A diagnostic system for identifying accident conditions in a nuclear reactor

Review of R&D activities in Level-1 Probabilistic Safety Assessment and aging studies

“…A neural network based diagnostic system for identification of accident scenarios in 220 MWe Indian pressurized heavy water reactors (PHWRs) has been developed for operator support and accident management [7,8]. The objective of one such system, the plant diagnostic system, is to give the plant operators appropriate inputs to formulate, conform, initiate and perform the corrective actions in any potentially unsafe scenario that may arise in the plant.…”

A Constraint-Based Random Search Algorithm for Optimizing Neural Network Architectures and Ensemble Construction in Detecting Loss of Coolant Accidents in Nuclear Power Plants

“…Wei X et al [13] developed self-organizing radial basis function (RBF) networks to predict fuel rod failure of nuclear reactors. Santhosh et al [3] trained a neural network on a transient dataset generated using RELAP5-3D to detect the size of a break, the location of the break in the PHT with the availability of the emergency core cooling system (ECCS) which automatically shuts down the reactor to prevent a subsequent accident.…”

Two neural network based strategies for the detection of a total instantaneous blockage of a sodium-cooled fast reactor

“…The ANN have been successfully applied to other incident scenarios. In [15,16], the authors deal with the problem of classifying different scenarios of accidents: loss of coolant accident in the reactor inlet heading, emergency core cooling system, among others. In [17] Nuclear Reactor (NR) such as the tube failure in the steam generator and the moderator heat exchanger.…”