- Microstructural properties, including grain morphology and crystal orientation, impact mechanical performance and consistency.
- Visual analysis and synthetic descriptors of both grain morphology and crystal orientation.
- Using separate methods for morphology and RGB intensity maps for orientation.
Develop a learning framework by integrating grain morphology and crystal orientation data for a microstructure characterization and classification.
- Multi-feature embedding using KDE.
- Manifold learning.
- Tensor analysis.
- Improving performance by automation.
- Increasing accuracy.
- Enabling classifying segments effectively.
Automated Characterization of Microstructure Data in Additive Manufacturing via Low-Dimensional Learning
Kamran Paynabar
Associate Chair for Innovation, Leadership, and Entrepreneurship
Fouts Family Chair
Professor
ISyE, Georgia Tech
Fouts Family Chair
Professor
ISyE, Georgia Tech
