About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing Modeling, Simulation and Artificial Intelligence
|
| Presentation Title |
Crystal Plasticity–Informed Surrogate Modeling for Predictive Laser Powder Bed Fusion Simulation of Ti-6Al-4V |
| Author(s) |
Mohamed Elleithy, Pinar Acar |
| On-Site Speaker (Planned) |
Mohamed Elleithy |
| Abstract Scope |
This research develops a microstructure-informed surrogate modeling framework to enhance predictive simulations of Laser Powder Bed Fusion (LPBF) for Ti-6Al-4V. LPBF presents steep thermal gradients and rapid solidification, producing microstructural heterogeneity, anisotropic deformation, and residual stresses that current homogenized models fail to capture. High-fidelity Crystal Plasticity simulations using DAMASK will generate a training dataset spanning relevant LPBF temperatures at fully solid state, strain-rate tensors, and orientations. A machine learning surrogate model will learn voxel-level mappings from local inputs-temperature, strain-rate, and grain orientation-to outputs including elastic stiffness tensor, yield strength, and hardening behavior. Integrated into an LPBF simulation framework, this surrogate will dynamically assign spatially varying material properties of fabricated architected topologies. The resulting tool enhances prediction of residual stresses and failure risk, while enabling surrogate-driven digital twins for additive manufacturing. This framework bridges microstructural response and large-scale simulation, informing process optimization and qualification of performance-critical aerospace components. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Additive Manufacturing, ICME, Titanium |