Prediction of Critical Heat Flux in Rod Bundles Using Tube-Based Hybrid Machine Learning Models in CTF

TL;DR

This paper explores machine learning models, including hybrid approaches, to accurately predict critical heat flux in rod bundles, demonstrating improved performance over traditional correlations and lookup tables in complex thermal hydraulic scenarios.

Contribution

It extends tube-based ML models to rod bundle geometries, implementing hybrid bias-correction models within the CTF code for enhanced CHF prediction accuracy.

Findings

ML models outperform traditional correlations in accuracy

Hybrid LUT model shows the best predictive performance

All ML approaches improve CHF location and magnitude predictions

Abstract

The prediction of critical heat flux (CHF) using machine learning (ML) approaches has become a highly active research activity in recent years, the goal of which is to build models more accurate than current conventional approaches such as empirical correlations or lookup tables (LUTs). Previous work developed and deployed tube-based pure and hybrid ML models in the CTF subchannel code, however, full-scale reactor core simulations require the use of rod bundle geometries. Unlike isolated subchannels, rod bundles experience complex thermal hydraulic phenomena such as channel crossflow, spacer grid losses, and effects from unheated conductors. This study investigates the generalization of ML-based CHF prediction models in rod bundles after being trained on tube-based CHF data. A purely data-driven DNN and two hybrid bias-correction models were implemented in the CTF subchannel code and used to predict CHF location and magnitude in the Combustion Engineering 5-by-5 bundle CHF test series. The W-3 correlation, Bowring correlation, and Groeneveld LUT were used as baseline comparators. On average, all three ML-based approaches produced magnitude and location predictions more accurate than the baseline models, with the hybrid LUT model exhibiting the most favorable performance metrics.