Development of a New Method for Forecasting Future States of NPPs Parameters in Transients

This study introduces a new method for forecasting future states of nuclear power plants (NPPs) parameters in abnormal conditions (i.e. transients). The proposed method consists of two steps. First, the type of transients is recognized by the modular EBP based identifier. A hybrid network is then used to forecast the selected parameters of the identified transient. ARIMA model is used to estimate the linear component of the selected parameters. The neural network developed by EBP learning algorithm is then used to estimate the nonlinear component of the selected parameters. Finally, prediction of parameters is obtained by adding the estimated linear and nonlinear components. To analyze the ability of the proposed method, Bushehr nuclear power plant (BNPP) parameters are forecasted. Results show good agreement of forecasted parameters with final safety analysis report (FSAR). Noticeable advantages of the proposed method are: forecasting any quantifiable parameter without necessity to know its correlation with other and possibility for prediction of parameters in long temporal dependencies. Extendibility for identification of more transients and forecasting more parameters without unfavorably affecting the existing system is another advantage and unique feature of the proposed design. The proposed method can be used as a support system for the NPPs operators to estimate future states of the plant and to perform appropriate actions before transient progresses into critical states.