Search papers, labs, and topics across Lattice.
This paper introduces a neural operator-based surrogate model for computational fluid dynamics (CFD) applied to the helical coil steam generator (HCSG) of a small modular reactor (SMR). The approach combines reduced-order models (ROMs), specifically MLP-based and convolutional autoencoders, with deep operator networks (DeepONet) and Fourier neural operators (FNO) to accelerate transient analysis. Results show that multi-scale L-DeepONet captures instantaneous vortex dynamics, while FNO variants predict time-averaged flow and pressure drop, offering a guideline for model selection based on CFD data type and flow resolution needs.
Neural operators can now provide real-time CFD-level analysis of complex SMR geometries, enabling digital twins for safer and more efficient reactor operation.
Real-time thermal-hydraulic simulation is essential for digital twin (DT) technology that supports the safe and efficient operation of small modular reactors (SMRs). Computational fluid dynamics (CFD) provides high-fidelity flow analysis, but its computational cost prevents direct use in DT applications. AI-based surrogate modeling has been actively investigated to address this limitation, yet neural operator--based surrogates for CFD-level transient analysis of SMR-specific geometries have not been reported. This study presents an integrated framework that combines a reduced-order model (ROM) with neural operators, applied to the helical coil steam generator (HCSG) of the System-integrated Modular Advanced Reactor (SMART). Two ROM strategies tailored to each CFD data type were compared, an MLP-based autoencoder (AE) for unstructured mesh data and a convolutional autoencoder (CAE) for structured mesh data, and each was coupled with the deep operator network (DeepONet) to construct the latent DeepONet (L-DeepONet). The Fourier neural operator (FNO) was additionally adopted for comparison. A multi-scale technique was incorporated into both frameworks to mitigate spectral bias and improve the prediction of K\'{a}rm\'{a}n vortex streets developing inside the HCSG. The multi-scale L-DeepONet captured the instantaneous periodic vortex dynamics in both velocity and pressure fields, while the FNO and its multi-scale variant predicted the time-averaged mean flow and provided reliable pressure drop estimates. These complementary characteristics provide a practical model-selection guideline that links each architecture to specific DT objectives based on CFD data type and the required level of flow resolution.
