Teaching solid mechanics to artificial intelligence—a fast solver for heterogeneous materials

作     者：Jaber Rezaei Mianroodi Nima H.Siboni Dierk Raabe 

作者机构：Microstructure Physics and Alloy DesignMax-Planck-Institut für EisenforschungDüsseldorfGermany DeepMetisBerlinGermany 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2021年第7卷第1期

页      面：899-908页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 080502[工学-材料学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Projekt DEAL 

主　　题：artificial network faster 

摘      要：We propose a deep neural network(DNN)as a fast surrogate model for local stress calculations in inhomogeneous non-linear *** show that the DNN predicts the local stresses with 3.8%mean absolute percentage error(MAPE)for the case of heterogeneous elastic media and a mechanical contrast of up to factor of 1.5 among neighboring domains,while performing 103 times faster than spectral *** DNN model proves suited for reproducing the stress distribution in geometries different from those used for *** the case of elasto-plastic materials with up to 4 times mechanical contrast in yield stress among adjacent regions,the trained model simulates the micromechanics with a MAPE of 6.4%in one single forward evaluation of the network,without any *** results reveal an efficient approach to solve non-linear mechanical problems,with an acceleration up to a factor of 8300 for elastic-plastic materials compared to typical solvers.