International safeguards currently rely on material accountancy to verify that declared nuclear material is present and unmodified. Although effective, material accountancy for large bulk facilities can be expensive to implement due to the high precision instrumentation required to meet regulatory targets. Process monitoring has long been considered to improve material accountancy. However, effective integration of process monitoring has been met with mixed results. Given the large successes in other domains, machine learning may present a solution for process monitoring integration. Past work has shown that unsupervised approaches struggle due to measurement error. Although not studied in depth for a safeguards context, supervised approaches often have poor generalization for unseen classes of data (e.g., unseen material loss patterns). This work shows that engineered datasets, when used for training, can improve the generalization of supervised approaches. Further, the underlying models needed to generate these datasets need only accurately model certain high importance features.
Sandia National Laboratories (SNL) is designing and developing an Artificial Intelligence (AI)-enabled smart digital assistant (SDA), Inspecta (International Nuclear Safeguards Personal Examination and Containment Tracking Assistant). The goal is to provide inspectors an in-field digital assistant that can perform tasks identified as tedious, challenging, or prone to human error. During 2021, we defined the requirements for Inspecta based on reviews of International Atomic Energy Agency (IAEA) publications and interviews with former IAEA inspectors. We then mapped the requirements to current commercial or open-source technical capabilities to provide a development path for an initial Inspecta prototype while highlighting potential research and development tasks. We selected a highimpact inspection task that could be performed by an early Inspecta prototype and are developing the initial architecture, including hardware platform. This paper describes the methodology for selecting an initial task scenario, the first set of Inspecta skills needed to assist with that task scenario and finally the design and development of Inspecta’s architecture and platform.
Advances on differentiating between malicious intent and natural "organizational evolution"to explain observed anomalies in operational workplace patterns suggest benefit from evaluating collective behaviors observed in the facilities to improve insider threat detection and mitigation (ITDM). Advances in artificial neural networks (ANN) provide more robust pathways for capturing, analyzing, and collating disparate data signals into quantitative descriptions of operational workplace patterns. In response, a joint study by Sandia National Laboratories and the University of Texas at Austin explored the effectiveness of commercial artificial neural network (ANN) software to improve ITDM. This research demonstrates the benefit of learning patterns of organizational behaviors, detecting off-normal (or anomalous) deviations from these patterns, and alerting when certain types, frequencies, or quantities of deviations emerge for improving ITDM. Evaluating nearly 33,000 access control data points and over 1,600 intrusion sensor data points collected over a nearly twelve-month period, this study's results demonstrated the ANN could recognize operational patterns at the Nuclear Engineering Teaching Laboratory (NETL) and detect off-normal behaviors - suggesting that ANNs can be used to support a data-analytic approach to ITDM. Several representative experiments were conducted to further evaluate these conclusions, with the resultant insights supporting collective behavior-based analytical approaches to quantitatively describe insider threat detection and mitigation.
Renewed interest in the development of molten salt reactors has created the need for analytical tools that can perform safeguards assessments on these advanced reactors. This work outlines a flexible framework to perform safeguards analyses on a wide range of advanced reactor designs. The framework consists of two parts, a process model and a safeguards tool. The process model, developed in MATLAB Simulink, simulates the flow materials through a reactor facility. These models are linked to SCALE/TRITON and SCALE/ORIGEN to approximate depletion and decay of fuel salts but are flexible enough to accommodate higher fidelity tools if needed. The safeguards tool uses the process data to calculate common statistical quantities of interest such as material unaccounted for (MUF) and Page's trend test on the standardized independent transformed MUF (SITMUF). This paper documents the development of these tools.
This work describes the ongoing work to develop a molten salt reactor (MSR) model and associated tools for safeguards analysis. A new flowsheet was developed in collaboration with Oak Ridge National Laboratory (ORNL) for the Molten Salt Demonstration Reactor (MSDR). This design was chosen by ORNL as a generic baseline design that could be used for safeguards research. The model has simple chemical processing that is less extensive than the two-fluid flowsheet developed in the last year. A detailed TRITON reactor physics model, provided by ORNL, was implemented into the process model. The process model now includes reactor parameters such as K-eff and decay heat, which could be used as part of an advanced safeguards approach. Finally, a set of generic safeguards tools based on current safeguards approaches were developed. These tools are flexible and can be used with most MSR flowsheets. ACKNOWLEDGEMENTS This work was funded by the Materials Protection Accounting and Control Technologies (MPACT) working group as part of the Fuel Cycle Technologies Program under the U.S. Department of Energy, Office of Nuclear Energy. The authors would also like to acknowledge Ben Betz ler for his work on the reactor physics models that were incorporated into the work and the continued collaboration with ORNL staff.