Application of neural networks to multiple alarm processing and diagnosis in nuclear power plants

Author

Cheon, Se Woo ; Chang, Soon Heung ; Chung, Hak Yeong ; Bien, Zeung Nam

Author_Institution

Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea

Volume

40

Issue

1

fYear

1993

fDate

2/1/1993 12:00:00 AM

Firstpage

11

Lastpage

20

Abstract

A feasibility study of multiple alarm processing and diagnosis using neural networks is presented. The backpropagation network (BPN) algorithm is applied to the training of multiple alarm patterns for the identification of faults in a reactor coolant pump (RCP) system. The general mapping capability of the neural network makes it possible to identify a fault easily. A number of case studies are performed, with emphasis on the applicability of the neural network to the pattern recognition of multiple alarms. Based on the case studies, the neural network can identify the cause of multiple alarms well, although untrained, incomplete/sensor-failed or time-varying alarm symptoms are given. Also, multiple faults are easily identified with a given alarm pattern

Keywords

alarm systems; backpropagation; fission reactor cooling and heat recovery; fission reactor safety; learning (artificial intelligence); neural nets; nuclear engineering computing; pattern recognition; pumps; backpropagation network; diagnosis; fault identification; multiple alarm processing; multiple faults; neural networks; nuclear power plants; pattern recognition; reactor coolant pump; training; Biological neural networks; Coolants; Fault diagnosis; Inductors; Intelligent networks; Multi-layer neural network; Neural networks; Pattern recognition; Power engineering and energy; Power generation;

fLanguage

English

Journal_Title

Nuclear Science, IEEE Transactions on

Publisher

ieee

ISSN

0018-9499

Type

jour

DOI

10.1109/23.199482

Filename

199482