An artificial neural network for surrogate modeling of stress fields in viscoplastic polycrystalline materials  

作　　者：Mohammad S.Khorrami Jaber R.Mianroodi Nima H.Siboni Pawan Goyal Bob Svendsen Peter Benner Dierk Raabe 

机构地区：[1]Microstructure Physics and Alloy Design,Max-Planck-Institut für Eisenforschung,Düsseldorf,Germany [2]Ergodic Labs,Lohmühlenstraße 65,12435 Berlin,Germany [3]Computational Methods in Systems and Control Theory,Max Planck Institute for Dynamics of Complex Technical Systems,Magdeburg,Germany [4]Material Mechanics,RWTH Aachen University,Aachen,Germany

出　　处：《npj Computational Materials》2023年第1期1981-1990,共10页计算材料学（英文）

摘　　要：The purpose of this work is the development of a trained artificial neural network for surrogate modeling of the mechanical response of elasto-viscoplastic grain microstructures.To this end,a U-Net-based convolutional neural network(CNN)is trained using results for the von Mises stress field from the numerical solution of initial-boundary-value problems(IBVPs)for mechanical equilibrium in such microstructures subject to quasi-static uniaxial extension.The resulting trained CNN(tCNN)accurately reproduces the von Mises stress field about 500 times faster than numerical solutions of the corresponding IBVP based on spectral methods.Application of the tCNN to test cases based on microstructure morphologies and boundary conditions not contained in the training dataset is also investigated and discussed.

关 键 词：METHODS BOUNDARY FASTER 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]