skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Expert systems with fuzzy logic for intelligent diagnosis and control of nuclear power plants

Abstract

A model-based production-rule analysis system was developed for the tracking and diagnosis of the condition of a reactor coolant system (RCS) using a fuzzy logic algorithm. Since nuclear power plants are large and complex systems, it is natural that vagueness, uncertainty, and imprecision are introduced to such systems. Even in fully automated power plants, the critical diagnostic and control changes must be made by operators who usually express their diagnostic and control strategies linguistically as sets of heuristic decision rules. Therefore, additional imprecisions are introduced into the systems because of the imprecise nature of such qualitative strategies when they are converted into quantitative rules. Such problems, in which the source of imprecision is the absence of sharply defined criteria of class membership, could be dealt with using fuzzy set theory. Hence, a fuzzy logic algorithm could be initiated to implement a known heuristic whenever the given information is vague and qualitative, and it will allow operators to introduce certain linguistic assertions and commands to diagnose and control the system.

Authors:
;  [1]
  1. Univ. of Tennessee, Knoxville (United States)
Publication Date:
OSTI Identifier:
6779750
Report Number(s):
CONF-901101-
Journal ID: ISSN 0003-018X; CODEN: TANSAO
Resource Type:
Conference
Journal Name:
Transactions of the American Nuclear Society; (United States)
Additional Journal Information:
Journal Volume: 62; Conference: American Nuclear Society (ANS) winter meeting, Washington, DC (United States), 11-16 Nov 1990; Journal ID: ISSN 0003-018X
Country of Publication:
United States
Language:
English
Subject:
22 GENERAL STUDIES OF NUCLEAR REACTORS; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; NUCLEAR POWER PLANTS; REACTOR CONTROL SYSTEMS; EXPERT SYSTEMS; ALGORITHMS; ARTIFICIAL INTELLIGENCE; DECISION MAKING; DIAGNOSTIC TECHNIQUES; KNOWLEDGE BASE; MATHEMATICAL LOGIC; REACTOR OPERATION; REACTOR OPERATORS; REACTOR SAFETY; SURVEILLANCE; TIME DEPENDENCE; ANIMALS; CONTROL SYSTEMS; MAMMALS; MAN; NUCLEAR FACILITIES; OPERATION; PERSONNEL; POWER PLANTS; PRIMATES; SAFETY; THERMAL POWER PLANTS; VERTEBRATES; 220900* - Nuclear Reactor Technology- Reactor Safety; 220400 - Nuclear Reactor Technology- Control Systems; 990200 - Mathematics & Computers

Citation Formats

Abdelhai, M I, and Upadhyaya, B R. Expert systems with fuzzy logic for intelligent diagnosis and control of nuclear power plants. United States: N. p., 1990. Web.
Abdelhai, M I, & Upadhyaya, B R. Expert systems with fuzzy logic for intelligent diagnosis and control of nuclear power plants. United States.
Abdelhai, M I, and Upadhyaya, B R. Mon . "Expert systems with fuzzy logic for intelligent diagnosis and control of nuclear power plants". United States.
@article{osti_6779750,
title = {Expert systems with fuzzy logic for intelligent diagnosis and control of nuclear power plants},
author = {Abdelhai, M I and Upadhyaya, B R},
abstractNote = {A model-based production-rule analysis system was developed for the tracking and diagnosis of the condition of a reactor coolant system (RCS) using a fuzzy logic algorithm. Since nuclear power plants are large and complex systems, it is natural that vagueness, uncertainty, and imprecision are introduced to such systems. Even in fully automated power plants, the critical diagnostic and control changes must be made by operators who usually express their diagnostic and control strategies linguistically as sets of heuristic decision rules. Therefore, additional imprecisions are introduced into the systems because of the imprecise nature of such qualitative strategies when they are converted into quantitative rules. Such problems, in which the source of imprecision is the absence of sharply defined criteria of class membership, could be dealt with using fuzzy set theory. Hence, a fuzzy logic algorithm could be initiated to implement a known heuristic whenever the given information is vague and qualitative, and it will allow operators to introduce certain linguistic assertions and commands to diagnose and control the system.},
doi = {},
url = {https://www.osti.gov/biblio/6779750}, journal = {Transactions of the American Nuclear Society; (United States)},
issn = {0003-018X},
number = ,
volume = 62,
place = {United States},
year = {1990},
month = {1}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: