A neural network-based method of determining the location and magnitude of trans-verse impact events on isotropic plates is investigated experimentally. Time data from four sensors mounted in the corners of an aluminum plate was processed to provide inputs for two backpropaga-tion neural networks. The first neural network was responsible for detecting impact location. After 1 million iterations of training, this neural network was able to locate impacts with an average RMS error of 1.55 radial centimeters on a 58.5 centimeter by 36.8 centimeter (23 inch by 14.5 inch) fully-clamped plate. The second neural network was responsible for impact magnitude detection. This neural network was able to determine the impact magnitude with an average of 13.8% error.
Get full access to this article
View all access options for this article.
References
1.
Ceravolo, R. and A. De Stefano. 1995. "Damage Location in Structures Through a Connectivistic Use of FEM Modal Analyses"'Modal Analy-sis, 10:176-176.
2.
Chance, J. E. , K. Worden and G. R. Tomlinson. 1991. "Processing Signals for Damage Detection in Structures Using Neural Networks', Dynamics and Control Research Group, Department of Engineering, The Univer-sity, Oxford Road, Manchester, M13 9PL, UK.
3.
Chen, S. S. and Sungkon Kim. 1994. "Neural Network Based Signal Moni-toring in a Smart Structural System", SPIE Proceedings of Smart Sens-ing, Processing and Instrumentation, 2191:187-198.
4.
Chiou, Y. , M. S. Tavakoli and S. Liang. 1992. "Bearing Fault Detection Based on Multiple Signal Features Using Neural Network Analysis", Proceedings of the 10th International Modal Analyses Conference, San Diego, 1:60-64.
5.
Elkordy, M. F. , K. C. Chang and G. C. Lee. 1993. "Neural Network Trained by Analytically Simulated Damage States", ASCE Journal of Computing in Civil Engineering, 7:130-145.
6.
Grossman, B. , X. Gao and Michael Thursby. 1991. "Composite Damage Assessment Employing an Optical Neural Network Processor and an Embedded Fiber Optic Sensor Array", SPIE Proceedings of Fiber Optic Smart Structures and Skins IV, 1588:64-75.
7.
Gunther, M. F. , A. Wang, R. P. Fogg, S. E. Starr, K. A. Murphy and R. O. Claus. 1992. "Fiber Optic Impact Detection and Location System Embedded in a Composite Material", SPIE Proceedings of Fiber Optic Smart Structures and Skins V1798:262-269.
8.
Jones, R. T. , J. S. Sirkis. E. J. Friebele and A. Kersey. 1995. "Location and Magnitude of Impact Detection in Composite Plates Using Neural Net-works"', SPIE Proceedings of Smart Sensing, Processing and Instrumen-tation, 2444:469-480.
9.
Kirkegaard, P. H. and A. Rytter. 1994. "Use of Neural Networks for Damage Assessment in a Steel Mast"'Proceedings of the 12th Interna-tional Modal Analysis Conference, Honolulu, 2:1128-1134.
10.
Kudva, J. N. , N. Munir and P. W. Tan. 1992. "Damage Detection in Smart Structures Using Finite-Element Analyses", Smart Materials and Struc-tures, 1:108-112.
11.
Manning, R. 1994. "Damage Detection in Adaptive Structures Using Neural Networks", AIAA/ASME Adaptive Structures Forum, 160-172.
12.
Pape, D. A. 1993. 'A Modal Analysis Approach to Flaw Detection in Ceramic Insulators", Proceedings of the 11th International Modal Analy-sis Conference, pp. 35-40.
13.
Povich, C. and T. Lim. 1994. 'An Artificial Neural Network Approach to Structural Damage Detection Using Frequency Response Functions", AIAA/ASME Adaptive Structures Forum, pp. 173-180.
14.
Rhim, J. and S. W. Lee. 1994. 'A Neural Network Approach for Damage Detection and Identification of Structures", AIAA/ASME Adaptive Struc-tures Forum, pp. 173-180.
15.
Schindler, P. M. , R. G. May, R. O. Claus and J. K. Shaw. 1995. "Location of Impacts on Composite Panels by Embedded Fiber Optic Sensors and Neural Network Processing", SPIE Proceedings of Smart Sensing, Proc-essing and Instrumentation, 2444:481-490.
16.
Shaw, J. K. , J. S. Sirkis, E. J. Friebele, R. T. Jones and A. D. Kersey. 1995. "Model of Transverse Plate Impact Dynamics for the Design of Impact Location Methodologies", AIAA Journal, 33:1327-1334.
17.
Simon, S. H.1993. 'A Neural Network/Expert System Hybrid Which Identifies Untrained Damage", SPIE Proceedings of Smart Sensing, Processing, and Instrumentation, 1918:131-137.
18.
Spillman, W. , D. Huston, P. Fuhr and J. Lord. 1993. "Neural Network Damage Detection in a Bridge Element"'SPIE Proceedings of Smart Sensing, Processing and Instrumentation, 1918:288-295.
19.
Szewczyk, P. Z. and P. Hajela. 1994. "Damage Detection in Structures Based on Feature-Sensitive Neural Networks", ASCE Journal of Comput-ing in Civil Engineering, 8:163-178.
20.
Tsou, P. and M. H. Herman Shen. 1994. "Structural Damage Detection and Identification Using Neural Networks", AIAA Journal, 32(1): 176-183.
21.
Weems, D. , H. T. Hahn, E. Granlund and I. G. Kim. 1991. "Impact Detec-tion in Composite Skin Panels Using Piezoelectric Sensors", 47th Annual Forum of the American Helicopter Society, Phoenix.
22.
Worden, K. , A. D. Ball and G. R. Tomlinson. 1993. "Neural Networks for Fault Detection"'Proceedings of the 11th International Modal Analysis Conference, pp. 47-54.
23.
Wu, X. , J. Ghasboussi and J. H. Garrett, Jr.1992. "Use of Neural Net-works in Detection of Structural Damage", Computers & Structures, 42(4):649-659.
