About this Abstract |
Meeting |
2025 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing Modeling, Simulation and Machine Learning
|
Presentation Title |
AlloyGPT: An Agent-Based LLM Framework for the Design of Additively Manufactured Structural Alloys in Extreme Environments |
Author(s) |
S. Mohadeseh Taheri-Mousavi |
On-Site Speaker (Planned) |
S. Mohadeseh Taheri-Mousavi |
Abstract Scope |
Traditionally human are involved in various planning, collecting knowledge, designing, validating structural alloys for a given application. Here, we present a large language model powered by collaborations of various AI agents to automate this process and accelerate the material discovery. We will talk how we applied our framework for the design of high-temperature strength printable Al alloys with thermal stability. We will show how GPT4-based LLMs which are trained by CALPHAD-based ICME data can predict microstructural features and properties in comparison with Bayesian optimization and conventional machine learning techniques. We will discuss the accuracy of the model and the efficiency in combining different agents in this design. This hybrid framework can lay the foundation for the automatic design of structural alloys which are manufactured by various techniques and are in extreme environments. |
Proceedings Inclusion? |
Planned: |
Keywords |
Additive Manufacturing, Machine Learning, Aluminum |