Application of Neural Network to Turbulence Control for Drag Reduction
نویسندگان
چکیده
A new adaptive controller based on a neural network was constructed and applied to turbulent channel ow for drag reduction. A simple control network, which employs blowing and suction at the wall based only on quantities measured at the wall, was shown to reduce the skin friction by as much as 20% in direct numerical simulations of low-Reynolds number turbulent channel ow. Also, a pattern was observed in the distribution of weights associated with the neural network. This allowed us to derive a simple control scheme that produced the same amount of drag reduction more e ciently.
منابع مشابه
Application of neural networks to turbulence control for drag reduction
A new adaptive controller based on a neural network was constructed and applied to turbulent channel flow for drag reduction. A simple control network, which employs blowing and suction at the wall based only on the wall-shear stresses in the spanwise direction, was shown to reduce the skin friction by as much as 20% in direct numerical simulations of a low-Reynolds number turbulent channel flo...
متن کاملActive Drag Reduction using Neural Networks
This paper presents the application of a neural network controller to the problem of active drag reduction in a fully turbulent 3D fluid flow regime. The neural network learns a function nearly identical to an analytically derived control law. We then demonstrate the ability of a neural controller to maintain a drag-reduced flow in a fully turbulent fluid simulation. Finally we examine the amou...
متن کاملTurbulent Drag Reduction by Spanwise Wall Oscillations
The objective of this paper is to examine the effectiveness of wall oscillation as a control scheme of drag reduction. Two flow configurations are considered: constant flow rate and constant mean pressure gradient. The Navier-Stokes equations are solved using Fourier-Chebyshev spectral methods and the oscillation in sinusoidal form is enforced on the walls through boundary conditions for the sp...
متن کاملParametric study of a viscoelastic RANS turbulence model in the fully developed channel flow
One of the newest of viscoelastic RANS turbulence models for drag reducing channel flow with polymer additives is studied in different flow and rheological properties. In this model, finitely extensible nonlinear elastic-Peterlin (FENE-P) constitutive model is used to describe the viscoelastic effect of polymer solution and turbulence model is developed in the k-ϵ-(ν^2 ) ̅-f framework. The geome...
متن کاملNumerical Simulation of Air Flow around the NP Car Using the Realizable k-ε Turbulence Model to Predict Aerodynamic Forces and Moments
In this study, a numerical computational fluid dynamics study is conducted in order to predict the aerodynamic forces on the NP car. The turbulent air flow around the car is modeled using the realizable k-ε model. First, results are validated against those presented for the Ahmed’s body. Next, the fluid flow around the car is simulated for different car speeds ( to mph) and fl...
متن کامل