Transactions of the Korean Society of Machine Tool Engineers (한국공작기계학회논문집)

The Korean Society of Manufacturing Technology Engineers (한국생산제조학회)
권호 표지

Availability Verification of Feature Variables for Pattern Classification on Weld Flaws

용접결함의 패턴분류를 위한 특징변수 유효성 검증

  • 김창현 (전남대학교 공과대학 전자컴퓨터공학부) ;
  • 김재열 (조선대학교 공과대학 메카트로닉스공학과) ;
  • 유홍연 (전남대학교 공과대학 전자컴퓨터공학부) ;
  • 홍성훈 (전남대학교 공과대학 전자컴퓨터공학부)
  • Published : 2007.12.15
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, the natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. Feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.

Keywords

References

  1. International Institute of Welding, 1987, The Evaluation of Ultrasonic Signals, Welding Institute for International Institute of Welding, Cambridge, England
  2. Brigham, E. O, 1988, The Fast Fourier Transform and Its Applications, Prentice- Hall, pp. 131-166
  3. Richard, O. D., Peter, E. H. and David, G. S., 2001, Pattern Classification, Willy- Interscience Publication, pp. 20-83
  4. Chiou, C. P. and Schmerr, L. W., 1991, 'A quasipulse-echo technique for ultrasonic flaw classification,' Ultrasonic, Vol. 29, pp. 471-481 https://doi.org/10.1016/0041-624X(91)90078-M
  5. Yoon, S. H., Kim, C. H. and Kim, J. Y, 2006, 'The Performance Comparison of Classifier Algorithm for Pattern Recognition of Welding Flaws,' Transactions of the Korean Society of Machine Tool Engineers, Vol. 15, No. 3, pp. 39-44
  6. Lee, K. Y. and Kim, J. S., 1995, 'Intelligence Package Development for UT Signal Pattern Recognition and Application to Classification of Defects in Austenitic Stainless Steel Weld,' Journal of the Korean Society for Nondestructive Testing, Vol. 15, No. 4, pp. 531-539
  7. Krautkramer, J. and Krautkramer, H., 1990, Ultrasonic Testing of Materials, 4th Edition, NewYork: Springer-Verlag
  8. Gruber, G. J., Hendrix, J. G. and Schick, W. R., 1984, 'Characterization of flaws in piping welds using satellite pulses,' Materials Evaluation, Vol. 42, pp. 426-432
  9. Kim, J. Y., Hong, S. J., Lee, K. T., Kim, B. H., Kim, H. C. and Kim, Y. J., 2000, 'A Study on the Application of Digital Signal Processing for Pattern Recognition of Microdefects,' Transactions of the Korean Society of Machine Tool Engineers, Vol. 9, No. 1, pp. 119-127
  10. Rose, J. L., Nestleoroth, J. B. and Banlas-bramanian, K., 1988, 'Utility of Feature Mapping in Ultrasonics Non-Destructive Evaluation,' Ultrasonics, Vol. 26, pp. 124-131 https://doi.org/10.1016/0041-624X(88)90002-9