High-fidelity Modeling of Full-scale Pressurized Water Reactor Flow Fields for Machine Learning Applications
arXiv:2605.24763v1 Announce Type: new Abstract: This work presents a high-fidelity computational fluid dynamics (CFD) and data-driven modeling framework for assembly-level flow characterization in a four-loop pressurized water reactor (PWR). A full lower-plenum and core-inlet domain was constructed using publicly available geometry and operating conditions, enabling transient simulations with pump-induced swirl boundary conditions. The results show that cold-leg swirl and lower-plenum transport generate strongly heterogeneous assembly-wise inlet flow distributions, particularly near the lower
The increasing maturity of AI and computational fluid dynamics allows for high-fidelity modeling of complex systems like nuclear reactors, which was previously computationally prohibitive.
Accurate modeling of nuclear reactor flow fields can significantly improve safety, efficiency, and design of pressurized water reactors, critically impacting energy production and the broader nuclear sector.
The ability to model critical nuclear components with high fidelity using AI opens new pathways for operational optimization, predictive maintenance, and next-generation reactor design that were not feasible through traditional methods.
- · Nuclear energy sector
- · AI/ML for scientific computing
- · Computational fluid dynamics engineers
- · Energy reliability
- · Traditional, less data-driven reactor design methodologies
Improved safety and more efficient operation of existing nuclear power plants.
Accelerated development and deployment of advanced modular reactors due to enhanced design and simulation capabilities.
Reduced reliance on fossil fuels as nuclear power becomes more economically competitive and easier to license.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG