AI transformers improve nuclear reactor simulations

[Marlin]

AI transformers improve nuclear reactor simulations

https://www.anl.gov/article/ai-transformers-improve-nuclear-reactor-simulations

[Core Content]

Argonne National Laboratory researchers are integrating transformer-based artificial intelligence into the System Analysis Module to enhance fluid-dynamics simulations for advanced reactors. This architecture allows for near-instantaneous modeling of turbulence and heat transfer with the accuracy of traditional, slower computational methods. The project aims to improve reactor design and safety by enabling more realistic simulations of entire power plant systems.

In large language models, transformers analyze relationships among words and sentences. Researchers at Argonne National Laboratory are applying the same underlying concept to physical data, helping them model complex physical systems such as advanced nuclear reactors.

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.

Read the full article at anl.gov:
https://www.anl.gov/article/ai-transformers-improve-nuclear-reactor-simulations