使用嵌入OpenFOAM的深度学习框架降低粗网格CFD模拟中的空间离散误差
Reducing Spatial Discretization Error on Coarse CFD Simulations Using an OpenFOAM-Embedded Deep Learning Framework
AI总结:
提出一种嵌入OpenFOAM的端到端可微深度学习框架,用神经网络替代对流项差分格式,在方柱绕流问题上将粗网格CFD模拟速度误差从120%降至25%。
摘要:
我们提出了一种通过使用深度学习提升低分辨率模拟质量来降低粗网格计算流体力学(CFD)问题空间离散误差的方法。我们将精细网格数据投影到粗网格离散化后输入模型。我们用一个前馈神经网络替代对流项的默认差分格式,该网络将速度从单元中心插值到面值,以产生能很好近似下采样精细网格数据的速度。该深度学习框架结合了开源CFD代码OpenFOAM,形成了一个端到端的可微模型。我们使用离散伴随代码版本对CFD物理进行自动微分。我们提出了一种TensorFlow(Python)和OpenFOAM(c++)之间的快速通信方法,加速了训练过程。我们将该模型应用于方柱绕流问题,与传统求解器使用x8粗网格相比,在训练分布内的模拟中,速度误差从120%降至25%。对于训练分布外的模拟,速度误差降低约50%。由于该架构利用了物理的局部特征,训练在时间和数据样本方面是可负担的。
英文摘要:
We propose a method for reducing the spatial discretization error of coarse computational fluid dynamics (CFD) problems by enhancing the quality of low-resolution simulations using deep learning. We feed the model with fine-grid data after projecting it to the coarse-grid discretization. We substitute the default differencing scheme for the convection term by a feed-forward neural network that interpolates velocities from cell centers to face values to produce velocities that approximate the down-sampled fine-grid data well. The deep learning framework incorporates the open-source CFD code OpenFOAM, resulting in an end-to-end differentiable model. We automatically differentiate the CFD physics using a discrete adjoint code version. We present a fast communication method between TensorFlow (Python) and OpenFOAM (c++) that accelerates the training process. We applied the model to the flow past a square cylinder problem, reducing the error from 120% to 25% in the velocity for simulations inside the training distribution compared to the traditional solver using an x8 coarser mesh. For simulations outside the training distribution, the error reduction in the velocities was about 50%. The training is affordable in terms of time and data samples since the architecture exploits the local features of the physics.
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。