With such advanced technology as machine learning and artificial intelligence, the digital model can be used to conduct simulations, analyze performance problems, and create improvements in the system.
Twins for two reactors: The Argonne researchers reported that they developed and applied a novel methodology to generate digital twins for two nuclear reactors: the old Experimental Breeder Reactor II (EBR-II) and the new generic Fluoride salt–cooled High-temperature Reactor (gFHR). The EBR-II is no longer in operation, but the research team created a digital twin of it to serve as a test case to help validate the simulation models. Case studies with both reactors were used to demonstrate the digital twins’ accuracy in forecasting operational transients.
GNNs and SAM: With the aid of the Argonne Leadership Computing Facility, Hu and his team used a type of AI called graph neural networks (GNNs), computer models that process system components as different types of graph nodes and their physical interconnections as edges. According to Hu and his coauthors, “A graph neural network combining graph convolution and temporal node attention is developed as the DT [digital twin], facilitating a comprehensive understanding of the system’s dynamic behavior.”
“By utilizing the [ANL-developed] System Analysis Module (SAM) code for simulating various operational transients,” the paper states, “we develop a graph-based database that trains the DT. This DT is characterized by two primary functions: It can infer the entire system’s status using sparse node information, and it can predict the progress of transients based on current and historical system information.”
Trained model: According to Argonne, the trained model can make accurate predictions based on limited real-time sensor data. This ability to deliver fast, authentic insights supports better planning for how reactors will respond to changes and better decision-making about their design and operation. It can also help reduce maintenance and operating costs.
A digital twin could also be used to continuously monitor the reactor to detect anomalies. If something seems out of the ordinary, the system can suggest changes to keep the reactor safe or run smoothly.
Many benefits: The new type of digital twin technology may provide more reliable predictions than previous modeling methods, Argonne noted. Such enhanced reliability would have many benefits, including in planning for emergencies, making informed decisions, and operating reactors autonomously.
According to Hu and his research team, the digital twin’s computation capabilities “enhance its potential for supporting advanced reactor operations, offering benefits in intelligent simulation, autonomous control, and anomaly detection, paving the way for improved safety analysis and intelligent component health management for advanced reactor systems and reducing their operations and maintenance cost.”
