基于改进高斯混合粒子滤波新算法的桥梁极值应力动态预测

Bridge extreme stress dynamic prediction based on improved Gaussian mixed particle filter new algorithm

将极值应力数据视为时间序列,提出了桥梁结构极值应力的改进高斯混合粒子滤波(IGMPF)动态预测新方法。首先,利用桥梁健康监测极值应力数据建立动态非线性模型,将其作为粒子滤波算法的状态方程和监测方程;然后,引入最大期望(EM)算法来估计目标状态的概率分布,并嵌入高斯混合粒子滤波器中,进而利用改进高斯混合粒子滤波算法,结合应力监测数据实现结构极值应力的动态预测;最后,通过在役桥梁监测数据对本文模型和方法的合理性进行验证。结果表明:本文方法预测精度高,可用于工程实际应用中。

The extreme stress data is taken as a time series,an improved Gaussian mixed particle filter(IGMPF)dynamic prediction new approach of bridge extreme stresses is proposed.Firstly,the dynamic nonlinear model,which provides state equation and monitored equation for the particle filter,is built with the monitored bridge extreme stress data;then,the EM algorithm is introduced to estimate the probability density function(PDF)of the target state and embedded in the Gaussian mixed particle filter(GMPF);further,with the IGMPF prediction approach,structural stresses are dynamically predicted based on the monitored extreme stress data;finally,the monitored stress data of an actual bridge is provided to illustrate the feasibility and application of the proposed models and methods.The result shows that the proposed algorithm has good prediction accuracy,can apply to real engineering.