Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Aircraft Defects in Walk Around Inspection(WAI) Using YOLO-based Deep Learning and Image Processing

영상처리와 YOLO 기반 딥러닝을 활용한 항공기 WAI 결함 검출

  • Jagyeom Kim (Air Force 81 Chang Air Parts Maintenance Factory Flight Control Team) ;
  • Doohyun Choi (School of Electronic and Electrical Engineering, Kyungpook National University)
  • 김자겸 (공군 81창 항공부품정비공장 비행제어팀) ;
  • 최두현 (경북대학교 전자전기공학부)
  • Received : 2025.06.18
  • Accepted : 2025.10.24
  • Published : 2025.12.05
Download PDF
⟨ Previous Next ⟩

Abstract

In the aviation industry, early detection of external defects is essential for flight safety and maintenance efficiency. Traditional Walk Around Inspection(WAI), which depends on human vision, is vulnerable to errors caused by lighting, weather, and inspector variability. To address these limitations, this study evaluates the applicability of deep learning-based object detection models for automating defect detection. Specifically, YOLOv5, YOLOv8, and YOLOv9 were trained and tested under identical conditions using two datasets: a public aircraft defect dataset from Roboflow and a custom-built dataset comprising 30 riveted aluminum panels that simulate real-world fuselage defects. Model performance was assessed using Precision, Recall, and mAP@0.5. Among the three, YOLOv9 achieved the highest accuracy across all metrics, followed by YOLOv8 and YOLOv5. These results demonstrate the effectiveness of YOLO-based models for detecting aircraft surface anomalies and support their potential for integration into automated inspection workflows in real maintenance environments.

Keywords

References

  1. Ultralytics GitHub Repository, "ultralytics/YOLOv8," GitHub, https://github.com/ultralytics/ultralytics
  2. Ministry of Land, Infrastructure and Transport, Aircraft Maintenance Engineer Standard Textbook, 2020. Available at: https://www.kaa.atims.kr/pubs/textbook/
  3. JinSoo Jang, and DooHyun Choi, "Implementation of an OpenCV based Low-Cost Surface Pressure Analysis System," Asia-pacific Journal of Convergent Research Interchange, Vol. 10, No. 4, pp. 37-49, 2024.
  4. Redmon, Joseph, et al., "You Only Look Once: Unified, Real-Time Object Detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp. 779-788, 2016.
  5. Bochkovskiy, Alexey, et al., "YOLOv4: Optimal Speed and Accuracy of Object Detection," arXiv preprint arXiv:2004.10934, 2020.
  6. Ultralytics, "YOLOv8 Documentation," Ultralytics, 2024, https://docs.ultralytics.com.
  7. Rublee, Ethan, et al., "ORB: An Efficient Alternative to SIFT or SURF," 2011 International Conference on Computer Vision(ICCV), IEEE, pp. 2564-2571, 2011.
  8. Rosten, Edward, and Tom Drummond, "Machine Learning for High-Speed Corner Detection," European Conference on Computer Vision(ECCV), Springer, pp. 430-443, 2006.
  9. Harris, Chris, and Mike Stephens, "A Combined Corner and Edge Detector," Alvey Vision Conference, pp. 147-151, 1988.
  10. Roboflow, "Aircraft Skin Defects Dataset," Roboflow Universe, https://universe.roboflow.com/aetherautomations/aircraft-skin-defects, Accessed: 2025.06.07.
  11. National Aircraft Skills Competition Committee, Aircraft Sheet Metal Defect Standards Drawing Book, Seoul: National Skills Competition Committee, 2024.
  12. Y. Chou, "Qatar Airways suspends 21 A350 aircraft due to faulty fuselage surface," World Daily, 2022, https://n.news.naver.com/mnews/article/022/0003661041.
  13. BAA Training, "Basic Aircraft Preflight Inspection," Youtube, 2014, https://youtu.be/x7u2_YcQESo?si=hFkJmZWllSJ224Pv.
  14. Innovation Hangar. Combined Innovation Hangar and Airplane Defect Detection 2 Dataset. Roboflow Universe, 2024, https://universe.roboflow.com/airplane-inspection/combined-innovation-hangar-and-airplane-defect-detection-2/dataset/3.
  15. Jocher, Glenn, et al., "YOLOv5 by Ultralytics," GitHub Repository, https://github.com/ultralytics/yolov5, Accessed May 2025.
  16. Ultralytics, "YOLOv9: SOTA Object Detection with Generalized ELAN and DFLv3," GitHub Repository, https://github.com/ultralytics/yolov9, Accessed May 2025.
  17. Chen, X., et al., "Surface Defect Detection of Metal Components Based on ORB Feature Matching," Journal of Manufacturing Processes, Vol. 48, pp. 205-214, 2019.
  18. Zhang, Y., et al., "ASD-YOLO: An Aircraft Surface Defects Detection Method," Measurement, Vol. 230, p. 114600, 2024.
  19. Li, H., et al., "YOLO-FDD: Efficient Defect Detection Network of Aircraft Skin Fastener Defects," Signal, Image and Video Processing, Vol. 18, pp. 2331-2344, 2023.
  20. Wang, J., et al., "LESM-YOLO: An Improved Aircraft Ducts Defect Detection Model in Low-Light Environments," Sensors, Vol. 24, No. 13, p. 4215, 2024.
  21. Khan, M., et al., "Aircraft Surface Defect Inspection System Using AI with UAVs," Preprint on ResearchGate, 2023.
  22. Chen, X., et al., "Aircraft Skin Machine Learning-Based Defect Detection and Size Estimation," Technologies, Vol. 11, No. 2, p. 158, 2023.