[论文解读] Fusion-DeepONet: A Data-Efficient Neural Operator for Geometry-Dependent Hypersonic and Supersonic Flows
本文提出 Fusion DeepONet,一种数据高效的神经算子,能够在均匀网格和不规则网格上学习几何相关的高超音速流场,在不规则网格上以更少的参数优于某些基线。
Shape optimization is essential in aerospace vehicle design, including reentry systems, and propulsion system components, as it directly influences aerodynamic efficiency, structural integrity, and overall mission success. Rapid and accurate prediction of external and internal flows accelerates design iterations. To this end, we develop a new variant of DeepONet, called Fusion-DeepONet as a fast surrogate model for geometry-dependent hypersonic and supersonic flow fields. We evaluated Fusion-DeepONet in learning two external hypersonic flows and a supersonic shape-dependent internal flow problem. First, we compare the performance of Fusion-DeepONet with state-of-the-art neural operators to learn inviscid hypersonic flow around semi-elliptic blunt bodies for two grid types: uniform Cartesian and irregular grids. Fusion-DeepONet provides comparable accuracy to parameter-conditioned U-Net on uniform grids while outperforming MeshGraphNet and Vanilla-DeepONet on irregular grids. Fusion-DeepONet requires significantly fewer trainable parameters than U-Net, MeshGraphNet, and FNO. For the second hypersonic problem, we set up Fusion-DeepONet to map from geometry and free stream Mach number to the temperature field around a reentry capsule traveling at hypersonic speed. This fast surrogate is then improved to predict the spatial derivative of the temperature, resulting in an accurate prediction of heat flux at the surfaces of the capsule. To enhance the accuracy of spatial derivative prediction, we introduce a derivative-enhanced loss term with the least computation overhead. For the third problem, we show that Fusion-DeepONet outperforms MeshGraphNet in learning geometry-dependent supersonic flow in a converging-diverging nozzle configuration. For all the problems, we used high-fidelity simulations with a high-order entropy-stable DGSEM solver to generate training datasets with limited samples.
研究动机与目标
- 推动快速、几何相关的高超音速流代理建模,以加速设计与几何形状的变形。
- 开发并比较用于在高保真数据稀缺的情况下学习椭圆形体周围流场的神经算子模型。
- 提出 Fusion DeepONet,以更少的参数在不规则网格上实现几何感知的预测。
- 分析几何条件化和多尺度融合如何提升对未知几何的泛化能力。
提出的方法
- 比较 DeepONet、POD-DeepONet、带参数条件的 U-Net、Fourier Neural Operator (FNO) 和 MeshGraphNet 在几何相关的高超音速流预测中的表现。
- 开发 Fusion DeepONet,通过将分支(几何)和主干(空间)网络与多层条件化整合,在多尺度上对神经场进行条件化。
- 使用稀少数据,在 36 个半椭圆形体的高保真 Euler 模拟上进行训练,采用具熵稳定性的 DGSEM 求解器。
- 在均匀笛卡尔网格和不规则非结构网格上进行评估,以测试离散化不变性和泛化能力。
- 使用 Rowdy 激活函数和自适应条件化来改善不连续处理和跨模态的信息流。
实验结果
研究问题
- RQ1在高保真数据有限的情况下,基于算子代理的模型是否能够学习几何相关的高超音速流场?
- RQ2不同的算子体系结构(原生 DeepONet、POD-DeepONet、U-Net、FNO、MeshGraphNet)在规则网格与不规则网格上的高超音速流预测性能如何?
- RQ3Fusion DeepONet 的多尺度条件化是否提升对未见几何和不规则网格的泛化能力?
- RQ4几何参数化和网格类型对预测精度与参数效率的影响如何?
- RQ5基函数分析(通过 SVD)如何揭示 Fusion DeepONet 的信息流?
主要发现
- Fusion DeepONet 在均匀网格上达到与带参数条件的 U-Net 相当的精度,但可训练参数显著更少。
- 在不规则、任意网格上,Fusion DeepONet 在预测高超音速流场方面优于 MeshGraphNet 和原生 DeepONet。
- 原生 DeepONet 与 MeshGraphNet 在不规则网格上表现吃力,突出了一些算子模型对离散化的敏感性。
- Fusion DeepONet 使用的参数显著少于 U-Net、MeshGraphNet 和 FNO,体现计算效率。
- SVD 分析表明 Fusion DeepONet 的主干-分支融合实现了更丰富的多尺度信息提取,并更好地泛化到未见解的解。
更好的研究,从现在开始
从论文设计到论文写作,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。