| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
2024 Technical Division Student Poster Contest
|
| Presentation Title |
SPG-31: Data-Driven Optimization of Wire Arc Directed Energy Deposition Manufacturing Conditions for Improved Bead Shape Prediction |
| Author(s) |
Stephen Price, Danielle Cote, Kyle Tsaknopoulos, Rodica Neamtu |
| On-Site Speaker (Planned) |
Stephen Price |
| Abstract Scope |
Traditional manufacturing of large parts requires a costly process of developing, certifying, storing, and maintaining physical casts. Wire Arc Directed Energy Deposition (Wire Arc DED), which uses an electric arc to 3D print metal layers, offers a potential improvement to this process by replacing physical molds with digital CAD models and has a higher deposition rate, increased material utilization, and improved energy efficiency over traditional manufacturing techniques. As a new technology, it could benefit from an optimized parameter selection process, enabling quicker and more efficient manufacturing. We have implemented a data-driven machine learning approach to train models to predict a printed layer's bead shape (width and height) using Wire Arc DED. Specifically, through a novel design of experiment (DOE) approach, expansive data collection, feature engineering, and extensive evaluation of distinct model architectures, we have advanced the state-of-the-art performance and generalizability in predicting the bead shape of Wire Arc DED samples. |
| Proceedings Inclusion? |
Undecided |
| Keywords |
Machine Learning, Additive Manufacturing, Iron and Steel |