About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
Deformation Mechanisms, Microstructure Evolution, and Mechanical Properties of Nanoscale Materials
|
Presentation Title |
A Machine Learning Approach to Model the Mechanical Response of Nanofoams |
Author(s) |
Sepideh Kavousi, Mohsen Asle Zaeem |
On-Site Speaker (Planned) |
Mohsen Asle Zaeem |
Abstract Scope |
Nanofoam metals are low-density and impact-absorbing materials with various potential applications, such as shock absorbers. In this study, we developed a machine learning model to investigate how geometric attributes of closed cell aluminum nanofoams affect their mechanical response. The Voronoi tessellation method is used to make closed-cell nanofoam models with random pore sizes between 15 and 39 nm and wall thicknesses between 2.8 and 10 nm. All the training and testing data are generated by molecular dynamics simulations of uniaxial tensile and compression loading of the nanofoams. The machine learning model correlates the mean size of nanopores, their size distribution, and wall thickness to various mechanical properties such as elastic modulus, yield stress and strain, and strain after unloading. |
Proceedings Inclusion? |
Planned: |
Keywords |
Modeling and Simulation, Machine Learning, |