| 残余力向量结构损伤诊断的神经网络方法 |
| |
| 引用本文： | 雷慧,李命成.残余力向量结构损伤诊断的神经网络方法[J].集美大学学报(自然科学版),2001,6(3):255-259. |
| |
| 作者姓名： | 雷慧 李命成 |
| |
| 作者单位： | 1. 集美大学机械工程学院,
2. 厦门宏业建设工程技术咨询公司, |
| |
| 摘 要： | 以残余力向量作为结构参数识别的网络输入，针对训练样本在数据空间分布不均匀的状况，提出了一种基于残余力向量结构参数识别的神经网络方法，并采用GSL变换对训练样本数据进行预处理，从而提高网络收敛速度及参数的识别精度，文中算例证明了该方法的有效性。
|
| 关 键 词： | 残余力向量 GSL变换 损伤诊断 神经网络 结构参数识别 结构损伤 |
| 文章编号： | 1007-7405(2001)03-0255-05 |
| 修稿时间： | 2000年10月8日 |
A Neural Networks Method for Structural Damage Detection Based on Dynamic Residual Vector |
| |
| LEI Hui ,LI Ming cheng.A Neural Networks Method for Structural Damage Detection Based on Dynamic Residual Vector[J].the Editorial Board of Jimei University(Natural Science),2001,6(3):255-259. |
| |
| Authors: | LEI Hui LI Ming cheng |
| |
| Institution: | LEI Hui 1,LI Ming cheng 2 |
| |
| Abstract: | A new method for structural damage detection using BP neural networks is proposed in this paper,which takes the dynamic residual vector of a structure as inputs of the neural networks for damage detection.The Generalized Spaced Lattice(GSL)is used to transform original input and/or output data points of all training patterns onto uniformly spaced lattice points over a multidimentional space.Thus,the neural network can learn the training patterns efficiently as well as accurately.A numerical example is given to show the effectiveness of the proposed method. |
| |
| Keywords: | dynamic residual vector GSL transform damage detection neural networks |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
