Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multifidelity Surrogate Modeling of Depressurized Loss of Forced Cooling in High-temperature Gas Reactors

Meredith Eaheart, Majdi I. Radaideh

Abstract

High-fidelity computational fluid dynamics (CFD) simulations are widely used to analyze nuclear reactor transients, but are computationally expensive when exploring large parameter spaces. Multifidelity surrogate models offer an approach to reduce cost by combining information from simulations of varying resolution. In this work, several multifidelity machine learning methods were evaluated for predicting the time to onset of natural circulation (ONC) and the temperature after ONC for a high-temperature gas reactor (HTGR) depressurized loss of forced cooling transient. A CFD model was developed in Ansys Fluent to generate 1000 simulation samples at each fidelity level, with low and medium-fidelity datasets produced by systematically coarsening the high-fidelity mesh. Multiple surrogate approaches were investigated, including multifidelity Gaussian processes and several neural network architectures, and validated on analytical benchmark functions before application to the ONC dataset. The results show that performance depends strongly on the informativeness of the input variables and the relationship between fidelity levels. Models trained using dominant inputs identified through prior sensitivity analysis consistently outperformed models trained on the full input set. The low- and high-fidelity pairing produced stronger performance than configurations involving medium-fidelity data, and two-fidelity configurations generally matched or exceeded three-fidelity counterparts at equivalent computational cost. Among the methods evaluated, multifidelity GP provided the most robust performance across input configurations, achieving excellent metrics for both time to ONC and temperature after ONC, while neural network approaches achieved comparable accuracy with substantially lower training times.

Multifidelity Surrogate Modeling of Depressurized Loss of Forced Cooling in High-temperature Gas Reactors

Abstract

High-fidelity computational fluid dynamics (CFD) simulations are widely used to analyze nuclear reactor transients, but are computationally expensive when exploring large parameter spaces. Multifidelity surrogate models offer an approach to reduce cost by combining information from simulations of varying resolution. In this work, several multifidelity machine learning methods were evaluated for predicting the time to onset of natural circulation (ONC) and the temperature after ONC for a high-temperature gas reactor (HTGR) depressurized loss of forced cooling transient. A CFD model was developed in Ansys Fluent to generate 1000 simulation samples at each fidelity level, with low and medium-fidelity datasets produced by systematically coarsening the high-fidelity mesh. Multiple surrogate approaches were investigated, including multifidelity Gaussian processes and several neural network architectures, and validated on analytical benchmark functions before application to the ONC dataset. The results show that performance depends strongly on the informativeness of the input variables and the relationship between fidelity levels. Models trained using dominant inputs identified through prior sensitivity analysis consistently outperformed models trained on the full input set. The low- and high-fidelity pairing produced stronger performance than configurations involving medium-fidelity data, and two-fidelity configurations generally matched or exceeded three-fidelity counterparts at equivalent computational cost. Among the methods evaluated, multifidelity GP provided the most robust performance across input configurations, achieving excellent metrics for both time to ONC and temperature after ONC, while neural network approaches achieved comparable accuracy with substantially lower training times.
Paper Structure (38 sections, 40 equations, 8 figures, 14 tables)

This paper contains 38 sections, 40 equations, 8 figures, 14 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. CFD Simulation and Data Generation
  4. Ansys Fluent Simulation
  5. Input Parameters and SA/UQ
  6. Fidelity Level Definition
  7. Multi-fidelity Machine Learning Methods
  8. Multi-fidelity Neural Network: Delta Method
  9. Multi-fidelity Neural Network: Flag Method
  10. Multi-fidelity Neural Network: Intermediate Method
  11. Multi-fidelity Neural Network: GPmimic Method
  12. Multi-fidelity Neural Network: Two-Step Method
  13. Multi-fidelity Neural Network: Three-Step Method
  14. Multi-fidelity Gaussian Process (MF-GP)
  15. Three-fidelity extensions
  16. ...and 23 more sections

Figures (8)

  • Figure 1: Computational domains with boundary conditions of the Ansys Fluent simulation
  • Figure 2: Global and local uncertainty quantification reproduced from a previous work eaheart2025sensitivity
  • Figure 3: Comparison of (left) low-fidelity (17.5k elements), (center) medium-fidelity (35k elements), and (right) high-fidelity (70k elements) mesh resolutions defining the fidelity hierarchy.
  • Figure 4: Parity plot comparing predicted and true high-fidelity outputs (top) and residual distribution (bottom) for the Booth (2D) benchmark. Labels: y_pred = predicted value, y_true=ground truth.
  • Figure 5: Parity plot comparing predicted and true high-fidelity outputs (top) and residual distribution (bottom) for the Borehole (8D) benchmark. Labels: y_pred = predicted value, y_true=ground truth
  • ...and 3 more figures