Abstract: 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.
Abstract: Extensive wind tunnel tests have been conducted to
investigate the unsteady flow field over and behind a 2D model of a
660 kW wind turbine blade section in pitching motion. The surface
pressure and wake dynamic pressure variation at a distance of 1.5
chord length from trailing edge were measured by pressure
transducers during several oscillating cycles at 3 reduced frequencies
and oscillating amplitudes. Moreover, form drag and linear
momentum deficit are extracted and compared at various conditions.
The results show that the wake velocity field and surface pressure of
the model have similar behavior before and after the airfoil beyond
the static stall angle of attack. In addition, the effects of reduced
frequency and oscillation amplitudes are discussed.