신경회로망을 이용한 원전SG 세관 결함패턴 분류성능 향상기법

다국어 초록 (Multilingual Abstract)

In this paper, we study the classification of defects at steam generator tube in nuclear power plant using eddy current testing (ECT). We consider 4 defect patterns of SG tube: Ⅰ-In type, Ⅰ-Out type, Ⅴ-In type, and Ⅴ-Out type. Through numerical analysis program based on finite element modeling, 400 ECT signals are generated by varying width and depth of each defect type. In order to improve the classification performance, we propose new feature extraction technique. After extracting new features from the generated ECT signals, multi-layer perceptron is used to classify the defect patterns. Through the computer simulation study, it is shown that the proposed method achieves 100% classification success rate while the previous method yields 91% success rate.

목차 (Table of Contents)

• Abstract
• 1. 서론
• 2. 결함패턴 분류를 위한 새로운 특징추출
• 3. 다층퍼셉트론
• 4. 컴퓨터 모의실험
• 5. 결론
• 감사의 글
• 참고문헌
• 저자소개

참고문헌 (Reference)

1 "Shape reconstruction of multiple cracks from ECT signals by means of a Stochastic method" 42 (42): 1079-1082, 2006

2 "Reconstruction of multiple cracks in an ECT round-robin test" 19 (19): 399-404, 2004

3 "Recent advancement of electromagnetic nondestructive inspection technology in japan" 38 (38): 321-326, 2002

4 "Proceedings of the IEEE" 1559-1589, 1992

5 "Numerical evaluation of ECT impedance signal due to minute cracks" 33 (33): 2123-2126, 1997

6 "Neural Networks" New Jersey: Prentic e-Hall 1999

7 "Neural Network Design" PWS Pub. Co 1995

8 "Inverse analyses for natural and multicracks using signals from adifferential transmit-receive ECT probe" 38 (38): 1009-1012, 2002

9 "Impedance calculation for a plate with crack in eddy current NDT using 3D indirect BIEM" 36 (36): 3131-3133, 2000

10 "Eddy current Flaw characterization in tubes by neural networks and finite element modeling" 33 : 233-243, 2000

11 "A novel signal processing technique for eddy-current testing ofsteam generator tubes" 34 (34): 642-648, 1998