APPLICATION OF NEURAL NETWORKS TO SIGNAL PREDICTION IN NUCLEAR-POWER-PLANT

This paper describes the feasibility study of an artificial neural net work for signal prediction. The purpose of signal prediction is to est imate the value of undetected next time step signal. As the prediction method, based on the idea of auto regression, a few previous signals are inputs to the artificial neural network and the signal value of ne xt time step is estimated with the outputs of the network. The artific ial neural network can be applied to the nonlinear system and answers in short time. The training algorithm is a modified backpropagation mo del, which can effectively reduce the training time. The target signal of the simulation is the steam generator water level, which is one of the important parameters in nuclear power plants. The simulation resu lt shows that the predicted value follows the real trend well.