EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Vibration Signal Processing and Fault Diagnosis Algorithms for High-Pressure Quintuplex Pumps

Zewei Liu, Yuanchen Zhu, Zhigang Zhang, Tao Zhang

Sensors · 04.08.2026 · 26 (15) · 4917

DOI: 10.3390/s26154917 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.08.2026. Verfasst von Zewei Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Sichuan University, Chengdu 610065, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Department of Sichuan Province, Sichuan Provincial Science and Technology Plan Project, Sichuan Provincial Science and Technology Achievement Transfer and Transformation Demonstration Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-pressure quintuplex pumps are key components in oil and gas drilling systems, but their fault diagnosis remains challenging due to severe inter-cylinder vibration crosstalk, operating-condition variability, and limited labeled samples. To address these issues, this paper proposes an integrated vibration-based diagnostic framework, termed VICA-DA-ViT. First, a VMD–FastICA-based blind source separation strategy is used to suppress inter-cylinder crosstalk and extract more discriminative vibration components from mixed signals. Then, angular-domain resampling and normalization are applied to reduce speed-induced non-stationarity and improve cycle consistency. The processed one-dimensional signals are further converted into two-dimensional GAF–RP representations, where GAF captures global temporal correlations and RP provides complementary recurrence information. Finally, a ViT-based domain-adaptive diagnostic framework is constructed for unsupervised cross-condition diagnosis by integrating domain-adversarial pretraining, weighted bidirectional sample pairing, and Gaussian-mixture-based confidence filtering around a standard Vision Transformer backbone. Rather than modifying the internal architecture of ViT, the proposed framework improves cross-condition generalization by combining signal decoupling, angular-domain alignment, and domain-adaptation strategies for high-pressure quintuplex pump fault diagnosis. Experiments on a quintuplex pump dataset under multiple operating conditions show that the proposed framework achieves an average cross-condition accuracy of 87.42%, outperforming CD-Trans by 11.94%. These results demonstrate that VICA-DA-ViT can effectively improve the robustness of small-sample cross-condition fault diagnosis for high-pressure quintuplex pumps.

Schlagwörter

Stichwörter der Autor:innen

Gramian Angular Fieldangular-domain resamplingblind source separationfault diagnosisquintuplex pumpsrecurrence plotunsupervised cross-condition diagnosisvision transformer

Autor:innen und Institutionen

  • School of Mechanical Engineering, Sichuan University, Chengdu 610065, China.

Förderung

  • Science and Technology Department of Sichuan Province
  • Sichuan Provincial Science and Technology Plan Project
  • Sichuan Provincial Science and Technology Achievement Transfer and Transformation Demonstration Project

Zitieren

APA

Liu, Z., Zhu, Y., Zhang, Z., & Zhang, T. (2026). Research on Vibration Signal Processing and Fault Diagnosis Algorithms for High-Pressure Quintuplex Pumps. Sensors, 26(15), 4917. https://doi.org/10.3390/s26154917

Vancouver

Liu Z, Zhu Y, Zhang Z, Zhang T. Research on Vibration Signal Processing and Fault Diagnosis Algorithms for High-Pressure Quintuplex Pumps. Sensors. 2026;26(15):4917. doi:10.3390/s26154917

BibTeX
@article{Liu2026,
  author = {Liu, Zewei and Zhu, Yuanchen and Zhang, Zhigang and Zhang, Tao},
  title = {Research on Vibration Signal Processing and Fault Diagnosis Algorithms for High-Pressure Quintuplex Pumps},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {15},
  pages = {4917},
  doi = {10.3390/s26154917}
}
Kostenlos starten →