A Deep Learning Perspective on Dropwise Condensation
| العنوان: | A Deep Learning Perspective on Dropwise Condensation |
|---|---|
| المؤلفون: | Kazi Fazle Rabbi, Jonggyu Lee, Longnan Li, Youngjoon Suh, Xiao Yan, Peter Simadiris, Yoonjin Won, Nenad Miljkovic, Soumyadip Sett |
| المصدر: | Advanced Science, Vol 8, Iss 22, Pp n/a-n/a (2021) Advanced Science |
| بيانات النشر: | Wiley, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Thermal science, Process (engineering), Computer science, General Chemical Engineering, Science, Population, Big data, Nucleation, General Physics and Astronomy, Medicine (miscellaneous), 02 engineering and technology, 010402 general chemistry, 01 natural sciences, Biochemistry, Genetics and Molecular Biology (miscellaneous), droplet statistics, General Materials Science, education, Process engineering, Research Articles, education.field_of_study, business.industry, Deep learning, Condensation, General Engineering, deep learning, dropwise condensation, 021001 nanoscience & nanotechnology, 0104 chemical sciences, real‐time heat transfer mapping, AI computer vision, Heat transfer, Artificial intelligence, 0210 nano-technology, business, Research Article |
| الوصف: | Condensation is ubiquitous in nature and industry. Heterogeneous condensation on surfaces is typified by the continuous cycle of droplet nucleation, growth, and departure. Central to the mechanistic understanding of the thermofluidic processes governing condensation is the rapid and high‐fidelity extraction of interpretable physical descriptors from the highly transient droplet population. However, extracting quantifiable measures out of dynamic objects with conventional imaging technologies poses a challenge to researchers. Here, an intelligent vision‐based framework is demonstrated that unites classical thermofluidic imaging techniques with deep learning to fundamentally address this challenge. The deep learning framework can autonomously harness physical descriptors and quantify thermal performance at extreme spatio‐temporal resolutions of 300 nm and 200 ms, respectively. The data‐centric analysis conclusively shows that contrary to classical understanding, the overall condensation performance is governed by a key tradeoff between heat transfer rate per individual droplet and droplet population density. The vision‐based approach presents a powerful tool for the study of not only phase‐change processes but also any nucleation‐based process within and beyond the thermal science community through the harnessing of big data. A vision‐based framework utilizing artificial intelligence is proposed to meet the challenges in acquiring physical descriptors of dropwise condensation. Using this framework, the study investigates the relationship between droplet statistics and heat and mass transfer with unprecedented spatio‐temporal resolutions. The results show the importance of codesigning heat transfer rate per droplet and droplet number density to optimize heat transfer performance. |
| اللغة: | English |
| تدمد: | 2198-3844 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a127d28004e5e9eeec3321a1b60e4e1 https://doaj.org/article/f635050c728e448c9df6263d5c9f0d44 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....5a127d28004e5e9eeec3321a1b60e4e1 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 21983844 |
|---|