Title :
Application of pattern recognition techniques to nuclear reactor surveillance
Author_Institution :
University of Tennessee, Knoxville, TN
Abstract :
A multivariate statistical pattern recognition system for analyzing reactor noise signatures is presented. The capabilities of the system to detect deviations from normal operation were evaluated by experiments conducted at the Oak Ridge National Laboratory High-Flux Isotope Reactor. Power perturbations of less than 0.1% of the mean value in selected frequency ranges were readily detected by the system.
Keywords :
Contracts; Cooling; Inductors; Instruments; Isotopes; Laboratories; Nuclear power generation; Pattern recognition; Surveillance;
Conference_Titel :
Decision and Control including the Symposium on Adaptive Processes, 1979 18th IEEE Conference on
Conference_Location :
Fort Lauderdale, FL, USA
DOI :
10.1109/CDC.1979.270117
