摘要
基于振动信号应用神经网络研究层合板分层损伤的检测方法.对层合板分层损伤区域,采用相同坐标不同节点建立了分层损伤处的有限元模型;通过数值模拟提取结构无损和不同程度面积分层损伤的全局振动标识量;重点研究神经网络对层合板分层损伤位置和损伤程度的检测技术.研究表明,用结构全局振动标识量作为人工神经网络的输入,对层合板结构分层损伤检测是一种很有效的工程实用技术,可应用于实际结构的在线损伤检测.
In this paper,a delamination identification strategy based on vibration signatures by using artificial neural networks is presented Through different nodes with same coordinates,a finite element model for internal delamination is established.The global vibration identification factors of damaged and damage free laminates are obtained by numerical simulation.In the studies,the identification capability for the quantitative prediction of delamination in composites laminates is focused.The results show that the strategy based on the vibration signal measurement and artificial neural networks is efficient to detect delamination defects and there is a good possiblity to apply the proposed method to the helth monitoring of a practical composite structure.
出处
《力学与实践》
CSCD
北大核心
2011年第1期24-28,共5页
Mechanics in Engineering
基金
国家自然科学基金资助项目(50977070)
关键词
层合板
分层损伤
振动信号
神经网络
损伤检测
composisite laminates
delamination
vibration signature
neural network
damage identification
