%0 Journal Article
%T Identification of damage in rectangular plates based on neural network technique with sub-regions<br>矩形板结构损伤的分区域神经网络识别方法
%A Wang Dengming Zhou Youhe
%A <br>王等明
%A 周又和
%J 力学学报
%D 2005
%I 
%X This paper presents an identification approach based on neural network method with sub-regions to identify damages in a rectangular plate using the LM optimized algorithm. The numerical results of simulations for the cantilever plate with some damages show that this approach is better than that from the conventional method with single network. Since this method realizes the synchronous output of position and intensity of damages in the structure, this approach does not need many sub-networks appeared in a conventional hierarchical identification method.
%K rectangular plate
%K damage identification
%K combinatorial input parameters
%K neural network method with sub-regions
%K FEM<br>识别方法
%K 神经网络
%K 结构损伤
%K 分区域
%K 矩形板
%K 网络训练
%K 预测精度
%K 优化算法
%K 识别问题
%K 对称结构
%K 矩形薄板
%K 精度要求
%K 预测输出
%K 收敛速度
%K 输入参数
%K 模拟结果
%K 预测结果
%K 同步输出
%K 子网络
%K 输出量
%K 预测量
%K 板结构
%K 误差
%K 数值
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=6E709DC38FA1D09A4B578DD0906875B5B44D4D294832BB8E&cid=5D344E2AD54D14F8&jid=4100DA4A1A3BA1B0CE5AD99AE1DFB420&aid=73AF5D873C5BAD9A&yid=2DD7160C83D0ACED&vid=42425781F0B1C26E&iid=38B194292C032A66&sid=5F8BAECF36EB55E2&eid=389106FB36CA8332&journal_id=0459-1879&journal_name=力学学报&referenced_num=0&reference_num=8