Predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning

作     者：Taher Hajilounezhad Rina Bao Kannappan Palaniappan Filiz Bunyak Prasad Calyam Matthew R.Maschmann 

作者机构：Mechanical&Aerospace EngineeringUniversity of MissouriColumbiaMOUSA Electrical Engineering and Computer ScienceUniversity of MissouriColumbiaMOUSA 

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：1214-1224页

核心收录：

学科分类：07[理学] 070205[理学-凝聚态物理] 081203[工学-计算机应用技术] 08[工学] 080501[工学-材料物理与化学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0835[工学-软件工程] 0702[理学-物理学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors would like to acknowledge funding from National Science Foundation(NSF)under award CCMI 2026847 and CMMI 1651538(for T.H.and M.R.M.) partial support from NSF MRI CNS-1429294 and Army Research Laboratory award W911NF-1820285(for K.P.,R.B.,and F.B.) The computation for this work was performed on a GPU cluster from the Army Research Office DURIP award W911NF1910181 Any opinions,findings,and conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the U.S.Government or agency thereof 

主　　题：carbon properties overcome 

摘      要：Understanding and controlling the self-assembly of vertically oriented carbon nanotube(CNT)forests is essential for realizing their potential in myriad *** governing process–structure–property mechanisms are poorly understood,and the processing parameter space is far too vast to exhaustively explore *** overcome these limitations by using a physics-based simulation as a high-throughput virtual laboratory and image-based machine learning to relate CNT forest synthesis attributes to their mechanical *** CNTNet,our image-based deep learning classifier module trained with synthetic imagery,combinations of CNT diameter,density,and population growth rate classes were labeled with an accuracy of91%.The CNTNet regression module predicted CNT forest stiffness and buckling load properties with a lower root-mean-square error than that of a regression predictor based on CNT physical *** results demonstrate that image-based machine learning trained using only simulated imagery can distinguish subtle CNT forest morphological features to predict physical material properties with high *** paves the way to incorporate scanning electron microscope imagery for high-throughput material discovery.