基于降阶模型和数据驱动的动态结构数字孪生方法  

A Digital Twin Method for Dynamic Structures Based on Reduced Order Models and Data Driving

作　　者：王青山 严波[1] 陈岩 邓茂 蔡源斌 WANG Qingshan;YAN Bo;CHEN Yan;DENG Mao;CAI Yuanbin(College of Aerospace Engineering,Chongqing University,Chongqing 400044,P.R.China)

机构地区：[1]重庆大学航空航天学院,重庆400044

出　　处：《应用数学和力学》2023年第7期757-768,共12页Applied Mathematics and Mechanics

基　　金：国家自然科学基金项目(11572060)。

摘　　要：针对受动载荷作用的结构,提出了一种基于降阶模型库和机器学习数据驱动的数字孪生构建方法.首先根据物理结构服役过程中可能出现的损伤状态,采用有限单元法建立高保真有限元模型.其次采用Krylov子空间模型降阶方法对模型进行降阶,建立了物理结构各种状态下的降阶模型,形成模型库.最后利用随机森林机器学习算法训练获得模型选择器,通过物理结构上传感器的数据推断当前物理结构的状态,驱动数字孪生体跟随物理结构一同演化.设计制作了一个框架结构物理模型,模拟了结构不同位置损伤及不同损伤程度,验证了提出的数字孪生构建方法.A digital twin construction method based on the reduced order model library and machine learning was proposed for structures under dynamic loads.Firstly,the high-fidelity finite element models were established according to the possible damage states occurring during the service of the physical structures.Secondly,the Krylov subspace order reduction method was used to reduce the orders of the models and the reduced order models were assembled to a library.Finally,the random forest machine learning algorithm was used to train the model selector,infer the current state of the physical structure through the sensor data from the structure,and then drive the digital twin to evolve with the physical structure.A physical frame structure was designed and manufactured to simulate the damages of different degrees at different points,and verify the proposed digital twin construction method for dynamic structures.

关 键 词：结构数字孪生 降阶模型库 Krylov子空间模型降阶 随机森林 数据驱动 

分 类 号：O32[理学—一般力学与力学基础]