用扩散模型快速预测氮化铝原子级裂纹扩展，无需应力数据
Diffusion-based Generative Machine Learning Model for Predicting Crack Propagation in Aluminum Nitride at the Atomic Scale
- 基于初始微观结构嵌入生成裂纹演化过程
- 速度提升显著，准确预测裂纹萌生、分叉和原子桥接
- 物理保真度高，可推广至未见多裂纹场景
预测氮化铝（AlN）中原子尺度裂纹扩展对半导体可靠性至关重要，但分子动力学（MD）模拟成本过高。我们开发了一种基于扩散的生成式机器学习模型，仅通过初始微观结构嵌入即可预测AlN中的原子级裂纹扩展，该模型在单裂纹系统MD数据上训练。模型实现显著加速，准确预测裂纹萌生、分支及原子尺度桥接等动态断裂过程。关键在于其内在物理保真度，能复现材料固有机制而忽略周期性边界效应，并泛化至未见的多裂纹配置。与MD基准验证表明，该模型无需额外应力或能量数据即可捕捉复杂断裂物理，实现裂纹主导失效的快速探索，助力半导体可靠性优化。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。