The Recognition Algorithm of Two-Phase Flow Patterns Based on GoogLeNet+5 Coord Attention
The two-phase flow in a microchannel consists of liquid–liquid and gas–liquid material components. The automatic recognition of flow patterns using deep learning approaches has been emerging. This study aimed to improve the recognition accuracy of flow patterns in the two-phase flow images. The diff...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/14/2/462 |
| _version_ | 1797619264027361280 |
|---|---|
| author | Jinsong Zhang Xinpeng Wei Zhiliang Wang |
| author_facet | Jinsong Zhang Xinpeng Wei Zhiliang Wang |
| author_sort | Jinsong Zhang |
| collection | DOAJ |
| description | The two-phase flow in a microchannel consists of liquid–liquid and gas–liquid material components. The automatic recognition of flow patterns using deep learning approaches has been emerging. This study aimed to improve the recognition accuracy of flow patterns in the two-phase flow images. The different convolutional kernels in the GoogLeNet algorithm extracted the image features with different scales. In order to strengthen the important channel and spatial features, this paper proposes the combined five-layer Coord attention and GoogLeNet algorithm to enhance the accuracy of the new algorithm. The optimized algorithm model was derived from image datasets with different liquid–liquid two-phase flows (NaAlg–Oil, GaInSn–Water), and its accuracy was 95.09% in training and 98.12% in testing. This new model was also applied to predict the flow patterns, with a recognition accuracy of more than 97% in both the liquid–liquid and gas–liquid two-phase flows (water–soybean oil, water–lubricating oil, and argon–water). |
| first_indexed | 2024-03-11T08:24:39Z |
| format | Article |
| id | doaj.art-d3e19bfb5e814833800784bbb49cb99f |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-11T08:24:39Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-d3e19bfb5e814833800784bbb49cb99f2023-11-16T22:12:35ZengMDPI AGMicromachines2072-666X2023-02-0114246210.3390/mi14020462The Recognition Algorithm of Two-Phase Flow Patterns Based on GoogLeNet+5 Coord AttentionJinsong Zhang0Xinpeng Wei1Zhiliang Wang2School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaSchool of Mechanics and Engineering Science, Shanghai University, Shanghai 200444, ChinaThe two-phase flow in a microchannel consists of liquid–liquid and gas–liquid material components. The automatic recognition of flow patterns using deep learning approaches has been emerging. This study aimed to improve the recognition accuracy of flow patterns in the two-phase flow images. The different convolutional kernels in the GoogLeNet algorithm extracted the image features with different scales. In order to strengthen the important channel and spatial features, this paper proposes the combined five-layer Coord attention and GoogLeNet algorithm to enhance the accuracy of the new algorithm. The optimized algorithm model was derived from image datasets with different liquid–liquid two-phase flows (NaAlg–Oil, GaInSn–Water), and its accuracy was 95.09% in training and 98.12% in testing. This new model was also applied to predict the flow patterns, with a recognition accuracy of more than 97% in both the liquid–liquid and gas–liquid two-phase flows (water–soybean oil, water–lubricating oil, and argon–water).https://www.mdpi.com/2072-666X/14/2/462deep learning algorithmtwo-phase flow imagepattern recognitionattention mechanism |
| spellingShingle | Jinsong Zhang Xinpeng Wei Zhiliang Wang The Recognition Algorithm of Two-Phase Flow Patterns Based on GoogLeNet+5 Coord Attention Micromachines deep learning algorithm two-phase flow image pattern recognition attention mechanism |
| title | The Recognition Algorithm of Two-Phase Flow Patterns Based on GoogLeNet+5 Coord Attention |
| title_full | The Recognition Algorithm of Two-Phase Flow Patterns Based on GoogLeNet+5 Coord Attention |
| title_fullStr | The Recognition Algorithm of Two-Phase Flow Patterns Based on GoogLeNet+5 Coord Attention |
| title_full_unstemmed | The Recognition Algorithm of Two-Phase Flow Patterns Based on GoogLeNet+5 Coord Attention |
| title_short | The Recognition Algorithm of Two-Phase Flow Patterns Based on GoogLeNet+5 Coord Attention |
| title_sort | recognition algorithm of two phase flow patterns based on googlenet 5 coord attention |
| topic | deep learning algorithm two-phase flow image pattern recognition attention mechanism |
| url | https://www.mdpi.com/2072-666X/14/2/462 |
| work_keys_str_mv | AT jinsongzhang therecognitionalgorithmoftwophaseflowpatternsbasedongooglenet5coordattention AT xinpengwei therecognitionalgorithmoftwophaseflowpatternsbasedongooglenet5coordattention AT zhiliangwang therecognitionalgorithmoftwophaseflowpatternsbasedongooglenet5coordattention AT jinsongzhang recognitionalgorithmoftwophaseflowpatternsbasedongooglenet5coordattention AT xinpengwei recognitionalgorithmoftwophaseflowpatternsbasedongooglenet5coordattention AT zhiliangwang recognitionalgorithmoftwophaseflowpatternsbasedongooglenet5coordattention |