Application of neural network and pattern recognition software to the automated analysis of continuous nuclear monitoring of on-load reactors

Conference · Sun Aug 01 04:00:00 EDT 1993

OSTI ID:10179646

Howell, J A; Eccleston, G W; Halbig, J K; Klosterbuer, S F ^[1]; Larson, T W ^[2]

---

1. Los Alamos National Lab., NM (United States)
2. California Polytechnic State Univ., San Luis Obispo, CA (US)

Automated analysis using pattern recognition and neural network software can help interpret data, call attention to potential anomalies, and improve safeguards effectiveness. Automated software analysis, based on pattern recognition and neural networks, was applied to data collected from a radiation core discharge monitor system located adjacent to an on-load reactor core. Unattended radiation sensors continuously collect data to monitor on-line refueling operations in the reactor. The huge volume of data collected from a number of radiation channels makes it difficult for a safeguards inspector to review it all, check for consistency among the measurement channels, and find anomalies. Pattern recognition and neural network software can analyze large volumes of data from continuous, unattended measurements, thereby improving and automating the detection of anomalies. The authors developed a prototype pattern recognition program that determines the reactor power level and identifies the times when fuel bundles are pushed through the core during on-line refueling. Neural network models were also developed to predict fuel bundle burnup to calculate the region on the on-load reactor face from which fuel bundles were discharged based on the radiation signals. In the preliminary data set, which was limited and consisted of four distinct burnup regions, the neural network model correctly predicted the burnup region with an accuracy of 92%.

• Research Organization: Los Alamos National Lab., NM (United States)
• Sponsoring Organization: USDOE, Washington, DC (United States)
• DOE Contract Number: W-7405-ENG-36
• OSTI ID: 10179646
• Report Number(s): LA-UR--93-2537; CONF-930749--48; ON: DE93018371
• Country of Publication: United States
• Language: English

Related Subjects

055002
21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS
210500
98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL PROTECTION
BREEDER REACTORS
DATA ANALYSIS
DATA COVARIANCES
DATA PROCESSING
NEURAL NETWORKS
NONTECHNICAL ASPECTS
NUCLEAR INSTRUMENT MODULES
NUCLEAR MATERIALS MANAGEMENT
PATTERN RECOGNITION
PLUTONIUM
POWER DISTRIBUTION
POWER REACTORS
BREEDING
PROLIFERATION
RADIATION DETECTORS
REACTOR FUELING
SAFEGUARDS
SPENT FUELS