| About this Abstract |
| Meeting |
MS&T21: Materials Science & Technology
|
| Symposium
|
Additive Manufacturing of Metals:
ICME Gaps: Material Property and Validation Data to Support Certification
|
| Presentation Title |
Predicting Melt Properties Using Atomistic Simulations with a Highly Accurate Physically Informed Neural Network Interatomic Potential |
| Author(s) |
Vesselin I. Yamakov, Yuri Mishin, Edward H Glaessgen |
| On-Site Speaker (Planned) |
Vesselin I. Yamakov |
| Abstract Scope |
This presentation discusses the use of a recently developed machine learning (ML) interatomic potential for molecular dynamics simulations of aluminum melt properties. Such properties are critical for process modelling in additive manufacturing, including the melt pool size, solidification, and formation of solidification microstructures. Direct first-principles modeling of these processes is computationally prohibitive whereas simulations employing ML potentials combine the high accuracy of quantum-mechanical methods with high computational speeds. The physically-informed neural network (PINN) method used herein, integrates a high-dimensional regression implemented by an artificial neural network with a physics-based bond-order interatomic potential. PINN potentials can accurately reproduce many properties of aluminum in both crystalline-solid and liquid phases. We examine the accuracy of a PINN Al potential in predicting the density, self-diffusivity, viscosity, and the tension of the liquid surface and liquid-solid interfaces. Comparison with experimental data and ab initio molecular dynamics calculations shows very good agreement for all properties tested. |