STUDIES ON THE DETECTION OF INCIPIENT COOLANT BOILING IN NUCLEAR-REACTORS USING ARTIFICIAL NEURAL NETWORKS

The sensitivity of coolant boiling monitoring based on the analysis of signals of neutron detectors in a nuclear reactor is studied. Thermal hydraulic processes related to coolant boiling have typical time cons tant in the order of a few seconds. An efficient coolant-state monitor ing system should have a response time comparable with this value of t he time constant in order to detect changes at an early stage. The pro posed system described in this paper has the required fast response. T he proposed monitoring system utilizes advanced signal processing meth ods based on artificial neural networks in order to achieve early dete ction of changes in the state of the coolant. The networks have been t rained to identify small variations in the power spectral density func tions of neutron detector signals. The boiling monitoring method has b een tested by using in-core neutron detector signals measured at the N IOBE loop located in the Hoger Onderwijs Reactor (HOR) of Interfaculty Reactor Institute, Delft, The Netherlands. It is shown that boiling d etection can be accomplished within about 16 s after the onset of surf ace boiling in a coolant channel. Results obtained by artificial neura l networks have been compared with the efficiency of anomaly detection based on the analysis of band-passed variance of neutronic fluctuatio ns. It is shown that artificial neural nets detect the anomaly faster and more reliably than variance-based statistical methods.