Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202854188> ?p ?o ?g. }
- W3202854188 abstract "Carbon fiber and graphene-based nanostructures such as carbon nanotubes (CNTs) and defective structures have extraordinary potential as strong and lightweight materials. A longstanding bottleneck has been lack of understanding and implementation of atomic-scale engineering to harness the theoretical limits of modulus and tensile strength, of which only a fraction is routinely reached today. Here we demonstrate accurate and fast predictions of mechanical properties for CNTs and arbitrary 3D graphitic assemblies based on a training set of over 1000 stress-strain curves from cutting-edge reactive MD simulation and machine learning (ML). Several ML methods are compared and show that our newly proposed hierarchically structured graph neural networks with spatial information (HS-GNNs) achieve predictions in modulus and strength for any 3D nanostructure with only 5-10% error across a wide range of possible values. The reliability is sufficient for practical applications and a great improvement over off-the shelf ML methods with up to 50% deviation, as well as over earlier models for specific chemistry with 20% deviation. The algorithms allow more than 10 times faster mechanical property predictions than traditional molecular dynamics simulations, the identification of the role of defects and random 3D morphology, and high-throughput screening of 3D structures for enhanced mechanical properties. The algorithms can be scaled to morphologies up to 100 nm in size, expanded for chemically similar compounds, and trained to predict a broader range of properties." @default.
- W3202854188 created "2021-10-11" @default.
- W3202854188 creator A5020217603 @default.
- W3202854188 creator A5030187457 @default.
- W3202854188 creator A5056825063 @default.
- W3202854188 creator A5064535564 @default.
- W3202854188 creator A5075561024 @default.
- W3202854188 date "2021-10-01" @default.
- W3202854188 modified "2023-10-17" @default.
- W3202854188 title "Prediction of Carbon Nanostructure Mechanical Properties and Role of Defects Using Machine Learning" @default.
- W3202854188 cites W1019830208 @default.
- W3202854188 cites W1501856433 @default.
- W3202854188 cites W1531674615 @default.
- W3202854188 cites W1556631438 @default.
- W3202854188 cites W1901616594 @default.
- W3202854188 cites W1977446441 @default.
- W3202854188 cites W2019465613 @default.
- W3202854188 cites W2029413789 @default.
- W3202854188 cites W2038702914 @default.
- W3202854188 cites W2051585621 @default.
- W3202854188 cites W2081855562 @default.
- W3202854188 cites W2096736341 @default.
- W3202854188 cites W2104330751 @default.
- W3202854188 cites W2104489082 @default.
- W3202854188 cites W2116341502 @default.
- W3202854188 cites W2118849046 @default.
- W3202854188 cites W2143612262 @default.
- W3202854188 cites W2149185044 @default.
- W3202854188 cites W2163605009 @default.
- W3202854188 cites W2194775991 @default.
- W3202854188 cites W2279490987 @default.
- W3202854188 cites W2290847742 @default.
- W3202854188 cites W2316932441 @default.
- W3202854188 cites W2337496963 @default.
- W3202854188 cites W2343416635 @default.
- W3202854188 cites W2560609797 @default.
- W3202854188 cites W2565212977 @default.
- W3202854188 cites W2606213227 @default.
- W3202854188 cites W2606780347 @default.
- W3202854188 cites W2626898927 @default.
- W3202854188 cites W2735246657 @default.
- W3202854188 cites W2749279690 @default.
- W3202854188 cites W2768880080 @default.
- W3202854188 cites W2795934726 @default.
- W3202854188 cites W2800868414 @default.
- W3202854188 cites W2811124557 @default.
- W3202854188 cites W2917193084 @default.
- W3202854188 cites W2961492614 @default.
- W3202854188 cites W2962711740 @default.
- W3202854188 cites W2963403868 @default.
- W3202854188 cites W2963509914 @default.
- W3202854188 cites W2963806772 @default.
- W3202854188 cites W2963977738 @default.
- W3202854188 cites W2964015378 @default.
- W3202854188 cites W2964051675 @default.
- W3202854188 cites W2964113829 @default.
- W3202854188 cites W2964145825 @default.
- W3202854188 cites W2964237352 @default.
- W3202854188 cites W2964311892 @default.
- W3202854188 cites W2966357564 @default.
- W3202854188 cites W2970395725 @default.
- W3202854188 cites W2970987097 @default.
- W3202854188 cites W2978788714 @default.
- W3202854188 cites W2983288276 @default.
- W3202854188 cites W2996443485 @default.
- W3202854188 cites W3102380997 @default.
- W3202854188 cites W3140579943 @default.
- W3202854188 cites W3188339431 @default.
- W3202854188 doi "https://doi.org/10.48550/arxiv.2110.00517" @default.
- W3202854188 hasPublicationYear "2021" @default.
- W3202854188 type Work @default.
- W3202854188 sameAs 3202854188 @default.
- W3202854188 citedByCount "0" @default.
- W3202854188 crossrefType "posted-content" @default.
- W3202854188 hasAuthorship W3202854188A5020217603 @default.
- W3202854188 hasAuthorship W3202854188A5030187457 @default.
- W3202854188 hasAuthorship W3202854188A5056825063 @default.
- W3202854188 hasAuthorship W3202854188A5064535564 @default.
- W3202854188 hasAuthorship W3202854188A5075561024 @default.
- W3202854188 hasBestOaLocation W32028541881 @default.
- W3202854188 hasConcept C112950240 @default.
- W3202854188 hasConcept C11413529 @default.
- W3202854188 hasConcept C119857082 @default.
- W3202854188 hasConcept C147597530 @default.
- W3202854188 hasConcept C149635348 @default.
- W3202854188 hasConcept C159985019 @default.
- W3202854188 hasConcept C171250308 @default.
- W3202854188 hasConcept C173608175 @default.
- W3202854188 hasConcept C185592680 @default.
- W3202854188 hasConcept C186187911 @default.
- W3202854188 hasConcept C190475519 @default.
- W3202854188 hasConcept C192562407 @default.
- W3202854188 hasConcept C193867417 @default.
- W3202854188 hasConcept C2780513914 @default.
- W3202854188 hasConcept C30080830 @default.
- W3202854188 hasConcept C41008148 @default.
- W3202854188 hasConcept C50644808 @default.
- W3202854188 hasConcept C513720949 @default.
- W3202854188 hasConcept C59593255 @default.
- W3202854188 hasConceptScore W3202854188C112950240 @default.