Application of Artificial Neural Network for the Prediction of Pressure Distribution of a Plunging Airfoil

Series of experimental tests were conducted on a section of a 660 kW wind turbine blade to measure the pressure distribution of this model oscillating in plunging motion. In order to minimize the amount of data required to predict aerodynamic loads of the airfoil, a General Regression Neural Network, GRNN, was trained using the measured experimental data. The network once proved to be accurate enough, was used to predict the flow behavior of the airfoil for the desired conditions. Results showed that with using a few of the acquired data, the trained neural network was able to predict accurate results with minimal errors when compared with the corresponding measured values. Therefore with employing this trained network the aerodynamic coefficients of the plunging airfoil, are predicted accurately at different oscillation frequencies, amplitudes, and angles of attack; hence reducing the cost of tests while achieving acceptable accuracy.

Authors:

• F. Rasi Maezabadi
• M. Masdari
• M. R. Soltani

Keywords:

• Airfoil
• experimental
• GRNN
• Neural Network
• Plunging.

References:

[1] J., Leishman, "Principles of helicopter aerodynamic," Cambridge Press,
2000.
[2] Jeppe, Johansen, "Unsteady airfoil flows with application to aero elastic
stability," Riso laboratory, Roskilde, Denmark, October 1999.
[3] Joseph C., Tayler, and , J. Gordon, Leishman, "An analysis of pitch and
plunge effects on unsteady airfoil behavior," Presented at the 47th
Annual Forum of the American Helicopter Society, May1991.
[4] S. J., Schreck, and , W. E., Faller, "Encoding of three dimensional
unsteady separated flow field dynamics in neural network architectures,"
AIAA 95-0103, 33rd Aerospace Science Meeting and Exhibit, 1995.
[5] R.L., McMillen, J.E., Steck, and K., Rokhsaz, "Application of an
artificial neural network as a flight test data estimator," AIAA Paper 95-
0561, presented at AIAA 33rd Aerospace Sciences Meeting and Exhibit,
Reno, Nev., Jan. 1995.
[6] K., Rokhsaz, and J.E., Steck, "Application of artificial neural networks
in nonlinear aerodynamics and aircraft design," SAE Paper 932533, SAE
Transactions, pp. 1790- 1798, 1993.
[7] M.R., Soltani, F., Rasi Marzabadi, and M., Seddighi, "Surface pressure
variation on an airfoil in plunging and pitching motions," 25th ICAS
Congress, Hamburg, Germany, September, 2006.
[8] F. A., Carta, "A comparison of the pitching and plunging response of an
oscillating airfoil," NASA CR-3172, 1979.
[9] Donald, F. Specht, "A General Regression Neural Network," IEEE,
Vol.2 No.6, November, 1991.
[10] W.Mciscl, Brichman, and E., Pursell, "Variable kernel estimates of
multivariate densities," Technometries, Vol. 19 No. 2, May, 1977.