Modeling of deviation angle and performance losses in wet steam turbines using GMDH-type neural networks

In the present study group method of data handling (GMDH) type of artificial neural networks are used to model deviation angle (theta), total pressure loss coefficient (omega), and performance loss coefficient (xi) in wet steam turbines. These parameters are modeled with respect to four input variables, i.e., stagnation pressure (P-z), stagnation temperature (T-z), back pressure (P-b), and inflow angle (beta). The required input and output data to train the neural networks has been taken from numerical simulations. An AUSM-Van Leer hybrid scheme is used to solve twophase transonic steam flow numerically. Based on results of the paper, GMDH-type neural networks can successfully model and predict deviation angle, total pressure loss coefficient, and performance loss coefficient in wet steam turbines. Absolute fraction of variance (R-2) and root-mean-squared error related to total pressure loss coefficient (omega) are equal to 0.992 and 0.002, respectively. Thus GMDH models have enough accuracy for turbomachinery applications.