A Deep Learning-Based Approach for Two-Phase Flow Pattern Classification Using Void Fraction Time Series Analysis
Flow regime classification is essential for analyzing and modeling two-phase flows, as it demarcates the flow behavior and influences the selection of appropriate predictive models. Machine learning-based approaches have gained relevance in flow regime classification research in the last few years....
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10840192/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Flow regime classification is essential for analyzing and modeling two-phase flows, as it demarcates the flow behavior and influences the selection of appropriate predictive models. Machine learning-based approaches have gained relevance in flow regime classification research in the last few years. However, they are still solidly based on the construction and careful definition of hand-crafted features. Deep learning approaches, on the other hand, can provide more robust and end-to-end solutions. However, they are underexplored and have not evaluated the generalization of the models to other data or acquisition systems. Hence, this work proposes using end-to-end state-of-the-art (SOTA) time-series classification methods (ResNet, LSTM-FCN, and TSTPlus) for two-phase flow patterns (churn, bubbly, and slug). We also present the generalization analysis of the models with cross-dataset experiments, training the model with one dataset and testing it with another dataset collected in another system for two datasets: HZDR (from the Helmholtz-Zentrum Dresden-Rossendorf research laboratory) and TUD (from Technische Universität Dresden). The results demonstrate that the approach chosen here presents superior classification metrics in all cases evaluated, particularly in cross-dataset experiments. With our proposed SOTA methods, all the evaluated metrics (accuracy and F1-Score) consistently surpass 85% in all cases, while the baseline method can decrease the performance under 75%. This demonstrates the relevance of the analysis proposed here for flow regime classification literature and opens up a new set of possibilities for research in this area, aiming at robust solutions that are viable for practical use. Codes are available at <uri>https://github.com/ambrosioj/two-phase-time-series-deep-learning</uri>. |
|---|---|
| ISSN: | 2169-3536 |