An Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine Blade
The hollow turbine blade plays an important role in the propulsion of the aeroengine. However, due to its complex hollow structure and nickel-based superalloys material property, only industrial computed tomography (ICT) could realize its nondestructive detection with sufficient intuitiveness. The I...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/22/4230 |
| _version_ | 1827644212006354944 |
|---|---|
| author | Jia Zheng Chuan Tang Yuanxi Sun Mingchi Feng Congzhe Wang |
| author_facet | Jia Zheng Chuan Tang Yuanxi Sun Mingchi Feng Congzhe Wang |
| author_sort | Jia Zheng |
| collection | DOAJ |
| description | The hollow turbine blade plays an important role in the propulsion of the aeroengine. However, due to its complex hollow structure and nickel-based superalloys material property, only industrial computed tomography (ICT) could realize its nondestructive detection with sufficient intuitiveness. The ICT detection precision mainly depends on the segmentation accuracy of target ICT images. However, because the hollow turbine blade is made of special superalloys and contains many small unique structures such as film cooling holes, exhaust edges, etc., the ICT image quality of the hollow turbine blades is often deficient, with artifacts, low contrast, and inhomogeneity scattered around the blade contour, making it hard for traditional mathematical model-based methods to acquire satisfying segmentation precision. Therefore, this paper presents a deep learning-based approach, i.e., the enhanced U-net with multiscale inputs, dense blocks, focal loss function, and residual path in the skip connection to realize the high-precision segmentation of the hollow turbine blade. The experimental results show that our proposed enhanced U-net can achieve better segmentation accuracy for practical turbine blades than conventional U-net and traditional mathematical model-based methods. |
| first_indexed | 2024-03-09T18:10:44Z |
| format | Article |
| id | doaj.art-47d70a0ea5ba4f4ea345b505ac0df466 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T18:10:44Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-47d70a0ea5ba4f4ea345b505ac0df4662023-11-24T09:08:06ZengMDPI AGMathematics2227-73902022-11-011022423010.3390/math10224230An Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine BladeJia Zheng0Chuan Tang1Yuanxi Sun2Mingchi Feng3Congzhe Wang4School of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaSchool of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaState Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing 400044, ChinaSchool of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaSchool of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaThe hollow turbine blade plays an important role in the propulsion of the aeroengine. However, due to its complex hollow structure and nickel-based superalloys material property, only industrial computed tomography (ICT) could realize its nondestructive detection with sufficient intuitiveness. The ICT detection precision mainly depends on the segmentation accuracy of target ICT images. However, because the hollow turbine blade is made of special superalloys and contains many small unique structures such as film cooling holes, exhaust edges, etc., the ICT image quality of the hollow turbine blades is often deficient, with artifacts, low contrast, and inhomogeneity scattered around the blade contour, making it hard for traditional mathematical model-based methods to acquire satisfying segmentation precision. Therefore, this paper presents a deep learning-based approach, i.e., the enhanced U-net with multiscale inputs, dense blocks, focal loss function, and residual path in the skip connection to realize the high-precision segmentation of the hollow turbine blade. The experimental results show that our proposed enhanced U-net can achieve better segmentation accuracy for practical turbine blades than conventional U-net and traditional mathematical model-based methods.https://www.mdpi.com/2227-7390/10/22/4230segmentationcomputed tomographyU-nethollow turbine blade |
| spellingShingle | Jia Zheng Chuan Tang Yuanxi Sun Mingchi Feng Congzhe Wang An Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine Blade Mathematics segmentation computed tomography U-net hollow turbine blade |
| title | An Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine Blade |
| title_full | An Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine Blade |
| title_fullStr | An Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine Blade |
| title_full_unstemmed | An Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine Blade |
| title_short | An Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine Blade |
| title_sort | enhanced u net approach for segmentation of aeroengine hollow turbine blade |
| topic | segmentation computed tomography U-net hollow turbine blade |
| url | https://www.mdpi.com/2227-7390/10/22/4230 |
| work_keys_str_mv | AT jiazheng anenhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT chuantang anenhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT yuanxisun anenhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT mingchifeng anenhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT congzhewang anenhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT jiazheng enhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT chuantang enhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT yuanxisun enhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT mingchifeng enhancedunetapproachforsegmentationofaeroenginehollowturbineblade AT congzhewang enhancedunetapproachforsegmentationofaeroenginehollowturbineblade |