EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detection of micro-pinhole defects on surface of metallized ceramic ring combining improved DETR network with morphological operations

Yisong Xiao iD, Xian Wang iD, Yunlong Liu, Tianlong Yang, Jigang Wu

PLOS One · 2025

DOI: 10.1371/journal.pone.0321849 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Yisong Xiao und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Hunan University of Science and Technology, Xiangtan, China. Hauptthemen laut MEDLINE: Ceramics, Metals. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, the Major Landmark Innovation Demonstration Project in Hunan Province, the National Natural Science Foundation of Hunan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Metallized Ceramic Ring is a novel electronic apparatus widely applied in communication, new energy, aerospace and other fields. Due to its complicated technique, there would be inevitably various defects on its surface; among which, the tiny pinhole defects with complex texture are the most difficult to detect, and there is no reliable method of automatic detection. This Paper proposes a method of detecting micro-pinhole defects on surface of metallized ceramic ring combining Improved Detection Transformer (DETR) Network with morphological operations, utilizing two modules, namely, deep learning-based and morphology-based pinhole defect detection to detect the pinholes, and finally combining the detection results of such two modules, so as to obtain a more accurate result. In order to improve the detection performance of DETR Network in aforesaid module of deep learning, EfficientNet-B2 is used to improve ResNet-50 of standard DETR network, the parameter-free attention mechanism (SimAM) 3-D weight attention mechanism is used to improve Sequeeze-and-Excitation (SE) attention mechanism in EfficientNet-B2 network, and linear combination loss function of Smooth L1 and Complete Intersection over Union (CIoU) is used to improve regressive loss function of training network. The experiment indicates that the recall and the precision of the proposed method are 83.5% and 86.0% respectively, much better than current mainstream methods of micro defect detection, meeting requirements of detection at industrial site.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CeramicsMetalsDeep LearningAlgorithmsSurface PropertiesNeural Networks, Computer

Substanzen

Metals

Autor:innen und Institutionen

  • School of Mechanical Engineering, Hunan University of Science and Technology, Xiangtan, China.
  • State Grid Hunan Electric Power Company Research Institute, Changsha, China.

ORCID-Profile: Yisong Xiao, Xian Wang

Förderung

  • National Key Research and Development Program of China
  • the Major Landmark Innovation Demonstration Project in Hunan Province
  • the National Natural Science Foundation of Hunan Province
  • the Open Research Project of the National Key Laboratory of Offshore Wind Power Generation Equipment and Efficient Wind Energy Utilization

Zitieren

APA

Xiao, Y., Wang, X., Liu, Y., Yang, T., & Wu, J. (2025). Detection of micro-pinhole defects on surface of metallized ceramic ring combining improved DETR network with morphological operations. PLOS One. https://doi.org/10.1371/journal.pone.0321849

Vancouver

Xiao Y, Wang X, Liu Y, Yang T, Wu J. Detection of micro-pinhole defects on surface of metallized ceramic ring combining improved DETR network with morphological operations. PLOS One. 2025. doi:10.1371/journal.pone.0321849

BibTeX
@article{Xiao2025,
  author = {Xiao, Yisong and Wang, Xian and Liu, Yunlong and Yang, Tianlong and Wu, Jigang},
  title = {Detection of micro-pinhole defects on surface of metallized ceramic ring combining improved DETR network with morphological operations},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0321849}
}
Kostenlos starten →