A Deep Learning Perspective on Dropwise Condensation
Abstract 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‐fi...
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Wiley
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/f635050c728e448c9df6263d5c9f0d44 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:f635050c728e448c9df6263d5c9f0d44 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:f635050c728e448c9df6263d5c9f0d442021-11-17T08:40:31ZA Deep Learning Perspective on Dropwise Condensation2198-384410.1002/advs.202101794https://doaj.org/article/f635050c728e448c9df6263d5c9f0d442021-11-01T00:00:00Zhttps://doi.org/10.1002/advs.202101794https://doaj.org/toc/2198-3844Abstract 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.Youngjoon SuhJonggyu LeePeter SimadirisXiao YanSoumyadip SettLongnan LiKazi Fazle RabbiNenad MiljkovicYoonjin WonWileyarticleAI computer visiondeep learningdroplet statisticsdropwise condensationreal‐time heat transfer mappingScienceQENAdvanced Science, Vol 8, Iss 22, Pp n/a-n/a (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
AI computer vision deep learning droplet statistics dropwise condensation real‐time heat transfer mapping Science Q |
| spellingShingle |
AI computer vision deep learning droplet statistics dropwise condensation real‐time heat transfer mapping Science Q Youngjoon Suh Jonggyu Lee Peter Simadiris Xiao Yan Soumyadip Sett Longnan Li Kazi Fazle Rabbi Nenad Miljkovic Yoonjin Won A Deep Learning Perspective on Dropwise Condensation |
| description |
Abstract 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. |
| format |
article |
| author |
Youngjoon Suh Jonggyu Lee Peter Simadiris Xiao Yan Soumyadip Sett Longnan Li Kazi Fazle Rabbi Nenad Miljkovic Yoonjin Won |
| author_facet |
Youngjoon Suh Jonggyu Lee Peter Simadiris Xiao Yan Soumyadip Sett Longnan Li Kazi Fazle Rabbi Nenad Miljkovic Yoonjin Won |
| author_sort |
Youngjoon Suh |
| title |
A Deep Learning Perspective on Dropwise Condensation |
| title_short |
A Deep Learning Perspective on Dropwise Condensation |
| title_full |
A Deep Learning Perspective on Dropwise Condensation |
| title_fullStr |
A Deep Learning Perspective on Dropwise Condensation |
| title_full_unstemmed |
A Deep Learning Perspective on Dropwise Condensation |
| title_sort |
deep learning perspective on dropwise condensation |
| publisher |
Wiley |
| publishDate |
2021 |
| url |
https://doaj.org/article/f635050c728e448c9df6263d5c9f0d44 |
| work_keys_str_mv |
AT youngjoonsuh adeeplearningperspectiveondropwisecondensation AT jonggyulee adeeplearningperspectiveondropwisecondensation AT petersimadiris adeeplearningperspectiveondropwisecondensation AT xiaoyan adeeplearningperspectiveondropwisecondensation AT soumyadipsett adeeplearningperspectiveondropwisecondensation AT longnanli adeeplearningperspectiveondropwisecondensation AT kazifazlerabbi adeeplearningperspectiveondropwisecondensation AT nenadmiljkovic adeeplearningperspectiveondropwisecondensation AT yoonjinwon adeeplearningperspectiveondropwisecondensation AT youngjoonsuh deeplearningperspectiveondropwisecondensation AT jonggyulee deeplearningperspectiveondropwisecondensation AT petersimadiris deeplearningperspectiveondropwisecondensation AT xiaoyan deeplearningperspectiveondropwisecondensation AT soumyadipsett deeplearningperspectiveondropwisecondensation AT longnanli deeplearningperspectiveondropwisecondensation AT kazifazlerabbi deeplearningperspectiveondropwisecondensation AT nenadmiljkovic deeplearningperspectiveondropwisecondensation AT yoonjinwon deeplearningperspectiveondropwisecondensation |
| _version_ |
1718425710306000896 |