Journal of Korean Society of Steel Construction (한국강구조학회 논문집)

Korean Society of Steel Construction (한국강구조학회)
권호 표지

Frequency Domain Pattern Recognition Method for Damage Detection of a Steel Bridge

강교량의 손상감지를 위한 주파수 영역 패턴인식 기법

  • 이정휘 (서울대학교 지진공학연구센터) ;
  • 김성곤 (서울산업대학교 구조공학과) ;
  • 장승필 (서울대학교 지구환경시스템공학부)
  • Received : 2004.11.02
  • Accepted : 2005.01.24
  • Published : 2005.02.27
Download PDF
⟨ Previous Next ⟩

Abstract

A bi-level damage detection algorithm that utilizes the dynamic responses of the structure as input and neural network (NN) as pattern classifier is presented. Signal anomaly index (SAI) is proposed to express the amount of changes in the shape of frequency response functions (FRF) or strain frequency response function (SFRF). SAI is calculated using the acceleration and dynamic strain responses acquired from intact and damaged states of the structure. In a bi-level damage identification algorithm, the presence of damage is first identified from the magnitude of the SAI value, then the location of the damage is identified using the pattern recognition capability of NN. The proposed algorithm is applied to an experimental model bridge to demonstrate the feasibility of the algorithm. Numerically simulated signals are used for training the NN, and experimentally-acquired signals are used to test the NN. The results of this example application suggest that the SAI-based pattern recognition approach may be applied to the structural health monitoring system for a real bridge.

이 논문에서는 구조물의 동적응답을 입력으로 하고, 패턴인식을 위해 신경망기법(Neural Network, NN)을 사용하는 손상감지기법을 제시하였다. 입력된 동적응답, 즉 주파수응답함수(FRF) 또는 변형률 주파수응답함수(SFRF)의 변화를 정량적으로 표현하기 위해 신호변형지수(Signal Anomaly Index, SAI)를 고안하여 사용하였으며, 이 신호변형지수는 손상 전 및 손상 후의 구조물로부터 측정된 가속도 또는 동적 변형률 신호를 사용하여 계산된다. 제안된 알고리즘은 2단계로 구성되며, 1단계에서는 신호변형지수 값의 크기 변화를 사용하여 구조물의 손상발생 유무를 판별하고, 여기서 구조물에 손상이 발생한 것으로 분석되면 2단계에서 신경망기법을 사용한 패턴인식을 통해 손상의 위치를 찾아낸다. 이 방법의 타당성 및 적용성을 확인하기 위해 강교량 축소모형에 대한 실험을 수행하였다. 신경망의 학습에는 수치해석을 통해 생성한 가상 신호를 사용하였으며, 학습이 완료된 신경망과 실험을 통해 측정한 실제 신호를 사용하여 손상발견을 수행하였다. 모형 교량에 대한 적용 결과로부터 이 알고리즘의 타당성이 검증되었으며, 향후 실 교량에 대한 적용도 가능할 것으로 판단된다.

