基于神经网络的贮仓结构参数识别
|
摘要
利用神经网络技术,提出了识别结构物理参数的一种方法。用单元刚度矩阵基本值和模态应变能来选择基本模态,用修正的Latin超立方采样技术和模态准入准则来产生网络的输入数据。贮仓在动载作用下的自振频率和模态作为网络的输入,子矩阵参与系数作为网络的输出,用Levenberg-Marquardt算法训练网络。仿真计算表明,方法是可行的。
A method to identify the physical parameters of structure system has been developed by using neural network . Element-stiffness matrix baseline parameters and modal strain energy are employed for the selection of the base modes. An updated-Latin hypercube sampling and modal assurance criteria are adopted for efficient generation of the patterns for training the neural network. The neural network is composed in which the input signals are the silo natural frequencies and its mode shapes ,and output signals are the submatrix scaling factor . The Levenberg-Marquardt algorithm is applied to modify the weight matrices of neural network. Results from computer simulation studies show that the method is valid and feasible.
A method to identify the physical parameters of structure system has been developed by using neural network . Element-stiffness matrix baseline parameters and modal strain energy are employed for the selection of the base modes. An updated-Latin hypercube sampling and modal assurance criteria are adopted for efficient generation of the patterns for training the neural network. The neural network is composed in which the input signals are the silo natural frequencies and its mode shapes ,and output signals are the submatrix scaling factor . The Levenberg-Marquardt algorithm is applied to modify the weight matrices of neural network. Results from computer simulation studies show that the method is valid and feasible.
引文
1葛增杰,李锡夔.深基坑开挖工程多层土体物性参数识别的BP法大连理工大学学报.2000,40(3):739—743
2.Kao C Y,Hung Shih Lin.detection of structural damage via free vibration responses generated by approximating artificial neural networks.computers&structures,2003,81:2631—2644
3.Tae W.Lim submatrix approach to stiffness Matrix correction u-sing modal test data AIAA Journal.1990,28(6):1123—1130
4.Tae W.Lim structural damage detection using modal test data AIAA Journal,1991,29(12):2271—2274
5.Alvar M.Kabe stiffness Matrix adjustment using mode data.AIAA Journal1985,23(9):1431—1436
6.张令心江近仁.Latin超立方采样技术及其在结构可靠性分析中的应用世界地震工程,1997,13(4):1—6
7·杨宇,于德介,程军圣.基于EMD与神经网络的滚动轴承故障诊断方法.振动与冲击,2005,24(1):85—89
8·马广,黄方林,曾储惠.基于神经网络技术的南京长江大桥桥墩船舶撞击力识别.振动与冲击,2005,24(6):127—131
2.Kao C Y,Hung Shih Lin.detection of structural damage via free vibration responses generated by approximating artificial neural networks.computers&structures,2003,81:2631—2644
3.Tae W.Lim submatrix approach to stiffness Matrix correction u-sing modal test data AIAA Journal.1990,28(6):1123—1130
4.Tae W.Lim structural damage detection using modal test data AIAA Journal,1991,29(12):2271—2274
5.Alvar M.Kabe stiffness Matrix adjustment using mode data.AIAA Journal1985,23(9):1431—1436
6.张令心江近仁.Latin超立方采样技术及其在结构可靠性分析中的应用世界地震工程,1997,13(4):1—6
7·杨宇,于德介,程军圣.基于EMD与神经网络的滚动轴承故障诊断方法.振动与冲击,2005,24(1):85—89
8·马广,黄方林,曾储惠.基于神经网络技术的南京长江大桥桥墩船舶撞击力识别.振动与冲击,2005,24(6):127—131
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心