基于Hopfield 神经网络的有限元模型修正  

Finite Element Model Modification Based on Hopfield Neural Network

作　　者：杨昕怡 YANG Xin-yi(School of Civil Engineering and Architecture,Wuhan University of Technology,Wuhan 430000,China)

机构地区：[1]武汉理工大学土木工程与建筑学院,武汉430070

出　　处：《建材世界》2022年第4期46-48,65,共4页The World of Building Materials

基　　金：武汉理工大学土木工程与建筑学院国家级大学生创新创业训练计划资助(202110497067)。

摘　　要：工程结构的有限元模型对结构的健康监测与可靠性评估有重大意义,但实际工程中测量数据和模型都与结构初始有限元模型有一定的差异,因此有必要对实际结构的有限元模型进行修正。首先建立有限元模型修正方程来表达结构响应与待修正参数之间的关系,再通过Hopfield递归神经网络技术,对模型修正方程进行求解。通过一个数值梁模型对提出的方法进行了验证,结果显示Hopfield神经网络在求解线性模型修正仿真中有较好的效果。The finite element model of engineering structure was of great significance to the health monitoring and reliability evaluation of the structure,but the measured data and the model in the actual engineering were different from the initial finite element model of the structure,so it was necessary to modify the finite element model of the actual structure.Firstly,the finite element model modification equation was established to express the relationship between structural response and parameters to be modified,and then the Hopfield recursive neural network technology was used to solve the model modification equation.A numerical beam model was used to verify the proposed method,and the results showed that Hopfield neural network was effective in solving linear model modification simulation.

关 键 词：HOPFIELD神经网络 模型修正 线性方程组 有限元模型 

分 类 号：TB115[理学—数学] TP183[理学—应用数学]