Study on dryout point by wavelet and GNN

Abstract

In this study, the local modulus maxima of cubic B-spline wavelet transform is introduced to determine the location of dryout point. Based on genetic algorithm and artificial neural network, a Genetic Neural Network (GNN) model predicting dryout-type critical heat flux (CHF) for flowing upward in vertical narrow annuli with bilateral heating has been developed. The GNN mode has some advantages of its global optimal searching, quick convergence speed and solving non-linear problem. The methods of establishing the model and training of GNN are discussed in the article. The mainly parametric trends of the CHF are analyzed by applying GNN. The results agree well with practical behavior as they are generally understood. They proved the validity of GNN. At last, the prediction of dryout point is investigated by GNN with distilled water flowing upward through narrow annular channel with 0.95 mm and 1.5 mm gaps, respectively. The GNN prediction results have a good agreement with experimental data. Simulation and analysis results show that the network model can effectively predict CHF.