Graph-Based Stochastic Learning to Build Physics-Informed AI for Discovering Defect Mechanisms in Powder-based Fabrication
Abstract
The proposed research aims to integrate computational material sciences, multi-physics simulations, statistical modeling, in-situ sensing, and Graphnets to create physics-informed AI software that accelerates the discovery of defect formation. This project will establish a theoretical framework to study combinatorial generalization problems (CG) that can empower AI to make inferences on new scenarios given piecewise knowledge learned from multiple data sources, such as multi-physics simulation and experimental data. The research will develop theories and algorithms based on physics-informed Graphnets and generative AI to solve CG problems in three thrust areas, helping discover unmeasurable defect mechanisms in powder-based fabrication.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Mar 14, 2024
- Source ID
- FA95502310739
Entities
People
- Hui Wang
Organizations
- Air Force Office of Scientific Research
- Florida A&M University
- United States Air Force