A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm
Abstract Cavitation is a technical challenge for high-speed underwater vehicles, such as nuclear submarines and underwater robots, et al. The cavitation phenomena of hydrofoils are typically studied through water tunnel experiments or numerical simulations, which yield extensive cavitation images. T...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88582-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862327200448512 |
|---|---|
| author | Yingyuan Liu Yizhi Wang Kang An |
| author_facet | Yingyuan Liu Yizhi Wang Kang An |
| author_sort | Yingyuan Liu |
| collection | DOAJ |
| description | Abstract Cavitation is a technical challenge for high-speed underwater vehicles, such as nuclear submarines and underwater robots, et al. The cavitation phenomena of hydrofoils are typically studied through water tunnel experiments or numerical simulations, which yield extensive cavitation images. To conveniently extract cavitation features from the massive images, a feature extraction method for hydrofoil cavitation was proposed in this work based on deep learning image semantic segmentation techniques. This method is employed to investigate the mechanism of the transition process from sheet cavitation to cloud cavitation on hydrofoils. The accuracy and generalization ability of the proposed method have been validated. The results indicate that, in addition to accurately obtaining the cavitation length automatically, the method can also derive more sensitive indicators such as area and position changes of the cavitation regions. This heightened sensitivity is invaluable for precisely pinpointing the transition from sheet-like cavitation to cloud cavitation, thereby aiding in a more effective analysis of the development mechanism of attached cavitation. In summary, our proposed method not only streamlines the extraction of cavitation features from massive images but also enhances the understanding of development mechanisms of attached cavitation by providing additional data and more sensitive indicators for analysis. |
| format | Article |
| id | doaj-art-a7479445eb8a4cf9924f841b2f9105ec |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a7479445eb8a4cf9924f841b2f9105ec2025-02-09T12:35:34ZengNature PortfolioScientific Reports2045-23222025-02-0115111210.1038/s41598-025-88582-4A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithmYingyuan Liu0Yizhi Wang1Kang An2The College of Information, Mechanical and Electrical Engineering, Shanghai Normal UniversityThe College of Information, Mechanical and Electrical Engineering, Shanghai Normal UniversityThe College of Information, Mechanical and Electrical Engineering, Shanghai Normal UniversityAbstract Cavitation is a technical challenge for high-speed underwater vehicles, such as nuclear submarines and underwater robots, et al. The cavitation phenomena of hydrofoils are typically studied through water tunnel experiments or numerical simulations, which yield extensive cavitation images. To conveniently extract cavitation features from the massive images, a feature extraction method for hydrofoil cavitation was proposed in this work based on deep learning image semantic segmentation techniques. This method is employed to investigate the mechanism of the transition process from sheet cavitation to cloud cavitation on hydrofoils. The accuracy and generalization ability of the proposed method have been validated. The results indicate that, in addition to accurately obtaining the cavitation length automatically, the method can also derive more sensitive indicators such as area and position changes of the cavitation regions. This heightened sensitivity is invaluable for precisely pinpointing the transition from sheet-like cavitation to cloud cavitation, thereby aiding in a more effective analysis of the development mechanism of attached cavitation. In summary, our proposed method not only streamlines the extraction of cavitation features from massive images but also enhances the understanding of development mechanisms of attached cavitation by providing additional data and more sensitive indicators for analysis.https://doi.org/10.1038/s41598-025-88582-4HydrofoilCavitation lengthImage semantic segmentationDeep learning |
| spellingShingle | Yingyuan Liu Yizhi Wang Kang An A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm Scientific Reports Hydrofoil Cavitation length Image semantic segmentation Deep learning |
| title | A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm |
| title_full | A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm |
| title_fullStr | A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm |
| title_full_unstemmed | A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm |
| title_short | A feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm |
| title_sort | feature extraction method for hydrofoil attached cavitation based on deep learning image semantic segmentation algorithm |
| topic | Hydrofoil Cavitation length Image semantic segmentation Deep learning |
| url | https://doi.org/10.1038/s41598-025-88582-4 |
| work_keys_str_mv | AT yingyuanliu afeatureextractionmethodforhydrofoilattachedcavitationbasedondeeplearningimagesemanticsegmentationalgorithm AT yizhiwang afeatureextractionmethodforhydrofoilattachedcavitationbasedondeeplearningimagesemanticsegmentationalgorithm AT kangan afeatureextractionmethodforhydrofoilattachedcavitationbasedondeeplearningimagesemanticsegmentationalgorithm AT yingyuanliu featureextractionmethodforhydrofoilattachedcavitationbasedondeeplearningimagesemanticsegmentationalgorithm AT yizhiwang featureextractionmethodforhydrofoilattachedcavitationbasedondeeplearningimagesemanticsegmentationalgorithm AT kangan featureextractionmethodforhydrofoilattachedcavitationbasedondeeplearningimagesemanticsegmentationalgorithm |