비파괴검사학회지 (Journal of the Korean Society for Nondestructive Testing)

  • 제24권1호
  • /
  • Pages.8-14
  • /
  • 2004
  • /
  • 1225-7842(pISSN)
  • /
  • 2287-402X(eISSN)
한국비파괴검사학회 (The Korean Society for Nondestructive Testing)
권호 표지

증기발생기 세관 와전류 탐상신호의 모델링기반 해석 및 실험적 검증

Model-Based Interpretation and Experimental Verification of ECT Signals of Steam Generator Tubes

  • 발행 : 2004.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

증기발생기 세관의 결함을 정량적으로 평가하기 위해서 신경회로망과 전자기 유한요소 모델링을 사용한 모델링기반 와전류 신호해석기법을 개발해왔다. 본 연구에서는 개발된 신호해석 기법을 검증하기 위해서 실제로 얻어진 와전류 신호를 해석하였다. 유한요소 모델링을 이용하여 생성된 모사 와전류 신호로 데이터베이스를 구성하였으며, 이들을 사용하여 PNN 분류기와 BPNN 크기 산정 신경회로망을 학습시켰다. 축대칭 가공 결함에서 실험 와전류 신호를 획득하였으며, 이 신호를 신경회로망에 입력시켜서 신호를 해석하였다. 신호 해석 결과는 매우 우수하여, 모델링을 이용하여 개발한 신호해석기법은 실제 와전류 신호 해석에 활용할 수 있음을 알았다.

Model-based inversion tools for eddy current signals have been developed by combining neural networks and finite element modeling, for quantitative flaw characterization in steam generator tubes. In the present work, interpretation of experimental eddy current signals was carried out in order to validate the developed inversion tools. A database was constructed using the synthetic flaw signals generated by the finite element model. The hybrid neural networks composed of a PNN classifier and BPNN size estimators were trained using the synthetic signals. Experimental eddy current signals were obtained from axisymmetric artificial flaws. Interpretation of flaw signals was conducted by feeding the experimental signals into the neural networks. The interpretation was excellent, which shows that the developed inversion tools would be applicable to the Interpretation of real eddy current signals.

키워드

참고문헌

  1. L. Udpa and S. S. Udpa, 'Eddy current defect characterization using neural networks,' Materials Evaluation, Vol. 48, pp. 342-347, 353, (1990)
  2. M. T. Shyamsunder, C. Rajagopalan, B. Raj, S. K. Dewangan, B. P. C. Rao and K. K. Ray, 'Pattern recognition approaches for the detection and characterization of discontinuities by eddy current testing, Materials Evaluation, Vol. 58, pp. 93-101, (2000)
  3. S. J. Song and Y. K. Shin, 'Eddy current Flaw characterization in tubes by neural networks and finite element modeling', NDT& E International, Vol. 33, pp. 233-243, (2000) https://doi.org/10.1016/S0963-8695(99)00046-8
  4. S. J. Song, H. J. Park, Y. K. Shin, and H. B. Lee, 'Flaw characterization in pipes by inversion of eddy current signal using neural networks trained by finite element model-based synthetic data,' in Review of Progress in QNDE, Vol. 18, eds. D. O. Thompson and D. E. Chimenti, pp. 881-888, Kluwer Academic/Plenum, New York, (1999)
  5. S. J. Song, C. H. Kim, Y. K. Shin, H. B. Lee, Y. W. Park and C. J. Yim., 'Neural network inversion of synthetic eddy current testing signals from flaws in steam generator tubes,' in Review of Progress in QNDE, Vol. 20, eds. D. O. Thompson and D. E. Chimenti, pp. 664-671, AIP, Melville, (2001)
  6. D. F. Specht, 'Probabilistic neural networks for classification, mapping, or associative memory,' Proceedings of the IEEE International Conference on Neural Networks, Vol. 1. pp. 525-532, (1998)
  7. D. E. Rumelhart, G. E. Hinton and R. J. Williams, 'Learning internal representations by error propagation,' in Parallel Distribute Processing, ed. D. E. Rumelhart and J. L. McClelland, pp. 318-363, MIT Press, MA, (1986)