About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Forming and Joining of Advanced Sheet Metal Materials
|
| Presentation Title |
Physics-based AI-assisted Design and Control of Metal Forming Processes |
| Author(s) |
Jian Cao, Fanglei Hu, Putong Kang, Itzel Salgado, Deepak Sharma, Derick Andres Suarez, Brett Baxter Wadman, Wei Chen, Ping Guo |
| On-Site Speaker (Planned) |
Jian Cao |
| Abstract Scope |
We aim to advance the capability to co-design materials and manufacturing processes by integrating hybrid approaches that combine physics-based modeling with data-driven techniques. In this talk, I will demonstrate our work in developing differentiable simulation tools, advanced sensing strategies, and intelligent process control systems. These tools allow us to effectively predict and control metal forming processes, particularly flexible metal forming processes as demonstrated in our digital twin effort through the NSF Engineering Research Center HAMMER. Furthermore, I will demonstrate how we use machine learning to accelerate the physics-based simulations. Our solutions particularly target three notoriously challenging aspects of the process: long history-dependent properties, complex geometric features, and the high dimensionality of their design space. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, Shaping and Forming, Other |