无粘结预应力混凝土梁桥自振频率的RBF网络识别.pdf

学兔兔 桥梁建设 2o12年第42卷第2期(总第212期) 28 Bridge Construction，Vo1．42，No．2，2012(Totally No．212) 文章编号：1003—4722(2012)02—0028—06 无粘结预应力混凝土梁桥自振频率的RBF网络识别 李瑞鸽 ，杨国立 ，张耀庭 (1．台州学院建筑工程学院，浙江 台州 318000；2．华中科技大学土木工程与力学学院，湖北 武汉430074) 摘 要：为研究采用神经网络的方法识别无粘结预应力混凝土梁桥的自振频率，收集以往PC 梁的动力试验数据，并在此基础上补充制作5根PC梁进行动力试验，采集相关数据。构建径向基 (RBF)神经网络，采用泛化回归神经网络(GRNN)进行函数逼近，径向基函数的光滑因子取为 0．15。筛选9个影响PC梁自振频率的关键参数作为神经网络的输入参数，用收集到的试验数据 对神经网络进行训练，并预留出1根PC梁的试验数据对网络进行仿真。仿真结果表明，采用所研 究的神经网络方法识别无粘结预应力混凝土梁桥的自振频率是可行的，这种网络具有很好的预测 能力和泛化能力。 关键词：预应力混凝土梁；神经网络；自振频率；动力试验；识别；仿真 中图分类号：U448．35 文献标志码：A Identifying of Natural Vibration Frequencies of Unbonded PC Beam Bridges by RBF Neural Network LI Rui—ge ，YANG Guo—li 。ZHANG Yao—ting (1．School of Architectural Engineering，Taizhou Institute，Taizhou 318000。 China；2．School of Civil Engineering and Mechanics，Huazhong University of Science and Technology，Wuhan 430074，China) Abstract：To study the identifying of natural vibration frequencies of unbonded prestressed concrete(PC)beam bridges by the artificial neural network method，the previous dynamic test data of PC beams were collected and in addition to the collected data，another five beams were made and the dynamic tests for the beams were carried out to supplement more relevant data．The radial～based function(RBF)neural network was built，the generalization regression neural net— work(GRNN)was used to approach the RBF．The smooth factor of the RBF was taken as 0．15 and nine contro】parameters that had influence on the natura J vibration frequencies of the PC beams were sifted as the in