Rapid Defects Features Extract Techniques with Chirp Signal in Plate Structures
Fei Deng, Honglei Chen
Available Online August 2015.
- https://doi.org/10.2991/msam-15.2015.51How to use a DOI?
- BP neural networks; chirp excitation; defects identification; plate style structures
- 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.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
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 PB - Atlantis Press SP - 224 EP - 228 SN - 1951-6851 UR - https://doi.org/10.2991/msam-15.2015.51 DO - https://doi.org/10.2991/msam-15.2015.51 ID - Deng2015/08 ER -