Aggregation of Published Non-Uniform Axial Power Data for Phase II of the OECD/NEA AI/ML Critical Heat Flux Benchmark
This study addresses the need for accurate CHF predictions under spatially varying power profiles in light-water reactors, which is crucial for safe reactor design and operation, though it is incremental as it focuses on data preparation and baseline modeling for an existing benchmark.
This work compiled and digitized a broad dataset of critical heat flux (CHF) data, including both uniform and non-uniform axial heating conditions, to support Phase II of the OECD/NEA AI/ML CHF benchmark, revealing that classical correlations and neural networks trained on uniform data fail to generalize to non-uniform scenarios.
Critical heat flux (CHF) marks the onset of boiling crisis in light-water reactors, defining safe thermal-hydraulic operating limits. To support Phase II of the OECD/NEA AI/ML CHF benchmark, which introduces spatially varying power profiles, this work compiles and digitizes a broad CHF dataset covering both uniform and non-uniform axial heating conditions. Heating profiles were extracted from technical reports, interpolated onto a consistent axial mesh, validated via energy-balance checks, and encoded in machine-readable formats for benchmark compatibility. Classical CHF correlations exhibit substantial errors under uniform heating and degrade markedly when applied to non-uniform profiles, while modern tabular methods offer improved but still imperfect predictions. A neural network trained solely on uniform data performs well in that regime but fails to generalize to spatially varying scenarios, underscoring the need for models that explicitly incorporate axial power distributions. By providing these curated datasets and baseline modeling results, this study lays the groundwork for advanced transfer-learning strategies, rigorous uncertainty quantification, and design-optimization efforts in the next phase of the CHF benchmark.