Pattern-recognition software for plant surveillance

Conference · Thu Jan 01 04:00:00 EST 1987 · Trans. Am. Nucl. Soc.; (United States)

OSTI ID:6194066

Mott, J; Young, J; Bertch, W; King, R W

A power plant in steady-state operation has almost all plant signals in definite relations to each other, and a new approach to plant surveillance, which compares the patterns representing these relations, has been used to measure the consistency of many plant signals simultaneously and so derive a measure of the validity of each individual signal. In the application of this process, the real plant is used as a model from which to learn the pattern relations, and the surveillance function compares learned signal values with currently observed signal values by using contrast-enhancing, pattern-recognition algorithms. System state analyzer (SSA) software embodying this technique has been developed for the daily surveillance of the Experimental Breeder Reactor-II (EBR-II) at the Argonne National Laboratory-West site.

• Research Organization: Energy Inc., Idaho Falls, ID (US); Argonne National Lab. West, Idaho Falls, ID (US)
• OSTI ID: 6194066
• Report Number(s): CONF-870837-
• Conference Information: Journal Name: Trans. Am. Nucl. Soc.; (United States) Journal Volume: 54:1
• Country of Publication: United States
• Language: English

Related Subjects

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS
22 GENERAL STUDIES OF NUCLEAR REACTORS
220400* -- Nuclear Reactor Technology-- Control Systems
220600 -- Nuclear Reactor Technology-- Research
Test & Experimental Reactors
220900 -- Nuclear Reactor Technology-- Reactor Safety
ALGORITHMS
ANL
COMPUTER CODES
EXPERIMENTAL REACTORS
MATHEMATICAL LOGIC
NATIONAL ORGANIZATIONS
NUCLEAR FACILITIES
NUCLEAR POWER PLANTS
PATTERN RECOGNITION
POWER PLANTS
REACTOR MONITORING SYSTEMS
REACTOR SAFETY
REACTORS
RESEARCH AND TEST REACTORS
SAFETY
SURVEILLANCE
THERMAL POWER PLANTS
US AEC
US DOE
US ERDA
US ORGANIZATIONS