Numerical Optimization of the Hydraulic Turbine Runner Blades Applying Neuronal Networks

Abstract

This paper presents numerical optimization of turbomachinery blade shapes, using artificial neural network. This model takes into account the parameters of operation of the turbine (mass flow, direction of the flor and velocity angular). For the networks, the Levenberg-Marquardt learning algorithm, the hyperbolic tangent sigmoid transfer-function and the linear transfer-function were used. The best fitting training data set was obtained with three neurons in the hidden layer, which made it possible to predict efficiency with accuracy at least as good as that of the theoretical error, over the whole theoretical range. On the validation data set, simulations and theoretical data test were in good agreement (r2>0.99). The developed model can be used for the prediction of the efficiency in short simulation time