Suscripción a Biblioteca: Guest

ISSN Online: 2377-424X

ISBN Print: 978-1-56700-421-2

International Heat Transfer Conference 15
August, 10-15, 2014, Kyoto, Japan

Experimental Study and Prediction of Film Cooling Effectiveness for a Guide Vane in Heavy Gas Turbine

Get access (open in a dialog) DOI: 10.1615/IHTC15.hte.009965
pages 4307-4318

Sinopsis

Film cooling is widely applied as an important cooling method for turbine cooling. It is usually used at the leading edge to protect the blade from high temperature stream. In this paper, an experimental model with showerhead film cooling configuration is designed based on a real turbine guide vane. Plenty of experiments are conducted on this vane to measure the cooling effectiveness. The effects of coolant injection parameters on the cooling performance are investigated. Then the CFD method, the empirical formula and genetic algorithm optimized BP neural network are used to predict the cooling effectiveness, and the predicted results are compared with the experimental results. It is indicated that genetic algorithm optimized BP neural network model has better accuracy and wider valid parameter range, with averaged error of only 2%. Though empirical formula is more widely used, it is limited in parameter range. Thus genetic algorithm optimized BP neural network is a more promising prediction method in predicting the cooling effectiveness for the film cooling.