EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning

Cem Ekin Sunal iD, Vladan Velisavljevic iD, Vladimir Dyo iD, Barry Newton, Jake Newton

Sensors · 11.04.2024 · 24 (8) · 2442

DOI: 10.3390/s24082442 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.04.2024. Verfasst von Cem Ekin Sunal und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, University of Bedfordshire, Luton LU1 3JU, UK. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovate UK, Deckpro Pumps/Uptime Systems Ltd., Innovate U.K..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The centrifugal pump is the workhorse of many industrial and domestic applications, such as water supply, wastewater treatment and heating. While modern pumps are reliable, their unexpected failures may jeopardise safety or lead to significant financial losses. Consequently, there is a strong demand for early fault diagnosis, detection and predictive monitoring systems. Most prior work on machine learning-based centrifugal pump fault detection is based on either synthetic data, simulations or data from test rigs in controlled laboratory conditions. In this research, we attempted to detect centrifugal pump faults using data collected from real operational pumps deployed in various places in collaboration with a specialist pump engineering company. The detection was done by the binary classification of visual features of DQ/Concordia patterns with residual networks. Besides using a real dataset, this study employed transfer learning from the image detection domain to systematically solve a real-life problem in the engineering domain. By feeding DQ image data into a popular and high-performance residual network (e.g., ResNet-34), the proposed approach achieved up to 85.51% classification accuracy.

Schlagwörter

Stichwörter der Autor:innen

Internet of thingscentrifugal pumpcondition monitoringmachine learning

Autor:innen und Institutionen

  • School of Computer Science and Technology, University of Bedfordshire, Luton LU1 3JU, UK.
  • Department of Electronic Engineering, Royal Holloway, University of London, Egham TW20 0EX, UK.
  • Uptime Systems Ltd., Leighton Buzzard LU7 4WG, UK.

ORCID-Profile: Cem Ekin Sunal, Vladan Velisavljevic, Vladimir Dyo

Förderung

  • Innovate UK
  • Deckpro Pumps/Uptime Systems Ltd.
  • Innovate U.K.

Zitieren

APA

Sunal, C. E., Velisavljevic, V., Dyo, V., Newton, B., & Newton, J. (2024). Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning. Sensors, 24(8), 2442. https://doi.org/10.3390/s24082442

Vancouver

Sunal CE, Velisavljevic V, Dyo V, Newton B, Newton J. Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning. Sensors. 2024;24(8):2442. doi:10.3390/s24082442

BibTeX
@article{Sunal2024,
  author = {Sunal, Cem Ekin and Velisavljevic, Vladan and Dyo, Vladimir and Newton, Barry and Newton, Jake},
  title = {Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {8},
  pages = {2442},
  doi = {10.3390/s24082442}
}
Kostenlos starten →