Journal of the Korean Society for Nondestructive Testing (비파괴검사학회지)

The Korean Society for Nondestructive Testing (한국비파괴검사학회)
권호 표지

Classification Technique for Ultrasonic Weld Inspection Signals using a Neural Network based on 2-dimensional fourier Transform and Principle Component Analysis

2차원 푸리에변환과 주성분분석을 기반한 초음파 용접검사의 신호분류기법

  • Kim, Jae-Joon (School of Computers and Communications Engineering, Daegu University)
  • 김재준 (대구대학교 정보통신대학 정보통신공학부)
  • Published : 2004.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

Neural network-based signal classification systems are increasingly used in the analysis of large volumes of data obtained in NDE applications. Ultrasonic inspection methods on the other hand are commonly used in the nondestructive evaluation of welds to detect flaws. An important characteristic of ultrasonic inspection is the ability to identify the type of discontinuity that gives rise to a peculiar signal. Standard techniques rely on differences in individual A-scans to classify the signals. This paper proposes an ultrasonic signal classification technique based on the information tying in the neighboring signals. The approach is based on a 2-dimensional Fourier transform and the principal component analysis to generate a reduced dimensional feature vector for classification. Results of applying the technique to data obtained from the inspection of actual steel welds are presented.

신경망 기반의 신호 분류 시스템은 비파괴 검사 시 추출되는 많은 양의 데이터를 처리하기 위한 방법으로 꾸준히 이용되고 있다. 비파괴검사 방법 중, 초음파 탐상법은 용접 지역에서 결함들을 찾기 위하여 비파괴 검사에서 일반적으로 사용되고 있는 추세다. 초음파 탐상법의 중요한 특징은 특정 신호에서 발생하는 불연속성을 판별해내는 능력이다. 지금까지의 보편화되어 있는 기술은 신호를 분류하기 위해 각각의 A-scan 신호를 처리하는 반면 본 논문에서는 이웃하는 A-scan 신호의 정보를 기반으로 하는 2차원 푸리에 변환(Fourier transform)과 주성분 분석(principal component analysis) 기법을 이용하여 특징 벡터를 추출, 분류하는 방법을 제시하고자 한다.

Keywords

References

  1. P. Ramuhalli, L. Udpa, and S. S. Udpa, 'An Automatic. Signal Classification System for Ultrasonic Weld Inspection Signals,' Materials Evaluation, Vol. 58, No.1, pp. 85-89, (2000)
  2. S. J. Song and Y. K. Shin, 'Eddy Current Flaw Characterization in Tubes by Neural Networks and Finite Element Modeling,' NDT International. Vol. 33, No.4, pp. 233-243, (2000) https://doi.org/10.1016/S0963-8695(99)00046-8
  3. J. H. Krautkramer, Ultrasonic Testing of Materials, 4th Edition, New York, Springer-Verlag, (1990)
  4. 이철구, 용접공학, 청문각, (2002)
  5. R. Polikar, L. Udpa, S. S. Udpa, and T. Taylor, 'Frequency Invariant Classification of Ultrasonic Weld Inspection Signals,' IEEE Trans. Ultrasonics, Ferroelectrics and Frequency Control, Vol. 45, No.3, pp. 614-625, (1998) https://doi.org/10.1109/58.677606
  6. Neural Networks and Semi-Automatic Scanners for NDE Applications, EPRI TR-107119, EPRI Final Report, (1996)
  7. J. L. Rose, M. J. Avioli, and M. E. Lapides, 'A Physically Modeled Feature Based Ultrasonic System for IGSCC Classification,' Material Evaluation, Vol. 40. No. 13, pp. 1367-1383, (1982)
  8. S. F. Burch, 'A Physical Approach to the Automated Ultrasonic Characterization of Buried Weld Defects in Ferritic Steel,' NDT International. Vol. 19, No.3, pp. 145-153, (1986) https://doi.org/10.1016/0308-9126(86)90103-3
  9. Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, Reading, MA: Addison-Wesley Publishing, (1992)
  10. Haykin Simon, Neural Networks, Prentice Hall, (1994)
  11. Looney, Carl G., Pattern Recognition Using Neural Networks : Theory and Algorithms for Engineers and Scientists, Oxford, (1991)
  12. Erkki Oja. 'Neural Networks, Principal Components, and Subspaces,' International Journal of Neural Systems, Vol. 1, No. 1, pp. 61-68, (1989) https://doi.org/10.1142/S0129065789000475
  13. W. K. Pratt, Digital Image Processing, John Wiley & Sons, Inc., New York, (2001)