发表机构
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究开发几何原生的机器学习方法，结合MambaIR网络重建DSMC矩场，在腔体和高超声速圆柱测试中显著降低热通量误差，提升了稀薄气体动力学的矩估计精度。
AI 中文摘要
直接模拟蒙特卡洛（DSMC）无需本构封闭即可求解稀薄气体动力学，但宏观矩的有限样本估计收敛速率差异显著。我们开发了一种非侵入式、几何原生的机器学习方法，用于重建保留的二维矩层级：数密度、两个速度分量、平移温度、三个压力张量分量以及两个热通量分量。基于三个采样块，该估计器利用从开发数据中学到的结构化先验，结合从当前观测计算得到的有界项进行校正，同时保持加性矩一致性和测得的零频内容。在腔体开发测试中，其先验为训练好的MambaIR复原网络的最终观测条件估计器，在两个稀薄条件下，将横向热通量误差降至十块直接平均法的0.658倍和0.672倍。对于高超声速圆柱，以圆柱为中心的估计器在评估前已固定，用于六组新观测/参考对的测试；其在每组中均提升了全局横向热通量和近壁法向热通量，算术平均归一化均方根误差（NRMSE）的比值为0.846和0.793，经Holm调整的单侧精确概率为0.03125。
英文摘要
Direct simulation Monte Carlo (DSMC) resolves rarefied-gas dynamics without a constitutive closure, but finite-sample estimates of macroscopic moments converge at markedly different rates. We develop a non-intrusive, geometry-native machine learning reconstruction of the retained two-dimensional moment hierarchy: number density, two velocity components, translational temperature, three pressure-tensor components, and two heat-flux components. From three sampling blocks, the estimator corrects a structured prior learned from development data with a bounded term computed from the current observation, while preserving additive-moment consistency and the measured zero-frequency content. In cavity development tests, the final observation-conditioned estimator, whose prior is a trained MambaIR restoration network, reduces transverse-heat-flux error to 0.658 and 0.672 times that of a ten-block direct average at two rarefied conditions. For a hypersonic cylinder, a cylinder-centred estimator is fixed before evaluation on six new observation/reference pairs. It improves both global transverse heat flux and near-wall normal heat flux in every pair; the ratios of arithmetic-mean normalised root-mean-square errors (NRMSEs) are 0.846 and 0.793, and the Holm-adjusted one-sided exact probabilities are 0.03125.
