EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A lightweight vision-based framework for automated aero-engine blade damage inspection

Xiaobo Ning, Hang Zhao iD, Kang Zeng, Zhengwei Zhang

PLOS One · 05.11.2026 · 21 (11) · e0362006

DOI: 10.1371/journal.pone.0362006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 05.11.2026. Verfasst von Xiaobo Ning und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Aviation, Zhejiang Institute of Communications, Hangzhou, Zhejiang, China. Hauptthemen laut MEDLINE: Aircraft. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Institute of Communications.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated visual inspection of aero-engine blades is central to aviation safety, yet it is challenged by damage that is small and low-contrast against a strongly textured metal surface, and by the need for models that are light enough for edge deployment. This paper presents a lightweight vision-based framework for automated blade damage inspection. Rather than assembling independent detection modules, the framework is organized as a three-stage inspection pipeline: (1) a multi-scale feature-discrimination stage (MSBlock) captures defects across a wide size range at negligible computational cost; (2) a texture-suppression stage (TSA) filters high-frequency machining-background noise through product-based channel–spatial attention, exposing genuine defects; and (3) an efficient-prediction stage (Detect_Efficient) fuses cross-scale features and recalibrates confidence with roughly half the parameters of a standard head. On a self-built engine-blade dataset, the framework improves recall, F1-score, and mAP@0.5 by 4.8, 1.9, and 0.8 percentage points over YOLOv11n (reaching 92.0%, 91.6%, and 94.2%), while cutting parameters and computation by 50.0% and 58.7% and reaching 527 FPS. It also outperforms YOLOv8n, YOLOv9t, and YOLOv10n in recall and F1-score, confirming its suitability for real-time edge-based blade inspection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AircraftDetection AlgorithmsAutomationAlgorithms

Autor:innen und Institutionen

  • School of Aviation, Zhejiang Institute of Communications, Hangzhou, Zhejiang, China.
  • School of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China.
  • Loongair(Hangzhou) Aviation Maintenance Engineering Co., Ltd., Hangzhou, Zhejiang, China.

ORCID-Profile: Hang Zhao

Förderung

  • Zhejiang Institute of Communications

Zitieren

APA

Ning, X., Zhao, H., Zeng, K., & Zhang, Z. (2026). A lightweight vision-based framework for automated aero-engine blade damage inspection. PLOS One, 21(11), e0362006. https://doi.org/10.1371/journal.pone.0362006

Vancouver

Ning X, Zhao H, Zeng K, Zhang Z. A lightweight vision-based framework for automated aero-engine blade damage inspection. PLOS One. 2026;21(11):e0362006. doi:10.1371/journal.pone.0362006

BibTeX
@article{Ning2026,
  author = {Ning, Xiaobo and Zhao, Hang and Zeng, Kang and Zhang, Zhengwei},
  title = {A lightweight vision-based framework for automated aero-engine blade damage inspection},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0362006},
  doi = {10.1371/journal.pone.0362006}
}
Kostenlos starten →