Back to Search Start Over

Locating Low Velocity Impacts on a Composite Plate Using Multi-Frequency Image Fusion and Artificial Neural Network.

Authors :
Feng, Bo
Ribeiro, Artur Lopes
Pasadas, Dario J.
Ramos, Helena Geirinhas
Source :
Journal of Nondestructive Evaluation; Jun2022, Vol. 41 Issue 2, p1-9, 9p
Publication Year :
2022

Abstract

To find out impact induced defects in a large aerospace structure is quite time consuming due to the large scanning area to be considered. Accurate localization of impacts could narrow the scanning area and improve testing efficiency. In this paper, the multi-frequency characteristic of impact induced guided waves is analyzed. The time of arrival features at various frequencies are extracted from time domain signal by continuous wavelet transform, cross-correlation and Hilbert transform. Two methods, namely image fusion and artificial neural network, are proposed to accomplish the fusion of multi-frequency features. The results show that the mean localization error for the two fusion methods are 4.39 mm and 3.61 mm respectively, the median error for the two methods are 3.56 mm and 3.13 mm. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
01959298
Volume :
41
Issue :
2
Database :
Complementary Index
Journal :
Journal of Nondestructive Evaluation
Publication Type :
Academic Journal
Accession number :
156891388
Full Text :
https://doi.org/10.1007/s10921-022-00865-2