Applications of genetic neural network for prediction of critical heat flux

In this study, the data set of the 2006 CHF look-up table is partitioned into five subsets by using Fuzzy c-means (FCM) clustering algorithm. The elements of the same subset are ‘similar’ to each other in some sense while those assign to different subsets are ‘dissimilar’. At the same time, a Genetic Neural Network (GNN) model for predicting critical heat flux (CHF) is set up. It has some advantages of its globe optimal searching, quick convergence speed and solving non-linear problem. The methods of establishing the model and training of GNN are discussed particularly in the article. Local condition type CHF is predicted by GNN on the basis of 6930 CHF data from the 2006 CHF look-up table. The prediction results are consistent with database very well. Next, the mainly parametric trends of the CHF are analyzed by applying GNN. At last, 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 prediction results by GNN have a good agreement with experimental data. Simulation and analysis results show that the network model can effectively predict CHF.