ON/OFF State Classification of a Reactor Facility Using Gas Effluence Measurements

摘要: Inferring the ON/OFF operational state of a reactor facility using measurements from an independent monitoring system is critical to assessment its compliance agreements. We consider problem inferring Ar-41, Cs-138, and Xe-138 gas effluence types collected at facility’s off-gas stack. present classifiers based on thresholding individual types, then fusers that combine their outputs or measurements. five simple majority rule, Chow’s pattern recognition function, Fisher’s combined ${p}$ -value statistic, physics-based Poisson radiation counts model, correlation coefficient (CC) method. In addition, we also test machine learning methods nonlinear classifiers, which are available as R packages. Our results show that: 1) these effective in facility, for example, best achieve ~97% detection ~1% false alarm rate 2) all models, CC, method outperform fusers, methods, well when they applied pairs types.