Modern nuclear facilities, such as reprocessing plants, present inspectors with significant challenges due in part to the sheer amount of equipment that must be safeguarded. The Sandia-developed and patented Knowledge Generation system was designed to automatically analyze large amounts of safeguards data to identify anomalous events of interest by comparing sensor readings with those expected from a process of interest and operator declarations. This paper describes a demonstration of the

more »

... edge Generation system using simulated accountability tank sensor data to represent part of a reprocessing plant. The demonstration indicated that Knowledge Generation has the potential to address several problems critical to the future of safeguards. It could be extended to facilitate remote inspections and trigger random inspections. Knowledge Generation could analyze data to establish trust hierarchies, to facilitate safeguards use of operator-owned sensors. 6 Knowledge Generation has the potential to address several problems critical to the future of safeguards. It could be extended to be a near-real-time tool to facilitate remote inspections and, via remote monitoring, flag anomalies that could trigger random inspections. Further, Knowledge Generation could analyze data to establish trust hierarchies, in which the outputs of authenticated sensors could be used to authenticate data from operator-owned sensors. For example, authenticated accountability tank sensor data could be analyzed for patterns to establish a level of trust of the operator sensors in the surge tank.