Digital Twin to Detect Nuclear Proliferation: A Case Study

Abstract

This case study describes the development of technologies that enable digital-engineering and digital-twinning efforts in proliferation detection. The project presents a state-of-the-art approach to supporting IAEA safeguards by incorporating diversion-pathway analysis, facility misuse, and detection of indicators within the reactor core, applying the safeguards-by-design concept, and demonstrates its applicability as a sensitive monitoring system for advanced reactors and power plants. There are two pathways a proliferating state might take using the reactor core. One is “diversion,” where special fissionable nuclear material—i.e., Pu-239, U-233, U enriched in U-233/235—that has been declared to the International Atomic Energy Agency (IAEA) is removed surreptitiously, either by taking small amounts of nuclear material over a long time (known as protracted diversion) or large amounts in a short time (known as abrupt diversion). The second pathway is “misuse,” where undeclared source material—material that can be transmuted into special fissionable nuclear material: depleted uranium, natural uranium, and thorium—is placed in the core, where it uses the neutron flux for transmutation. Digital twinning and digital engineering have demonstrated significant performance improvement and schedule reduction in the aerospace, automotive, and construction industries. This integrated modeling approach has not been fully applied to nuclear safeguards programs in the past. Digital twinning, combined with machine learning technologies, can lead to new innovations in process-monitoring detection, specifically in event classification, real-time notification, and data tampering. It represents a technological leap in evaluation and detection capability to safeguard any nuclear facility.

Advanced manufacturing and digital twin technology for nuclear energy*

“…This effort enables more efficient operations, streamlined supply chains, and reduced costs. Moreover, digital twin technology allows for real-time monitoring and analysis of nuclear systems, enabling proactive identification of potential issues, optimization of processes, and continuous improvement (Ritter et al, 2022;Xu et al, 2022).…”

An efficient digital twin based on machine learning SVD autoencoder and generalised latent assimilation for nuclear reactor physics

“…Related works on digital twins in nuclear engineering are recent, for instance, [51,32,65]. For example.…”

“…A more detailed discussion on digital twin concepts with uncertainty for nuclear power applications can be found in [47]. Additionally, the work [65] focuses on the development of technologies that enable digital-twinning efforts in nuclear proliferation detection. The technical reports [59,58] released by Argonne National Lab (ANL) describe the development of a digital twin predictive model for Pressure Water Reactor (PWR) components, in a physics-infused and AI/ML-based framework.…”

An Autonomous Critical Data Extrapolator for the AGN-201m [Slides]

“…al. Idaho State University AGN-201 Low Power Teaching Reactor -An Overlooked GemAGN-201m Reactor Physics Model• Water temperature, FCR, and CCR data is used in Serpent predict K-effective[3].• Surrogate model will constantly in these variables to constantly determine K-effective• First iteration of K-effective must be determined from critical dataCredit: Stewart et al, A digital twin of the AGN-201 reactor to simulate nuclear proliferation Recognizing Reactor Startup • Detect initial increase in slope of power (Super-Critical) • Detect stabilization of slope of power (Critical) • General critical power ~10 mW…”