Computational & Technology Resources
an online resource for computational,
engineering & technology publications
COMPUTATIONAL ENGINEERING USING METAPHORS FROM NATURE
Edited by: B.H.V. Topping
Use of Neural Networks for Damage Detection in Structural Elements using Wave Propagation
L. Ziemianski and G. Piatkowski
Department of Structural Mechanics, Rzeszow University of Technology, Rzeszow, Poland
L. Ziemianski, G. Piatkowski, "Use of Neural Networks for Damage Detection in Structural Elements using Wave Propagation", in B.H.V. Topping, (Editor), "Computational Engineering using Metaphors from Nature", Civil-Comp Press, Edinburgh, UK, pp 25-30, 2000. doi:10.4203/ccp.64.1.4
This paper presents an application of Artificial Neural Networks (ANN) for damage detection in rod structures. The identification method has been based on the analysis of propagation of wave in solids. To simulate wave propagation in rod element the Finite Element Method (FEM) has been used. Direct integration method of a motion equation has been used to determinate time signal in several measurement points for different states describing changes in rod.
Then using calculated relationship, i.e. the correlation between an element time signal and parameters describing failure, the neural networks have been trained.
The assessed problem is of the Feature Identification type in which the force and response of a Mechanical Structure are given and the identification of feature is the expected result.
purchase the full-text of this paper (price £20)