An official website of the United States government
ABSTRACT For droplet vaporization on a superheated hydrophilic surface, earlier studies have demonstrated that use of machine learning tools to analyze both image information from high-speed video and digital data from sensors can be an effective path to understanding the physics and developing a useful model to predict performance when the surface superheat is at low to moderate levels. For such conditions, the two-phase morphology of the system is usually well-behaved, exhibiting conduction-dominated film evaporation of the spread droplet, or nucleate boiling at active nucleation sites in the liquid film of the spread droplet. At higher surface superheat levels, experiments have shown that the droplet vaporization process becomes chaotic, with the process alternating between rapid vaporization of liquid in contact with the surface and ejection of liquid off the surface by strong vapor recoil forces. For our experiments with water droplets at atmospheric pressure, this regime corresponds to superheat levels ranging from about 35 to 55 deg. C. At the low superheat end of this regime, extremely high mean heat flux levels are achieved, but as superheat further increases, less of the surface stays wetted due to the increasing vapor recoil forces, and heat flux begins to decrease as the boiling process becomes like transition pool boiling with progressively less of the surface in contact with liquid. This exploration of the use of a specialized convolution neural network (CNN) to simultaneously analyze high speed video images and digital data for this high-superheat, near-critical-heat-flux regime of droplet vaporization is of special interest for two reasons. First, this vaporization regime results in high heat flux levels that make it attractive for high heat flux cooling for high-powered electronics. Use of machine learning tools to learn more about the mechanisms of this vaporization regime may open the door to new high flux thermal management technologies. In addition, because of its complexity, the two-phase morphology of the vaporization process in this regime is expected to be a very challenging task for CNN machine learning tools. In this study we conducted deposited water droplet spreading and vaporization experiments that captured digital data input (measured surface superheat, mean heat flux during the vaporization process, wetting contact angle, droplet size, etc.) and images of the droplet vaporization two-phase morphology from high-speed video during each experiment. This paper summarizes our successful development of a specialized hybrid CNN design that is trained using the combination of digital measurements and images obtained in our experiments. This CNN design provides deep insight into correlation between the two-phase morphology and heat transfer performance for this near critical heat flux vaporization regime. It also provides a pathway to a heat transfer performance model that fits the performance data to a high level of agreement. Using data collected from the droplet deposition experiment, this network design has been trained to predict the mean heat flux with a root mean square percent error of only about 2.0% and 8.0% on a training and testing dataset respectively. The hybrid network developed in this research appears to be a promising strategy for analyzing experimental data for physical systems with complex morphology that are best investigated experimentally with a combined use of imaging and digital sensor instrumentation.
more »
« less
This content will become publicly available on November 1, 2026
A Convolution Neural Network Design for Combined Image and Sensor Data Analysis to Determine Droplet Vaporization Regime and Heat Transfer Performance
Abstract Combining high-speed video cameras and optical measurement techniques with digital sensors controlled by a data acquisition system can provide an effective means of exploring boiling process thermophysics and heat transfer mechanisms. Imaging can provide qualitative and quantitative information that complements data provided by temperature, pressure, and other sensors. This paper summarizes the results of an exploration of machine learning strategies to optimally combine and analyze boiling process images and digital sensor information from experiments. We specifically sought a convolution neural network (CNN) to analyze the vaporization of deposited water droplets on superheated surfaces that may have varying degrees of nucleate boiling effects. Two specialized CNN models were developed in this study that can simultaneously analyze both image and digital data. One of our CNN model designs (case B) was trained to take an image of the vaporization process and nonthermal digital data as input and predict thermal heat transfer performance. This model predicts performance remarkably well given its nonthermal inputs, matching independent heat flux test data to a root-mean-square percent error (RMSPE) of 10.3%. This model appears to learn how the variations of nucleate boiling, vapor recoil activity, and local dryout over the surface vary with surface temperature and/or heat flux from changes in boiling system images. We also describe a CNN model (case C) that takes digital nonthermal data, digital thermal data, and image information and provides a high-fidelity prediction of vaporization heat transfer performance. This model predicted performance very well—better than our conventional fit to data (case A) and on par with best fits to quality nucleate boiling heat transfer data in the literature. This type of trained model fit independent heat flux test data to an RMSPE of 5.8%. Our results indicate that training this type of model which predicts performance from input image information and digital operating condition thermal data makes the resulting predictive model more accurate and robust. The successful use of the hybrid CNN models described here suggests that there is a strong correlation between two-phase morphology variations and changes in heat transfer performance. The hybrid CNN modeling approach developed in this research appears to be a promising strategy for analyzing experimental data for physical systems that are best investigated experimentally with combined use of imaging and digital sensor instrumentation. Possible use of this type of modeling in other systems is also discussed.
