Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.13445 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915861677211648 |
|---|---|
| author | Lu, Jiali Yang, Shengfeng |
| author_facet | Lu, Jiali Yang, Shengfeng |
| contents | Predicting atomic-scale crack propagation in aluminum nitride (AlN) is critical for semiconductor reliability but remains prohibitively expensive via molecular dynamics (MD). We develop a diffusion-based generative machine learning model to predict atomic-scale crack propagation in AlN, a critical semiconductor material, by conditioning solely on initial microstructure embeddings. Trained on MD simulations of single-crack systems, the model achieves a significant speedup while accurately forecasting dynamic fracture processes, including stress-driven crack initiation, crack branching, and atomic-scale bridging ligaments. Crucially, it demonstrates inherent physical fidelity by reproducing material-intrinsic mechanisms while disregarding periodic boundary artifacts, and generalizes to unseen multi-crack configurations. Validation against MD ground truth confirms the capability of the model to capture complex fracture physics without auxiliary stress or energy data, enabling rapid exploration of crack-mediated failure for semiconductor reliability optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13445 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Diffusion-based Generative Machine Learning Model for Predicting Crack Propagation in Aluminum Nitride at the Atomic Scale Lu, Jiali Yang, Shengfeng Materials Science Machine Learning Predicting atomic-scale crack propagation in aluminum nitride (AlN) is critical for semiconductor reliability but remains prohibitively expensive via molecular dynamics (MD). We develop a diffusion-based generative machine learning model to predict atomic-scale crack propagation in AlN, a critical semiconductor material, by conditioning solely on initial microstructure embeddings. Trained on MD simulations of single-crack systems, the model achieves a significant speedup while accurately forecasting dynamic fracture processes, including stress-driven crack initiation, crack branching, and atomic-scale bridging ligaments. Crucially, it demonstrates inherent physical fidelity by reproducing material-intrinsic mechanisms while disregarding periodic boundary artifacts, and generalizes to unseen multi-crack configurations. Validation against MD ground truth confirms the capability of the model to capture complex fracture physics without auxiliary stress or energy data, enabling rapid exploration of crack-mediated failure for semiconductor reliability optimization. |
| title | Diffusion-based Generative Machine Learning Model for Predicting Crack Propagation in Aluminum Nitride at the Atomic Scale |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2603.13445 |