FPGA-Microprocessor Based Sensor for Faults Detection in Induction Motors Using Time-Frequency and Machine Learning Methods
Sensors · 22.04.2024 · 24 (8) · 2653
DOI: 10.3390/s24082653 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.04.2024. Verfasst von Roque Alfredo Osornio-Rios und 5 weiteren Autor:innen. Beteiligte Einrichtung: Cuerpo Académico (CA) Mecatrónica, Facultad de Ingeniería, Campus San Juan del Río, Universidad Autónoma de Querétaro, Av. Río Moctezuma 249, San Jua…. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Spanish 'Ministerio de Ciencia Innovación y Universidades' and FEDER program, the Spanish ‘Ministerio de Ciencia Innovación y Universidades’, FEDER program in the framework of the ‘Proyectos de Generación de Conocimiento 2021 del Programa Estatal para Impulsar la Investigación Científico-Técnica y su….
Abstract (Originalsprache)
Induction motors (IM) play a fundamental role in the industrial sector because they are robust, efficient, and low-cost machines. Changes in the environment, installation errors, or modifications to working conditions can generate faults in induction motors. The trend on IM fault detection is focused on the design techniques and sensors capable of evaluating multiple faults with various signals using non-invasive analysis. The methodology is based on processing electric current signals by applying the short-time Fourier transform (STFT). Additionally, the computation of the mean and standard deviation of infrared thermograms is proposed as main indicators. The proposed system combines both parameters by means of Support Vector Machine and k-nearest-neighbor classifiers. The development of the diagnostic system was done with digital hardware implementations using a Xilinx PYNQ Z2 card that integrates an FPGA with a microprocessor, thus taking advantage of the acquisition and processing of digital signals and images in hardware. The proposed method has proved to be effective for the classification of healthy (HLT), misalignment (MAMT), unbalance (UNB), damaged bearing (BDF), and broken rotor bar (BRB) faults with an accuracy close to 99%.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cuerpo Académico (CA) Mecatrónica, Facultad de Ingeniería, Campus San Juan del Río, Universidad Autónoma de Querétaro, Av. Río Moctezuma 249, San Juan del Río 76807, Querétaro, Mexico.
- Departamento de Ingeniería Gráfica, Universitat Politecnica de Valencia (UPV), 46022 Valencia, Spain.
- Instituto Tecnológico de la Energía, Universitat Politecnica de Valencia (UPV), Camino de Vera s/n, 46022 Valencia, Spain.
ORCID-Profile: Roque Alfredo Osornio-Rios, Isaias Cueva-Perez, Alvaro Ivan Alvarado-Hernandez, Larisa Dunai, Jose Alfonso Antonino-Daviu
Förderung
- Spanish 'Ministerio de Ciencia Innovación y Universidades' and FEDER program
- the Spanish ‘Ministerio de Ciencia Innovación y Universidades’
- FEDER program in the framework of the ‘Proyectos de Generación de Conocimiento 2021 del Programa Estatal para Impulsar la Investigación Científico-Técnica y su…
Zitieren
APA
Osornio-Rios, R. A., Cueva-Perez, I., Alvarado-Hernandez, A. I., Dunai, L., Zamudio-Ramirez, I., & Antonino-Daviu, J. A. (2024). FPGA-Microprocessor Based Sensor for Faults Detection in Induction Motors Using Time-Frequency and Machine Learning Methods. Sensors, 24(8), 2653. https://doi.org/10.3390/s24082653
Vancouver
Osornio-Rios RA, Cueva-Perez I, Alvarado-Hernandez AI, Dunai L, Zamudio-Ramirez I, Antonino-Daviu JA. FPGA-Microprocessor Based Sensor for Faults Detection in Induction Motors Using Time-Frequency and Machine Learning Methods. Sensors. 2024;24(8):2653. doi:10.3390/s24082653
BibTeX
@article{OsornioRios2024,
author = {Osornio-Rios, Roque Alfredo and Cueva-Perez, Isaias and Alvarado-Hernandez, Alvaro Ivan and Dunai, Larisa and Zamudio-Ramirez, Israel and Antonino-Daviu, Jose Alfonso},
title = {FPGA-Microprocessor Based Sensor for Faults Detection in Induction Motors Using Time-Frequency and Machine Learning Methods},
journal = {Sensors},
year = {2024},
volume = {24},
number = {8},
pages = {2653},
doi = {10.3390/s24082653}
}
EUVIMED