Deep material network via a quilting strategy: visualization for explainability and recursive training for improved accuracy  

作　　者：Dongil Shin Ryan Alberdi Ricardo A.Lebensohn Rémi Dingreville 

机构地区：[1]Center for Integrated Nanotechnologies,Sandia National Laboratories,Albuquerque,NM 87185,USA [2]Simulation Modeling Sciences,Sandia National Laboratories,Albuquerque,NM 87185,USA [3]Theoretical Division,Los Alamos National Laboratory,Los Alamos,NM 87845,USA

出　　处：《npj Computational Materials》2023年第1期1023-1038,共16页计算材料学（英文）

基　　金：This work was supported by the Advanced Engineering Materials program.

摘　　要：Recent developments integrating micromechanics and neural networks offer promising paths for rapid predictions of the response of heterogeneous materials with similar accuracy as direct numerical simulations.The deep material network is one such approaches,featuring a multi-layer network and micromechanics building blocks trained on anisotropic linear elastic properties.Once trained,the network acts as a reduced-order model,which can extrapolate the material’s behavior to more general constitutive laws,including nonlinear behaviors,without the need to be retrained.However,current training methods initialize network parameters randomly,incurring inevitable training and calibration errors.Here,we introduce a way to visualize the network parameters as an analogous unit cell and use this visualization to“quilt”patches of shallower networks to initialize deeper networks for a recursive training strategy.The result is an improvement in the accuracy and calibration performance of the network and an intuitive visual representation of the network for better explainability.

关 键 词：networks DEEP NETWORK 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]