Statistical Method Application to Knowledge Base Building for Reactor Accident Diagnostic System

Kazuo Yoshida, Masao Yokobayashi, Kiyoshi Matsumoto, Atsuo Kohsaka

Research output: Contribution to journalArticle

Abstract

In the development of a knowledge based expert system, one of key issues is how to build the knowledge base (KB) in an efficient way with keeping the objectivity of KB. In order to solve this issue, an approach has been proposed to build a prototype KB systematically by a statistical method, factor analysis. For the verification of this approach, factor analysis was applied to build a prototype KB for the JAERI expert system DISKET. To this end, alarm and process information was generated by a PWR simulator and the factor analysis was applied to this information to define taxonomy of accident hypotheses and to extract rules for each hypothesis. The prototype KB thus built was tested through inferring against several types of transients including double-failures. In each diagnosis, the transient type was well identified. Furthermore, newly introduced standards for rule extraction showed good effects on the enhancement of the performance of prototype KB.

Original languageEnglish
Pages (from-to)1002-1012
Number of pages11
JournalJournal of Nuclear Science and Technology
Volume26
Issue number11
DOIs
Publication statusPublished - 1989
Externally publishedYes

Fingerprint

Factor analysis
accidents
Statistical methods
Accidents
reactors
Expert systems
factor analysis
prototypes
expert systems
Taxonomies
Simulators
taxonomy
warning systems
simulators
augmentation

Keywords

  • DISKET
  • double failures
  • expert systems
  • factor analysis
  • knowledge base
  • PWR type reactors
  • reactor accident diagnostic systems
  • reactor simulators
  • statistical method

ASJC Scopus subject areas

  • Nuclear and High Energy Physics
  • Nuclear Energy and Engineering

Cite this

Statistical Method Application to Knowledge Base Building for Reactor Accident Diagnostic System. / Yoshida, Kazuo; Yokobayashi, Masao; Matsumoto, Kiyoshi; Kohsaka, Atsuo.

In: Journal of Nuclear Science and Technology, Vol. 26, No. 11, 1989, p. 1002-1012.

Research output: Contribution to journalArticle

Yoshida, Kazuo ; Yokobayashi, Masao ; Matsumoto, Kiyoshi ; Kohsaka, Atsuo. / Statistical Method Application to Knowledge Base Building for Reactor Accident Diagnostic System. In: Journal of Nuclear Science and Technology. 1989 ; Vol. 26, No. 11. pp. 1002-1012.
@article{15122e151ee743d9bcb3bfd786803a5c,
title = "Statistical Method Application to Knowledge Base Building for Reactor Accident Diagnostic System",
abstract = "In the development of a knowledge based expert system, one of key issues is how to build the knowledge base (KB) in an efficient way with keeping the objectivity of KB. In order to solve this issue, an approach has been proposed to build a prototype KB systematically by a statistical method, factor analysis. For the verification of this approach, factor analysis was applied to build a prototype KB for the JAERI expert system DISKET. To this end, alarm and process information was generated by a PWR simulator and the factor analysis was applied to this information to define taxonomy of accident hypotheses and to extract rules for each hypothesis. The prototype KB thus built was tested through inferring against several types of transients including double-failures. In each diagnosis, the transient type was well identified. Furthermore, newly introduced standards for rule extraction showed good effects on the enhancement of the performance of prototype KB.",
keywords = "DISKET, double failures, expert systems, factor analysis, knowledge base, PWR type reactors, reactor accident diagnostic systems, reactor simulators, statistical method",
author = "Kazuo Yoshida and Masao Yokobayashi and Kiyoshi Matsumoto and Atsuo Kohsaka",
year = "1989",
doi = "10.3327/jnst.26.1002",
language = "English",
volume = "26",
pages = "1002--1012",
journal = "Journal of Nuclear Science and Technology",
issn = "0022-3131",
publisher = "Atomic Energy Society of Japan",
number = "11",

}

TY - JOUR

T1 - Statistical Method Application to Knowledge Base Building for Reactor Accident Diagnostic System

AU - Yoshida, Kazuo

AU - Yokobayashi, Masao

AU - Matsumoto, Kiyoshi

AU - Kohsaka, Atsuo

PY - 1989

Y1 - 1989

N2 - In the development of a knowledge based expert system, one of key issues is how to build the knowledge base (KB) in an efficient way with keeping the objectivity of KB. In order to solve this issue, an approach has been proposed to build a prototype KB systematically by a statistical method, factor analysis. For the verification of this approach, factor analysis was applied to build a prototype KB for the JAERI expert system DISKET. To this end, alarm and process information was generated by a PWR simulator and the factor analysis was applied to this information to define taxonomy of accident hypotheses and to extract rules for each hypothesis. The prototype KB thus built was tested through inferring against several types of transients including double-failures. In each diagnosis, the transient type was well identified. Furthermore, newly introduced standards for rule extraction showed good effects on the enhancement of the performance of prototype KB.

AB - In the development of a knowledge based expert system, one of key issues is how to build the knowledge base (KB) in an efficient way with keeping the objectivity of KB. In order to solve this issue, an approach has been proposed to build a prototype KB systematically by a statistical method, factor analysis. For the verification of this approach, factor analysis was applied to build a prototype KB for the JAERI expert system DISKET. To this end, alarm and process information was generated by a PWR simulator and the factor analysis was applied to this information to define taxonomy of accident hypotheses and to extract rules for each hypothesis. The prototype KB thus built was tested through inferring against several types of transients including double-failures. In each diagnosis, the transient type was well identified. Furthermore, newly introduced standards for rule extraction showed good effects on the enhancement of the performance of prototype KB.

KW - DISKET

KW - double failures

KW - expert systems

KW - factor analysis

KW - knowledge base

KW - PWR type reactors

KW - reactor accident diagnostic systems

KW - reactor simulators

KW - statistical method

UR - http://www.scopus.com/inward/record.url?scp=85007721171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007721171&partnerID=8YFLogxK

U2 - 10.3327/jnst.26.1002

DO - 10.3327/jnst.26.1002

M3 - Article

AN - SCOPUS:85007721171

VL - 26

SP - 1002

EP - 1012

JO - Journal of Nuclear Science and Technology

JF - Journal of Nuclear Science and Technology

SN - 0022-3131

IS - 11

ER -