Physics-based parameters selection and machine learning driven prediction of pool boiling bubble departure diameter

To predict the bubble departure diameter in pool boiling heat transfer, this study proposes a deep-learning neural network based on physical input parameters from the existing bubble departure diameter predicting correlations and Pearson correlation for a variety of working fluids, engineered surfaces, and materials subjected to different pool boiling testing conditions. This work analyzes nearly 5,000 data points (from the literature) of bubble departure diameters ranging from 0.2-28.7 mm using neural network by incorporating the impactful input parameters such as saturation temperature, pressure, contact angle, surface roughness, surface tension, liquid density, vapor density, wall superheat, and heat flux, and other thermophysical properties, predicting their impact on the bubble departure diameter, and also uses them for training neural networks. The best neural network designated as Case-4, selected on the basis of coefficient of determination (R2), mean absolute error (MAE), and mean-square error (MSE) was used to understand the degree of influence of each input parameter and it was found that surface inclination (theta) and heat flux (Q) have the highest impact on the model. A comparison was also done to the existing correlations and it was found that neural networks have much better efficiency and accuracy than the empirical correlations for the considered data range and thus can be an essential tool to predict the bubble diameter.