Advertisement

Journal of Mechanical Science and Technology

, Volume 32, Issue 7, pp 3073–3080 | Cite as

Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments

  • Nauman Munir
  • Hak-Joon Kim
  • Sung-Jin Song
  • Sung-Sik Kang
Article
  • 45 Downloads

Abstract

Ultrasonic signal classification of defects in weldment, in automatic fashion, is an active area of research and many pattern recognition approaches have been developed to classify ultrasonic signals correctly. However, most of the developed algorithms depend on some statistical or signal processing techniques to extract the suitable features for them. In this work, data driven approaches are used to train the neural network for defect classification without extracting any feature from ultrasonic signals. Firstly, the performance of single hidden layer neural network was evaluated as almost all the prior works have applied it for classification then its performance was compared with deep neural network with drop out regularization. The results demonstrate that given deep neural network architecture is more robust and the network can classify defects with high accuracy without extracting any feature from ultrasonic signals.

Keywords

Deep neural network Drop out Ultrasonic testing Weldment flaws classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    S. J. Song and L. W. Schmerr, Ultrasonic flaw classification in weldments using probabilistic neural networks, Journal of Nondestructive Evaluation, 11 (2) (1992) 69–77.CrossRefGoogle Scholar
  2. [2]
    A. Masnata and M. Sunseri, Neural network classification of flaws detected by ultrasonic means, NDT & E International, 29 (2) (1996) 87–93.CrossRefGoogle Scholar
  3. [3]
    F. W. Margrave, K. Rigas, D. A. Bradley and P. Barrowcliffe, The use of neural networks in ultrasonic flaw detection, Measurement, 25 (2) (1999) 143–154.CrossRefGoogle Scholar
  4. [4]
    R. Drai, M. Khelil and A. Benchaala, Time frequency and wavelet transform applied to selected problems in ultrasonics, NDE. NDT & E International, 35 (8) (2002) 567–572.CrossRefGoogle Scholar
  5. [5]
    S. J. Song, H. J. Kim and H. Cho, Development of an intelligent system for ultrasonic flaw classification in weldments, Nuclear Engineering and Design, 212 (1) (2002) 307–320.CrossRefGoogle Scholar
  6. [6]
    F. Cau, A. Fanni, A. Montisci, P. Testoni and M. Usai, Artificial neural networks for non-destructive evaluation with ultrasonic waves in not accessible pipes, Industry Applications Conference, 2005. Fourtieth IAS Annual Meeting (2005).CrossRefGoogle Scholar
  7. [7]
    S. Sambath, P. Nagaraj and N. Selvakumar, Automatic defect classification in ultrasonic NDT using artificial intelligence, Journal of Nondestructive Evaluation, 30 (1) (2011) 20–28.CrossRefGoogle Scholar
  8. [8]
    E. F. Simas Filho, M. M. Silva, P. C. Farias, M. C. Albuquerque, I. C. Silva and C. T. Farias, Flexible decision support system for ultrasound evaluation of fiber–metal laminates implemented in a DSP, NDT & E International, 79 (2016) 38–45.CrossRefGoogle Scholar
  9. [9]
    F. C. Cruz, E. F. Simas Filho, M. C. Albuquerque, I. C. SIlva, C. T. Farias and L. L. Gouvêa, Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing, Ultrasonics, 73 (2017) 1–8.CrossRefGoogle Scholar
  10. [10]
    Y. LeCun, Y. Bengio and G. Hinton, Deep learning, Nature, 521 (7553) (2015) 436–444.CrossRefGoogle Scholar
  11. [11]
    J. Schmidhuber, Deep learning in neural networks: An overview, Neural Networks, 61 (2015) 85–117.CrossRefGoogle Scholar
  12. [12]
    A. Géron, Hands on machine learning with scikit-learn and tensorflow, O’Reilly, Media (2017).Google Scholar
  13. [13]
    G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever and R. R. Salakhutdinov, Improving neural networks by preventing co-adaptation of feature detectors, arXiv preprint, p. arXiv:1207.0580 (2012).zbMATHGoogle Scholar
  14. [14]
    N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, Dropout: A simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, 15 (1) (2014) 1929–1958.MathSciNetzbMATHGoogle Scholar
  15. [15]
    V. Nair and G. E. Hinton, Rectified linear units improve restricted boltzmann machines, Proceedings of the 27th International Conference on Machine Learning (ICML-10) (2010).Google Scholar
  16. [16]
    A. L. Maas, A. Y. Hannun and A. Y. Ng, Rectifier nonlinearities improve neural network acoustic models, Proc. ICML, June (2013).Google Scholar
  17. [17]
    A. Krizhevsky, I. Sutskever and G. E. Hinton, Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems (2012).Google Scholar
  18. [18]
    T. Rashid, Make your own neural network, CreateSpace Independent Publishing Platform (2016).Google Scholar

Copyright information

© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Nauman Munir
    • 1
  • Hak-Joon Kim
    • 1
  • Sung-Jin Song
    • 1
  • Sung-Sik Kang
    • 2
  1. 1.Department of Mechanical EngineeringSungkyunkwan UniversitySuwonKorea
  2. 2.Korea Institute of Nuclear SafetyDaejeonKorea

Personalised recommendations