Grain-level micromechanical modeling and assessment of fatigue-critical pores using graph neural networks
Luca Loiodice, Krzysztof S Stopka, Yixuan Sun, Guang Lin, Michael D Sangid · 2026
Read Grain-level micromechanical modeling and assessment of fatigue-critical pores using graph neural networks by Luca Loiodice, Krzysztof S Stopka, Yixuan Sun, Guang Lin, Michael D Sangid (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13477975.txt.
Description
Luca Loiodice and four colleagues built in 2026 a fast graph-network tool to judge which pores threaten fatigue life in 3D-printed nickel alloy parts. Full crystal plasticity simulation captures grain-level fatigue but takes months, so they trained surrogate models on such data to predict grain stresses and damage energy.
The models predicted grain-average and grain-maximum stress and accumulated plastic strain energy, a damage marker tied to crack starts, though accuracy fell for extreme plastic cases. Predicted peak damage energy flagged whether fatigue hotspots sat beside pores. The tool enables rapid screening of fatigue-critical pores in printed components.
Catalog record
| CREATOR | Luca Loiodice, Krzysztof S Stopka, Yixuan Sun, Guang Lin, Michael D Sangid |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |