EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Pipeline Magnetic Flux Leakage Testing Defect Classification Based on Generate Expansion and Dual-Channel Vision Transformer

Xulai Zhu, Yuxiang Zhang, Qiansheng Fang, Jin Jiang, Nana Zhang, Shiheng Tang, Gongquan Zhang

Applied Sciences · 19.06.2026 · 16 (12) · 6214

DOI: 10.3390/app16126214 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 19.06.2026. Verfasst von Xulai Zhu und 6 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Anhui Provincial Natural Science Foundation Key Project, Higher Education Doctoral Student Entrepreneurship Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Magnetic flux leakage (MFL) testing is a vital non-destructive testing method used to identify defects in oil and gas pipelines and critical components. However, variations in defect geometry and testing conditions can lead to inaccurate data and imbalanced feature distributions, which compromise detection outcomes. To address these challenges, this paper presents a defect classification approach for MFL testing based on generating expansion and the Dual-Channel Vision Transformer (DC-ViT). First, COMSOL finite element software (version 6.1) was used to simulate magnetic flux leakage for different types of pipeline defects. Axial and radial dual-channel signals were extracted to create the initial dataset. Next, a Conditional Variational Autoencoder (CVAE) was used for Generate Expansion to effectively mitigate sample scarcity and defect category imbalance. Finally, the DC-ViT model was constructed and trained using the Generate Expansion dataset as input to achieve multidimensional feature fusion and classification prediction for defects. Experimental results demonstrate 97.97% detection accuracy. The DC-ViT model outperforms traditional convolutional neural networks and single-channel models in terms of accuracy, precision, recall, and F1-score. These results validate the method’s effectiveness and robustness in complex defect scenarios and offer a novel approach to magnetic leakage signal detection.

Förderung

  • National Key R&D Program of China
  • Anhui Provincial Natural Science Foundation Key Project
  • Higher Education Doctoral Student Entrepreneurship Fund

Zitieren

APA

Zhu, X., Zhang, Y., Fang, Q., Jiang, J., Zhang, N., Tang, S., & Zhang, G. (2026). Research on Pipeline Magnetic Flux Leakage Testing Defect Classification Based on Generate Expansion and Dual-Channel Vision Transformer. Applied Sciences, 16(12), 6214. https://doi.org/10.3390/app16126214

Vancouver

Zhu X, Zhang Y, Fang Q, Jiang J, Zhang N, Tang S, et al. Research on Pipeline Magnetic Flux Leakage Testing Defect Classification Based on Generate Expansion and Dual-Channel Vision Transformer. Applied Sciences. 2026;16(12):6214. doi:10.3390/app16126214

BibTeX
@article{Zhu2026,
  author = {Zhu, Xulai and Zhang, Yuxiang and Fang, Qiansheng and Jiang, Jin and Zhang, Nana and Tang, Shiheng and Zhang, Gongquan},
  title = {Research on Pipeline Magnetic Flux Leakage Testing Defect Classification Based on Generate Expansion and Dual-Channel Vision Transformer},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {12},
  pages = {6214},
  doi = {10.3390/app16126214}
}
Kostenlos starten →