Predicting The Power Level Of A Nuclear Reactor Using A Time Series-based Approach

Detecting the power level of a nuclear reactor and in turn verifying that it is operating at the declared power level is a problem of interest for the nuclear nonproliferation community. We use data collected from multiple sensor modalities (seismic, acoustic, radiation, current clamps, power ground lines, and ventilation flow rates) positioned near a collocated research nuclear reactor and reprocessing facility at Oak Ridge National Laboratory for the Multi-Informatics for Nuclear Operations Scenarios (MINOS) venture. Naïve Bayes, a classification method which is robust against missing data, has demonstrated greater predictability than random forest for the power level of a reactor. However, this classification method assumes samples are independent, which has been found prone to rapid variations and difficulties in predicting short-term power holds. Realistically, there is temporal dependency in the reactor power, i.e., reactor power cannot change by a large amount in a short period and the reactor is more likely to stay at the previous power level. In this paper, we augment the Naïve Bayes classifier to take into account this temporal dependency using a time series-based approach. In addition, some sensor modalities are sensitive to environmental changes, e.g., seismic and acoustic sensors are sensitive to changes in temperature and radiation measurements are affected by wind speed and direction. Thus, we also incorporate environmental factors through conditional distributions into the model.