基于模型智能修正的桥梁健康状态评估  

Evaluation of Bridge Health Condition Through Model Updating by Neural Network Approach

作　　者：范剑锋[1] 袁海庆[1] 彭自强[1] 王佶[1] 

机构地区：[1]武汉理工大学道路桥梁与结构工程湖北省重点实验室,武汉430070

出　　处：《武汉理工大学学报》2008年第4期84-87,共4页Journal of Wuhan University of Technology

基　　金：湖北省交通厅科技项目(鄂交科教[2005]361号)

摘　　要：利用神经网络方法来修正结构模型,然后再进行桥梁状态评估。在模型修正中引入模态频率和模态柔度指标作为神经网络系统的输入指标,修正后的结构数值模型能够准确反映桥梁的实际健康状态。通过巴东长江大桥实例进行了可行性验证,然后在此基础上进行各种计算工况的加载,可以评估当前桥梁的实际状态。The intelligent updated model of neural network structure was set up to assess the bridge health condition in this paper.The mode flexibility and the mode frequency were introduced to the input parameter of neural network system.Through the network training and amending,the updated FEM model was carried out.By an example,it proved that the updated model could reflect the bridge actual state accurately.Then,with the various loads combinations on the updated model,it could evaluate the real state condition of...

关 键 词：桥梁状态评估 神经网络 模型修正 模态柔度 

分 类 号：U446[建筑科学—桥梁与隧道工程]