Analysis of neutron noise spectra using neural networks

Conference · Tue Jan 01 04:00:00 EST 1991

OSTI ID:5906494

Korsah, K ^[1]; Uhrig, R E ^[2]

---

1. Oak Ridge National Lab., TN (USA)
2. Oak Ridge National Lab., TN (USA) Tennessee Univ., Knoxville, TN (USA)

Neural network architectures based on the back-propagation paradigm have been developed to recognize the features, and detect resonance shifts in, power spectral density (PSD) data. Our goal is to advance the state of the art in the application of noise analysis techniques to monitor nuclear reactor internals. The initial objectives have been to use PSD data, acquired over a period of about 2 years by PSDREC (power spectral density recognition system), to develop neural networks that are able to differentiate between normal neutron power spectral density data and anomalous spectral data, and detect significant shifts in the positions of spectral resonances while reducing the effect of small shifts. Neural network systems referred to in this paper as spectral feature detectors (SFDs) and integral network filters have been developed to meet these objectives. The performance of the SFDs is the subject of this paper. 2 refs., 2 figs.

• Research Organization: Oak Ridge National Lab., TN (USA)
• Sponsoring Organization: DOE; USDOE, Washington, DC (USA)
• DOE Contract Number: AC05-84OR21400
• OSTI ID: 5906494
• Report Number(s): CONF-910603-7; ON: DE91007676
• Country of Publication: United States
• Language: English

Related Subjects

22 GENERAL STUDIES OF NUCLEAR REACTORS
220100* -- Nuclear Reactor Technology-- Theory & Calculation
99 GENERAL AND MISCELLANEOUS
990200 -- Mathematics & Computers
DATA ANALYSIS
FUNCTIONS
MEASURING INSTRUMENTS
MONITORING
NEURAL NETWORKS
NEUTRON DETECTORS
NEUTRON SPECTRA
NOISE
NUCLEAR FACILITIES
NUCLEAR POWER PLANTS
PERFORMANCE
POWER PLANTS
RADIATION DETECTORS
SPECTRA
SPECTRAL DENSITY
SPECTRAL FUNCTIONS
THERMAL POWER PLANTS