This paper shows the feasibility of using a very simple feed-forward backpropagation neural network for fast and accurate estimation of the location and size of a crack in a cantilever beam. The presented network is trained and tested using data generated by a linear, closed-form, one-dimensional theoretical model of the cracked beam. It is shown that the neural network is a very attractive alternative to presently used methods.
Get full access to this article
View all access options for this article.
References
1.
Anifantis, N. , and Dimarogonas, 1983, "Stability of Columns with a Single Crack Subjected to Follower and Vertical Loads,"International Journal of Solids Structures, Vol. 19, No. 3, pp. 281-291.
2.
Chukwujekwu Okafor, A. , Chandrashekhara, K., and Jiang, Y. P., June 1996, "Delamination Prediction in Composite Beams with Built-in Piezoelectric Devices Using Modal Analysis and Neural Network,"Smart Materials & Structures, Vol. 5, Number 3, pp. 338-347.
3.
Ganguli, R. , Chopra, I., and Haas, D. J., April 15-17, 1996, "Detection of Helicopter Rotor System Simulated Faults Using Neural Networks," AIAA-96-1646-CP, Proceedings of the 37th Structures, Structural Dynamics and Materials Conference, Salt Lake City, Utah, pp. 1246-1263.
4.
Lyon, R. H. , January 1995, "Structural Diagnostics Using Vibration Transfer Functions,"Sound & Vibration, Volume 29, Number 1, pp. 28-31.
5.
Napolitano, K. L. , and Kosmatka, J. B., April 15-17, 1996, "Damage Detection of a Damped Structure with Neural Networks," AIAA-96-1225-CP, Proceedings of the 37th Structures, Structural Dynamics and Materials Conference, Salt Lake City, Utah, pp. 209-213.
6.
Ostachowicz, W. M. and Krawczuk, M., 1991, "Analysis of the Effect of Cracks on the Natural Frequencies of a Cantilever Beam,"Journal of Sound and Vibration, Vol. 150, Nr. 2, pp. 191-201.
7.
Phillips, E. H. , "Blade Failure Focus of NTSB Crash Probe,"August 28, 1995, Aviation Week and Space Technology, p. 31-31.
8.
Povich, C. R. , and Lim T., W., April 21-22,1994, "An Artificial Neural Network Approach to Structural Damage Detection Using Frequency Response,"AIAA/ASME Adaptive Structures Forum, Hilton Head, SC., pp. 151-159.
9.
Rhim, J. and Lee, S. W., April 21-22, 1994, "A Neural Network Approach for Damage Detection and Identification of Structures,"AIAA/ASME Adaptive Structures Forum, Hilton Head, SC., pp. 173-180.
10.
Rizos, P. F. , Aspragathos, N. and Dimarogonas, A. D., 1990, "Identification of Crack Location and Magnitude in a Cantilever Beam from the Vibration Modes,"Journal of Sound and Vibration, Vol. 138, No. 3, pp. 381-388.
11.
Stubbs, N. and Kim, J.-T., August 1996, "Damage Localization in Structures without Baseline Modal Parameters,"AIAA Journal, Vol. 34, No. 8, pp. 1645-1649.
12.
Thomas, M. D. and Flockton, S. J., 12-14 October 1994, "Fault Detection in a Mechanical System by Neural Networks,"Second European Conference on Smart Structures and Materials, Glasgow, Scotland, pp. 55-58.
13.
Zgonc, K. and Achenbach, J. D., 1996, "A Neural Network for Crack Sizing Trained by Finite Element Calculations,"NDT&Elnternational, Vol. 29, No. 3, pp. 147-155.
