Feature-selective clustering for ultrasonic-based automatic defect detection in FRP structures

Abstract Ultrasonic inspection technique has been commonly used in defect detection of fiber reinforced polymer (FRP) materials, which transmits sound waves into materials and analyses the reflection signals. Although a variety of signal processing methods have been applied to highlight the defect features contained in ultrasonic signals, the most usual way to identify the defective regions is still not automatic, which is not only time-consuming but also critically dependent upon operator's experience. In order to solve this problem, a feature-selective unsupervised clustering method is adopted for automatic defect detection. By adaptively choosing the useful subset of features, the sizes and locations of the defective regions can be identified accurately, with the defect depths estimated at the same time. The feasibility of the proposed method is illustrated by the experiment on a carbon fiber reinforced polymer (CFRP) specimen constructed with known artificial defects by resin transfer molding.

[1]  C. H. Chen,et al.  Handbook of Pattern Recognition and Computer Vision , 1993 .

[2]  P. Rousseeuw,et al.  Alternatives to the Median Absolute Deviation , 1993 .

[3]  Yufeng Liu,et al.  Variable Selection via A Combination of the L0 and L1 Penalties , 2007 .

[4]  Ahmad Osman,et al.  Automated Evaluation of Three Dimensional Ultrasonic Datasets , 2014 .

[5]  Rachel S. Edwards,et al.  Characterisation of defects in the railhead using ultrasonic surface waves , 2006 .

[6]  Krishnan Balasubramaniam,et al.  Directional filter bank-based segmentation for improved evaluation of nondestructive evaluation images , 2007 .

[7]  Robert Tibshirani,et al.  A Framework for Feature Selection in Clustering , 2010, Journal of the American Statistical Association.

[8]  Yuan Yao,et al.  Thermographic clustering analysis for defect detection in CFRP structures , 2016 .

[9]  Waleed Al-Nuaimy,et al.  Combining fuzzy logic and neural networks in classification of weld defects using ultrasonic time-of-flight diffraction , 2007 .

[10]  Yuan Yao,et al.  Improved non-destructive testing of carbon fiber reinforced polymer (CFRP) composites using pulsed thermograph , 2015 .

[11]  Sam-Kit Sin,et al.  A comparison of deconvolution techniques for the ultrasonic nondestructive evaluation of materials , 1992, IEEE Trans. Image Process..

[12]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[13]  Radislav Smid,et al.  Classification of ultrasonic signals , 2006 .

[14]  Benammar Abdessalem,et al.  Enhancement of Phased Array Ultrasonic Signal in Composite Materials using TMST Algorithm , 2015 .

[15]  Lalita Udpa,et al.  Neural networks for ultrasonic detection of intergranular stress corrosion cracking , 2000 .

[16]  Yuan Yao,et al.  Defect detection in CFRP structures using pulsed thermographic data enhanced by penalized least squares methods , 2015 .

[17]  Daniel Massicotte,et al.  Ultrasonic NDE of composite material structures using wavelet coefficients , 2001 .

[18]  Ilkka Ylaekoski.  Unsupervised classification of ultrasonic nondestructive testing (NDT) data , 1994, Other Conferences.

[19]  Yuan Yao,et al.  Online estimation and monitoring of local permeability in resin transfer molding , 2016 .

[20]  Joseph Moysan,et al.  Bscan image segmentation by thresholding using cooccurrence matrix analysis , 1996, Pattern Recognit..

[21]  S.S. Udpa,et al.  Frequency invariant classification of ultrasonic weld inspection signals , 1998, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.