| About this Abstract |
| Meeting |
6th World Congress on Integrated Computational Materials Engineering (ICME 2022)
|
| Symposium
|
6th World Congress on Integrated Computational Materials Engineering (ICME 2022)
|
| Presentation Title |
Machine Learning Based Hierarchical Multiscale Modeling of Mechanical Deformation for Metal-Matrix-Nanocomposites |
| Author(s) |
Md Shahrier Hasan, Wenwu Xu, Gregory Berkeley |
| On-Site Speaker (Planned) |
Md Shahrier Hasan |
| Abstract Scope |
The mechanical properties of Metal-Matrix-Nanocomposites (MMNCs) have demonstrated significant enhancement with the presence of a small fraction of nano-inclusions. To understand this nano-inclusion-induced enhancement, multi-scale modeling is necessary, one that can pass the atomistic mechanism-dependent information to the continuum calculations. Here, a novel Machine Learning (ML) enabled hierarchical multiscale modeling was developed by coupling the atomistic Molecular Dynamics (MD) simulations with the macroscale Finite Element Method (FEM) to understand and make predictions on how the nano-inclusions affect the macroscopic properties of MMNCs. At first, MD simulations for various loading conditions and nano-inclusion structures were conducted to generate a sufficient amount of deformation and mechanical property-related data to train various ML classification and regression models which were in turn utilized in the macroscale FEM model as constitutive laws. Finally, the multiscale modeling results were qualitatively verified against the relevant modeling and experimental data for MMNCs. |
| Proceedings Inclusion? |
Definite: Other |