Application of neural networks to signal prediction in nuclear power plant

Author

Kim, Wan Joo ; Chang, Soon Heung ; Lee, Byung Ho

Author_Institution

Dept. of Nucl. Eng., Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea

Volume

40

Issue

5

fYear

1993

fDate

10/1/1993 12:00:00 AM

Firstpage

1337

Lastpage

1341

Abstract

The feasibility of using an artificial neural network for signal prediction is studied. The purpose of signal prediction is to estimate the value of the undetected next-time-step signal. In the prediction method, which is based on the idea of autoregression, a few previous signals are input to the artificial neural network, and the signal value of next time step is estimated from the outputs of the network. The artificial neural network can be applied to a nonlinear system and has fast response. The training algorithm is a modified backpropagation model, which can effectively reduce the training time. The target signal of the simulation is the steam generator water level in a nuclear power plant. The simulation result shows that the predicted value follows the real trend well

Keywords

backpropagation; feedforward neural nets; fission reactor cooling and heat recovery; fission reactor safety; nuclear engineering computing; nuclear power stations; nuclear reactor steam generators; power station computer control; signal processing; artificial neural network; autoregression; backpropagation model; nonlinear system; nuclear power plant; signal prediction; steam generator water level; training algorithm; Artificial neural networks; Backpropagation algorithms; Neural networks; Nonlinear systems; Nuclear power generation; Power generation; Power system modeling; Prediction methods; Predictive models; Signal generators;

fLanguage

English

Journal_Title

Nuclear Science, IEEE Transactions on

Publisher

ieee

ISSN

0018-9499

Type

jour

DOI

10.1109/23.234547

Filename

234547