About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
In Tribute to Robert Wagoner: A Pioneer in Metal Forming and Constitutive Modeling
|
| Presentation Title |
Hybrid Modeling for Aluminum Materials With Applications to Deep Drawing |
| Author(s) |
Oana Cazacu, Benoit Revil-Baudard |
| On-Site Speaker (Planned) |
Oana Cazacu |
| Abstract Scope |
While in recent years a great deal of efforts have been undertaken in order to substitute full-scale testing with virtual evaluation, the accuracy of the predictions for forming operations depend not only on the adequacy of the constitutive model but also on the quality of parametrization. Furthermore, high-fidelity simulations can be very expensive. Given that variability in mechanical properties even between batches of the same material produced by the same supplier are unavoidable, it is essential to predict how these variabilities will affect overall performance in service. In this talk, we present a new approach which relies on highly performant physics-based analytic anisotropic models and data-driven solutions to incorporate pre-existing knowledge and enhance processing time. Illustration of this approach is done for aluminum alloys subject to deep drawing. Results show the benefits in terms of better control of the component performance |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Aluminum, Machine Learning, Modeling and Simulation |