arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1805.07472cs.CEcs.AI
收藏

非定常流动的深层动力学建模与控制

Deep Dynamical Modeling and Control of Unsteady Fluid Flows

Stanford University(斯坦福大学);Texas A&M University(德州农工大学)

Jeremy Morton, Freddie D. Witherden, Antony Jameson, Mykel J. Kochenderfer

摘要:

由于控制流体流动的方程的非线性性质,流量控制系统的设计仍然是一个挑战。然而,计算流体动力学(CFD)的最新进展已经能够高精度地模拟复杂的流体流动,从而打开了使用基于学习的方法来促进控制器设计的可能性。我们提出了一种直接从CFD数据学习圆柱体上气流的强迫和非强迫动力学的方法。所提出的方法,在Koopman理论的基础上,产生稳定的动力学模型,可以预测在扩展的时间范围内的气缸系统的时间演变。最后,通过执行模型预测控制与学习的动态模型,我们能够找到一个简单的,可解释的控制规律,抑制涡脱落后的气缸。

英文摘要:

The design of flow control systems remains a challenge due to the nonlinear nature of the equations that govern fluid flow. However, recent advances in computational fluid dynamics (CFD) have enabled the simulation of complex fluid flows with high accuracy, opening the possibility of using learning-based approaches to facilitate controller design. We present a method for learning the forced and unforced dynamics of airflow over a cylinder directly from CFD data. The proposed approach, grounded in Koopman theory, is shown to produce stable dynamical models that can predict the time evolution of the cylinder system over extended time horizons. Finally, by performing model predictive control with the learned dynamical models, we are able to find a straightforward, interpretable control law for suppressing vortex shedding in the wake of the cylinder.

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。

↑