Machine learning enabled autonomous microstructural characterization in 3D samples

作     者：Henry Chan Mathew Cherukara Troy D.Loeffler Badri Narayanan Subramanian K.R.S.Sankaranarayanan 

作者机构：Center for Nanoscale MaterialsArgonne National LaboratoryArgonneILUSA Department of Mechanical EngineeringUniversity of LouisvilleLouisvilleKYUSA Department of Mechanical and Industrial EngineeringUniversity of Illinois at ChicagoChicagoILUSA 

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

年 卷 期：2020年第6卷第1期

页      面：1654-1662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] 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：Use of the Center for Nanoscale Materials was supported by the U.S.Department of Energy,Office of Science,Office of Basic Energy Sciences,under Contract No.DEAC02-06CH11357 This research used resources of the Argonne Leadership Computing Facility at Argonne National Laboratory,which is supported by the Office of Science of the U.S.Department of Energy under contract DE-AC02-06CH11357 This research used resources of the National Energy Research Scientific Computing Center a DOE Office of Science User Facility supported by the Office of Science of the U.S.Department of Energy under Contract No.DEAC02-05CH11231 

主　　题：microstructure polycrystalline porosity 

摘      要：We introduce an unsupervised machine learning(ML)based technique for the identification and characterization of microstructures in three-dimensional(3D)samples obtained from molecular dynamics simulations,particle tracking data,or *** technique combines topology classification,image processing,and clustering algorithms,and can handle a wide range of microstructure types including grains in polycrystalline materials,voids in porous systems,and structures from self/directed assembly in soft-matter complex *** technique does not require a priori microstructure description of the target system and is insensitive to disorder such as extended defects in polycrystals arising from line and plane *** demonstrate quantitively that our technique provides unbiased microstructural information such as precise quantification of grains and their size distributions in 3D polycrystalline samples,characterizes features such as voids and porosity in 3D polymeric samples and micellar size distribution in 3D complex *** demonstrate the efficacy of our ML approach,we benchmark it against a diverse set of synthetic data samples representing nanocrystalline metals,polymers and complex fluids as well as experimentally published characterization *** technique is computationally efficient and provides a way to quickly identify,track,and quantify complex microstructural features that impact the observed material behavior.