Microscopic Defect Detection on Aircraft Engine Blades via Improved YOLOv8
To fully bring into play the functions of aircraft engine blades, it is indispensable to perform regular inspections of engine blades, which currently rely on inefficient manual visual assessments. While artificial intelligence technology can be utilized, benchmark datasets are not available yet. To...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10815949/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550738700894208 |
|---|---|
| author | Yujie Jiang Ping Li Bing Lin Yingying Wang Tian Li Hui Xue Weidong Liu Zaihu Han Dan Wang Junlei Tang |
| author_facet | Yujie Jiang Ping Li Bing Lin Yingying Wang Tian Li Hui Xue Weidong Liu Zaihu Han Dan Wang Junlei Tang |
| author_sort | Yujie Jiang |
| collection | DOAJ |
| description | To fully bring into play the functions of aircraft engine blades, it is indispensable to perform regular inspections of engine blades, which currently rely on inefficient manual visual assessments. While artificial intelligence technology can be utilized, benchmark datasets are not available yet. To tackle these issues, in this work, we first construct two datasets that are collected from real blade defect images at different microscopic magnifications under an electron microscope and a metallographic microscope. Subsequently, we propose an efficient lightweight YOLOv8 framework, incorporating a hierarchical feature fusion module MS-Block for better multi-scale integration, as well as an Efficient Multi-Scale Attention (EMA) and Dilation-wise Residual (DWR) modules to enhance the detection of small targets and replace the loss function with Inner-IoU. The improved YOLOv8 demonstrates a noteworthy increase in mean average precision (mAP), achieving an enhancement of 1.5% on the Electron Microscope Taken (EMT) dataset and 1.8% on the Metallographic Microscope Taken (MMT) dataset compared to the original model. Our approach significantly surpasses the performance of contemporary target detection algorithms, thereby offering a robust solution for microscopic defect detection in aeroengines. This advancement not only streamlines the inspection process but also contributes to the overall safety and reliability of aircraft operations. |
| format | Article |
| id | doaj-art-11082fb7692b472eb48c605fce826f07 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-11082fb7692b472eb48c605fce826f072025-01-10T00:01:19ZengIEEEIEEE Access2169-35362025-01-01134932494610.1109/ACCESS.2024.352224010815949Microscopic Defect Detection on Aircraft Engine Blades via Improved YOLOv8Yujie Jiang0https://orcid.org/0009-0004-2968-022XPing Li1https://orcid.org/0000-0002-8391-6510Bing Lin2Yingying Wang3Tian Li4Hui Xue5Weidong Liu6Zaihu Han7Dan Wang8https://orcid.org/0000-0002-2467-905XJunlei Tang9https://orcid.org/0000-0003-4114-4409School of Chemistry and Chemical Engineering, Institute for Carbon Neutrality, Southwest Petroleum University, Chengdu, ChinaSchool of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu, ChinaSchool of Chemistry and Chemical Engineering, Institute for Carbon Neutrality, Southwest Petroleum University, Chengdu, ChinaKey Laboratory of Optoelectronic Chemical Materials and Devices, Ministry of Education, Jianghan University, Wuhan, ChinaAECC Chengdu Engine Company Ltd., Chengdu, ChinaAECC Chengdu Engine Company Ltd., Chengdu, ChinaAECC Chengdu Engine Company Ltd., Chengdu, ChinaAECC Chengdu Engine Company Ltd., Chengdu, ChinaSchool of Electrical and Automation Engineering, Changshu Institute of Technology, Suzhou, Jiangsu, ChinaSchool of Chemistry and Chemical Engineering, Institute for Carbon Neutrality, Southwest Petroleum University, Chengdu, ChinaTo fully bring into play the functions of aircraft engine blades, it is indispensable to perform regular inspections of engine blades, which currently rely on inefficient manual visual assessments. While artificial intelligence technology can be utilized, benchmark datasets are not available yet. To tackle these issues, in this work, we first construct two datasets that are collected from real blade defect images at different microscopic magnifications under an electron microscope and a metallographic microscope. Subsequently, we propose an efficient lightweight YOLOv8 framework, incorporating a hierarchical feature fusion module MS-Block for better multi-scale integration, as well as an Efficient Multi-Scale Attention (EMA) and Dilation-wise Residual (DWR) modules to enhance the detection of small targets and replace the loss function with Inner-IoU. The improved YOLOv8 demonstrates a noteworthy increase in mean average precision (mAP), achieving an enhancement of 1.5% on the Electron Microscope Taken (EMT) dataset and 1.8% on the Metallographic Microscope Taken (MMT) dataset compared to the original model. Our approach significantly surpasses the performance of contemporary target detection algorithms, thereby offering a robust solution for microscopic defect detection in aeroengines. This advancement not only streamlines the inspection process but also contributes to the overall safety and reliability of aircraft operations.https://ieeexplore.ieee.org/document/10815949/Microscopic defect detectionYOLOv8deep learningaeroengine |
| spellingShingle | Yujie Jiang Ping Li Bing Lin Yingying Wang Tian Li Hui Xue Weidong Liu Zaihu Han Dan Wang Junlei Tang Microscopic Defect Detection on Aircraft Engine Blades via Improved YOLOv8 IEEE Access Microscopic defect detection YOLOv8 deep learning aeroengine |
| title | Microscopic Defect Detection on Aircraft Engine Blades via Improved YOLOv8 |
| title_full | Microscopic Defect Detection on Aircraft Engine Blades via Improved YOLOv8 |
| title_fullStr | Microscopic Defect Detection on Aircraft Engine Blades via Improved YOLOv8 |
| title_full_unstemmed | Microscopic Defect Detection on Aircraft Engine Blades via Improved YOLOv8 |
| title_short | Microscopic Defect Detection on Aircraft Engine Blades via Improved YOLOv8 |
| title_sort | microscopic defect detection on aircraft engine blades via improved yolov8 |
| topic | Microscopic defect detection YOLOv8 deep learning aeroengine |
| url | https://ieeexplore.ieee.org/document/10815949/ |
| work_keys_str_mv | AT yujiejiang microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT pingli microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT binglin microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT yingyingwang microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT tianli microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT huixue microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT weidongliu microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT zaihuhan microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT danwang microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 AT junleitang microscopicdefectdetectiononaircraftenginebladesviaimprovedyolov8 |