A Pattern Recognition Method of Fatigue Crack Growth on Metal using Acoustic Emission

음향방출을 이용한 금속의 피로 균열성장 패턴인식 기법

  • Lee, Soo-Ill (School of Electrical Engineering and Computer Science, KAIST) ;
  • Lee, Jong-Seok (School of Electrical Engineering and Computer Science, KAIST) ;
  • Min, Hwang-Ki (School of Electrical Engineering and Computer Science, KAIST) ;
  • Park, Cheol-Hoon (School of Electrical Engineering and Computer Science, KAIST)
  • 이수일 (한국과학기술원 전자전산학부) ;
  • 이종석 (한국과학기술원 전자전산학부) ;
  • 민황기 (한국과학기술원 전자전산학부) ;
  • 박철훈 (한국과학기술원 전자전산학부)
  • Published : 2009.05.25

Abstract

Acoustic emission-based techniques are being used for the nondestructive inspection of mechanical systems used in service. For reliable fault monitoring related to the crack growth, it is important to identify the dynamical characteristics as well as transient crack-related signals. Widely used methods which are based on physical phenomena of the three damage stages for detecting the crack growth have a problem that crack-related acoustic emission activities overlap in time, therefore it is insufficient to estimate the exact crack growth time. The proposed pattern recognition method uses the dynamical characteristics of acoustic emission as inputs for minimizing false alarms and miss alarms and performs the temporal clustering to estimate the crack growth time accurately. Experimental results show that the proposed method is effective for practical use because of its robustness to changes of acoustic emission caused by changes of pressure levels.

음향방출 기법은 작동중인 상태에서 기계 설비를 비파괴 검사할 수 있는 기법이며, 균열성장 같은 장애의 신뢰성 있는 감시를 위해서 순간적인 균열신호뿐만 아니라 동특성을 이용하는 것이 중요하다. 균열성장을 검출하기 위해 널리 사용되는 물리적 파괴 3단계는 음향방출 현상이 시간에 따라 서로 겹치는 문제점이 있어 정확한 균열성장 시간을 추정하기 어렵다. 제안한 패턴인식 기법은 오경보와 미탐지를 최소화하기 위해서 음향방출 동특성을 입력으로 사용하고, 균열성장 시간을 정확히 추정하기 위해 시간에 따른 클러스터링 기법을 사용한다. 실험결과는 제안한 패턴인식 기법이 압력의 변화에 의한 음향방출의 변화의 강인함 때문에 실용화에 효율적임을 보여준다.

Keywords

References

  1. D. Fang and A. Berkovits, "Fatigue design model based on damage mechanisms revealed by acoustic emission measurements," Journal of Engineering Materials and Technology, vol. 117, no. 2, pp. 200-208, 1995 https://doi.org/10.1115/1.2804530
  2. N. Godin, S. Huguet, and R. Gaertner, "Integration of the Kohonen's self-organising map and k-means algorithm for the segmentation of the AE data collected during tensile tests on cross-ply composites," NDT&E International, vol. 38, no. 4, pp. 299-309, 2005 https://doi.org/10.1016/j.ndteint.2004.09.006
  3. Z. Shi, B. Beadle, S. Hurlebaus, J. Jarzynski, and L. Jacobs, "Study of acoustic emission from incipient fatigue failure," Review of Progress in QNDE, vol. 18, pp. 295-401, 1999
  4. I. M. Daniel, C. G. Sifniotopoulos and J.-J. Luo, "Analysis of acoustic emission output from propagating crack," Review of Progress in QNDE, vol. 17, pp. 1331-1338, 1998
  5. S. Rippengill, K. Worden, K. M. Holford, and R. Pullin, "Automatic Classification of Acoustic Emission Patterns," Journal of the British Society for Strain Measurement, vol. 39, no. 1, pp. 31-41, 2003 https://doi.org/10.1046/j.1475-1305.2003.00041
  6. M. Huang, L. Jiang, P. K. Liaw, C. R. Brooks, T. Seeley, and D. L. Klarstrom, "Using acoustic emission in fatigue and fracture Materials research," Journal of the Minerals, Metals and Materials Society, vol. 11, pp. 1-14, 1998
  7. C. Ennaceur, A. Laksimi, C. Herve, and M. Cherfaoui, "Monitoring crack growth in pressure vessel steels by the acoustic emission technique and the mothod of potential difference," Int. Journal of Pressure Vessels and Piping, vol. 86, pp.197-204, 2006 https://doi.org/10.1016/j.ijpvp.2005.12.004
  8. C. C. Tan, N. F. Thornhill, and R. M. Belchamber, "Principal component analysis of spectra with application to acoustic emissions from mechanical equipment," Transactions of Institute of Measurement and Control, vol. 24, no. 4, pp. 333-353, 2002 https://doi.org/10.1191/0142331202tm067oa
  9. V. Kappatos and E .Dermatas, "Classification of acoustic emission and drop signals using SVM, MLP and RBF Networks," in Proc. 5th National Conference on Non-Destructive Testing of the Hellenic Society for NDT, Athens, Hellas, Nov. 2005
  10. S. Hugueta, N. Godin, R. Gaertner, L. Salmon, and D. Villard, "Use of acoustic emission to identify damage modes in glass fibre reinforced polyester," Composites Science and Technology, vol. 62, no. 10, pp. 1433-1444, 2002 https://doi.org/10.1016/S0266-3538(02)00087-8
  11. H. K. Min, C. Y. Lee, J.-S. Lee, and C. H. Park, "Abnormal Signal Detection in Gas Pipes Using Neural Networks," in Proc. IEEE Int. Conf. Industrial Electronics Society, pp. 2503-2508, Taipei, Taiwan, Nov. 2007
  12. P. H. Hutton, R. J. Kurtz, M. A. Friesel, J. R. Skorpik, and J. F. Dawson, "Acoustic emission/flaw relationships for inservice monitor of LWRs", Pacific Northwest Laboratory, Tech. Rep. NUREG/CR-5645: PNL-7479, Oct. 1991
  13. X, Huang, A. Acero, and H. -W, Hon, Spoken Language Processing: A Guide to Theory, Algorithm, and Systems Development, Prentice Hall, 2001
  14. R. M. Stern, B. Raj, and P. J. Moreno, "Compensation for environmental degradation in automatic speech recognition," in Proc. ESCA-NATO Tutorial and Research Workshop on Robust Speech Recognition using Unknown Communication Channels, pp. 33-42, Pont-à-Mousson, France, April, 1997
  15. T. H. Applebaum and B. A. Hanson, "Regression features for recognition of speech in quiet and in noise," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, pp. 985-988, Toronto, Canada, April 1991
  16. K. Goebel and W. Yan, Feature selection for tool wear diagnosis using soft computing techniques, in Proc. ASME Manufacturing in Engineering Division, vol. 18, pp.157-163, 2000.
  17. Standard test method for measurement of fatigue crack growth rates, ASTM Std. E647-05, July 2005
  18. M. T. Hagan and M. B. Menhaj, "Training feedforward networks with the marquardt algorithm," IEEE Transactions on Neural Networks, vol. 5, no. 6, pp. 989-993, Nov. 1994 https://doi.org/10.1109/72.329697