基于结构动力参数的RBF损伤辨识方法  

Application of RBF Networks for Damage Identification in Simply Supported Beam

作　　者：赵迁乔[1] 靳露[1] 宋夫才 

机构地区：[1]山东科技大学资源与环境工程学院,青岛266510 [2]青岛市公路规划设计院,266061

出　　处：《特种结构》2011年第1期14-18,共5页Special Structures

摘　　要：本文研究了基于不同结构动力参数的径向基网络损伤辨识方法,并结合简支梁损伤辨识进行了应用。研究发现:(1)径向基网络的输入参数选择对结果有较大影响;(2)使用模态曲率变化作为输入参数的网络辨识效果优于采用频率变化率的辨识效果;(3)综合使用频率变化率和模态曲率变化的网络辨识效果优于单独使用频率变化率或模态曲率的效果。结果表明,基于动力参数和径向基神经网络的结构损伤辨识方法能够准确地辨识结构损伤。RBF damage identification based on different structural dynamic parameters is studied in this paper. The method is applied in the damage detection for the simply supported beam.The study reveals that：the input parameters of RBF networks have bigger influence for the identification effect;taking the change of mode shape curvature、as input parameter,the identification effect is better than taking the change of frequency as input parameter;further more,the combination of the frequency change and change of mode shape curvature gives the best results.The research proved that the structural damage can be identified by using RBF networks and dynamic parameters.

关 键 词：损伤辨识 径向基网络 动力参数 

分 类 号：TU311.3[建筑科学—结构工程]