Applying Bayesian optimization with Gaussian process regression to computational fluid dynamics problems

Applying Bayesian optimization with Gaussian process regression to computational fluid dynamics problems
复制标题

将贝叶斯优化与高斯过程回归应用于计算流体动力学问题

DOI:
10.1016/j.jcp.2021.110788
复制
发表时间:
2022
影响因子:
4.1
通讯作者:
and P. Schlatter
and P. Schlatter
中科院分区:
物理与天体物理2区
文献类型:
--
作者:
Y. Morita;S. Rezaeiravesh;N. Tabatabaei;R. Vinuesa;K. Fukagata;and P. Schlatter

文献摘要

参考文献

被引文献

相似文献

将基于高斯过程回归(GPR)的贝叶斯优化(BO)应用于不同的CFD(计算流体力学)问题,具有实际意义。这些问题包括:1)盖子驱动腔体的形状优化,以最小化或最大化能量耗散;2)通道流动壁面的形状优化,以获得在另一壁面形成的湍流边界层边缘的理想压力梯度分布;3)扰流冰模型的控制参数优化,以获得实际表面冰的翼型气动特性。优化问题的多样性、优化方法与任何伴随信息的独立性、在优化循环中使用不同CFD求解器的便利性,以及更重要的是,所需的流动模拟数量相对较少,显示了BO-GPR方法在CFD应用中的灵活性、效率和通用性。计算结果表明,为了保证最大尺寸为8的设计参数的全局最优,CFD求解的执行次数少于90次。此外,观察到流动模拟的次数并不随设计参数的增加而显著增加。这些模拟的相关计算成本对于许多具有实际意义的优化案例来说是可以承受的。
Bayesian optimization (BO) based on Gaussian process regression (GPR) is applied to different CFD (computational fluid dynamics) problems which can be of practical relevance. The problems are i) shape optimization in a lid-driven cavity to minimize or maximize the energy dissipation, ii) shape optimization of the wall of a channel flow in order to obtain a desired pressure-gradient distribution along the edge of the turbulent boundary layer formed on the other wall, and finally, iii) optimization of the controlling parameters of a spoiler-ice model to attain the aerodynamic characteristics of the airfoil with an actual surface ice. The diversity of the optimization problems, independence of the optimization approach from any adjoint information, the ease of employing different CFD solvers in the optimization loop, and more importantly, the relatively small number of the required flow simulations reveal the flexibility, efficiency, and versatility of the BO-GPR approach in CFD applications. It is shown that to ensure finding the global optimum of the design parameters of the size up to 8, less than 90 executions of the CFD solvers are needed. Furthermore, it is observed that the number of flow simulations does not significantly increase with the number of design parameters. The associated computational cost of these simulations can be affordable for many optimization cases with practical relevance.
DOI: 10.2514/1.j053340
发表时间: 2014
期刊: AIAA Journal
影响因子: 2.5
作者:
L. Gicquel
通讯作者: L. Gicquel
基于噪声评估的全局优化:两种统计方法的实证研究
DOI: 10.1088/1742-6596/135/1/012100
发表时间: 2008
期刊: Journal of Physics: Conference Series
影响因子: --
作者:
E. Vázquez;Julien Villemonteix;Maryan Sidorkiewicz;E. Walter
通讯作者: E. Walter
流量控制问题的数值解:动态边界作用降低涡度
DOI: 10.1137/s1064827595294678
发表时间: 1998
影响因子: 3.1
作者:
M. Berggren
通讯作者: M. Berggren
DOI: 10.2514/6.2001-90
发表时间: 2001
期刊:
影响因子: --
作者:
M. Papadakis;Hsiung;R. Chandrasekharan;M. Hinson;T. Ratvasky;J. Giriunas
通讯作者: J. Giriunas
DOI: 10.1063/1.168744
发表时间: 1998-11-01
期刊: COMPUTERS IN PHYSICS
影响因子: --
作者:
Weller, HG;Tabor, G;Fureby, C
通讯作者: Fureby, C