| Autor: |
Dávalos, J. O., García, J. C., Urquiza, G., Huicochea, A., De Santiago, O. |
| Předmět: |
|
| Zdroj: |
International Journal of Turbo & Jet-Engines; May2018, Vol. 35 Issue 2, p101-111, 11p |
| Abstrakt: |
In this work, the area-averaged film cooling effectiveness (AAFCE) on a gas turbine blade leading edge was predicted by employing an artificial neural network (ANN) using as input variables: hole diameter, injection angle, blowing ratio, hole and columns pitch. The database used to train the network was built using computational fluid dynamics (CFD) based on a two level full factorial design of experiments. The CFD numerical model was validated with an experimental rig, where a first stage blade of a gas turbine was represented by a cylindrical specimen. The ANN architecture was composed of three layers with four neurons in hidden layer and Levenberg-Marquardt was selected as ANN optimization algorithm. The AAFCE was successfully predicted by the ANN with a regression coefficient R2<0.99 and a root mean square error RMSE=0.0038. The ANN weight coefficients were used to estimate the relative importance of the input parameters. Blowing ratio was the most influential parameter with relative importance of 40.36 % followed by hole diameter. Additionally, by using the ANN model, the relationship between input parameters was analyzed. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
