<p>Understanding bubble dynamics during boiling is crucial to the design of surface enhancements for improved heat transfer. The stochastic nature of bubble nucleation, growth, and coalescence processes makes it challenging to obtain mechanistic models that can predict boiling heat flux based on the bubble dynamics. However, the bubbles generated are likely to encode important information about the boiling performance of a surface. Traditional boiling image analysis is typically limited to the extraction of simple physical quantities and dimensions, such as the vapor fraction or bubble sizes. Recently, machine-learning-aided analysis has shown promise in extracting richer information, such as in boiling crisis detection, heat flux prediction, and real-time image analysis. &nbsp;Most of these previous studies, however, have focused on analyzing static boiling images, failing to leverage the dynamic behaviors of the bubbles while gathering information. In the present work, a convolutional long short-term memory (ConvLSTM) model is developed to enable quantitative prediction of heat flux based on temporal sequences of boiling images, where the convolutional layers are used to extract the features of the boiling images and the LSTM layers to identify the temporal features of the sequences. A convolutional neural network (CNN) model based on the classification of static images is also developed as a benchmark. Both models are trained using image data obtained from high-speed visualization of HFE-7100 pool boiling on silicon micropillar arrays at different steady-state heat fluxes. The ConvLSTM model leads to improved accuracies in heat flux predictions compared to the CNN model for both seen and unseen data, indicating a higher level of generality. The present work demonstrates the advantages of sequence-based predictions over static-image-based predictions for heat flux quantification.</p>

Boiling Heat Flux Prediction Using a Convolutional Long Short-Term Memory (Convlstm) Model Trained on Image Sequences

Paper Proceedings: https://asmedigitalcollection.asme.org/InterPACK/InterPACK2021/volume/85505

ASME 2021 International Electronic Packaging Technical Conference and Exhibition (InterPACK2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.