采用贝叶斯理论的渡槽结构有限元模型更新方法  

A finite element model updating method for aqueduct structures based on Bayesian theory

作　　者：吴西杰 张龑[2] 尹进步[1] 何军龄 张曜 WU Xijie;ZHANG Yan;YIN Jinbu;HE Junling;ZHANG Yao(College of Water Resources and Architectural Engineering,Northwest A&F University,Yangling 712100,China;State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin,China Institute of Water Resources and Hydropower Research,Beijing 100038,China)

机构地区：[1]西北农林科技大学水利与建筑工程学院,陕西杨凌712100 [2]中国水利水电科学研究院流域水循环模拟与调控国家重点实验室,北京100038

出　　处：《水利水运工程学报》2024年第6期148-156,共9页Hydro-Science and Engineering

基　　金：水利青年人才发展基金资助项目(JHQB202215);中国水利水电科学研究院五大人才计划项目(SD0145B042021);流域水循环模拟与调控国家重点实验室自主研究课题(SKL2020ZY10)。

摘　　要：渡槽在服役过程中,其结构状态受到多种因素影响会发生改变,在进行有限元分析时,建模所用参数并不是结构实时参数。因此,需要通过监测结构的动力响应来对结构的有限元模型参数进行更新,达到准确评价结构实际运行状态的目的。提出了一种基于贝叶斯理论的有限元模型更新方法,该方法以确定性模型更新结果作为不确定性更新的初始模型参数值,使用MH算法得到模型参数的后验分布,通过ABAQUS有限元模型与MATLAB更新程序的交互访问,实现复杂结构有限元模型参数的自动更新。开展了渡槽模型试验,利用所提方法对渡槽有限元模型进行更新。结果表明,以确定性更新结果作为贝叶斯更新的参数初始值,有限元模型更新的计算效率提高了25%,更新后的误差为0.19%~6.42%,该更新方法能有效改善有限元模型的预测能力。The structural condition of aqueducts changes over time due to various influencing factors.Consequently,parameters used in finite element analysis may not reflect the real-time state of the structure.Therefore,it is necessary to update the finite element model parameters by monitoring the dynamic response of the structure to accurately assess its operational state.This paper proposes a finite element model updating method based on Bayesian theory.The method uses deterministic model updating results as the initial parameters for the uncertain model update.The posterior distribution of model parameters is obtained using the Metropolis-Hastings(MH)algorithm.By integrating ABAQUS finite element models with MATLAB updating programs,automatic parameter updating for complex structural finite element models is achieved.An aqueduct model test was conducted to validate this method.Results indicate that using deterministic updating results as initial parameters for Bayesian updating improves computational efficiency by 25%,with an updated error range of 0.19%to 6.42%.This updating method effectively enhances the predictive capability of finite element models.

关 键 词：有限元模型 模型参数更新 贝叶斯理论 MH算法 随机子空间法 

分 类 号：TV312[水利工程—水工结构工程]