arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.03097physics.flu-dyncs.LG
收藏

机器学习湍流热流模型在气膜冷却中的推广应用

Generalization of machine-learned turbulent heat flux models applied to film cooling flows

Stanford University(斯坦福大学);Citrine Informatics(Citrine Informatics公司)

Pedro M. Milani, Julia Ling, John K. Eaton

摘要:

气膜冷却系统的设计在很大程度上依赖于雷诺平均纳维尔-斯托克斯(RANS)模拟,该模拟求解平均量并模拟所有湍流尺度。大多数湍流热流模型都是基于各向同性扩散和固定的湍流普朗特数($Pr_t$),不能准确地预测气膜冷却流动中的传热。在本工作中,使用各种数据集作为训练集来训练机器学习模型以预测非均匀$Pr_t$场。这些模型的能力,以概括超出他们被训练的流量进行了探讨。此外,可视化技术被用来比较不同的数据集,并帮助解释交叉验证结果。

英文摘要:

The design of film cooling systems relies heavily on Reynolds-Averaged Navier-Stokes (RANS) simulations, which solve for mean quantities and model all turbulent scales. Most turbulent heat flux models, which are based on isotropic diffusion with a fixed turbulent Prandtl number ($Pr_t$), fail to accurately predict heat transfer in film cooling flows. In the present work, machine learning models are trained to predict a non-uniform $Pr_t$ field, using various datasets as training sets. The ability of these models to generalize beyond the flows on which they were trained is explored. Furthermore, visualization techniques are employed to compare distinct datasets and to help explain the cross-validation results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