Health monitoring of FRP using acoustic emission and artificial neural networks

被引：128

作者：

de Oliveira, R. ^{[1
]}

Marques, A. T. ^{[2
]}

机构：

[1] INEGI, P-4465591 Leca do Bailio, Portugal

[2] Univ Porto, Fac Engn, DEMEGI, P-4200465 Oporto, Portugal

来源：

COMPUTERS & STRUCTURES | 2008年 / 86卷 / 3-5期

关键词：

composite materials; health monitoring; damage; acoustic emission; waveform analysis; artificial neural networks; clustering;

D O I：

10.1016/j.compstruc.2007.02.015

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this study, a procedure is proposed for damage identification and discrimination for composite materials based on acoustic emission signals clustering using artificial neural networks. An unsupervised methodology based on the self-organizing map of Kohonen is developed. The methodology is described and applied to a cross-ply glass-fibre/polyester laminate submitted to a tensile test. Six different AE waveforms were identified. Hence, the damage sequence has been identified from the modal nature of the AE waves. (c) 2007 Elsevier Ltd. All rights reserved.

引用

页码：367 / 373

页数：7

共 12 条

[1]

Anastassopoulos A. A., 1995, Journal of Acoustic Emission, V13, P11

[2] Identification of failure modes in GFRP using PVDF sensors: ANN approach [J].