Prediction of Leak Flow Rate Using FNNs in Severe LOCA Circumstances

Leak flow rate is a function of break size, differential pressure ( i.e., difference between internal and external reactor vessel pressure), temperature, and so on. Specially, the leak flow rate is strongly dependent on the break size and the differential pressure, but the break size is not measured and the integrity of pressure sensors is not assured in severe circumstances. In this study, a fuzzy neural network (FNN) model is proposed to predict the leak flow rate out of break, which has a direct impact on the important times (time approaching the core exit temperature that exceeds 1200 .deg. F, core uncover time, reactor vessel failure time, etc.). Since FNN is a data-based model, it requires data to develop and verify itself. However, because actual severe accident data do not exist to the best of our knowledge, it is essential to obtain the data required in the proposed model using numerical simulations. These data were obtained by simulating severe accident scenarios for the optimized power reactor 1000 (OPR 1000) using MAAP4 code. In this study, FNN model was developed to predict the leak flow rate in severe post-LOCA circumstances.. The training data were selected from among all the acquired data using an SC method to train the proposed FNN model with more informative data. The developed FNN model predicted the leak flow rate using the time elapsed after reactor shutdown and the predicted break size, and its validity was verified in the basis of the simulation data of OPR1000 using MAAP4 code