About this Abstract |
Meeting |
2022 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing: Materials Design and Alloy Development IV: Rapid Development
|
Presentation Title |
Rapid Design and Evaluation of Compositionally Complex Alloys by Combining Additive Manufacturing with Machine Learning Methods |
Author(s) |
Phalgun Nelaturu, Jason Hattrick-Simpers, Michael Moorehead, Santanu Chauduri, Adrien Couet, Dan J Thoma |
On-Site Speaker (Planned) |
Phalgun Nelaturu |
Abstract Scope |
A framework was developed to rapidly explore any alloy system for any desired property by combining high-throughput experimental and computational techniques. We demonstrated this framework by designing materials with desired hardness in two quaternary alloy systems, Cr-Fe-Mn-Ni and Cr-Fe-Mo-Ni. In-situ alloying via directed energy deposition was used to rapidly synthesize more than 200 discrete, bulk samples of unique alloy compositions, exploring a vast portion of the composition space. Tight compositional control within ±10 at% and unmelted powder fraction <0.3% were achieved. The alloys were rapidly characterized via SEM, micro-hardness measurements, and automated XRD and EDS. This large dataset of experimentally measured properties was used to develop a predictive hardening model using active machine learning. The outcome of this effort was the discovery of a learned parameter, deltaLP, that was representative of the lattice distortion in these alloys. deltaLP was trained using the alloy compositions and was highly predictive of hardness. |
Proceedings Inclusion? |
Planned: |
Keywords |
Additive Manufacturing, High-Entropy Alloys, Machine Learning |