Related papers: Active Flow Control for Drag Reduction of a Plungi…
A comparative assessment of machine learning (ML) methods for active flow control is performed. The chosen benchmark problem is the drag reduction of a two-dimensional K\'arm\'an vortex street past a circular cylinder at a low Reynolds…
This study proposes a self-learning algorithm for closed-loop cylinder wake control targeting lower drag and lower lift fluctuations with the additional challenge of sparse sensor information, taking deep reinforcement learning as the…
We develop neural-network active flow controllers using a deep learning PDE augmentation method (DPM). The sensitivities for optimization are computed using adjoints of the governing equations without restriction on the terms that may…
For present study, setting Strouhal Number (St) as control parameter, numerical simulations for flow past oscillating NACA-0012 airfoil at 1,000 Reynolds Numbers (Re) are performed. Temporal profiles of unsteady forces; lift and thrust, and…
Turbulent drag reduction through streamwise travelling waves of spanwise wall oscillation is investigated over a wide range of Reynolds numbers. Here, in Part 1, wall-resolved large-eddy simulations in a channel flow are conducted to…
The unsteady aerodynamic thrust and aeroelastic response of a two-dimensional membrane airfoil under prescribed harmonic motion are investigated computationally with a high-order Navier-Stokes solver coupled to a nonlinear membrane…
This paper focuses on the active flow control (AFC) of the flow over a circular cylinder with synthetic jets through deep reinforcement learning (DRL) by implementing a reward function based on dynamic mode decomposition (DMD). As a main…
This work studies the effectiveness of several machine learning techniques for predicting extreme events occurring in the flow around an airfoil at low Reynolds. For certain Reynolds numbers the aerodynamic forces exhibit intermittent…
This paper focuses on developing a deep reinforcement learning (DRL) control strategy to mitigate aerodynamic forces acting on a three dimensional (3D) square cylinder under high Reynolds number flow conditions. Four jets situated at the…
In aerodynamic design, the use of Computational Fluid Dynamics (CFD) tools has long relied on Reynolds-Averaged Navier-Stokes (RANS) and Unsteady RANS (URANS) turbulence models. However, these methods face limitations in predicting…
The effect of duty cycle (DC) and blowing ratio on synthetic jet flow control over a stalled NACA 0025 airfoil at Re_c=10^5 was investigated experimentally. A finite-span microblower array operating with burst modulation was tested across a…
This paper focuses on a drag-reducing control strategy on a 2D-simulated laminar flow past a cylinder. Deep reinforcement learning algorithms have been implemented to discover efficient control schemes, using two synthetic jets located on…
Dimensionless frequency scaling laws for active separation control on flat-plate wings, using dielectric barrier discharge plasma actuators, were examined on the basis of maximum increases to lift coefficient, and compared with hovering…
Many experimental and numerical studies report a large reduction of the recirculation bubble in Backward-Facing Step flows or airfoils in stall situation when excited at the natural shedding frequency $f_0$. Through a simple experiment…
Reinforcement learning is applied to the development of control strategies in order to reduce skin friction drag in a fully developed turbulent channel flow at a low Reynolds number. Motivated by the so-called opposition control (Choi et…
Dynamic stall at low Reynolds numbers, $\mathit{Re} \sim \mathcal{O}(10^4)$, exhibits complex flow physics with co-existing laminar, transitional, and turbulent flow regions. Current state-of-the-art stall onset criteria use parameters that…
We present a deep reinforcement learning approach to a classical problem in fluid dynamics, i.e., the reduction of the drag of a bluff body. We cast the problem as a discrete-time control with continuous action space: at each time step, an…
Rotor blades of wind turbines in the atmospheric boundary layer regularly experience the aerodynamic phenomenon of dynamic stall consisting of a temporary overshoot of lift and detrimental fatigue loads. Particularly the formation of…
We perform particle-resolved simulations of subsonic and transonic flows past random arrays of spherical particles. The Reynolds number is held at $Re{\approx}300$ to ensure the flow remains in the continuum regime. At low volume fractions,…
We carried out high-resolution large-eddy simulations (LESs) to investigate the effects of several separation-control approaches on a NACA4412 wing section with spanwise width of $L_z = 0.6$ at an angle of attack of $AoA=11^{\circ}$ at a…