Predicting Critical Heat Flux with Uncertainty Quantification and Domain Generalization Using Conditional Variational Autoencoders and Deep Neural Networks

2024-09-09

arXiv.org

AI Summary

Addressing challenges in critical heat flux (CHF) prediction for nuclear systems—including data scarcity, difficulty in uncertainty quantification (UQ), and poor generalization across operating conditions—this work proposes a dual-path framework integrating generative modeling and regression learning. Specifically, we introduce the first application of conditional variational autoencoders (CVAEs) to CHF data augmentation and probabilistic uncertainty modeling, coupled with an ensemble of deep neural networks (DNNs) for regression and repeat-sampling-based UQ. The CVAE-generated synthetic data reduces mean relative error and cuts prediction standard deviation by 42%. Subsequent UQ-guided DNN ensemble further improves regression accuracy. Both components demonstrate low prediction errors under out-of-distribution operating conditions, confirming strong generalization capability. This work establishes a novel, interpretable, robust, and generalizable paradigm for small-sample CHF modeling.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Deep generative models (DGMs) have proven to be powerful in generating realistic data samples. Their capability to learn the underlying distribution of a dataset enable them to generate synthetic data samples that closely resemble the original training dataset, thus addressing the challenge of data scarcity. In this work, we investigated the capabilities of DGMs by developing a conditional variational autoencoder (CVAE) model to augment the critical heat flux (CHF) measurement data that was used to generate the 2006 Groeneveld lookup table. To determine how this approach compared to traditional methods, a fine-tuned deep neural network (DNN) regression model was created and evaluated with the same dataset. Both the CVAE and DNN models achieved small mean absolute relative errors, with the CVAE model maintaining more favorable results. To quantify the uncertainty in the model's predictions, uncertainty quantification (UQ) was performed with repeated sampling of the CVAE model and ensembling of the DNN model. Following UQ, the DNN ensemble notably improved performance when compared to the baseline DNN model, while the CVAE model achieved similar results to its non-UQ results. The CVAE model was shown to have significantly less variability and a higher confidence after assessment of the prediction-wise relative standard deviations. Evaluating domain generalization, both models achieved small mean error values when predicting both inside and outside the training domain, with predictions outside the training domain showing slightly larger errors. Overall, the CVAE model was comparable to the DNN regression model in predicting CHF values but with better uncertainty behavior.

Problem

• Predict Critical Heat Flux
• Uncertainty Quantification
• Domain Generalization

Innovation

• CVAE for data augmentation
• DNN for regression analysis
• UQ with repeated CVAE sampling