Application of neural networks to turbulence control for drag reduction

Changhoon Lee, John Kim, David Babcock, Rodney Goodman

Research output: Contribution to journalArticle

161 Citations (Scopus)

Abstract

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 flow. Also, a stable 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. This simple control scheme generates optimum wall blowing and suction proportional to a local sum of the wall-shear stress in the spanwise direction. The distribution of corresponding weights is simple and localized, thus making real implementation relatively easy. Turbulence characteristics and relevant practical issues are also discussed.

Original languageEnglish
Pages (from-to)1740-1747
Number of pages8
JournalPhysics of Fluids
Volume9
Issue number6
DOIs
Publication statusPublished - 1997 Jun

Fingerprint

drag reduction
turbulence
blowing
suction
channel flow
shear stress
network control
skin friction
low Reynolds number
direct numerical simulation
controllers

All Science Journal Classification (ASJC) codes

  • Computational Mechanics
  • Condensed Matter Physics
  • Mechanics of Materials
  • Mechanical Engineering
  • Fluid Flow and Transfer Processes

Cite this

Lee, Changhoon ; Kim, John ; Babcock, David ; Goodman, Rodney. / Application of neural networks to turbulence control for drag reduction. In: Physics of Fluids. 1997 ; Vol. 9, No. 6. pp. 1740-1747.
@article{949a4697de564c9a84b82a889a775922,
title = "Application of neural networks to turbulence control for drag reduction",
abstract = "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 flow. Also, a stable 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. This simple control scheme generates optimum wall blowing and suction proportional to a local sum of the wall-shear stress in the spanwise direction. The distribution of corresponding weights is simple and localized, thus making real implementation relatively easy. Turbulence characteristics and relevant practical issues are also discussed.",
author = "Changhoon Lee and John Kim and David Babcock and Rodney Goodman",
year = "1997",
month = "6",
doi = "10.1063/1.869290",
language = "English",
volume = "9",
pages = "1740--1747",
journal = "Physics of Fluids",
issn = "1070-6631",
publisher = "American Institute of Physics Publising LLC",
number = "6",

}

Application of neural networks to turbulence control for drag reduction. / Lee, Changhoon; Kim, John; Babcock, David; Goodman, Rodney.

In: Physics of Fluids, Vol. 9, No. 6, 06.1997, p. 1740-1747.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Application of neural networks to turbulence control for drag reduction

AU - Lee, Changhoon

AU - Kim, John

AU - Babcock, David

AU - Goodman, Rodney

PY - 1997/6

Y1 - 1997/6

N2 - 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 flow. Also, a stable 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. This simple control scheme generates optimum wall blowing and suction proportional to a local sum of the wall-shear stress in the spanwise direction. The distribution of corresponding weights is simple and localized, thus making real implementation relatively easy. Turbulence characteristics and relevant practical issues are also discussed.

AB - 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 flow. Also, a stable 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. This simple control scheme generates optimum wall blowing and suction proportional to a local sum of the wall-shear stress in the spanwise direction. The distribution of corresponding weights is simple and localized, thus making real implementation relatively easy. Turbulence characteristics and relevant practical issues are also discussed.

UR - http://www.scopus.com/inward/record.url?scp=0030776830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030776830&partnerID=8YFLogxK

U2 - 10.1063/1.869290

DO - 10.1063/1.869290

M3 - Article

AN - SCOPUS:0030776830

VL - 9

SP - 1740

EP - 1747

JO - Physics of Fluids

JF - Physics of Fluids

SN - 1070-6631

IS - 6

ER -