发表机构
National University of Defense Technology; Nanjing Agricultural University; National Key Laboratory of Parallel and Distributed Computing; National SuperComputer Center in Tianjin（国防科技大学; 南京农业大学; 并行与分布式计算国家重点实验室; 国家超级计算天津中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出TM4FF框架，结合残差小波Mamba、Transformer注意力与物理信息损失，在四个CFD数据集上实现高精度与稳健泛化。
AI 中文摘要
虽然深度学习加速了计算流体力学（CFD）中昂贵的偏微分方程求解，但现有方法如PINNs和FNOs通常在泛化能力、噪声鲁棒性和物理一致性方面存在不足。我们提出了流场Transformer-Mamba（TM4FF）框架，这是一种物理约束的算子学习模型，具有三项关键创新：用于特征去噪的残差小波Mamba（RWM）层、用于增强特征融合的基于Transformer的注意力机制，以及使用傅里叶导数强制执行Navier-Stokes方程的物理信息损失。在四个CFD数据集上的实验表明，TM4FF在不同流动条件下实现了高精度和稳健的泛化能力。
英文摘要
While deep learning accelerates expensive partial differential equation solving in computational fluid dynamics (CFD), existing methods like PINNs and FNOs often struggle with generalization, noise robustness, and physical consistency. We introduce the Transformer-Mamba for Flow Field (TM4FF) framework, a physics-constrained operator learning model with three key innovations: a Residual Wavelet Mamba (RWM) layer for feature denoising, a Transformer-based attention mechanism for enhanced feature fusion, and a physics-informed loss using Fourier derivatives to enforce the Navier-Stokes equations. Experiments on four CFD datasets show TM4FF achieves high accuracy and robust generalization across varying flow conditions.
CommentsCorrected manual data-entry errors (row/column misalignment and misplaced decimal points) in the baseline entries in Table 1. The results of the proposed method and the conclusions remain unchanged
DOI：10.1109/ICASSP55912.2026.11460626
