Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection
The presence of water accumulation on aircraft surfaces constitutes a considerable hazard to both performance and safety, necessitating vigilant inspection and maintenance protocols. In this study, we introduce an innovative semantic segmentation model, grounded in deep learning principles, for the...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/11/12/961 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846106482629672960 |
|---|---|
| author | Hang Fei Hongfu Zuo Han Wang Yan Liu Zhenzhen Liu Xin Li |
| author_facet | Hang Fei Hongfu Zuo Han Wang Yan Liu Zhenzhen Liu Xin Li |
| author_sort | Hang Fei |
| collection | DOAJ |
| description | The presence of water accumulation on aircraft surfaces constitutes a considerable hazard to both performance and safety, necessitating vigilant inspection and maintenance protocols. In this study, we introduce an innovative semantic segmentation model, grounded in deep learning principles, for the precise identification and delineation of water accumulation areas within infrared images of aircraft exteriors. Our proposed model harnesses the robust features of ResNet, serving as the foundational architecture for U-Net, thereby augmenting the model’s capacity for comprehensive feature characterization. The incorporation of channel attention mechanisms, spatial attention mechanisms, and depthwise separable convolution further refines the network structure, contributing to enhanced segmentation performance. Through rigorous experimentation, our model surpasses existing benchmarks, yielding a commendable 22.44% reduction in computational effort and a substantial 38.89% reduction in parameter count. The model’s outstanding performance is particularly noteworthy, registering a 92.67% mean intersection over union and a 97.97% mean pixel accuracy. The hallmark of our innovation lies in the model’s efficacy in the precise detection and segmentation of water accumulation areas on aircraft skin. Beyond this, our approach holds promise for addressing analogous challenges in aviation and related domains. The enumeration of specific quantitative outcomes underscores the superior efficacy of our model, rendering it a compelling solution for precise detection and segmentation tasks. The demonstrated reductions in computational effort and parameter count underscore the model’s efficiency, fortifying its relevance in broader contexts. |
| format | Article |
| id | doaj-art-49ae2f5e971d4673b652cd6e3d622b99 |
| institution | Kabale University |
| issn | 2226-4310 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj-art-49ae2f5e971d4673b652cd6e3d622b992024-12-27T14:02:22ZengMDPI AGAerospace2226-43102024-11-01111296110.3390/aerospace11120961Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress DetectionHang Fei0Hongfu Zuo1Han Wang2Yan Liu3Zhenzhen Liu4Xin Li5Civil Aviation Key Laboratory of Aircraft Health Monitoring and Intelligent Maintenance, College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaCivil Aviation Key Laboratory of Aircraft Health Monitoring and Intelligent Maintenance, College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaShanghai Aeronautical Measurement and Control Research Institute, Shanghai 201601, ChinaCivil Aviation Key Laboratory of Aircraft Health Monitoring and Intelligent Maintenance, College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaSchool of Mechanical Engineering, Anhui University of Technology, Ma’anshan 243032, ChinaCivil Aviation Key Laboratory of Aircraft Health Monitoring and Intelligent Maintenance, College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaThe presence of water accumulation on aircraft surfaces constitutes a considerable hazard to both performance and safety, necessitating vigilant inspection and maintenance protocols. In this study, we introduce an innovative semantic segmentation model, grounded in deep learning principles, for the precise identification and delineation of water accumulation areas within infrared images of aircraft exteriors. Our proposed model harnesses the robust features of ResNet, serving as the foundational architecture for U-Net, thereby augmenting the model’s capacity for comprehensive feature characterization. The incorporation of channel attention mechanisms, spatial attention mechanisms, and depthwise separable convolution further refines the network structure, contributing to enhanced segmentation performance. Through rigorous experimentation, our model surpasses existing benchmarks, yielding a commendable 22.44% reduction in computational effort and a substantial 38.89% reduction in parameter count. The model’s outstanding performance is particularly noteworthy, registering a 92.67% mean intersection over union and a 97.97% mean pixel accuracy. The hallmark of our innovation lies in the model’s efficacy in the precise detection and segmentation of water accumulation areas on aircraft skin. Beyond this, our approach holds promise for addressing analogous challenges in aviation and related domains. The enumeration of specific quantitative outcomes underscores the superior efficacy of our model, rendering it a compelling solution for precise detection and segmentation tasks. The demonstrated reductions in computational effort and parameter count underscore the model’s efficiency, fortifying its relevance in broader contexts.https://www.mdpi.com/2226-4310/11/12/961aircraft skinwater accumulation detectioninfrared image segmentationdeep learning |
| spellingShingle | Hang Fei Hongfu Zuo Han Wang Yan Liu Zhenzhen Liu Xin Li Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection Aerospace aircraft skin water accumulation detection infrared image segmentation deep learning |
| title | Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection |
| title_full | Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection |
| title_fullStr | Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection |
| title_full_unstemmed | Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection |
| title_short | Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection |
| title_sort | deep learning based infrared image segmentation for aircraft honeycomb water ingress detection |
| topic | aircraft skin water accumulation detection infrared image segmentation deep learning |
| url | https://www.mdpi.com/2226-4310/11/12/961 |
| work_keys_str_mv | AT hangfei deeplearningbasedinfraredimagesegmentationforaircrafthoneycombwateringressdetection AT hongfuzuo deeplearningbasedinfraredimagesegmentationforaircrafthoneycombwateringressdetection AT hanwang deeplearningbasedinfraredimagesegmentationforaircrafthoneycombwateringressdetection AT yanliu deeplearningbasedinfraredimagesegmentationforaircrafthoneycombwateringressdetection AT zhenzhenliu deeplearningbasedinfraredimagesegmentationforaircrafthoneycombwateringressdetection AT xinli deeplearningbasedinfraredimagesegmentationforaircrafthoneycombwateringressdetection |