用于耦合热流体场的注意力图神经网络的无标签有限体积残差训练
Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields
- Interdisciplinary Graduate Programme（交叉学科研究生项目）
- Nanyang Technological University（南洋理工大学）
- School of Future Technology（未来技术学院）
- Fuzhou University（福州大学）
- College of Computing and Data Science（计算与数据科学学院）
- Yunnan University（云南大学）
- School of Mechanical and Aerospace Engineering（机械与航空航天工程学院）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
研究针对耦合热流体场预测，提出通过最小化FVM残差训练注意力图神经网络的方法，无需标记数据。经四种情况评估，该方法在稳态基准上nRMSE达2.3-2.8%，在瞬态情况中准确性超监督基线且免数据生成成本，降低了模型开发成本。
中文摘要 AI 辅助
神经代理在科学机器学习中被广泛用于快速预测三维热流体场。然而，使用传统数值求解器生成训练数据通常会产生大量计算和存储成本。我们提出通过最小化控制方程的有限体积法（FVM）残差来训练注意力图神经网络。这些残差直接在网格上评估，无需标记数据。我们在四种情况下将训练后的代理与计算流体动力学（CFD）参考和数据监督基线进行评估。在两个稳态基准上，FVM损失模型实现了全场归一化均方根误差（nRMSE）为2.3-2.8%。在两个参数瞬态情况下，FVM损失模型在准确性方面优于监督基线，同时完全避免了数据生成成本。这些结果表明，FVM损失可以为神经代理提供实用的训练信号并降低模型开发成本。
英文摘要
Neural surrogates are widely used in scientific machine learning for fast prediction of three-dimensional (3D) thermo-fluid fields. However, generating training data using conventional numerical solvers often incurs substantial computational and storage costs. We propose to train an attention graph neural network by minimizing the finite-volume method (FVM) residuals of the governing equations. These residuals are evaluated directly on the mesh, requiring no labeled data. We evaluate the trained surrogates against computational fluid dynamics (CFD) references and a data-supervised baseline across four scenarios. On the two steady-state benchmarks, the FVM-loss model achieves an all-field normalized root-mean-square error (nRMSE) of 2.3-2.8%. It demonstrates close agreement with the CFD references, including the buoyancy-energy coupling. On the two parametric transient cases, the FVM-loss model outperforms the supervised baseline in terms of accuracy, while avoiding the data-generation cost entirely. These results indicate that the FVM loss can provide a practical training signal for neural surrogates and reduce the model development cost.
