About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing Modeling, Simulation and Artificial Intelligence
|
| Presentation Title |
Overcoming Strength-Ductility Trade-Offs in Additively Manufactured Aluminum Alloys Through Integrated Computational Design |
| Author(s) |
Avik K. Mahata |
| On-Site Speaker (Planned) |
Avik K. Mahata |
| Abstract Scope |
Additive manufacturing of aluminum alloys faces a persistent strength-ductility trade-off. This work introduces an integrated computational framework to design optimized alloys for laser powder bed fusion (LPBF). The framework combines machine learning (ML) for property prediction, conditional generative adversarial networks (CGANs) for inverse design of novel compositions, and molecular dynamics (MD) for physics-based validation. Trained on a comprehensive dataset, our ML models predict mechanical properties from compositional descriptors. CGANs then generate new alloy chemistries to meet specific performance targets. MD simulations validate these designs by analyzing fundamental dislocation mechanisms and stress-strain responses. This approach enabled the rapid identification of promising Al–Fe–Co–Ni–Ti compositions with enhanced high-temperature performance. Our framework offers a scalable, predictive path to overcome property trade-offs and accelerate the development of high-performance alloys for demanding applications. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Additive Manufacturing, Aluminum, Computational Materials Science & Engineering |