About this Abstract |
Meeting |
TMS Specialty Congress 2024
|
Symposium
|
Symposium on Digital & Robotic Forming 2024
|
Presentation Title |
Predictive Modeling of Material Deformation Using English Wheel Under Varying Loading Conditions |
Author(s) |
Ahmad Mitoubsi, Sam St John , Vispi Karkaria , Derick Suarez, Jie Chen, Fan Chen, Wei Chen, Kornel Ehmann, Jian Cao, Nicholas Dewberry, Chandra Jaiswal , Kevin Benton Benton, Issa AlHmoud, Balakrishna Gokaraju, Anahita Khojandi |
On-Site Speaker (Planned) |
Ahmad Mitoubsi |
Abstract Scope |
The English wheel, a traditional metalworking tool, is used to shape intricate curves and contours in metal sheets. This has applications spanning vital industries like automotive and aerospace. Finite Element Method (FEM) simulations have traditionally been used to calculate end-state geometry. This approach is often time-consuming and resource-intensive. To revolutionize manufacturing simulation, we focus on developing surrogate models for digital twin technology. This innovation leverages the potential of Graph Neural Networks (GNNs) for modeling complex relationships among metal sheet regions, enhancing multi-point displacement prediction and diverse structure simulations. The viability of this approach has been assessed through a preliminary neural network proof of concept. The research intends to provide more efficient and resource-conscious simulations that will benefit precision manufacturing and metal shaping industries. Our longer-term vision of this research includes an additional phase to incorporate the GNN into Virtual Reality (VR) simulations to provide enhanced modeling and visualization. |
Proceedings Inclusion? |
Definite: Other |