Abstract
This study examines the feasibility of using artificial neural network in conjunction with system identification techniques to detect the existence and to identify the characteristics of damage in composite structures. The methodology proposed here includes a training phase and a recognition phase. In the training phase, candidate models for structures with various types of damage are designated as the patterns. These patterns are organized into pattern classes according to the location and the severity of the damage. Then system identifications are performed to extract the transfer functions as the features of the structural systems. These transfer functions are fed into a multi-layer perceptron (MLP) as the input patterns for training. The MLP serves as a nearest neighborhood classifier. In the pattern recognition phase, a structure with unforeseen damage is classified within the closest class in the training set and the damage in the structure is identified as that of the class. The results of numerical tests demonstrate the feasibility of the proposed method.
Similar content being viewed by others
References
Barga, R. S.; Friesel, M. A.; Melton, R. B. 1990: Classification of acoustic emission waveforms for nondestructive evaluation using neural networks. SPIE Applications of Artificial Neural Networks. 1294: 545–556
Davies, W. D. T. 1970: System identification for adaptive-self control. Wiley-Interscience, New York
Doebling, S. W.; Hemez, F.; Barlow, M. S.; Peterson, L. D.; Farhat, C. 1993: Selection of experimental modal data sets for damage detection via model update. Proceedings of the 34th AIAA/ASME/AHS/ASC Structures, Structural Dynamics, and Materials Conference: 1506–1517
Lippmann, R. P. 1987: An introduction of computing with neural nets. IEEE ASSP Magazine 4: 4–22
Ljung, L. 1987: System identification: Theory for the user. Printice-Hall, Englewood Cliffs
Middleton, R. H.; Goodwin, G. C. 1990: Digital control are estimation: A unified approach. Printice-Hall, Englewood Cliffs
Pandey, A. K. 1991. Damage detection from changes in curvature mode shapes. Journal of Sound and Vibration. 145: 321–332
Pao, Y. H. 1989: Adaptive pattern recognition and neural networks. Addison-Wesley, Massachusetts
Paterson, L. D.; Alvin, K. F.; Doebling, S. W.; Park, K. C. 1993: Damage detection using experimentally measures mass and stiffness matrices. Proceedings of the 34th AIAA/ASME/AHS/ASC Structures, Structural Dynamics, and Materials Conference: 1518–1528
Ricles, J. M.; Kosmatka, J. B. 1992: Damage detection in elastic structures using vibratory residual forces and weighted sensitivity. AIAA Journal. 30: 2310–2316
Shen, M. H. H.; Grady, J. E. 1992: Free vibrations of delaminated beams. AIAA Journal. 30: 1361–1370
Smith, S. W.; McGowan, P. E. 1989: Locating damaged members in a truss structure using modal data: A demonstration experiment. NASA Technical Memorandum 101595
Tsou, P.; Shen, M. H. H. 1993: Structural damage detection and identification using neural network. Proceedings of the 34th AIAA/ASME/AHS/ASC Structures, Structural Dynamics, and Materials Conference: 3551–3560
Wasserman, P. D. 1989: Neural computing: Theory and practice. Van Nostrand Reinhold, New York
Wolff, T.; Richardson, M. 1989: Fault detection in structures from changes in their modal parameters. Proceedings of the 7th International Modal Analysis Conference: 87–94
Zimmerman, D. C.; Kaouk, M. 1992: Structural damage detection using a subspace rotation algorithm. Proceedings of the 33rd AIAA/ASME/AHS/ASC Structures, Structural Dynamics, and Materials Conference: 2341–2350
Author information
Authors and Affiliations
Additional information
Communicated by S. N. Atluri, 3 July 1995
Rights and permissions
About this article
Cite this article
Rhim, J., Lee, S.W. A neural network approach for damage detection and identification of structures. Computational Mechanics 16, 437–443 (1995). https://doi.org/10.1007/BF00370565
Issue Date:
DOI: https://doi.org/10.1007/BF00370565