Physics-Informed Network Models: a Data Science Approach to Metal Design

Abstract

Functional graded materials (FGM) allow for reconciliation of conflicting design constraints at different locations in the material. This optimization requires a priori knowledge of how different architectural measures are interdependent and combine to control material performance. In this work, an aluminum FGM was used as a model system to present a new network modeling approach that captures the relationship between design parameters and allows an easy interpretation. The approach, in an un-biased manner, successfully captured the expected relationships and was capable of predicting the hardness as a function of composition.

Document Details

Document Type
Pub Defense Publication
Publication Date
Dec 01, 2017
Source ID
10.1007/s40192-017-0104-5

Entities

People

  • Amit K. Verma
  • Jennifer Carter
  • Roger H. French

Organizations

  • United States Army Research Laboratory

Tags

Readers

  • Computational Modeling and Simulation
  • Neural Network Machine Learning.
  • Reinforced Composite Materials

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference