摘要
提出一种基于BP神经网络的结构破损诊断方法,该方法以结构破损前后柔度的变化作为破损诊断网络输入,为了解决由于系统响应样本数据空间分布不均匀对网络收敛速度及网络诊断影响问题,对网络训练样本采用广义空间格点进行了交换,模拟算例及应用实例均表明,本文方法能准确诊断结构破损位置与破坏程度,是一种有效的结构破损诊断方法。
A method for damage detection in structures using back propagation neural met works is proposed in this paper, which takes the flexibility difference vector of a structure as inputs of the neural network for parameter identification. The method uses the Generalized-Space Lattice（GSL）transform original input and/or output data points of all training patterns efficiently as well as accurately. The proposed method is applied to a simulated and experimental beam example. The results show that the proposed method can identify the location and magnitude of damages from measured vibration data effectively.
出处
《海洋工程》
CSCD
北大核心
2005年第4期47-51,共5页
The Ocean Engineering
基金
湖南省科技计划资助项目(04SK3077)
