Article Article
An Ultrasonic Guided Wave Signal Processing and Pattern Recognition Tool for Studying the Discontinuity Axial Length

Recently the use of ultrasonic guided wave for detecting has become attractive in nondestructive testing. The axial length of the pipe discontinuity is not linear with the guided wave signal amplitude. Thus, it is difficult to identify the degree of damage using the reflection coefficient. In order to explore the relationship between the guided wave signal and the discontinuity length, an ultrasonic processing and pattern recognition tool is studied. The characteristic information of the guided wave signal is extracted by wavelet packet decomposition technique. Several temporal characteristics on each scale are combined to a feature set. In order to reduce the computational complexity, the dimension of the feature set is reduced by the kernel sliced inverse regression (KSIR) algorithm. A pattern recognition model, the continuous hidden markov model (CHMM), is intro-duced to classify and identify different states of the pipe by pre-trained models. Comparing to the log-likelihood probability calculated by all classi-fiers, the maximum value corresponds to the right state. A guided wave test to a pipe with artificial corrosion on the outer surface was conducted to verify the correctness of the algorithm. Five discon-tinuity levels were identified correctly, achieving the objective of preliminary quantitative evaluation. The results show that the CHMM model is more robust and can accurately identify the axial discontinuities.


Demma A., P. Cawley and M. Lowe, “Scattering of the Fundamental Shear Horizontal Mode from Steps and Notches in Plates,” Journal of the Acoustical Society of America, Vol. 113, No. 4, 2003, pp. 1880–1891.

Lee, Jong Min, Seung-Jong Kim, Yoha Hwang, and Chang-Seop Song, “Diagnosis of Mechanical Fault Signals Using Continuous Hidden Markov Model,” Journal of Sound and Vibration, Vol. 276, No. 3–5,  2004, pp. 1065–1080.

Li, Ker-Chau, “Sliced Inverse Regression for Dimension Reduction,” Journal of the American Statistical Association, Vol. 86, No. 414, 1991, pp. 316–327.

Li, Shanglei, Anish Poudel, and Tsuchin Philip Chu, “Ultrasonic Defect Mapping Using Signal Correlation for NDE,” Research in Nondestructive Evaluation, Vol. 26, No. 2,  2015, pp. 90-106.

Poudel, A., Kanneganti, R., Li, S., Gupta, L., et al, “Classification of Ultra-sonic Echo Signals to Detect Embedded Defects in CFRP Panels,” Interna-tional Journal of Microstructure and Materials PropertiesVol. 10, No. 3-4, 2015,  pp. 216–230.

Rabiner, L. R., B.H. Juang, S.E. Levinson, and M.M. Sondhi,, “Recognition of Isolated Digits Using Hidden Markov Models with Continuous Mixture Densities,” AT&T Technical Journal, Vol. 64, No. 6, 1985,  pp. 1211–1234.

Rose, J. L.,2014, Ultrasonic Guided Waves in Solid Media, Cambridge: Cambridge University Press.

Siqueira M. H. S., C. E. N. Gatts, R. R. da Silva, and J.M.A. Rebello,, “The Use of Ultrasonic Guided Waves and Wavelets Analysis in Pipe Inspec-tion,” Ultrasonics, Vol. 41, No. 10, 2004, pp. 785–797.

Tse, Peter W. and X. Wang, “Characterization of Pipeline Defect in Guided-waves Based Inspection through Matching Pursuit with the Opti-mized Dictionary”,   NDT & E International, Vol .54, 2013, pp. 171–182.

Vinogradov, Sergey, “Development of Enhanced Guided Wave Screening Using Broadband Magnetostrictive Transducer and Non-Linear Signal Processing ,” Fourth Japan-US Symposium on Emerging NDE Capabilities for a Safer World, Maui Island, Hawaii 7–11 June 2010.

Wu, Han-Ming, “Kernel Sliced Inverse Regression with Applications to Classification,” Journal of Computational and Graphical Statistics, Vol. 17, No. 3, 2008, pp. 590–610.

Zhao, Li-Ye., Lei Wang, and Ru-Qiang Yan,,”Rolling Bearing Fault Diag-nosis Based on Wavelet Packet Decomposition and Multi-Scale Permuta-tion Entropy”, Entropy, Vol. 17, No. 9, 2015, pp. 6447–6461.

Usage Shares
Total Views
214 Page Views
Total Shares
0 Tweets
0 PDF Downloads
0 Facebook Shares
Total Usage