Reduced-Order Modeling of the Deformation Response of Polycrystalline Aggregates

Abstract

The primary objectives of this effort are to investigate: (a) the efficacy of applying machine learning algorithms in the determination of microstructure effects on anisotropic yield of key engineering components; and (b) reduced-order methodologies that allow for the linking of microstructural condition to macroscale deformation to aid in current life prediction model development. During this effort, researchers will work to develop a computational framework to allow for the simulation of component scale deformation processes with consideration from the microstructural condition. The majority of this effort will be focused on the implementation and development of a novel machine learning algorithms that will produce a reduced-parameter model describing the connection between crystal scale deformation phenomena and component scale plastic deformation phenomena

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 10, 2020
Source ID
FA86502015203

Entities

People

  • Matthew Kasemer

Organizations

  • Air Force Research Laboratory
  • United States Air Force
  • University of Alabama

Tags

Readers

  • Computational Fluid Dynamics (CFD)
  • Materials Science and Engineering.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks