Neural network based diagnostic system for accident management in nuclear power plants

An artificial neural network (ANN) based diagnostic system for identification of large break loss of coolant accident (LOCA) transients in nuclear power plants (NPPs) has been developed. This is an operator support system which assists the operator in identifying a transient quickly using ANNs. A large database of transient (LOCA) analyses of reactor process parameters has been generated for reactor core, containment, environmental dispersion and radiological dose to train the ANNs. These data have been generated using various codes e.g., RELAP5, CONTRAN. The trained neural network has been integrated with the diagnostic system for future transient prediction. The main diagnostic system features several important operator support features that are useful in accident management. This paper highlights the important features of diagnostic system. The present version of this system is capable of identifying large break LOCA scenarios of 220 MWe Indian PHWRs.