李彩云, 安慰, 刘学军, 等. 基于机器学习的非定常流场网格自适应[J]. 空气动力学学报, 2023, 41(6): 89−101. doi: 10.7638/kqdlxxb-2022.0034
引用本文: 李彩云, 安慰, 刘学军, 等. 基于机器学习的非定常流场网格自适应[J]. 空气动力学学报, 2023, 41(6): 89−101. doi: 10.7638/kqdlxxb-2022.0034
LI C Y, AN W, LIU X J, et al. Mesh adaptation for unsteady flow field based on machine learning[J]. Acta Aerodynamica Sinica, 2023, 41(6): 89−101. doi: 10.7638/kqdlxxb-2022.0034
Citation: LI C Y, AN W, LIU X J, et al. Mesh adaptation for unsteady flow field based on machine learning[J]. Acta Aerodynamica Sinica, 2023, 41(6): 89−101. doi: 10.7638/kqdlxxb-2022.0034

基于机器学习的非定常流场网格自适应

Mesh adaptation for unsteady flow field based on machine learning

  • 摘要: 现有针对非定常流场数值模拟的网格自适应方法,通常每隔一段时间步就进行一次网格调整,增加了计算复杂度和精度损失。针对这一问题,本文基于间断伽辽金(discontinuity Galerkin, DG)有限元法提出了结合BPNN(backpropagation neural network)和MMPDE(moving mesh partial differential equation)的非定常流场网格自适应方法。该方法首先采用DG有限元法对Navier-Stokes方程进行非定常计算,得到统计意义上的网格间断量;然后以初始网格和间断量训练BPNN回归模型,用于预测任意位置节点的间断量;接着使用MMPDE变分法移动网格节点,使其符合统计意义的间断量分布;最终通过Laplacian网格平滑法保证网格单元质量。圆柱绕流非定常流场算例的验证结果表明,该方法能够在不改变网格拓扑结构和不增加节点数的情况下完成一次性网格自适应,显著提高了非定常流场数值计算的精度和效率。

     

    Abstract: Existing grid adaptation methods for numerical simulation of unsteady flow fields usually perform grid adjustment every time step, which increases the computational complexity and the possibility of accuracy loss. In view of this, based on the DG finite element method, an MMPDE mesh adaptation method combined with BPNN is proposed for intelligent mesh optimization of unsteady flow fields. The method first uses the DG finite element method to solve the unsteady N-S equation and obtain the statistical grid discontinuity. Using the initial grid and grid discontinuity to train the BPNN regression model, the discontinuity value of any node at any position can be predicted. The variational method, MMPDE, is selected to move grid nodes to conform to the distribution of discontinuities. Finally, the Laplacian grid smoothing method improves the grid quality. The feasibility of the method is verified by cases of unsteady flow fields around cylinders. The calculation results show that the method can complete the one-time adaptive adjustment of the grid without changing the grid topology and the number of nodes, which can significantly improve the accuracy and efficiency of numerical simulations for unsteady flow fields.

     

/

返回文章
返回