Machine Learning for Carbon Nanotube Yarn Mechanical Properties

Carbon fiber and graphene-based nanomaterials, such as carbon nanotubes (CNTs), have extraordinary potential as strong and lightweight structural materials. However, a lack of understanding and implementation of atomic-scale engineering impedes the theoretical mechanical performance of these carbon-based materials when used in applications. Here we demonstrate a machine learning (ML) method to make accurate and fast predictions of mechanical properties for CNT yarns and arbitrary 3D graphitic assemblies based on a training set of over 1000 stress-strain curves from cutting-edge reactive MD simulation. Several ML methods are compared and show that our newly proposed hierarchically processed 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.