EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Comparative Analysis of Deep Learning Convolutional Neural Network Architectures for Fault Diagnosis of Broken Rotor Bars in Induction Motors

Kevin Barrera-Llanga iD, Jordi Burriel-Valencia iD, Ángel Sapena-Bañó iD, Javier Martínez-Román iD

Sensors · 30.09.2023 · 23 (19) · 8196

DOI: 10.3390/s23198196 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.09.2023. Verfasst von Kevin Barrera-Llanga und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Energy Engineering, Universitat Politècnica de València, Camino de Vera s/n, 46022 Valencia, Spain. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MCIN/AEI/10.13039/501100011033, Generalitat Valenciana.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Induction machines (IMs) play a critical role in various industrial processes but are susceptible to degenerative failures, such as broken rotor bars. Effective diagnostic techniques are essential in addressing these issues. In this study, we propose the utilization of convolutional neural networks (CNNs) for detection of broken rotor bars. To accomplish this, we generated a dataset comprising current samples versus angular position using finite element method magnetics (FEMM) software for a squirrel-cage rotor with 28 bars, including scenarios with 0 to 6 broken bars at every possible relative position. The dataset consists of a total of 16,050 samples per motor. We evaluated the performance of six different CNN architectures, namely Inception V4, NasNETMobile, ResNET152, SeNET154, VGG16, and VGG19. Our automatic classification system demonstrated an impressive 99% accuracy in detecting broken rotor bars, with VGG19 performing exceptionally well. Specifically, VGG19 exhibited high accuracy, precision, recall, and F1-Score, with values approaching 0.994 and 0.998. Notably, VGG19 exhibited crucial activations in its feature maps, particularly after domain-specific training, highlighting its effectiveness in fault detection. Comparing CNN architectures assists in selecting the most suitable one for this application based on processing time, effectiveness, and training losses. This research suggests that deep learning can detect broken bars in induction machines with accuracy comparable to that of traditional methods by analyzing current signals using CNNs.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligenceautomatic diagnosisbroken bar detectionconvolutional neural networkdeep learninginduction machine

Autor:innen und Institutionen

  • Institute for Energy Engineering, Universitat Politècnica de València, Camino de Vera s/n, 46022 Valencia, Spain.

ORCID-Profile: Kevin Barrera-Llanga, Jordi Burriel-Valencia, Ángel Sapena-Bañó, Javier Martínez-Román

Förderung

  • MCIN/AEI/10.13039/501100011033
  • Generalitat Valenciana

Zitieren

APA

Barrera-Llanga, K., Burriel-Valencia, J., Sapena-Bañó, Á., & Martínez-Román, J. (2023). A Comparative Analysis of Deep Learning Convolutional Neural Network Architectures for Fault Diagnosis of Broken Rotor Bars in Induction Motors. Sensors, 23(19), 8196. https://doi.org/10.3390/s23198196

Vancouver

Barrera-Llanga K, Burriel-Valencia J, Sapena-Bañó Á, Martínez-Román J. A Comparative Analysis of Deep Learning Convolutional Neural Network Architectures for Fault Diagnosis of Broken Rotor Bars in Induction Motors. Sensors. 2023;23(19):8196. doi:10.3390/s23198196

BibTeX
@article{BarreraLlanga2023,
  author = {Barrera-Llanga, Kevin and Burriel-Valencia, Jordi and Sapena-Bañó, Ángel and Martínez-Román, Javier},
  title = {A Comparative Analysis of Deep Learning Convolutional Neural Network Architectures for Fault Diagnosis of Broken Rotor Bars in Induction Motors},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {19},
  pages = {8196},
  doi = {10.3390/s23198196}
}
Kostenlos starten →