EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A CNN-Based Methodology for Identifying Mechanical Faults in Induction Motors Using Thermography

Omar Trejo-Chavez, Irving A. Cruz-Albarran, Emmanuel Resendiz-Ochoa, Alejandro Salinas-Aguilar, Luis A. Morales-Hernandez, Jesus A. Basurto-Hurtado, Carlos A. Perez-Ramirez

Machines · 18.07.2023 · 11 (7) · 752

DOI: 10.3390/machines11070752 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 18.07.2023. Verfasst von Omar Trejo-Chavez und 6 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared thermography (IRT) has become an interesting alternative for performing condition assessments of different types of induction motor (IM)-based equipment when it operates under harsh conditions. The reported results from state-of-the-art articles that have analyzed thermal images do not consider (1): the presence of more than one fault, and (2) the inevitable noise-corruption the images suffer. Bearing in mind these reasons, this paper presents a convolutional neural network (CNN)-based methodology that is specifically designed to deal with noise-corrupted images for detecting the failures that have the highest incidence rate: bearing and broken bar failures; moreover, rotor misalignment failure is also considered, as it can cause a further increase in electricity consumption. The presented results show that the proposal is effective in detecting healthy and failure states, as well as identifying the failure nature, as a 95% accuracy is achieved. These results allow considering the proposal as an interesting alternative for using IRT images obtained in hostile environments.

Zitieren

APA

Trejo-Chavez, O., Cruz-Albarran, I. A., Resendiz-Ochoa, E., Salinas-Aguilar, A., Morales-Hernandez, L. A., Basurto-Hurtado, J. A., & Perez-Ramirez, C. A. (2023). A CNN-Based Methodology for Identifying Mechanical Faults in Induction Motors Using Thermography. Machines, 11(7), 752. https://doi.org/10.3390/machines11070752

Vancouver

Trejo-Chavez O, Cruz-Albarran IA, Resendiz-Ochoa E, Salinas-Aguilar A, Morales-Hernandez LA, Basurto-Hurtado JA, et al. A CNN-Based Methodology for Identifying Mechanical Faults in Induction Motors Using Thermography. Machines. 2023;11(7):752. doi:10.3390/machines11070752

BibTeX
@article{TrejoChavez2023,
  author = {Trejo-Chavez, Omar and Cruz-Albarran, Irving A. and Resendiz-Ochoa, Emmanuel and Salinas-Aguilar, Alejandro and Morales-Hernandez, Luis A. and Basurto-Hurtado, Jesus A. and Perez-Ramirez, Carlos A.},
  title = {A CNN-Based Methodology for Identifying Mechanical Faults in Induction Motors Using Thermography},
  journal = {Machines},
  year = {2023},
  volume = {11},
  number = {7},
  pages = {752},
  doi = {10.3390/machines11070752}
}
Kostenlos starten →