首页 | 本学科首页   官方微博 | 高级检索  
     

基于位置和程度指标的结构损伤识别研究
引用本文:金虎,楼文娟.基于位置和程度指标的结构损伤识别研究[J].浙江大学学报(自然科学版 ),2006,40(8):1393-1398.
作者姓名:金虎  楼文娟
作者单位:金虎, 楼文娟(浙江大学 建筑工程学院,浙江 杭州 310027)
摘    要:为提高结构损伤识别的精度,提出基于动、静态数据融合的位置指标和完全基于频率的位置指标,并采用学习速率自适应调整的新型BP神经网络学习算法,其特点是在网络迭代过程中根据网络学习误差来调整学习速率的取值,该方法有效地克服了传统BP网络学习过程中容易陷入局部极小和收敛速度慢、学习效率不高的缺点,进一步讨论了参数输入方式对网络识别效果的影响,分别采用两步诊断法和一步诊断法进行损伤识别.结果显示,两步诊断法对损伤位置和程度的识别正确率较高,而一步诊断法识别效果却不令人十分满意;减少位置指标和程度指标的输入个数对损伤识别结果有显著的影响.

关 键 词:  style="font-family:  损伤识别" target="_blank">宋体">损伤识别    style="font-family:  数据融合" target="_blank">宋体">数据融合    style="font-family:  位置指标" target="_blank">宋体">位置指标    style="font-family:  程度指标" target="_blank">宋体">程度指标    style="font-family:  自适应宋体">自适应  BPlang="EN-US">BP  style="font-family:  网络" target="_blank">宋体">网络
文章编号:1008-973X(2006)08-1393-06
收稿时间:2005-10-05
修稿时间:2005年10月5日

Structural damage identification research based on location index and extent index
JIN Hu,LOU Wen-juan.Structural damage identification research based on location index and extent index[J].Journal of Zhejiang University(Engineering Science),2006,40(8):1393-1398.
Authors:JIN Hu  LOU Wen-juan
Affiliation:College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310027,China
Abstract:To increase the precision of structural damage identification, two kinds of new location indices based on the fusion of the static, dynamic data and natural frequency respectively were proposed. In view of the disadvantages of traditional BP neural networks, a self-adaptive algorithm which could adjust the value of learning rate according to output errors during the training process was introduced. The updated algorithm was proved to avoid oscillation phenomenon and improve learning rate effectively. The influence of input manner on identification effect was also discussed. Two-step-method and one-step-method using self-adaptive networks were adopted for damage detection respectively. It turned out that two-step-method made more accurate estimation for damage location and extent than one-step-method did. The number of location index and extent index influenced the identification effect greatly.
Keywords:damage identification  data fusion  location index  extent index  self-adaptive BP neural networks
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《浙江大学学报(自然科学版 )》浏览原始摘要信息
点击此处可从《浙江大学学报(自然科学版 )》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号