Subsurface Cracks in a Stainless Steel Plate Using Pulsed Eddy Current , 2013 .

[22]  Zheng Liu,et al.  Investigations on classifying pulsed eddy current signals with a neural network , 2003 .

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

[24]  Feilu Luo,et al.  PEC Frequency Band Selection for Locating Defects in Two-Layer Aircraft Structures With Air Gap Variations , 2013, IEEE Transactions on Instrumentation and Measurement.

[25]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[26]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[27]  E. Kriezis,et al.  Eddy currents: theory and applications , 1992, Proc. IEEE.

[28]  Chong-Oh Kim,et al.  The Pulsed Eddy Current Differential Probe to Detect a Thickness Variation in an Insulated Stainless Steel , 2010 .

[29]  Ruzlaini Ghoni,et al.  Defect Characterization Based on Eddy Current Technique: Technical Review , 2014 .

[30]  Seid Mohammad Saleh Hosseini.  DETECTION OF HIDDEN CORROSION BY PULSED EDDY CURRENT USING TIME FREQUENCY ANALYSIS , 2012 .

[31]  Colette A. Stott,et al.  Pulsed Eddy Current Detection of Cracks in Multilayer Aluminum Lap Joints , 2015, IEEE Sensors Journal.

[32]  Junzhe Gao,et al.  Defect classification based on rectangular pulsed eddy current sensor in different directions , 2010 .

[33]  D. S. Forsyth,et al.  Time-Frequency Analysis of Pulsed Eddy Current Signals , 2001 .

[34]  C. Mandache,et al.  Study of Lift-Off Invariance for Pulsed Eddy-Current Signals , 2009, IEEE Transactions on Magnetics.