Argonne National Laboratory applies transformer technology to speed up nuclear reactor modeling

US lab borrows ChatGPT's transformer tech for nuclear reactor modeling

Researchers at the U.S. Department of Energy's Argonne National Laboratory are using transformer-based models to speed up simulations of fluid dynamics in advanced nuclear reactors, potentially helping engineers study reactor safety and performance faster. Transformers are the neural network architecture behind many generative AI systems, but Argonne researchers are adapting the technology for a different task: modeling how fluids move and transfer heat inside nuclear power systems. The team is integrating transformer architectures into Argonne's System Analysis Module (SAM), a simulation tool used to study advanced nuclear reactors. The goal is to improve turbulence modeling, which helps researchers predict complex fluid behavior and its effects on reactor systems. By combining transformer-based models with turbulence simulations, the researchers aim to produce results that are both faster and more accurate than conventional approaches. The work could eventually allow engineers to model entire nuclear power plants, including reactors, cooling systems and other supporting infrastructure. In nuclear reactors, understanding fluid movement is critical because fluids transport heat and interact with components throughout the plant. Turbulence modeling helps researchers predict these complex flows, but detailed simulations can require significant computing resources. Argonne's transformer-based approach analyzes relationships between physical data points, including locations, velocities, and fluid flows. The model has already demonstrated high accuracy in representing resistance to fluid flow and heat transfer, two properties that are important for reliable turbulence simulations. "With AI, we can be as accurate as the complex methods and as fast as the simple methods," said Rui Hu, principle nuclear engineer and manager of the Safety and Engineering Analysis Department in Argonne's Nuclear Science and Engineering Division (NSED). "It is a union of accuracy and speed." According to Argonne, AI-based models can produce simulation results almost instantaneously while maintaining the accuracy associated with more complex computational methods. That could allow researchers to run more realistic simulations without the same time and computing demands. The improved modeling could support work on reactor design, performance and safety. It could also help engineers evaluate how changes in fluid behavior affect the wider nuclear system. The researchers' next step is to apply the model to simulations of entire power plants. These could include the reactor itself as well as cooling, safety, auxiliary, and other supporting systems. The team is also exploring digital twins, virtual representations of physical systems that can operate and update in real time. Argonne researchers say they are among the first to explore transformer architectures for digital twin technology in nuclear systems. Digital twins could eventually allow engineers to monitor and simulate nuclear facilities while incorporating real-time information from physical systems. Combined with faster simulation models, the technology could provide another tool for studying plant performance and identifying potential issues. Future work will focus on expanding the transformer-based models, improving their accuracy and flexibility, and integrating new AI-enabled capabilities into SAM's simulation workflow. The project is supported by the U.S. Department of Energy's Nuclear Energy Advanced Modeling and Simulation (NEAMS) Program.

AI Transformers Improve Nuclear Reactor Simulations

Turbulent viscosity fields predicted by data-driven model and two standard approaches (k-omega SST and k-epsilon). Newswise -- If you've used a large language model such as ChatGPT, you've interacted with a transformer, the neural network architecture that powers many generative artificial intelligence (AI) models. Researchers at the U.S. Department of Energy's (DOE) Argonne National Laboratory are adapting this architecture to model complex physical systems. They're using AI transformers to accelerate and improve fluid-dynamics simulations for advanced nuclear reactors. Better simulations strengthen nuclear energy systems, keeping them safe and efficient. In large language models, transformers analyze relationships among words and sentences. Argonne's approach applies the same underlying concept to physical data, such as locations, velocities and how fluids flow within a nuclear power plant. This helps AI find important physical relationships that affect reactor safety and performance. Predicting the effects of fluid flows is called turbulence modeling. Researchers at Argonne are adding transformer architectures into the System Analysis Module (SAM). SAM is a tool developed at Argonne for studying advanced nuclear reactors. By combining transformer-based AI with turbulence modeling, the team aims to improve SAM's ability to show complex fluid-dynamic behavior. Traditional codes often struggle to capture these behaviors. "With AI, we can be as accurate as the complex methods and as fast as the simple methods," said Rui Hu, principle nuclear engineer and manager of the Safety and Engineering Analysis group in Argonne's Nuclear Science and Engineering (NSE) division. "It is a union of accuracy and speed." Traditional high-fidelity simulations can be slow. They might take minutes or hours for each calculation. On the other hand, faster, simpler approaches can be inaccurate. AI-based models can deliver results almost instantaneously while keeping the accuracy of more complex methods. The new Argonne model in SAM has demonstrated high accuracy in representing the resistance of fluid to flow and how heat moves through it. The ability to capture these features is key to reliable turbulence modeling. This advancement lets researchers conduct more realistic simulations. These can help improve reactor design, performance and safety. Next, the team plans to use the model to simulate entire power plants, including reactors, supporting components, and cooling, safety and auxiliary systems. "Since we demonstrated that the architecture could show relationships between physical processes, it can be applied to other types of physics beyond fluid dynamics," said Eric Cervi, principal nuclear engineer in the NSE. The team is also exploring the use of digital twins, or virtual models of physical systems operating in real time. They are among the first to apply transformer architectures to digital twin technology for nuclear systems. Future research will focus on expanding these models, improving their accuracy and flexibility, and integrating new AI-enabled models into SAM's simulation workflow. By using advanced AI, Argonne is driving faster, more accurate simulations that support the safe and efficient operation of nuclear energy systems. This work is supported by the DOE's Nuclear Energy Advanced Modeling and Simulation (NEAMS) Program. Argonne National Laboratory seeks solutions to pressing national problems in science and technology by conducting leading-edge basic and applied research in virtually every scientific discipline. Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy's Office of Science. The U.S. Department of Energy's Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit https://energy.gov/science.