研究人员开发了一种多尺度特征增强图神经网络（ME-GNN），旨在提高复杂几何体中流体动力学预测的效率。这种新颖的方法在图神经网络中集成了两步消息传递机制，用于捕获详细的局部特征，并结合注意力U-Net提取精细和粗略特征。ME-GNN还采用K-hop采样，在保留关键局部细节的同时，实现对大型数据集的高效训练。该模型在基准数据集上展示了最先进的性能，在速度场、表面压力和流场方面实现了低误差率。 AI
影响 该模型有望显著降低工程领域流体动力学仿真的计算成本，加速设计和分析。
排序理由 该集群包含一篇详细介绍新型机器学习模型及其在基准数据集上评估的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2603.08465v3 Announce Type: replace Abstract: While Physics-Informed Neural Networks (PINNs) offer a mesh-free approach to solving fluid-flow PDEs, standard point-wise residual minimization suffers from convergence pathologies in topologically complex domains like Triply Pe…
arXiv:2607.11672v1 Announce Type: new Abstract: Industrial design in fields such as vehicle and aerospace engineering often relies on large-scale numerical simulations to evaluate fluid dynamics performance, which can incur substantial computational costs. Deep neural networks ha…
Industrial design in fields such as vehicle and aerospace engineering often relies on large-scale numerical simulations to evaluate fluid dynamics performance, which can incur substantial computational costs. Deep neural networks have shown promise in improving simulation efficie…