Keywords

References

  1. 김성곤 (1995) '구조물 모니터링 시스템의 개발.' 한국강구조학회지, v.7, n.4, pp 21-24 (1995-12)
  2. 윤자걸 (2002) 상시진동을 이용한 사장교 유한요소 모델의 보정, 박사학위 논문, 서울대학교 토목공학과
  3. 장정환, 이정휘, 김성곤, 장승필 (1997) '강부재의 손상발견을 위한 모달실험 기법.' 한국강구조학회지, v.9, n.4 , pp 467-477 (1997-12)
  4. Au, F. T. K., Cheng, Y. S., Tham, L. G., and Bai, Z. Z. (2003). 'Structural damage detection based on a micro-genetic algorithm using incomplete and noisy modal test data.' J. Sound and Vibration, 59(5), 1081-1094 https://doi.org/10.1016/0022-460X(78)90473-X
  5. Bolton, R., Stubbs, N., Sikorsky, C., and Choi, S. (2001). 'A comparison of modal properties derived from forced and output-only measurement for a reinforced concrete highway bridge.' Proc. of IMAC-XIX: A Conf. on Struct. Dyn., Vol. 1, 857-863
  6. Chan, T. H. T., Ni, Y. Q., and Ko, J. M. (1999). 'Neural network novelty filtering for anomaly detection of Tsing Ma bridge cables.' Proc. of the 2nd Int. Workshop on Struct. Health Monitoring, Stanford Univ., Stanford, CA
  7. Chang, S.-P. and Kim, S. (1996). 'Online Structural Monitoring of a Cable-Stayed Bridge.' Smart Structures and Materials 1996: Smart Systems for Bridges, Structures, and Highways, SPIE, Vol.2719, 150-158
  8. Chen, S. S. and Kim, S. (1995). 'Automated signal monitoring using neural networks in a smart structural system', J. Intelligent Material Systems and Struct., Vol.6, 508-515 https://doi.org/10.1177/1045389X9500600408
  9. Chou, J.-H. and Ghaboussi, J. (2001). 'Genetic algorithm in structural damage detection.' Computers and Structures, 79(14), 1335-1353 https://doi.org/10.1016/S0045-7949(00)00134-6
  10. Elkordy, M. F., Chang, K. C., and Lee, G. C. (1993). 'Neural network trained by analytically simulated damage states.' J. Computing in Civil Engrg., ASCE, 7(2), 130-145 https://doi.org/10.1061/(ASCE)0887-3801(1993)7:2(130)
  11. Farrar, C. R., and Doebling, S. W. (1999). 'Damage detection II: Field application to large structures.' in Modal Analysis and Testing, Nato science series, Kluwer academic publishers, Dordrecht, Netherlands
  12. Hjelmstad, K. D., and Shin, S. (1997). 'Damage detection and assessment of structures from static responses.' J. Engrg. Mech., ASCE, 123(6), 568-576 https://doi.org/10.1061/(ASCE)0733-9399(1997)123:6(568)
  13. Hou, Z., Noori, M., and St. Amand, R. (2000). 'Wavelet-based approach for structural damage detection.' J. Engrg. Mech., ASCE, 126(7), 677-683 https://doi.org/10.1061/(ASCE)0733-9399(2000)126:7(677)
  14. Jang, J.-H., Yeo, I., Shin, S., Chang, S.-P. (2002). 'Experimental Investigation of System- Identification-Based Damage Assessment on Structures.' J. Struct. Engrg., ASCE, 128(5), 673-682 https://doi.org/10.1061/(ASCE)0733-9445(2002)128:5(673)
  15. Ko, J. M., Ni, Y. Q., and Chan, T. H. T. (1999). 'Dynamic monitoring of structural health in cable-supported bridge.' in Smart Structures and Materials 1999: Smart Systems for Bridges, Structures, and Highways, S. C. Liu, Editor, Proceedings of SPIE, Vol. 3671, 161-172
  16. Lee, J. W., Kim, J. D., Yun, C. B., Yi, J. H., and Shim, J. M. (2002). 'Health-monitoring method for bridges under ordinary traffic loadings.' J. Sound and Vibration, 257(2), 247-264 https://doi.org/10.1006/jsvi.2002.5056
  17. Lieven, N. A. J. and D. J. Ewins (1988). 'Spatial Correlation of Mode Shapes, the Coordinate Modal Assurance Criterion(COMAC).' Proceedings of the 7th International Modal Analysis Conference, pp. 690-695
  18. Marwala, T. (2000). 'Damage identification using committee of neural networks.' J. Engrg. Mech., ASCE, 126(1), 43-50 https://doi.org/10.1061/(ASCE)0733-9399(2000)126:1(1)
  19. Masri, S. F., Smyth, A. W., Chassiakos, A. G., Caughey, T. K., and Hunter, N. F. (2000). 'Application of neural network for detection of changes in nonlinear systems.' J. Engrg. Mech., ASCE, 126(7), 666-676 https://doi.org/10.1061/(ASCE)0733-9399(2000)126:7(666)
  20. Park, H. W., Shin, S., and Lee, H. S. (2001). 'Determination of an optimal regularization factor in system identification with Tikhonov regularization for linear elastic continua.' Int. J. Numerical Methods in Engrg., 51(10), 1211-1230 https://doi.org/10.1002/nme.138
  21. Rhim, J., and Lee, S. W. (1995). 'A neural network approach for damage detection and identification of structures.' Computational Mechanics, Vol. 16, 437-443 https://doi.org/10.1007/BF00370565
  22. SAS IP, Inc. (1998). ANSYS User's Manual. Houston, PA, USA
  23. Sohn, H., and Law, K. H. (2000). 'Bayesian probabilistic damage detection of a reinforced-concrete bridge column.' Earthquake Engrg. and Struct. Dyn., 9(8), 1131-1152
  24. Sun, Z., Chang, C. C. (2002). 'Structural damage assessment based on wavelet packet transform.' J. Struct. Engrg., ASCE, 28(10), 1354-1361
  25. The MathWorks. (1999). Using MATLAB, version 5.3. Natick, MA, USA
  26. Vanik, M. W., Beck, J. L., and Au, S. K. (2000). 'Bayesian probabilistic approach to structural health monitoring.' J. Engrg. Mech., ASCE, 126(7), 738-745 https://doi.org/10.1061/(ASCE)0733-9399(2000)126:7(738)
  27. Yeo, I., Shin, S., Lee, H. S. and Chang, S.-P. (2000). 'Statistical damage assessment of framed structures from static responses.' J. Engrg. Mech., ASCE, 126(4), 414-421 https://doi.org/10.1061/(ASCE)0733-9399(2000)126:1(1)
  28. Yun, C.-B., Bahng, E.-Y., and Yi, J.-H. (1998). 'Neural network approach to damage assessment of civil structures.' Proc. of Struct. Engrg. World Wide 1998, SEWC, T131-2