Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Predicting critical heat flux with uncertainty quantification and domain generalization using conditional variational autoencoders and deep neural networks

Journal Article · · Annals of Nuclear Energy

Deep generative models (DGMs) can generate synthetic data samples that closely resemble the original dataset, addressing data scarcity. In this work, we developed a conditional variational autoencoder (CVAE) to augment critical heat flux (CHF) data used for the 2006 Groeneveld lookup table. To compare with traditional methods, a fine-tuned deep neural network (DNN) regression model was evaluated on the same dataset. Both models achieved small mean absolute relative errors, with the CVAE showing more favorable results. Uncertainty quantification (UQ) was performed using repeated CVAE sampling and DNN ensembling. The DNN ensemble improved performance over the baseline, while the CVAE maintained consistent results with less variability and higher confidence. Both models achieved small errors inside and outside the training domain, with slightly larger errors outside. Altogether, the CVAE performed better than the DNN in predicting CHF and exhibited better uncertainty behavior.

Research Organization:
North Carolina State University, Raleigh, NC (United States)
Sponsoring Organization:
USDOE Office of Nuclear Energy (NE)
Grant/Contract Number:
NE0009467
OSTI ID:
2563800
Alternate ID(s):
OSTI ID: 2562975
Journal Information:
Annals of Nuclear Energy, Journal Name: Annals of Nuclear Energy Vol. 220; ISSN 0306-4549
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (19)

An introduction to deep generative modeling journal May 2021
A survey of uncertainty in deep neural networks journal July 2023
A correction method for heated length effect in critical heat flux prediction journal June 2000
On the prediction of critical heat flux using a physics-informed machine learning-aided framework journal January 2020
Fault detection and diagnosis of energy system based on deep learning image recognition model under the condition of imbalanced samples journal February 2024
Developing semi-supervised latent dynamic variational autoencoders to enhance prediction performance of product quality journal January 2023
Application of generative deep learning to predict temperature, flow and species distributions using simulation data of a methane combustor journal December 2020
Neural network based correlation for critical heat flux in steam-water flows in pipes journal December 2009
Imbalanced data fault diagnosis method for nuclear power plants based on convolutional variational autoencoding Wasserstein generative adversarial network and random forest journal December 2024
Critical heat flux prediction by using radial basis function and multilayer perceptron neural networks: A comparison study journal February 2007
The 2006 CHF look-up table journal September 2007
Deep generative modeling-based data augmentation with demonstration using the BFBT benchmark void fraction datasets journal December 2023
Variational autoencoders and transformers for multivariate time-series generative modeling and forecasting: Applications to vortex-induced vibrations journal October 2024
Deep learning journal May 2015
Semi-conditional variational auto-encoder for flow reconstruction and uncertainty quantification from limited observations journal January 2021
Variational Inference: A Review for Statisticians journal July 2016
Intrusion Detection System After Data Augmentation Schemes Based on the VAE and CVAE journal June 2022
Learning Deep Generative Models journal April 2015
Variational Autoencoders for Data Augmentation in Clinical Studies journal July 2023