more »
« less
- Award ID(s):
- 2228373
- PAR ID:
- 10656805
- Publisher / Repository:
- ASME
- Date Published:
- Journal Name:
- ASME Journal of Heat and Mass Transfer
- Volume:
- 147
- Issue:
- 11
- ISSN:
- 2832-8450
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Combining high-speed video cameras and optimal measurement techniques with digital sensors controlled by a data acquisition system can yield a combination of experimental tools to explore boiling process thermophysics and heat transfer mechanisms. Imaging can provide qualitative and quantitative information that complements data provided by temperature, pressure, and more sensors. This paper summarizes the results of an exploration of machine learning strategies to optimally combine and analyze boiling process images and digital sensor information from experiments. We specifically sought a convolution neural network to analyze the vaporization of deposited water droplets on superheated surfaces that may have varying degrees of nucleate boiling effects. Through experimentation, we found that a hybrid parallel-series convolution/neuron neural network design worked very effectively. The network could extract the regime of droplet vaporization (conduction driven only, conduction plus nucleate boiling, or explosive boiling), the liquid morphology, and could predict the vaporization regime, the wall superheat, and mean heat transfer rate as a function of image input and operating system parameters. Using data collected from the droplet deposition experiment, this network design has been trained to predict the mean heat transfer rate with a root mean square percent error (RMSPE) of only 3.3% and 7.2% on a training and testing dataset respectively. The hybrid network developed in this research appears to be a promising strategy for analyzing experimental data for physical systems that are best investigated experimentally with a combined use of imaging and digital sensor instrumentation.more » « less
-
Combining high-speed video cameras and optimal measurement techniques with digital sensors controlled by a data acquisition system can yield a combination of experimental tools to explore boiling process thermophysics and heat transfer mechanisms. Imaging can provide qualitative and quantitative information that complements data provided by temperature, pressure, and more sensors. This paper summarizes the results of an exploration of machine learning strategies to optimally combine and analyze boiling process images and digital sensor information from experiments. We specifically sought a convolution neural network to analyze the vaporization of deposited water droplets on superheated surfaces that may have varying degrees of nucleate boiling effects. Through experimentation, we found that a hybrid parallel-series convolution/neuron neural network design worked very effectively. The network could extract the regime of droplet vaporization (conduction driven only, conduction plus nucleate boiling, or explosive boiling), the liquid morphology, and could predict the vaporization regime, the wall superheat, and mean heat transfer rate as a function of image input and operating system parameters. Using data collected from the droplet deposition experiment, this network design has been trained to predict the mean heat transfer rate with a root mean square percent error (RMSPE) of only 3.3% and 7.2% on a training and testing dataset respectively. The hybrid network developed in this research appears to be a promising strategy for analyzing experimental data for physical systems that are best investigated experimentally with a combined use of imaging and digital sensor instrumentation.more » « less
-
Abstract Nanostructured hydrophilic surfaces can enhance boiling processes due to the liquid wicking effect of the small surface structures. However, consistently uniform nanoscale interstitial spaces would require high superheat to initiate heterogeneous nucleation in the available small cavity spaces. Experimental studies indicate that surfaces of this type initiate onset of nucleate boiling at relatively low superheat levels, implying that significantly larger interstitial spaces exist, apparently as a consequence of the fabrication process. To explore the correlation between nanostructured surface morphology variations and variation of nucleation behavior with superheat, in this study, a zinc oxide nanostructured coating was fabricated on various copper substrates for wetting and droplet vaporization heat transfer experiments and morphology analysis. Our experiments determined the variation of mean droplet heat flux with superheat, and high-speed videos documented how nucleation features varied with superheat. Image analysis of the electron microscopy images was used to assess the variability of pore size and surface complexity (entropy) over the surface. Our data demonstrates the correlation between surface morphology feature distributions and the variation of nucleate boiling active site density with superheat. Specifically, our results indicate that increased availability of larger-scale surface irregularities with low surface entropy corresponds to enhanced probability of nucleation onset and an increase in active nucleation site density as superheat increases. This information can help guide development of enhanced boiling surfaces by providing insight into the nanosurface feature density distributions that enhance nucleation onset while also providing enhanced wicking and low contact angle over most of the surface.more » « less
-
Nanostructured hydrophilic surfaces can enhance boiling processes due to the liquid wicking effect of the small surface structures, but consistently uniform nanoscale interstitial spaces would provide very few heterogeneous nucleation sites, which would require high superheat to activate in, for example, liquid water. Experiments indicate that surfaces of this type initiate onset of nucleate boiling at relatively low superheat levels, implying that larger-than-average interstitial spaces exist, apparently as a consequence of larger micron-scale variations of the surface structure or surface chemistry (wetting) resulting from the fabrication process. The investigation summarized here explores the potential correlation between nanostructured surface morphology variations and onset of nucleation. A zinc oxide nanostructured coating was fabricated on a copper substrate for experiments and analysis in this study. The coated surface was subjected to water droplet deposition tests to evaluate wicking and contact angle, followed by vaporization tests at varying surface superheat levels, and extensive electron microscopy imaging of the surface. The results of the vaporization experiments determined the variation of mean heat flux to the droplet as a function of superheat, and high-speed videos documented the superheat at which onset of nucleate boiling (ONB) occurs and variation of nucleation site density with superheat. Image analysis of the electron microscopy images were used to assess the variability of pore size and surface complexity (entropy) over the surface. By determining macroscope bubble nucleation and boiling performance from measured data and high-speed video records for these surfaces, and simultaneously analyzing the morphology of that surface at the micro/nano scale, our data demonstrates the correlation between surface morphology variations and ONB and nucleate boiling active site density. Specifically, our results indicate that increased irregularities in the surface morphology correspond to enhanced probability of nucleation onset and an increase in active nucleation site density as superheat increases. Our data indicates the range of irregularity number density values (number per square millimeter) and the imperfection features that give rise to consistent low superheat ONB (∼ 15◦𝐶), leads to a robust increase in active site density during nucleate boiling as super heat increases. This information can help guide development of enhanced boiling surfaces by providing insight into the frequency of nanosurface morphology variations, per square millimeter, that enhance nucleation onset while also providing enhanced wicking and low contact angle over most of the surface. The implication of these results for design of different types of enhanced boiling surfaces is also discussed.more » « less
