EUVIMEDEUVIMED entdecken
Crossref

Spatial Contrast and Semantic Difference Perception Network for Aeroengine Blade Damage Segmentation

Chuhan Wang, Haiyong Chen, Yining Wang, Shenshen Zhao, Kun Liu

IEEE Transactions on Aerospace and Electronic Systems · 2025-04 · 61 (2) · 2040-2056

DOI: 10.1109/taes.2024.3467208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2025-04. Verfasst von Chuhan Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Hebei Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aeroengine blades are critical components in engines, and any minor surface damage may lead to severe consequences. Therefore, high-precision damage segmentation techniques are crucial for accurately identifying blade damage. However, the high-precision localization of blade damages faces challenges due to the loss of detailed spatial features and the confusion of semantic features. In this article, we propose a spatial contrast and semantic difference perception network (SSPN) for aeroengine blade damage segmentation, which effectively enhances the discriminative ability of spatial and semantic feature representations. Specifically, we propose a class-aware spatial contrast (CSC) module to first generate segmentation masks and highlight categories. Then, CSC utilizes a class-aware contrastive learning method to enhance the distinguishability of spatial features. To establish clear semantic boundaries, we design a semantic difference perception (SDP) module that first extracts semantic difference information between feature maps. Then, SDP uses a difference perception loss function to focus on low-quality areas and capture subtle semantic variances, which can produce a more balanced and contrasting semantic feature representation. We conduct comprehensive experiments to demonstrate the superiority of SSPN that achieves 93.42% mIoU on our blade dataset, surpassing existing state-of-the-art methods. Furthermore, we build an aeroengine blade damage analysis system to formulate more rational and economical maintenance strategies that can facilitate the development of the aviation engineering field.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Hebei Province
  • Interdisciplinary postgraduate Training Program of Hebei University of Technology

Zitieren

APA

Wang, C., Chen, H., Wang, Y., Zhao, S., & Liu, K. (2025). Spatial Contrast and Semantic Difference Perception Network for Aeroengine Blade Damage Segmentation. IEEE Transactions on Aerospace and Electronic Systems, 61(2), 2040-2056. https://doi.org/10.1109/taes.2024.3467208

Vancouver

Wang C, Chen H, Wang Y, Zhao S, Liu K. Spatial Contrast and Semantic Difference Perception Network for Aeroengine Blade Damage Segmentation. IEEE Transactions on Aerospace and Electronic Systems. 2025;61(2):2040-2056. doi:10.1109/taes.2024.3467208

BibTeX
@article{Wang2025,
  author = {Wang, Chuhan and Chen, Haiyong and Wang, Yining and Zhao, Shenshen and Liu, Kun},
  title = {Spatial Contrast and Semantic Difference Perception Network for Aeroengine Blade Damage Segmentation},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2025},
  volume = {61},
  number = {2},
  pages = {2040--2056},
  doi = {10.1109/taes.2024.3467208}
}
Kostenlos starten →