Prediction of carbon nanostructure mechanical properties and the role of defects using machine learning

被引:3
作者
Winetrout, Jordan J. [1 ,2 ]
Li, Zilu [3 ]
Zhao, Qi [3 ]
Gaber, Landon [4 ]
Unnikrishnan, Vinu [4 ,5 ]
Varshney, Vikas
Xu, Yanxun [6 ]
Wang, Yusu [3 ,7 ]
Heinz, Hendrik [1 ,2 ]
机构
[1] Univ Colorado Boulder, Dept Chem & Biol Engn, Boulder, CO 80309 USA
[2] Univ Colorado Boulder, Coll Engn & Appl Sci, Mat Sci & Engn Program, Boulder, CO 80309 USA
[3] Univ Calif San Diego, Dept Comp Sci & Engn, La Jolla, CA 92093 USA
[4] West Texas A&M Univ, Coll Engn, Civil Engn, Canyon, TX 79016 USA
[5] US Air Force, Res Lab, Mat & Mfg Directorate, Dayton, OH 45433 USA
[6] Johns Hopkins Univ, Dept Appl Math & Stat, Baltimore, MD 21218 USA
[7] Univ Calif San Diego, Halicioglu Data Sci Inst, La Jolla, CA 92093 USA
关键词
carbon nanotubes; database; simulation; mechanical properties; machine learning; NANOTUBES; RECOGNITION; NUCLEATION; MODULUS; DENSITY; MODELS;
D O I
10.1073/pnas.2415068122
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Graphene- based nanostructures hold immense potential as strong and lightweight materials, however, their mechanical properties such as modulus and strength are difficult to fully exploit due to challenges in atomic- scale engineering. This study presents a database of over 2,000 pristine and defective nanoscale CNT bundles and other graphitic assemblies, inspired by microscopy, with associated stress-strain curves from reactive (IFF- R). These 3D structures, containing up to 80,000 atoms, enable detailed analyses of structure- stiffness- failure relationships. By leveraging the database and physics- and chemistry- informed machine learning (ML), accurate predictions of elastic moduli and tensile strength are demonstrated at speeds 1,000 to 10,000 times faster than effierties of arbitrary carbon nanostructures with only 3 to 6% mean relative error. The tions, and carbon fiber cross- sections outside the training distribution. The physics- and range while XGBoost works well with limited training data inside the training range. mental and simulation data, scalable beyond 100 nm size, and extendable to chemically for applications in structural materials, nanoelectronics, and carbon- based catalysts.
引用
收藏
页数:12
相关论文
共 87 条
[1]   Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning [J].
Alipanahi, Babak ;
Delong, Andrew ;
Weirauch, Matthew T. ;
Frey, Brendan J. .
NATURE BIOTECHNOLOGY, 2015, 33 (08) :831-+
[2]   Machine learning electron density in sulfur crosslinked carbon nanotubes [J].
Alred, John M. ;
Bets, Ksenia V. ;
Xie, Yu ;
Yakobson, Boris I. .
COMPOSITES SCIENCE AND TECHNOLOGY, 2018, 166 :3-9
[3]   Carbon nanotube bundles with tensile strength over 80 GPa [J].
Bai, Yunxiang ;
Zhang, Rufan ;
Ye, Xuan ;
Zhu, Zhenxing ;
Xie, Huanhuan ;
Shen, Boyuan ;
Cai, Dali ;
Liu, Bofei ;
Zhang, Chenxi ;
Jia, Zhao ;
Zhang, Shenli ;
Li, Xide ;
Wei, Fei .
NATURE NANOTECHNOLOGY, 2018, 13 (07) :589-+
[4]   Boron Nitride Nanotubes: Force Field Parameterization, Epoxy Interactions, and Comparison with Carbon Nanotubes for High- Performance Composite Materials [J].
Bamane, Swapnil S. ;
Jakubinek, Michael B. ;
Kanhaiya, Krishan ;
Ashrafi, Behnam ;
Heinz, Hendrik ;
Odegard, Gregory M. .
ACS APPLIED NANO MATERIALS, 2023, 6 (05) :3513-3524
[5]   The formation of a connection between carbon nanotubes in an electron beam [J].
Banhart, F .
NANO LETTERS, 2001, 1 (06) :329-332
[6]   Characterization methods of carbon nanotubes: a review [J].
Belin, T ;
Epron, F .
MATERIALS SCIENCE AND ENGINEERING B-SOLID STATE MATERIALS FOR ADVANCED TECHNOLOGY, 2005, 119 (02) :105-118
[7]   A study on mechanical strength and stability of partially-fused carbon nanotube junctions [J].
Bhusal, Shusil ;
Sihn, Sangwook ;
Varshney, Vikas ;
Roy, Ajit K. .
CARBON TRENDS, 2021, 3
[8]   CAM: CAUSAL ADDITIVE MODELS, HIGH-DIMENSIONAL ORDER SEARCH AND PENALIZED REGRESSION [J].
Buehlmann, Peter ;
Peters, Jonas ;
Ernest, Jan .
ANNALS OF STATISTICS, 2014, 42 (06) :2526-2556
[9]   High strength and high modulus carbon fibers [J].
Chae, Han Gi ;
Newcomb, Bradley A. ;
Gulgunje, Prabhakar V. ;
Liu, Yaodong ;
Gupta, Kishor K. ;
Kamath, Manjeshwar G. ;
Lyons, Kevin M. ;
Ghoshal, Sushanta ;
Pramanik, Chandrani ;
Giannuzzi, Lucille ;
Sahin, Korhan ;
Chasiotis, Ioannis ;
Kumar, Satish .
CARBON, 2015, 93 :81-87
[10]   Structural and Functional Fibers [J].
Chang, Huibin ;
Luo, Jeffrey ;
Gulgunje, Prabhakar V. ;
Kumar, Satish .
ANNUAL REVIEW OF MATERIALS RESEARCH, VOL 47, 2017, 47 :331-359