Efficient and accurate machine learning models for volume of fluid (VOF) simulation on uniform Cartesian mesh
In this paper, we describe a machine learning (ML) approach for estimating interface orientation in multiphase flow using the volume of fluid (VOF) method on a uniform Cartesian mesh. By using complex shapes generated with the parametric radial star formula during training, we significantly improve...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Engineering Applications of Computational Fluid Mechanics |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19942060.2025.2451774 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841525733564874752 |
|---|---|
| author | Mostafa A. Rushdi Shigeo Yoshida Changhong Hu Tarek N. Dief Abdulrahman E. Salem Mohamed M. Kamra |
| author_facet | Mostafa A. Rushdi Shigeo Yoshida Changhong Hu Tarek N. Dief Abdulrahman E. Salem Mohamed M. Kamra |
| author_sort | Mostafa A. Rushdi |
| collection | DOAJ |
| description | In this paper, we describe a machine learning (ML) approach for estimating interface orientation in multiphase flow using the volume of fluid (VOF) method on a uniform Cartesian mesh. By using complex shapes generated with the parametric radial star formula during training, we significantly improve prediction accuracy without increasing the network's structural complexity or processing cost. Our key contribution is the development of a robust ML model capable of reliably predicting interface orientation angles on uniform Cartesian grids. To enhance performance and robustness, we conducted a parametric study of the ML models' hyperparameters. The proposed method produced two models: a full augmented (9-cell) stencil and a compact (5-cell) stencil. Both were compared against popular finite difference/volume methods commonly used in VOF schemes. The results show that our approach is more accurate while remaining computationally efficient, particularly when employing a small stencil. Numerical studies, including challenging flow scenarios, demonstrate that the technique can predict interface orientation with an absolute mean error of less than 1 degree. Implemented in the OpenFOAM isoAdvector, our technique reliably produces accurate interface tracking with minimal deviation from the exact solution. These findings highlight the potential for incorporating machine learning approaches into classical numerical methods to improve the accuracy and reliability of the VOF method in a variety of challenging applications using uniform Cartesian meshes. |
| format | Article |
| id | doaj-art-d1981884cd7b401c905b58a3f2fbfdcf |
| institution | Kabale University |
| issn | 1994-2060 1997-003X |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Engineering Applications of Computational Fluid Mechanics |
| spelling | doaj-art-d1981884cd7b401c905b58a3f2fbfdcf2025-01-17T07:46:20ZengTaylor & Francis GroupEngineering Applications of Computational Fluid Mechanics1994-20601997-003X2025-12-0119110.1080/19942060.2025.2451774Efficient and accurate machine learning models for volume of fluid (VOF) simulation on uniform Cartesian meshMostafa A. Rushdi0Shigeo Yoshida1Changhong Hu2Tarek N. Dief3Abdulrahman E. Salem4Mohamed M. Kamra5Research Institute for Applied Mechanics (RIAM), Kyushu University, Fukuoka, JapanResearch Institute for Applied Mechanics (RIAM), Kyushu University, Fukuoka, JapanResearch Institute for Applied Mechanics (RIAM), Kyushu University, Fukuoka, JapanCollege of Engineering, UAE University, Al-Ain, United Arab EmiratesCollege of Engineering, UAE University, Al-Ain, United Arab EmiratesCollege of Engineering, UAE University, Al-Ain, United Arab EmiratesIn this paper, we describe a machine learning (ML) approach for estimating interface orientation in multiphase flow using the volume of fluid (VOF) method on a uniform Cartesian mesh. By using complex shapes generated with the parametric radial star formula during training, we significantly improve prediction accuracy without increasing the network's structural complexity or processing cost. Our key contribution is the development of a robust ML model capable of reliably predicting interface orientation angles on uniform Cartesian grids. To enhance performance and robustness, we conducted a parametric study of the ML models' hyperparameters. The proposed method produced two models: a full augmented (9-cell) stencil and a compact (5-cell) stencil. Both were compared against popular finite difference/volume methods commonly used in VOF schemes. The results show that our approach is more accurate while remaining computationally efficient, particularly when employing a small stencil. Numerical studies, including challenging flow scenarios, demonstrate that the technique can predict interface orientation with an absolute mean error of less than 1 degree. Implemented in the OpenFOAM isoAdvector, our technique reliably produces accurate interface tracking with minimal deviation from the exact solution. These findings highlight the potential for incorporating machine learning approaches into classical numerical methods to improve the accuracy and reliability of the VOF method in a variety of challenging applications using uniform Cartesian meshes.https://www.tandfonline.com/doi/10.1080/19942060.2025.2451774Machine learningvolume of fluid (VOF) methodinterface orientationmultiphase flowCartesian mesh |
| spellingShingle | Mostafa A. Rushdi Shigeo Yoshida Changhong Hu Tarek N. Dief Abdulrahman E. Salem Mohamed M. Kamra Efficient and accurate machine learning models for volume of fluid (VOF) simulation on uniform Cartesian mesh Engineering Applications of Computational Fluid Mechanics Machine learning volume of fluid (VOF) method interface orientation multiphase flow Cartesian mesh |
| title | Efficient and accurate machine learning models for volume of fluid (VOF) simulation on uniform Cartesian mesh |
| title_full | Efficient and accurate machine learning models for volume of fluid (VOF) simulation on uniform Cartesian mesh |
| title_fullStr | Efficient and accurate machine learning models for volume of fluid (VOF) simulation on uniform Cartesian mesh |
| title_full_unstemmed | Efficient and accurate machine learning models for volume of fluid (VOF) simulation on uniform Cartesian mesh |
| title_short | Efficient and accurate machine learning models for volume of fluid (VOF) simulation on uniform Cartesian mesh |
| title_sort | efficient and accurate machine learning models for volume of fluid vof simulation on uniform cartesian mesh |
| topic | Machine learning volume of fluid (VOF) method interface orientation multiphase flow Cartesian mesh |
| url | https://www.tandfonline.com/doi/10.1080/19942060.2025.2451774 |
| work_keys_str_mv | AT mostafaarushdi efficientandaccuratemachinelearningmodelsforvolumeoffluidvofsimulationonuniformcartesianmesh AT shigeoyoshida efficientandaccuratemachinelearningmodelsforvolumeoffluidvofsimulationonuniformcartesianmesh AT changhonghu efficientandaccuratemachinelearningmodelsforvolumeoffluidvofsimulationonuniformcartesianmesh AT tarekndief efficientandaccuratemachinelearningmodelsforvolumeoffluidvofsimulationonuniformcartesianmesh AT abdulrahmanesalem efficientandaccuratemachinelearningmodelsforvolumeoffluidvofsimulationonuniformcartesianmesh AT mohamedmkamra efficientandaccuratemachinelearningmodelsforvolumeoffluidvofsimulationonuniformcartesianmesh |