☆ 4.7 Article

Machine-learning flow control with few sensor feedback and measurement noise

PHYSICS OF FLUIDS (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Mechanics

Comparative analysis of machine learning methods for active flow control

Fabio Pino et al.

Summary: This work presents a comparative analysis of machine learning frameworks such as genetic programming and reinforcement learning in flow control. The algorithms are benchmarked against global optimization techniques and tested on three test cases. The results show differences in exploration versus exploitation and the balance between model capacity and required complexity. The comparison paves the way for hybridization of methods and offers perspectives on future development in flow control problems.

JOURNAL OF FLUID MECHANICS (2023)

添加到收藏夹

Article Mechanics

Unsupervised modelling of a transitional boundary layer

F. Foroozan et al.

Summary: A data-driven method is proposed for identifying local turbulent flow states and their dynamics using the -medoids clustering algorithm and multidimensional scaling (MDS) technique. This approach reduces computational cost and effectively describes the dynamics of state transitions through transition probability matrix and transition trajectory graph.

JOURNAL OF FLUID MECHANICS (2021)

添加到收藏夹

Article Mechanics

Explorative gradient method for active drag reduction of the fluidic pinball and slanted Ahmed body

Yiqing Li et al.

Summary: The explorative gradient method (EGM) addresses the challenge of optimizing multiple actuation parameters by alternately performing exploitative and explorative steps, ensuring convergence rate of a gradient based method and exploration of better minima. EGM outperforms other optimization methods in analytical tests and applications to flow control problems.

JOURNAL OF FLUID MECHANICS (2021)

添加到收藏夹

Article Mechanics

Reinforcement-learning-based control of confined cylinder wakes with stability analyses

Jichao Li et al.

Summary: This research utilizes Reinforcement Learning for flow control by setting up synthetic jets on both sides of a cylinder to suppress vortex shedding. Through global linear stability and sensitivity analyses, and incorporating physical results in the design of control policies, the study finds that the controlled wake converges to the unstable base flow, requiring persistent oscillating control for maintaining this state. Additionally, embedding flow stability information in the reward function can lead to a more stable controlled flow.

JOURNAL OF FLUID MECHANICS (2021)

添加到收藏夹

Article Mechanics

Robust flow control and optimal sensor placement using deep reinforcement learning

Romain Paris et al.

Summary: This research utilizes deep reinforcement learning algorithms to optimize the drag control strategy of a cylinder in laminar flow conditions, achieving closed-loop control through synthetic jets and pressure sensors. The study demonstrates that the proposed control strategy exhibits good robustness under different Reynolds numbers and measurement noise, effectively reducing drag.

JOURNAL OF FLUID MECHANICS (2021)

添加到收藏夹

Article Mechanics

Stabilization of the fluidic pinball with gradient-enriched machine learning control

Guy Y. Cornejo Maceda et al.

Summary: We stabilize flow past a cluster of three rotating cylinders, known as the fluidic pinball, using automated gradient-enriched machine learning algorithms to optimize control laws and achieve better performance through increasingly richer search spaces.

JOURNAL OF FLUID MECHANICS (2021)

添加到收藏夹

Article Mechanics

Applying deep reinforcement learning to active flow control in weakly turbulent conditions

Feng Ren et al.

Summary: This study demonstrates the feasibility and effectiveness of deep reinforcement learning in active flow control under weakly turbulent conditions, achieving around 30% drag reduction and exploring optimal sensor network layout.

PHYSICS OF FLUIDS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Cluster-based network modeling-From snapshots to complex dynamical systems

Daniel Fernex et al.

Summary: This study introduces a universal method for data-driven modeling of complex nonlinear dynamics, bridging machine learning, network science, and statistical physics. The proposed cluster-based network modeling (CNM) describes short- and long-term behavior and is fully automatable. This approach complements network connectivity science and offers fast-track avenues for understanding, estimating, predicting, and controlling complex systems in all scientific fields.

SCIENCE ADVANCES (2021)

添加到收藏夹

Article Mechanics

Cluster-based network model

Hao Li et al.

