摘要
由于用人工神经网络进行结构损伤检测会受到环境噪声的影响,故提出了运用概率神经网络(PNN)进行结构损伤检测的方法和基本原理,并通过一个两层框架的模型对PNN和传统的BP网络的损伤识别精度作了对比。针对基本PNN的不足之处,提出了自适应PNN,并将其损伤识别精度与基本的PNN进行比较。研究发现,运用PNN进行结构损伤识别精度要优于传统的BP网络,而且自适应PNN要比基本的PNN精度高。
A probabilistic neural network(PNN) is proposed for structural damage detection in the paper.It is compared with the traditional BP network for damage identification accuracy by a tow-layer-frame mode.A adaptive PNN is presented to improve the basic PNN and to compare with the basic PNN.The results show that the identification accuracy of the PNN is better than that of the traditional BP network,and the adaptive PNN is better than the basic PNN.
出处
《振动.测试与诊断》
EI
CSCD
2007年第1期13-15,共3页
Journal of Vibration,Measurement & Diagnosis
基金
国家自然科学基金资助项目(编号:60275004)
关键词
概率神经网络
结构
损伤检测
噪声
probabilistic neural network structure damage detection noise