Experiments are carried out behind a square cylinder mounted in the freestream of a wind tunnel, and hot-wire anemometry is used to determine the profiles of the mean and statistical turbulence quantities. Artificial neural networks and fuzzy-logic models successfully predict the statistical quantities like mean velocity profiles and Reynolds stresses. The fuzzy-logic modeling is more convenient to use, is less computationally intensive, and gives a higher correlation coefficient in comparison to the neural network.

Issue Section:
Technical Briefs
Keywords:
wakes, turbulence, fuzzy logic, fuzzy neural nets, perceptrons, flow control, statistical analysis
Topics:
Artificial neural networks, Cylinders, Fuzzy logic, Statistics, Turbulence, Modeling
1.
Sen, M., and Goodwine, J. W., 2001, “Soft Computing in Control,” The MEMS Handbook, M. Gad-el-Hak, ed., CRC Press, Boca Raton, FL, Chap. 14, pp. 1–37.
2.
Dutta, S., Muralidhar, K., and Panigrahi, P. K., 2002, “Influence of the Orientation of a Square Cylinder on the Wake Properties,” Exp. Fluids, in press.
3.
Panigrahi, P. K., Khandelwal, V., and Sen, M., 2002, “Prediction of Turbulent Statistics Behind a Rib Using Artificial Neural Network,” Proceedings of the Fifth ISHMT/ASME Heat & Mass Transfer Conference & Sixteenth National Heat & Mass Transfer Conference, Calcutta, Jan. 3–5, Tata McGraw-Hill, pp. 676–681.
4.
Xie
,
H.
,
Mahajan
,
R. L.
, and
Lee
,
Y.
,
1995
, “
Fuzzy Logic Models for Thermally Based Microelectronic Manufacturing Processes
,”
IEEE Trans. Semicond. Manuf.
,
8
(
3
), pp.
219
–
226
.
5.
Rediniotis
,
O. K.
, and
Chrysanthakopoulos
,
G.
,
1988
, “
Application of Neural Networks and Fuzzy Logic to the Calibration of the Seven-Hole Probe
,”
ASME J. Fluids Eng.
,
120
, pp.
95
–
101
.
Copyright © 2003
 by ASME
You do not currently have access to this content.