径向基神经网络的大桥形变预测  

Deformation prediction of bridge based on radial basis function neural network

作　　者：黄国斌[1,2] 田林亚[2,3] 赵小飞[4] 

机构地区：[1]江苏建筑职业技术学院建筑工程学院,江苏徐州221116 [2]武汉大学精密工程与工业测量国家测绘地理信息局重点实验室,湖北武汉430079 [3]河海大学地球科学与工程学院,江苏南京210098 [4]山东公路技师学院土木工程系,山东济南250000

出　　处：《辽宁工程技术大学学报（自然科学版）》2013年第8期1103-1106,共4页Journal of Liaoning Technical University (Natural Science)

基　　金：精密工程与工业测量国家测绘地理信息局重点实验室开放基金资助项目(PF2012-3)

摘　　要：为解决由于材料老化、疲劳效应、荷载作用和环境变化等多种因素造成的大桥基础及上部结构形变影响,必须对大桥形变及其影响因素进行监测.针对大桥形变影响因素复杂多变的特点,采用径向基神经网络形变预测模型,推导了网络参数的改进算法,利用大桥实际监测数据,建立了径向基网络形变预测模型.研究结果表明:该方法在水平方向和垂直方向均能够达到4 mm以内的形变预测精度,能够为大桥的安全运行提供保障.To solve the influence of various factors as material aging,fatigue effect,load effect and environmental changes,the monitoring for the deformation of the bridge must be carried out.Considering the complex characteristics of factors influencing the bridge deformation,the deformation predication model based on radial basis function neural network(RBF) and the improved algorithm of network parameters was studied.Combined with the monitoring data of the bridge,a RBF network deformation forecasting model was established,the calculation results show that RBF modal can attain a 4mm accuracy of deformation prediction which is enough to guarantee the safety of bridge.

关 键 词：大桥形变监测 径向基神经网络 聚类分析 形变预测 网络参数 中心向量 规划因子 连接权 

分 类 号：N5[自然科学总论]