There is increasing demand for sustainable electricity across the world and scientists are focusing on the development of very small nuclear reactors. These are called microreactors (MR). To make these reactors safer, researchers have turned to a new technology powered by AI that can detect potential hazards in these reactors in seconds.
This technology is referred to as smart component systems and it can provide remote surveillance of MR. Developed by researchers at the Ulsan National Institute of Science and Technology (UNIST) in South Korea, the system includes embedded optical fiber sensors to monitor components in the reactor and send alerts during abnormal conditions.
The UNIST breakthrough involves a novel technology that combines 3D printing with AI, allowing the rapid processing of multiple continuous variables from optical fiber sensors. The team successfully manufactured smart nuclear parts using a Directed Energy Deposition (DED) printing method. They seamlessly integrated fiber optic sensors within the metal components.
MR designs vary, but most of them would be able to produce one to twenty megawatts of thermal energy that could be used directly as heat or converted to electric power. They can be used to generate clean and reliable electricity for commercial use. They could also be used for non-electric applications such as district heating, water desalination and hydrogen fuel production. These MRs are compact enough to be transported by truck and could help solve energy challenges in a number of areas.
Most MR designs will require nuclear fuel with a higher concentration of uranium-235 than is currently used in today’s full-sized reactors. However, some MRs may benefit from the use of high temperature moderating materials that would reduce fuel enrichment requirements while maintaining the small system size.
The recent study proposes a novel DED approach to incorporate an optical fiber sensor into MR components, enabling real-time monitoring with artificial intelligence.
Researchers conducting the study said, “The embedded optical fiber generates real-time data that allows for AI-driven in-vivo thermal deformation analysis. Our smart MR component can detect structural anomalies, identify abnormal operations, and assess operational conditions through augmented reality interfaces and AI technology.”
Im Doo Jung is a Professor from the Department of Mechanical Engineering, UNIST. He stated that researchers tackled the challenges associated with traditional inspection methods through AI convergence technology. This can greatly enhance the stable and efficient operation of next-generation small nuclear power plants.
Jung continued, “This convergence technology could extend its applications beyond nuclear power, potentially benefiting diverse industries such as autonomous manufacturing systems, aerospace, and advanced defense. We introduced a novel method for producing smart micro reactor components by embedding optical fiber sensors during the DED process. This method includes an optimized DED process for metal components of MR systems.”
Researchers emphasized that the proposed process, involving sensor embedding within metal components, could be applied to create smart metal components with various sensors with the DED process.
This research will also allow expanded applications in a variety of industries and research fields which require digitalization and AI within additively manufactured component.