期刊
ACTA MECHANICA SINICA
卷 37, 期 12, 页码 1786-1798出版社
SPRINGER HEIDELBERG
DOI: 10.1007/s10409-021-01149-0
关键词
Bayesian optimization; Flow control; Drag reduction; Turbulence
资金
- MathWorks Faculty Research Innovation Fellowship at MIT
- French National Research Agency (ANR) via the grant FlowCon [ANR-17-ASTR0022]
- LIMSI/CNRS
- Paris-Sud University
- National Science Foundation of China (NSFC) [12172109, 11632006, 91752109, 91952204]
This study utilizes Bayesian optimization to design open-loop controllers for fluid flows, achieving good performance in both computational and experimental settings. The research demonstrates that Bayesian optimization can identify optimal controllers at a fraction of the cost of other optimization strategies considered in previous studies. Additionally, Bayesian optimization provides a surrogate model for the latent cost function, assisting in painting a complete picture of the control landscape.
A key question in flow control is that of the design of optimal controllers when the control space is high-dimensional and the experimental or computational budget is limited. We address this formidable challenge using a particular flavor of machine learning and present the first application of Bayesian optimization to the design of open-loop controllers for fluid flows. We consider a range of acquisition functions, including the recently introduced output-informed criteria of Blanchard and Sapsis (2021), and evaluate performance of the Bayesian algorithm in two iconic configurations for active flow control: computationally, with drag reduction in the fluidic pinball; and experimentally, with mixing enhancement in a turbulent jet. For these flows, we find that Bayesian optimization identifies optimal controllers at a fraction of the cost of other optimization strategies considered in previous studies. Bayesian optimization also provides, as a by-product of the optimization, a surrogate model for the latent cost function, which can be leveraged to paint a complete picture of the control landscape. The proposed methodology can be used to design open-loop controllers for virtually any complex flow and, therefore, has significant implications for active flow control at an industrial scale.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据