A Machine Learning Approach to Volume Tracking in Multiphase Flow Simulations
This work presents a machine learning (ML) approach to volume-tracking for computational simulations of multiphase flow. It is an alternative to a commonly used procedure in the volume-of-fluid (VOF) method for volume tracking, in which the phase interfaces are reconstructed for flux calculation fol...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Fluids |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2311-5521/10/2/39 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849718565410701312 |
|---|---|
| author | Aaron Mak Mehdi Raessi |
| author_facet | Aaron Mak Mehdi Raessi |
| author_sort | Aaron Mak |
| collection | DOAJ |
| description | This work presents a machine learning (ML) approach to volume-tracking for computational simulations of multiphase flow. It is an alternative to a commonly used procedure in the volume-of-fluid (VOF) method for volume tracking, in which the phase interfaces are reconstructed for flux calculation followed by volume advection. Bypassing the computationally expensive steps of interface reconstruction and flux calculation, the proposed ML approach performs volume advection in a single step, directly predicting the volume fractions at the next time step. The proposed ML function is two-dimensional and has eleven inputs. It was trained using MATLAB’s (R2021a) Deep Learning Toolbox with a grid search method to find an optimal neural network configuration. The performance of the ML function is assessed using canonical test cases, including translation, rotation, and vortex tests. The errors in the volume fraction fields obtained by the ML function are compared with those of the VOF method. In ideal conditions, the ML function speeds up the computations four times compared to the VOF method. However, in terms of overall robustness and accuracy, the VOF method remains superior. This study demonstrates the potential of applying ML methods to multiphase flow simulations while highlighting areas for further improvement. |
| format | Article |
| id | doaj-art-a3353b47ffae4dffa6c0e5adf64e40b4 |
| institution | DOAJ |
| issn | 2311-5521 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fluids |
| spelling | doaj-art-a3353b47ffae4dffa6c0e5adf64e40b42025-08-20T03:12:20ZengMDPI AGFluids2311-55212025-02-011023910.3390/fluids10020039A Machine Learning Approach to Volume Tracking in Multiphase Flow SimulationsAaron Mak0Mehdi Raessi1Department of Mechanical Engineering, University of Massachusetts—Dartmouth, Dartmouth, MA 02747, USADepartment of Mechanical Engineering, University of Massachusetts—Dartmouth, Dartmouth, MA 02747, USAThis work presents a machine learning (ML) approach to volume-tracking for computational simulations of multiphase flow. It is an alternative to a commonly used procedure in the volume-of-fluid (VOF) method for volume tracking, in which the phase interfaces are reconstructed for flux calculation followed by volume advection. Bypassing the computationally expensive steps of interface reconstruction and flux calculation, the proposed ML approach performs volume advection in a single step, directly predicting the volume fractions at the next time step. The proposed ML function is two-dimensional and has eleven inputs. It was trained using MATLAB’s (R2021a) Deep Learning Toolbox with a grid search method to find an optimal neural network configuration. The performance of the ML function is assessed using canonical test cases, including translation, rotation, and vortex tests. The errors in the volume fraction fields obtained by the ML function are compared with those of the VOF method. In ideal conditions, the ML function speeds up the computations four times compared to the VOF method. However, in terms of overall robustness and accuracy, the VOF method remains superior. This study demonstrates the potential of applying ML methods to multiphase flow simulations while highlighting areas for further improvement.https://www.mdpi.com/2311-5521/10/2/39volume-of-fluidtwo-phase flowmultiphase flowcomputational fluid dynamicsmachine learningdeep learning |
| spellingShingle | Aaron Mak Mehdi Raessi A Machine Learning Approach to Volume Tracking in Multiphase Flow Simulations Fluids volume-of-fluid two-phase flow multiphase flow computational fluid dynamics machine learning deep learning |
| title | A Machine Learning Approach to Volume Tracking in Multiphase Flow Simulations |
| title_full | A Machine Learning Approach to Volume Tracking in Multiphase Flow Simulations |
| title_fullStr | A Machine Learning Approach to Volume Tracking in Multiphase Flow Simulations |
| title_full_unstemmed | A Machine Learning Approach to Volume Tracking in Multiphase Flow Simulations |
| title_short | A Machine Learning Approach to Volume Tracking in Multiphase Flow Simulations |
| title_sort | machine learning approach to volume tracking in multiphase flow simulations |
| topic | volume-of-fluid two-phase flow multiphase flow computational fluid dynamics machine learning deep learning |
| url | https://www.mdpi.com/2311-5521/10/2/39 |
| work_keys_str_mv | AT aaronmak amachinelearningapproachtovolumetrackinginmultiphaseflowsimulations AT mehdiraessi amachinelearningapproachtovolumetrackinginmultiphaseflowsimulations AT aaronmak machinelearningapproachtovolumetrackinginmultiphaseflowsimulations AT mehdiraessi machinelearningapproachtovolumetrackinginmultiphaseflowsimulations |