Rapid Defects Features Extract Techniques with Chirp Signal in Plate Structures

DOI

10.2991/msam-15.2015.51How to use a DOI?

Keywords

BP neural networks; chirp excitation; defects identification; plate style structures

Abstract

This work presents a convenience means to get defects features with linear chirp signal and demonstrate it with finite element method and BP neural networks. Aluminum plate models with various kinds of defects modeling with numerical simulation software ABAQUS to get pattern recognition samples.In order to acquire tone burst responses at a wide range of frequencies, we take chirp signals as excitation. The defects scattering signals, which would be used to build sample library, are extracted from the calculated tone burst results. .Finally, two 2-layers BP neural networks are utilized to realize defects types and sizes identification. Test results show that this rapid defects features extract approach is useful to recognize the defect characteristics, although some misidentification exist.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fei Deng
AU  - Honglei Chen
PY  - 2015/08
DA  - 2015/08
TI  - Rapid Defects Features Extract Techniques with Chirp Signal in Plate Structures
BT  - Proceedings of the 2015 International Conference on Modeling, Simulation and Applied Mathematics
PB  - Atlantis Press
SP  - 224
EP  - 228
SN  - 1951-6851
UR  - https://doi.org/10.2991/msam-15.2015.51
DO  - 10.2991/msam-15.2015.51
ID  - Deng2015/08
ER  -