摘要
机器学习在流体动力学中的应用日益普遍,尤其是针对偏微分方程的正反问题加速计算方面(如流场重建).然而,现有的端到端方法在训练过程中往往严重依赖于特定的低保真模式或特定稀疏率,而由于实际输入可能会偏离训练分布或包含未预见噪声,因此限制了传统方法在实际场景中的有效性.扩散模型提供了一种有前景的替代方案,相比通常局限于单一问题类型的直接映射方法,扩散模型通过学习将各种低保真分布转换为高保真分布,具有更大的灵活性.在本研究中,我们提出了物理信息残差扩散模型,该模型能够泛化处理多种输入,包括均匀下采样的传感器数据、带有高斯噪声的稀疏传感器数据以及随机采样的稀疏传感器数据.通过将偏微分方程约束纳入目标函数,我们的方法显著提高了重建高保真流场的准确性,同时确保遵循基本的物理定律.实验结果表明,我们的模型在无需重新训练的情况下,成功地在各种低保真输入条件下为二维Navier-Stokes方程和Kolmogorov湍流场景生成了高质量重建结果.
The application of machine learning in fluid dynamics has become increasingly prevalent for accelerating computa-tions in solving forward and inverse problems governed by partial differential equations,particularly flow field reconstruction.However,existing end-to-end methods often depend heavily on specific low-fidelity patterns or sparsity rates during training,lim-iting their effectiveness in real-world scenarios where inputs may deviate from the training distribution or contain unanticipated noise.Diffusion models present a promising alternative by learning to transform various low-fidelity distributions into high-fidelity ones,offering greater flexibility than direct mapping approaches that are typically constrained to single problem types.In this work,we introduce the physics-informed residual diffusion model,which generalizes across diverse inputs,including evenly down-sampled sensor data,sparse sensor data with Gaussian noise,and randomly sampled sparse sensor data.By incorporating partial differential equation constraints into the objective function,our approach significantly improves the accuracy of recon-structed high-fidelity flow fields while ensuring adherence to underlying physical laws.Experimental results demonstrate that our model successfully generates high-quality outcomes for two-dimensional Navier-Stokes equation flow and Kolmogorov flow under varied low-fidelity input conditions,without the need for retraining.