Summary: An automatable data-driven methodology for robust nonlinear reduced-order modelling is proposed, utilizing kinematical coarse-graining and directed network construction to resolve coherent-structure evolution.

JOURNAL OF FLUID MECHANICS (2021)

添加到收藏夹

Review Mechanics

Machine Learning for Fluid Mechanics

Steven L. Brunton et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 52 (2020)

添加到收藏夹

Article Mechanics

Machine learning strategies applied to the control of a fluidic pinball

C. Raibaudo et al.

PHYSICS OF FLUIDS (2020)

添加到收藏夹

Article Mechanics

Active flow control with rotating cylinders by an artificial neural network trained by deep reinforcement learning

Hui Xu et al.

JOURNAL OF HYDRODYNAMICS (2020)

添加到收藏夹

Article Mechanics

Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning

Hongwei Tang et al.

PHYSICS OF FLUIDS (2020)

添加到收藏夹

Article Mechanics

Artificial intelligence control of a turbulent jet

Yu Zhou et al.

JOURNAL OF FLUID MECHANICS (2020)

添加到收藏夹

Article Mechanics

Controlling Rayleigh-Benard convection via reinforcement learning

Gerben Beintema et al.

JOURNAL OF TURBULENCE (2020)

添加到收藏夹

Article Multidisciplinary Sciences

Reinforcement learning for bluff body active flow control in experiments and simulations

Dixia Fan et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

添加到收藏夹

Article Mechanics

Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control

Jean Rabault et al.

JOURNAL OF FLUID MECHANICS (2019)

添加到收藏夹

Article Physics, Fluids & Plasmas

Drag reduction mechanisms of a car model at moderate yaw by bi-frequency forcing

Ruiying Li et al.

PHYSICAL REVIEW FLUIDS (2019)

添加到收藏夹

Article Mechanics

Cluster-based feedback control of turbulent post-stall separated flows

Aditya G. Nair et al.

JOURNAL OF FLUID MECHANICS (2019)

添加到收藏夹

Article Mechanics

Active control of vortex-induced vibration of a circular cylinder using machine learning

Feng Ren et al.

PHYSICS OF FLUIDS (2019)

添加到收藏夹

Article Mechanics

Accelerating deep reinforcement learning strategies of flow control through a multi-environment approach

Jean Rabault et al.

PHYSICS OF FLUIDS (2019)

添加到收藏夹

Article Nanoscience & Nanotechnology

Exploiting locality and translational invariance to design effective deep reinforcement learning control of the 1-dimensional unstable falling liquid film

Vincent Belus et al.

AIP ADVANCES (2019)

添加到收藏夹

Article Engineering, Mechanical

Jet mixing optimization using machine learning control

Zhi Wu et al.

EXPERIMENTS IN FLUIDS (2018)

添加到收藏夹

Article Engineering, Mechanical

Drag reduction of a car model by linear genetic programming control

Ruiying Li et al.

EXPERIMENTS IN FLUIDS (2017)

添加到收藏夹

Article Mechanics

Frequency selection by feedback control in a turbulent shear flow

Vladimir Parezanovic et al.

JOURNAL OF FLUID MECHANICS (2016)

添加到收藏夹

Article Multidisciplinary Sciences

Learning to soar in turbulent environments

Gautam Reddy et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2016)

添加到收藏夹

Article Mechanics

Closed-loop separation control using machine learning

N. Gautier et al.

JOURNAL OF FLUID MECHANICS (2015)

添加到收藏夹

Article Mathematics, Applied

REINFORCEMENT LEARNING AND WAVELET ADAPTED VORTEX METHODS FOR SIMULATIONS OF SELF-PROPELLED SWIMMERS

Mattia Gazzola et al.

SIAM JOURNAL ON SCIENTIFIC COMPUTING (2014)

添加到收藏夹

Review Multidisciplinary Sciences

Some aspects of aerodynamic flow control using synthetic-jet actuation

Ari Glezer

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2011)

添加到收藏夹

Article Engineering, Multidisciplinary

Gmsh: A 3-D finite element mesh generator with built-in pre- and post-processing facilities

Christophe Geuzaine et al.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING (2009)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.