About this Abstract |
Meeting |
2025 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2025)
|
Symposium
|
2025 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2025)
|
Presentation Title |
Large Language Model enabled Process Map Discovery Within Additive Manufacturing. |
Author(s) |
Peter Myung-Won Pak, Amir Barati Farimani |
On-Site Speaker (Planned) |
Peter Myung-Won Pak |
Abstract Scope |
We investigate the potential of Large Language Models (LLMs) to predict defect regimes in additive manufacturing processes based on sets of input process parameters. To this end, we fine-tune a collection of models using a curated dataset that maps process parameters to common defect types, including Keyholing, Lack of Fusion, and Balling. Furthermore, incorporating natural language inputs offers a streamlined pathway for users to interact with process parameters, supporting easier optimization of build settings for desired manufacturing outcomes. |
Proceedings Inclusion? |
Planned: Post-meeting proceedings |