About this Abstract |
| Meeting |
TMS Specialty Congress 2025
|
| Symposium
|
Joint Sessions of AIM, ICME, & 3DMS
|
| Presentation Title |
Generalized Graph Foundation Models as Versatile Data-Driven Digital Twins for Complex Technological Systems |
| Author(s) |
Pawan Kumar Tripathi, Benjamin G. Pierce, Hein Htet Aung, Tommy Ciardi, Kristen Hernandez, Raymond J. Wieser, Yangxin Fan, Weiqi Yue, Erika I. Barcelos, Jayvic Cristian Jimenez, Brian Giera, Robert Gao, Mengjie Li, Kristopher Davis, Laura Bruckman, Roger French, Quynh D. Tran |
| On-Site Speaker (Planned) |
Quynh D. Tran |
| Abstract Scope |
Generalized graph foundation models offer a flexible approach to constructing data-driven digital twins (ddDTs) for complex technological systems. Unlike traditional, physics-based digital twins that require idealized models built from first principles, ddDTs leverage real-world data streams to provide adaptable and modular representations of system behavior. By using spatiotemporal graph neural networks (st-GNNs) as a foundation, ddDTs capture dynamic interactions and performance characteristics, allowing for accurate monitoring and prediction across a range of applications. This work introduces a unified pipeline to develop graph-based foundation models for diverse systems, including solar photovoltaic fleets, direct ink write additive manufacturing, and laser powder bed fusion. The proposed approach avoids the constraints of physics-based assumptions, enabling a single ddDT architecture to address various performance issues and operational questions without extensive reconfiguration. These foundation models streamline digital twin implementation, supporting efficient, data-driven decision-making in technologically complex environments. |
| Proceedings Inclusion? |
Definite: Post-meeting proceedings |