基于改进BP算法的刚框架连接损伤识别方法
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
运用权值、阈值同步学习BP算法(简称为改进BP算法)对钢框架连接损伤进行识别,并且选用由结构正则化的频率变化率和少数点的振型模态分量构成的组合参数作为网络输入参数.通过对一个4层钢框架数值模拟,比较了改进算法和传统算法测试结果,从而证明改进算法更加精确、优越.
The BP algorithm with weight and threshold synchro-learning ability(shortened as improved BP algorithm)is used to identify steel frame connection damage,and a synthesized parameter vector called combined parameter,which is obtained by combining the regularizing change rate of frequency and mode shape at a few selected points,is used as input parameter to improved BP algorithm.Through numerical simulation on a four-story steel frame,the test results of improved BP algorithm and traditional BP algorithm are compared.As a result,it is proved that the improved method is more accurate and more superior.
引文
[1]姜绍飞.基于神经网络的结构优化与损伤检测[M].北京:科学出版社,2002.
    [2]李学良,霍达,腾海文.基于权值、阈值同步学习BP算法的结构损伤检测[J].世界地震工程,2005,21(2):52-56.
    [3]Caw ley P,A dam s R D.The Location of Detects in Stru-ctures from Measurements of Natural Frequencies[J].Journal ofStrain Analysis,1979,14:49-57.
    [4]Lam H F,Ko J M,Wong C W.Localization of Damaged Struc-tural Connections Based on Experimental Modal and SensitivityAnalysis[J].Journal of sound and Vibration,1998,210:91-115.
    [5]沈东强,徐礼华,龚建伍.基于BP网络的结构损伤识别[J].武汉理工大学学报,2004,26(9):48-50.
    [6]杜永峰,陈文元.小波分析与神经网络在结构损伤检测中的应用[J].兰州理工大学学报,2005,31(5):121-124.
    [7]飞思达科技产品研发中心.MATLAB6.5辅助神经网络分析与设计[M].电子工业出版社,2003.
    [8]唐和生,薛松涛,陈钅容,等.采用组合参数的神经网络结构损伤检测分析研究[J].应用数学和力学,2005,26(1):40-46.
    [9]李一洁,申东日,陈义蛟.一种改进的小波网络与故障检测[J].甘肃科学学报,2005,17(1):61-64.

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