Damage Detection Using Neural Networks: An Initial Experimental Study on Debonded Beams

Abstract

Frequency response data obtained from a pieoelec tric actuator/sensor pair bonded to a composite/aluminum beam structure with a debond between the interface is used to train an ar tificial neural network by backpropagation to identify the severity and presence of a delamination. The PZT actuator/sensor pair is so arranged that the damage site lies between the actuator and sensor. The damage consists of an artificially created de-bonding between an aluminum beam and a bonded composite patch. The experi mentally obtained transfer function data in the form of a magnitude and phase, over a specified frequency range, is obtained from a sig nal analyzer. The training process consists of training the network with several fully bonded specimens and several debonded speci mens with various sized damage. The effectiveness of several different configurations of the network applied to this problem is investigated. The neural network after training on a limited number of training data is able to identify the damaged specimens with substantial accuracy.

Get full access to this article

View all access options for this article.

References

Caudill, M. AND C. Butler. 1992. Understanding Neural Networks: Computer Explorations, Vols. 1 and 2 Cambridge, MA: The MIT Press.

Cawley, P. AND R.D. Adams. 1979. "The Location of Defects in Structures from Measurements of Natural Frequencies", Journal of Strain Analysis, 14(2):49-57.

Demuth, H. AND M. Beale. 1992. Neural Network Toolbox User's Guide Matick, MA. The mathWorks, Inc .

Elkordy M.F. , K.C. Chang AND G.C. Lee. 1993. "Neural Networks Trained by Analytically Simulated Damage States", ASCE Journal of Computing in Civil Engineering, 7(2):130-145.

Kim, H.M. AND T.J. Bartkowicz . 1993. "Damage Detection and Health Monitoring of Large Space Structures", Proceedings, AIAA/ASCE/ ASME/AHS/ASC 34th Structures, Structural Dynamics, and Materials Conference, La Jolla, CA, 19-22 April 1993 Washington, D.C.: AIAA, Inc., Paper No. AIAA 93-1705-CP, pp. 3527-3533.

Kudva, J.N. , N. Munir AND P.W. Tan. 1992 "Damage Detection in Smart Structures Using Neural Networks and Finite-Element Analyses", Smart Material Structures, 1:108-112.

Piezo Systems. 1987. "Piezoelectric Motor Actuation Kit Manual", Piezo Electric Products, Inc., Advanced Technology Group, Cambridge, MA.

Simon S.H. 1991. "A Fault-Tolerant Neural Network Applied to Nondestructive Inspection", in Handbook of Expert Systems in Manufacturing , R. Maus and J. Keyes, eds., New York, NY : McGraw-Hill, Inc., pp. 269-279.

Tsou , AND M.H.H. Shen. 1993. "Structural Damage Detection and Identification Using Neural Network", Proceedings, AIAA/ASCE/ASME/ AHS/ASC 34th Structures, Structural Dynamics and Materials Conference, La Jolla, CA, 19-22 April 1993, AIAA, Inc. , Washington D.C. Paper No. AIAA-93-1708-CP, pp. 3551-3560.

10.

Wu, X. , J. Ghaboussi , AND J.H. Garrett, JR. 1992. "Use of Neural Networks in Detection of Structural Damage", Computers & Structures , 42(4):649-659.

11.

Zonic A&D Corporation. 1992. World Class Analyzer, Hardware and software system for spectral analysis.