EUVIMEDEUVIMED entdecken
Crossref

GC-Net: a surface defect detection network for aero-engine with geometric adaptation and context optimization

Xiongxin Li, Sirui Chen, Kaomin Zhang, Tao Xie

Measurement Science and Technology · 22.05.2026 · 37 (21) · 216204

DOI: 10.1088/1361-6501/ae6dec ↗

Kurz gefasst

Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 27.05.2026. Verfasst von Xiongxin Li und 3 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The safe and reliable operation of aero-engines critically depends on the structural integrity of their key components. To address the challenges in aero-engine defect detection, including diverse morphologies, complex backgrounds, small targets, and large-scale variations, a geometry-adaptive and context-optimized fusion network (GC-Net) was proposed. To enhance feature extraction for geometrically complex defects, an adaptive geometric convolution module dynamically aligns convolution kernels with irregular contours of defects via deformable sampling and an edge-aware mechanism. A cascaded context optimization module was designed to integrate dual-path channel aggregation and dual-axis spatial attention to suppress background interference and improve the feature representation of small targets. A dual-direction detail-enhanced fusion network was constructed to facilitate deep interactions across multi-scale features and improve detection consistency for defects at different scales. A cross-scale fusion detection head was developed to achieve dynamic multi-scale feature fusion and accurate bounding box localization. Furthermore, a composite regression loss function combining scale‐dynamic loss and shape‐aware IoU was designed to further optimize the model’s performance in detecting multi‐scale and irregularly shaped defects. Experimental results on a self-built aero-engine borescope image dataset show that GC-Net surpasses the baseline model by 4.8% in mAP 50 and 3.8% in mAP 50:95 , with notable relative improvements on small and medium-sized defects despite severe class imbalance inherent in real-world inspection data. The model achieves a recall of 81.5% and a precision of 93.3%, while maintaining 5.1 M parameters and 135.5 FPS. Cross-domain experiments on the public industrial surface defect datasets GC10-DET and NEU-DET further validate the robustness and transferability of the proposed method, demonstrating its potential applicability beyond the specific aero-engine domain. GC-Net achieves an excellent balance between accuracy, speed, and model complexity, offering a reliable and efficient visual inspection solution for the intelligent maintenance of aero-engines.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, X., Chen, S., Zhang, K., & Xie, T. (2026). GC-Net: a surface defect detection network for aero-engine with geometric adaptation and context optimization. Measurement Science and Technology, 37(21), 216204. https://doi.org/10.1088/1361-6501/ae6dec

Vancouver

Li X, Chen S, Zhang K, Xie T. GC-Net: a surface defect detection network for aero-engine with geometric adaptation and context optimization. Measurement Science and Technology. 2026;37(21):216204. doi:10.1088/1361-6501/ae6dec

BibTeX
@article{Li2026,
  author = {Li, Xiongxin and Chen, Sirui and Zhang, Kaomin and Xie, Tao},
  title = {GC-Net: a surface defect detection network for aero-engine with geometric adaptation and context optimization},
  journal = {Measurement Science and Technology},
  year = {2026},
  volume = {37},
  number = {21},
  pages = {216204},
  doi = {10.1088/1361-6501/ae6dec}
}
Kostenlos starten →