Prediction of Reynolds stresses in high-Mach-number turbulent boundary layers using physics-informed machine learning
Prediction of Reynolds stresses in high-Mach-number turbulent boundary layers using physics-informed machine learning
复制标题
DOI：
10.1007/s00162-018-0480-2
复制
发表时间：
2018-08
影响因子：
3.4
通讯作者：
Jian-Xun Wang;Junji Huang;L. Duan;Heng Xiao
中科院分区：
文献类型：
--
作者：
Jian-Xun Wang;Junji Huang;L. Duan;Heng Xiao
建模雷诺应力是雷诺平均纳维斯托克斯 (RANS) 模拟中模型形式不确定性的主要来源。最近，提出了一种基于物理的机器学习 (PIML) 方法来重建 RANS 建模的雷诺应力中的差异。 PIML 框架的优点已经在几个规范的不可压缩流中得到了证明。然而，其在高马赫数流上的性能仍不清楚。在这项工作中，我们使用 PIML 方法通过现有的 DNS 数据库来预测高马赫数平板湍流边界层中 RANS 建模的雷诺应力的差异。具体来说，首先使用 DNS 训练流构建差异函数，然后用于在与 DNS 不同的流条件下校正 RANS 预测的雷诺应力。机器学习技术被证明可以显着改善 RANS 模型的湍流法向应力、湍流动能和雷诺应力各向异性。当使用不同的训练数据集时，可以持续观察到改进。此外，使用高维可视化技术和距离度量来提供仅基于 RANS 模拟的预测置信度的先验评估。这项研究表明，PIML 方法是一种计算上负担得起的技术，可在缺乏实验和高保真模拟的情况下提高高马赫数湍流的 RANS 建模雷诺应力的准确性。
Modeled Reynolds stress is a major source of model-form uncertainties in Reynolds-averaged Navier–Stokes (RANS) simulations. Recently, a physics-informed machine learning (PIML) approach has been proposed for reconstructing the discrepancies in RANS-modeled Reynolds stresses. The merits of the PIML framework have been demonstrated in several canonical incompressible flows. However, its performance on high-Mach-number flows is still not clear. In this work, we use the PIML approach to predict the discrepancies in RANS-modeled Reynolds stresses in high-Mach-number flat-plate turbulent boundary layers by using an existing DNS database. Specifically, the discrepancy function is first constructed using a DNS training flow and then used to correct RANS-predicted Reynolds stresses under flow conditions different from the DNS. The machine learning technique is shown to significantly improve RANS-modeled turbulent normal stresses, the turbulent kinetic energy, and the Reynolds stress anisotropy. Improvements are consistently observed when different training datasets are used. Moreover, a high-dimensional visualization technique and a distance metrics are used to provide a priori assessment of prediction confidence based only on RANS simulations. This study demonstrates that the PIML approach is a computationally affordable technique for improving the accuracy of RANS-modeled Reynolds stresses for high-Mach-number turbulent flows when there is a lack of experiments and high-fidelity simulations.