The Journal of the Korea Contents Association (한국콘텐츠학회논문지)

The Korea Contents Association (한국콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Adaption of Neural Network Algorithm for Pattern Recognition of Weld Flaws

용접결함 패턴인식을 위한 신경망 알고리즘 적용

  • 김창현 (전남대학교 전자컴퓨터공학부) ;
  • 유홍연 (전남대학교 전자컴퓨터공학부) ;
  • 홍성훈 (전남대학교 전자컴퓨터공학부)
  • Published : 2007.01.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we used nondestructive test based on ultrasonic test as inspection method and compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as pattern recognition algorithm of weld flaws. For this purpose, variables are applied the same to two algorithms. Where, feature variables are zooming flaw signals of reflected whole signals from weld flaws in time domain. Through this process, we compared advantages/ disadvantages of two algorithms and confirmed application methods of two algorithms.

본 연구에서는 초음파 검사를 기반으로 하는 비파괴검사 방법을 사용하였으며, 용접결함의 패턴인식 알고리즘으로서 역전파 신경망과 확률 신경망을 비교하였다. 이러한 목적을 위한 과정에서 두 가지 알고리즘에 동일한 변수를 적용하였으며, 여기서 사용된 특징변수는 용접결함으로부터 반사된 시간영역 상의 전체 결함신호로부터 결함부분만을 분리한 신호파형을 사용하였다. 이상의 절차를 통하여 두 가지 알고리즘의 적용방안을 확인하였으며, 두 가지 알고리즘에 대하여 각각의 장단점을 비교하였다.

Keywords

References

  1. J. L. Rose, Ultrasonics Waves in Solid Media, Cambridge University Press, 1999.
  2. W. Zhu, J. L. Rose, J. N. Barshinger J. N, and V. S. Agarwala, "Ultrasonic guided wave NDT for hidden corrosion detection," Research in Noalestructive Evaluation, Vol.10, No.4, pp.205-225, 1998. https://doi.org/10.1080/09349849809409629
  3. L. Liu, M J. Avioli, and J. L. Rose, "Incident angle selection for the guided wave inspection of pipe defects," J. of Insight, Vol.43, No.2, 2001.
  4. T. R Hay, W. Luo, J. L. Rose, and T. Hayashi，''Rapid Inspection of Cornposite Skin-Honeycomb Core Structures with Ultrasonic Guided Waves," J. of Composite Materials, Vol.37, pp.929-939, 2003. https://doi.org/10.1177/0021998303037010005
  5. J. Y. Kim, B. O. Roh, S. You, C. H. Kim, and M S. Ko, "A Study on the Extraction of Feature Variables for the Pattern Recognition of Welding Flaws," J. of KSPE, Vol.19, No.11, pp.103-111, 2002.
  6. K I. Vinay and G. P John, Digital Signal Processing. Sigma-press Pub, pp.353-428, 1998
  7. L. Rutkowski, New Sofr Cmputin Techniques for System Modeling, Pattern Classification and Irmge Processing, New York :Springer-Verlag, 2004.
  8. 이현엽，문경일， Matlab을 이용한 퍼지-뉴로， 아진출판사， pp.209-325, 1999.
  9. S. J. Song, ''Nondestructive Flaw Classi-fication by Pattern Recongnition Approach," J. of KSNT, Vol.19, No.5, pp.378-391, 1999.
  10. T. Ganchev, N. Fakotakis, and G. Kokkinakis, "Text-Independent Speaker Verification Based on Probabilistic Neural Networks," Proc. of the Acoustics, pp.159-166, 2002.
  11. L. Rutkowski and K Cpalka, ''Flexible neuro-fuzzy systems," IEEE Trans. Neural Networks, Vol.14, pp.554-574, 2003.
  12. A O. Mohammed and A S. Walid，"Speeding Up Back-Propagation Neural Networks," Proc. of Informing Science IT Education Joint Conference, pp.167 -173, 2005.
  13. J. K Park, U. S. Park, Y. W. Kim, S. C. Kang, T. H. Choi, and J. H. Lee, ''Models of Reliability Assessment of Ultrasonic Nondestructive Inspection," J. of KSNT, Vol.21, No.6, pp.607-611, 2001.
  14. W. Yi and I. S. Yun, "A Study on defect Classification and Evaluation in Weld Zone od Austenite Stainless Steel 304 Using Neural Network," J. of KSPE, Vol.15, No.7, pp.149-159, 1998.

Cited by

  1. A Novel Data Prediction Model using Data Weights and Neural Network based on R for Meaning Analysis between Data vol.18, pp.4, 2015, https://doi.org/10.9717/kmms.2015.18.4.524