Prediction of the morphological evolution of a splashing drop using an encoder–decoder
The impact of a drop on a solid surface is an important phenomenon that has various implications and applications. However, the multiphase nature of this phenomenon causes complications in the prediction of its morphological evolution, especially when the drop splashes. While most machine-learning-b...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/acc727 |
| _version_ | 1797844578740469760 |
|---|---|
| author | Jingzu Yee Daichi Igarashi(五十嵐大地) Shun Miyatake(宮武駿) Yoshiyuki Tagawa(田川義之) |
| author_facet | Jingzu Yee Daichi Igarashi(五十嵐大地) Shun Miyatake(宮武駿) Yoshiyuki Tagawa(田川義之) |
| author_sort | Jingzu Yee |
| collection | DOAJ |
| description | The impact of a drop on a solid surface is an important phenomenon that has various implications and applications. However, the multiphase nature of this phenomenon causes complications in the prediction of its morphological evolution, especially when the drop splashes. While most machine-learning-based drop-impact studies have centred around physical parameters, this study used a computer-vision strategy by training an encoder–decoder to predict the drop morphologies using image data. Herein, we show that this trained encoder–decoder is able to successfully generate videos that show the morphologies of splashing and non-splashing drops. Remarkably, in each frame of these generated videos, the spreading diameter of the drop was found to be in good agreement with that of the actual videos. Moreover, there was also a high accuracy in splashing/non-splashing prediction. These findings demonstrate the ability of the trained encoder–decoder to generate videos that can accurately represent the drop morphologies. This approach provides a faster and cheaper alternative to experimental and numerical studies. |
| first_indexed | 2024-04-09T17:24:36Z |
| format | Article |
| id | doaj.art-1ca4543fe21948d9b8ddc10d43c67360 |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-04-09T17:24:36Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-1ca4543fe21948d9b8ddc10d43c673602023-04-18T13:53:31ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014202500210.1088/2632-2153/acc727Prediction of the morphological evolution of a splashing drop using an encoder–decoderJingzu Yee0https://orcid.org/0000-0002-0549-165XDaichi Igarashi(五十嵐大地)1Shun Miyatake(宮武駿)2Yoshiyuki Tagawa(田川義之)3https://orcid.org/0000-0002-0049-1984Department of Mechanical Systems Engineering, Tokyo University of Agriculture and Technology , Koganei, Tokyo 184-8588, JapanDepartment of Mechanical Systems Engineering, Tokyo University of Agriculture and Technology , Koganei, Tokyo 184-8588, JapanDepartment of Mechanical Systems Engineering, Tokyo University of Agriculture and Technology , Koganei, Tokyo 184-8588, JapanDepartment of Mechanical Systems Engineering, Tokyo University of Agriculture and Technology , Koganei, Tokyo 184-8588, Japan; Institute of Global Innovation Research, Tokyo University of Agriculture and Technology , Koganei, Tokyo 184-8588, JapanThe impact of a drop on a solid surface is an important phenomenon that has various implications and applications. However, the multiphase nature of this phenomenon causes complications in the prediction of its morphological evolution, especially when the drop splashes. While most machine-learning-based drop-impact studies have centred around physical parameters, this study used a computer-vision strategy by training an encoder–decoder to predict the drop morphologies using image data. Herein, we show that this trained encoder–decoder is able to successfully generate videos that show the morphologies of splashing and non-splashing drops. Remarkably, in each frame of these generated videos, the spreading diameter of the drop was found to be in good agreement with that of the actual videos. Moreover, there was also a high accuracy in splashing/non-splashing prediction. These findings demonstrate the ability of the trained encoder–decoder to generate videos that can accurately represent the drop morphologies. This approach provides a faster and cheaper alternative to experimental and numerical studies.https://doi.org/10.1088/2632-2153/acc727multiphase flowdrop impactsplashingmachine learningcomputer vision |
| spellingShingle | Jingzu Yee Daichi Igarashi(五十嵐大地) Shun Miyatake(宮武駿) Yoshiyuki Tagawa(田川義之) Prediction of the morphological evolution of a splashing drop using an encoder–decoder Machine Learning: Science and Technology multiphase flow drop impact splashing machine learning computer vision |
| title | Prediction of the morphological evolution of a splashing drop using an encoder–decoder |
| title_full | Prediction of the morphological evolution of a splashing drop using an encoder–decoder |
| title_fullStr | Prediction of the morphological evolution of a splashing drop using an encoder–decoder |
| title_full_unstemmed | Prediction of the morphological evolution of a splashing drop using an encoder–decoder |
| title_short | Prediction of the morphological evolution of a splashing drop using an encoder–decoder |
| title_sort | prediction of the morphological evolution of a splashing drop using an encoder decoder |
| topic | multiphase flow drop impact splashing machine learning computer vision |
| url | https://doi.org/10.1088/2632-2153/acc727 |
| work_keys_str_mv | AT jingzuyee predictionofthemorphologicalevolutionofasplashingdropusinganencoderdecoder AT daichiigarashiwǔshílándàde predictionofthemorphologicalevolutionofasplashingdropusinganencoderdecoder AT shunmiyatakegōngwǔjùn predictionofthemorphologicalevolutionofasplashingdropusinganencoderdecoder AT yoshiyukitagawatiánchuānyìzhī predictionofthemorphologicalevolutionofasplashingdropusinganencoderdecoder |