arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.03591physics.flu-dynphysics.comp-ph
收藏

槽道湍流各向异性雷诺应力张量的神经网络模型

Neural Network Models for the Anisotropic Reynolds Stress Tensor in Turbulent Channel Flow

Rui Fang, David Sondak, Pavlos Protopapas, Sauro Succi

摘要:

雷诺平均Navier-Stokes(RANS)方程是目前最流行的湍流模型之一。进行RANS模拟需要对各向异性雷诺应力张量进行额外的建模,但传统的雷诺应力闭合模型只能得到部分可靠的预测。近年来,基于数据驱动的雷诺各向异性张量湍流模型和新型机器学习技术得到了广泛的关注和快速发展。针对湍流槽道流的具体情况,本文提出了三个标准神经网络的修改,以考虑各向异性张量的无滑移边界条件,雷诺数依赖性和空间非局部性的雷诺应力封闭建模。修改后的模型,以提供更高的预测精度相比,标准的神经网络,当他们在不同的雷诺数通道流的训练和测试。结合边界条件和雷诺数注入的模型产生的最佳性能。该模型也优于张量基础神经网络(Ling等人,2016年)在湍流通道流数据集上。

英文摘要:

Reynolds-averaged Navier-Stokes (RANS) equations are presently one of the most popular models for simulating turbulence. Performing RANS simulation requires additional modeling for the anisotropic Reynolds stress tensor, but traditional Reynolds stress closure models lead to only partially reliable predictions. Recently, data-driven turbulence models for the Reynolds anisotropy tensor involving novel machine learning techniques have garnered considerable attention and have been rapidly developed. Focusing on modeling the Reynolds stress closure for the specific case of turbulent channel flow, this paper proposes three modifications to a standard neural network to account for the no-slip boundary condition of the anisotropy tensor, the Reynolds number dependence, and spatial non-locality. The modified models are shown to provide increased predicative accuracy compared to the standard neural network when they are trained and tested on channel flow at different Reynolds numbers. The best performance is yielded by the model combining the boundary condition enforcement and Reynolds number injection. This model also outperforms the Tensor Basis Neural Network (Ling et al., 2016) on the turbulent channel flow dataset.

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。

↑