Application of neural network and pattern recognition software to the automated analysis of continuous nuclear monitoring of on-load reactors
- Los Alamos National Lab., NM (United States)
- California Polytechnic State Univ., San Luis Obispo, CA (United States)
Operators of on-load nuclear reactors may remotely obtain access to the core from both ends, and the reactors can be continuously fueled without shutting them down. Such an operation offers a fuel management advantage, but a safeguards challenge, because it provides a greater opportunity for the diversion of nuclear material. 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 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%.
- OSTI ID:
- 61449
- Report Number(s):
- CONF-930749-; TRN: IM9526%%231
- Resource Relation:
- Conference: 34. annual meeting of the Institute of Nuclear Materials Management, Scottsdale, AZ (United States), 18-21 Jul 1993; Other Information: PBD: 1993; Related Information: Is Part Of Nuclear materials management. 34th Annual meeting proceedings: Volume 22; PB: 1190 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Automated software analysis of nuclear core discharge data
Automated software analysis of nuclear core discharge data