Evaluation of Bending Fatigue Damage for FRP laminate with AE. Application of Fractal Dimension of Wavelet Transform Results and Neural Network.
-
- TAKUMA Masanori
- 関西大学
-
- SHINKE Noboru
- 関西大学
-
- SUZUKI Ken
- 関西大学大学院工学研究科
-
- FUJII Toshiyuki
- 関西大学大学院工学研究科
Bibliographic Information
- Other Title
-
- AE信号のウェーブレット変換によるFRP積層板の曲げ疲労損傷評価 フラクタル次元とニューラルネットワークの適用
- AE シンゴウ ノ ウエーブレット ヘンカン ニ ヨル FRP セキソウバン ノ マゲ ヒロウ ソンショウ ヒョウカ フラクタルジゲン ト ニューラル ネットワーク ノ テキヨウ
- Application of Fractal Dimension of Wavelet Transform Results and Neural Network
- フラクタル次元とニューラルネットワークの適用
Search this article
Abstract
Fiber reinforced plastics (FRP) has become one of the important structural materials in the various fields. Therefore, it is important to evaluate the fracture modes and the fatigue damage of FRP laminates. Acoustic emission (AE) monitoring is useful to study its damage and the modes. However, it is difficult to evaluate the damage and the modes during the fatigue testing. Recently, Wavelet Transform (WT) are the center of attention at the analysis of the signals. The resultant mapping of wavelet coefficients in the time-frequency coordinate plane provides more informative characterization of the signals than the power-density spectra from Fourier Transform (FT). In this report, the AE signals of CFRP and GFRP laminates (i.e. [0°], [0°/90°] and [±45°]) subjecting to cyclic bending loads were recorded at each cycle during the fatigue testing, and were analyzed with WT for evaluating its damage and the modes. By observing the resultant mapping at each cycle, it is possible to develop a methodology for evaluating the damage and the modes by using the characteristic features of the mapping. This system consists of an AE measuring device and a neural network. The network has learned the pattern sets dealing with the interaction between the features of the mapping and the fatigue damage. The character of the mapping was expressed by fractal dimensions that were led by the box-counting method. The effectiveness of this system is demonstrated by comparing results of the neural network with experimental data obtained from the fatigue tests.
Journal
-
- Journal of the Japan Society for Precision Engineering
-
Journal of the Japan Society for Precision Engineering 68 (10), 1309-1315, 2002
The Japan Society for Precision Engineering
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390001204795967232
-
- NII Article ID
- 110001373296
-
- NII Book ID
- AN1003250X
-
- ISSN
- 1882675X
- 09120289
-
- NDL BIB ID
- 6324700
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed