Journal of Nondestructive Evaluation

, Volume 30, Issue 1, pp 20–28 | Cite as

Automatic Defect Classification in Ultrasonic NDT Using Artificial Intelligence

  • S. SambathEmail author
  • P. Nagaraj
  • N. Selvakumar


A methodology is developed to detect defects in NDT of materials using an Artificial Neural Network and signal processing technique. This technique is proposed to improve the sensibility of flaw detection and to classify defects in Ultrasonic testing. Wavelet transform is used to derive a feature vector which contains two-dimensional information on various types of defects. These vectors are then classified using an ANN trained with the back propagation algorithm. The inputs of the ANN are the features extracted from each ultrasonic oscillogram. Four different types of defect are considered namely porosity, lack of fusion, and tungsten inclusion and non defect. The training of the ANN uses supervised learning mechanism and therefore each input has the respective desired output. The available dataset is randomly split into a training subset (to update the weight values) and a validation subset. With the wavelet features and ANN, good classification at the rate of 94% is obtained. According to the results, the algorithms developed and applied to ultrasonic signals are highly reliable and precise for online quality monitoring.


Ultrasonic testing TIG welding Defect classification Wavelet transform Artificial neural networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Martın, O., Lopez, M., Martın, F.: Artificial neural networks for quality control by ultrasonic testing in resistance spot weldin. J. Mater. Process. Technol. 183, 226–233 (2007) CrossRefGoogle Scholar
  2. 2.
    Cau, F., Fanni, A., Montisci, A., Testoni, P., Usai, M.: Signal-processing tool for non-destructive testing of inaccessible pipe. Eng. Appl. Artif. Intell. 19, 753–760 (2006) CrossRefGoogle Scholar
  3. 3.
    Veiga, J.L.B.C., de Carvalho, A.A., da Silva, I.C., Rebello, J.M.A.: The use of artificial neural network in the classification of pulse-echo and TOFD ultra-sonic signals. J. Braz. Soc. Mech. Sci. Eng. 27(4), 394–398 (2005) Google Scholar
  4. 4.
    Bettayeb, F., Rachedi, T., Benbartaoui, H.: An improved automated ultrasonic NDE system by wavelet and neuron networks. Ultrasonics 43, 853–858 (2004) CrossRefGoogle Scholar
  5. 5.
    Moura, E.P., Silva, R.R., Siqueira, M.H.S., Rebello, J.M.A.: Pattern recognition of weld defects in preprocessed TOFD signals using linear classifiers. J. Nondestruct. Eval. 23(4), 163–172 (2004) CrossRefGoogle Scholar
  6. 6.
    Drai, R., Khelil, M., Benchaala, A.: Time frequency and wavelet transform applied to selected problems in ultrasonics NDE. NDT&E Int. 35, 567–572 (2002) CrossRefGoogle Scholar
  7. 7.
    Obaidat, M.S., Suhail, M.A., Sadoun, B.: An intelligent simulation methodology to characterize defects in materials. Inf. Sci. 137, 33–41 (2001) zbMATHCrossRefGoogle Scholar
  8. 8.
    Margrave, F.W., Rigas, K., Bradley, D.A., Barrowcliffe, P.: The use of neural networks in ultrasonic flaw detection. Measurement 25, 143–154 (1999) CrossRefGoogle Scholar
  9. 9.
    Graps, A.S.: An introduction to wavelets. IEEE Comput. Sci. Eng. 2(2), 50–61 (1995) CrossRefGoogle Scholar
  10. 10.
    Burrus, C.S., Gopinath, R.A., Guo, H.: Introducing to Wavelets and Wavelet Transformation. Prentice-Hall, Englewood Cliffs (1998) Google Scholar
  11. 11.
    İşcan, Z., Kurnaz, M.N., Dokur, Z., Olmez, T.: Ultrasound image segmentation by using wavelet transform and self-organizing neural network. Neural Inf. Process. 10(89), 183–191 (2006) Google Scholar
  12. 12.
    Mallat, S.: A theory for multi resolution signal processing: the wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 11, 674–693 (1989) zbMATHCrossRefGoogle Scholar
  13. 13.
    The Math Works, Inc. 1998: Neural Network Toolbox for use with Matlab 5.3/Version 2007, Natick, MA Google Scholar
  14. 14.
    Selvakumar, N., Radha, P., Narayanasamy, R., Joseph Davidson, M.: Prediction of deformation characteristics of sintered aluminium performs using neural networks. Model. Simul. Mater. Sci. Eng. 12(4), 611–620 (2004) CrossRefGoogle Scholar
  15. 15.
    McBride, J., Malinov, S., Sha, W.: Modelling tensile properties of gamma based titanium aluminides using artificial neural network. Mater. Sci. Eng. A 384, 129–137 (2004) CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  1. 1.Department of Mechanical EngineeringMepco Schlenk Engineering CollegeVirudhunagar Dist.India

Personalised recommendations