VP-DDBM 代理模型加速 Al-Cu 相场凝固模拟，速度提升约 73 倍
Surrogate Models for Stochastic Al-Cu Phase-Field Solidification
材料模拟圈的朋友可以看看，扩散桥模型把 Al-Cu 凝固相场模拟提速约 73 倍，还不会像 U-Net 那样把枝晶抹平。
研究提出方差保持去噪扩散桥模型 VP-DDBM，用于二维 Al-Cu 合金快速凝固的相场模拟。模型根据当前相场、浓度和温度场预测下一时刻状态，并可自回归 rollout。在两个留出温度梯度上，VP-DDBM 的长程误差低于确定性 U-Net 和 SI-ConvNeXt 基线，覆盖域平均相场、域平均 Cu 浓度和枝晶尖端位置三项指标。确定性 U-Net 在长 rollout 中会逐渐抹平枝晶形貌，而 VP-DDBM 能保留细枝晶结构。预测速度比相场求解器快约 73 倍，可用于工艺条件筛选和系综微结构研究。
Surrogate Models for Stochastic Al-Cu Phase-Field Solidification
Phase-field models resolve microstructural evolution during rapid alloy solidification, but their computational cost limits long trajectories, stochastic ensembles, and studies across process conditions. We present a variance-preserving denoising diffusion bridge model (VP-DDBM) for state-conditioned prediction of two-dimensional Al-Cu solidification. Given the current phase, concentration, and prescribed temperature fields, the model predicts the subsequent state and is applied autoregressively. Across two held-out thermal gradients, VP-DDBM produces lower long-horizon errors than deterministic U-Net and SI-ConvNeXt baselines in domain-mean phase, domain-mean Cu concentration, and leading-tip position. It also retains fine dendritic structure over long rollouts, whereas the deterministic U-Net progressively smooths the morphology. VP-DDBM predicts the phase and concentration evolution approximately $73\times$ faster than the phase-field solver, showing potential for faster process-condition screening and ensemble-based microstructure studies.