Skip to main content
Dryad

Data for: A temporal–spatial framework for efficient heat flux monitoring of transient boiling

Dunlap, Christy1; Li, Changgen1; Pandey, Hari1; Sun, Ying2; Hu, Han1

Published Jun 23, 2025 on Dryad. https://doi.org/10.5061/dryad.6m905qgc7

Data files

Jun 23, 2025 version files 4.51 GB

Abstract

Two-phase cooling offers superior heat dissipation compared to conventional single-phase cooling methods. Nevertheless, the occurrence of critical heat flux (CHF) during boiling introduces reliability concerns, potentially leading to system failure. To improve system reliability, optical imaging is employed to analyze and monitor cooling systems without disrupting the boiling dynamics. These methods involve analyzing images of the boiling process to identify boiling regimes and evaluate heat flux. However, current optical-based methods are limited to static images, thereby missing out on the valuable temporal information captured by high-speed imaging. Inspired by the successful integration of temporal information in other fields, this work aims to exploit the temporal information from transient pool boiling captured via high-speed imaging for enhanced heat flux monitoring. For this purpose, two frameworks, comprising six different machine-learning models, have been developed for a comparative analysis. Specifically, the first framework includes two models that use static images for monitoring, serving as a representation of existing methodologies and a benchmark against which the second framework is measured. The remaining four models within the dynamic image-based framework (the 2nd framework) leverage sequences of images to capture temporal information. To evaluate the advantage of incorporating temporal information, transient boiling experiments were conducted to construct the dataset. A comparative analysis confirmed that temporal information significantly enhances the accuracy of the developed heat flux monitoring models. Among these models, the developed principal components (PCs)-convolutional neural network (CNN) stands out with a superior determination coefficient of 97.4% and a mean absolute percentage error of 7.0%, achieving an excellent balance between monitoring accuracy and computational efficiency.