| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Frontiers of Materials Award Symposium: Physics-Informed Machine Learning for Modeling and Design of Materials and Manufacturing Processes
|
| Presentation Title |
Inverse Design for Crystal Plasticity Model Identification via Physics-informed Neural Networks |
| Author(s) |
Pinar Acar, Ender Eger, Arulmurugan Senthilnathan, Md Mahmudul Hasan, Mohamed Elleithy |
| On-Site Speaker (Planned) |
Pinar Acar |
| Abstract Scope |
This study develops a physics-informed machine learning (ML) model to identify the crystal plasticity (CP) parameters of Ti-7Al alloy, a candidate aerospace alloy for jet engine components. An inverse design problem is solved to obtain the optimum slip and twin parameters of the alloy by minimizing the difference between the experimental data and ML model predictions on the deformed texture. We find that the physics-informed ML model performs more efficiently than the data-driven (physics-uninformed) ML model by improving accuracy, computational efficiency, and explainability. Our approach builds a Physics-Informed Neural Network (PINN) incorporating the underlying problem physics through the loss function definition. In this application problem, the PINN is tested in a small-data problem driven by a CP model that needs to satisfy the physics-based constraints of the microstructural orientation space while obtaining the slip and twin parameters of Ti-7Al alloy. |
| Proceedings Inclusion? |
Planned: None Selected |