Journal article
A machine-learning-enhanced hierarchical multiscale method for bridging from molecular dynamics to continua
Neural computing & applications, Vol.32(18), pp.14359-14373
09/18/2019
DOI: 10.1007/s00521-019-04480-7
Abstract
In the community of computational materials science, one of the challenges in hierarchical multiscale modeling is information-passing from one scale to another, especially from the molecular model to the continuum model. A machine-learning-enhanced approach, proposed in this paper, provides an alternative solution. In the developed hierarchical multiscale method, molecular dynamics simulations in the molecular model are conducted first to generate a dataset, which represents physical phenomena at the nanoscale. The dataset is then used to train a material failure/defect classification model and stress regression models. Finally, the well-trained models are implemented in the continuum model to study the mechanical behaviors of materials at the macroscale. Multiscale modeling and simulation of a molecule chain and an aluminum crystalline solid are presented as the applications of the proposed method. In addition to support vector machines, extreme learning machines with single-layer neural networks are employed due to their computational efficiency.
Details
- Title: Subtitle
- A machine-learning-enhanced hierarchical multiscale method for bridging from molecular dynamics to continua
- Creators
- Shaoping Xiao - University of IowaRenjie Hu - University of IowaZhen Li - University of IowaSiamak Attarian - University of IowaKaj-Mikael Björk - Arcada University of Applied SciencesAmaury Lendasse - University of Houston
- Resource Type
- Journal article
- Publication Details
- Neural computing & applications, Vol.32(18), pp.14359-14373
- Publisher
- Springer London
- DOI
- 10.1007/s00521-019-04480-7
- ISSN
- 0941-0643
- eISSN
- 1433-3058
- Language
- English
- Date published
- 09/18/2019
- Academic Unit
- Mechanical Engineering; Iowa Technology Institute
- Record Identifier
- 9984196652802771
Metrics
32 Record Views