| About this Abstract |
| Meeting |
TMS Specialty Congress 2025
|
| Symposium
|
3rd World Congress on Artificial Intelligence in Materials & Manufacturing (AIM 2025)
|
| Presentation Title |
An Interleaved Physics-Based Deep-Learning Framework as a New Cycle Jumping Approach for Microstructurally Small Fatigue Crack Growth Simulations |
| Author(s) |
Vignesh Babu Rao, Ashley D. Spear |
| On-Site Speaker (Planned) |
Ashley D. Spear |
| Abstract Scope |
Predicting the growth of microstructurally small fatigue cracks (MSCs) is essential for developing next-generation fatigue-resistant materials and for realizing digital twins. While MSC simulation frameworks involving crystal plasticity can resolve material deformation and micromechanical fields at the MSC scale, running such simulations over realistic cycle counts remains computationally intractable. This work introduces an interleaved physics-based deep-learning (PBDL) framework that combines rapid predictive capabilities of deep-learning models with the accuracy of physics-based models. Uncertainty quantification (UQ) plays a key role in determining when to update the state of the physics-based model using the deep-learning predictions, prior to resuming deep-learning predictions using the updated physics-based model as input. The PBDL framework enables simulation of MSC growth over a realistic number of cycle counts while reining in model error and uncertainty propagation associated with sequential deep-learning predictions. The work represents a significant advancement in fatigue modeling and offers a template for other applications. |
| Proceedings Inclusion? |
Undecided |