摘要
本文提出了基于"能量—损伤"原理,综合利用小波包分析和神经网络的框架结构损伤诊断方法。在结构损伤诊断中,时域信号经小波分析后其缺损特征会更加明显,把分布在不同频带的结点能量作为神经网络的训练样本能够很好地反映结构缺损特征。以美国土木工程师学会提出的基准结构为例,阐述了结构损伤的发生、位置和程度诊断过程,取得了令人满意的结果。
In this paper,an approach based on'energydamage'theory for structural damage diagnosis is presented by use of wavelet packet analysis and improved BP neural network.The damage characteristics of the time domain response signals are more obvious after being transformed by the wavelet.Using the node energy in different frequency bands as a sample of the ANN can perfectly reflect the damage features.Finally,the benchmark structure given by the ASCE is used for describing the process of the damage diagnosis presented here.
出处
《地震工程与工程振动》
CSCD
北大核心
2003年第5期141-148,共8页
Earthquake Engineering and Engineering Dynamics
基金
辽宁省自然科学基金(2003)
建设厅科技项目(02001)
关键词
小波包分析
神经网络
框架结构
损伤诊断
基准结构
wavelet packet analysis
artificial neural network
damage diagnosis
benchmark structure
