Advancing Fault Diagnosis for Parallel Misalignment Detection in Induction Motors Based on Convolutional Neural Networks

Maintenance of machines is highly necessary to prolong the operational lifespan of induction motors. Prioritizing preventive measures is crucial in order to prevent more significant damage to the machinery. One of these measures includes detecting abnormalities, such as misalignment, in the motor sh...

Full description

Saved in:
Bibliographic Details
Main Authors: Hanif Adi Rahmawan, Bambang Lelono Widjianto, Katherin Indriawati, Rizki Mendung Ariefianto
Format: Article
Language:English
Published: Departement of Electrical Engineering, Faculty of Engineering, Universitas Brawijaya 2023-09-01
Series:Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems)
Subjects:
Online Access:https://jurnaleeccis.ub.ac.id/index.php/eeccis/article/view/1655
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122999202185216
author Hanif Adi Rahmawan
Bambang Lelono Widjianto
Katherin Indriawati
Rizki Mendung Ariefianto
author_facet Hanif Adi Rahmawan
Bambang Lelono Widjianto
Katherin Indriawati
Rizki Mendung Ariefianto
author_sort Hanif Adi Rahmawan
collection DOAJ
description Maintenance of machines is highly necessary to prolong the operational lifespan of induction motors. Prioritizing preventive measures is crucial in order to prevent more significant damage to the machinery. One of these measures includes detecting abnormalities, such as misalignment, in the motor shaft. This research is aimed to detect the misalignment of induction motor experimentally by varying the coupling between normal and parallel misalignment. The signal readings were analyzed in the frequency domain using Fast Fourier Transform (FFT). The results revealed that in the case of coupling misalignment, a peak appeared at f = 13.5 Hz, whereas in the parallel misalignment condition with a 1 cm misalignment, a peak was found at f+fr = 20 Hz. By utilizing the Convolutional Neural Network (CNN) system, normal and parallel conditions can be detected with an accuracy level of 87.5%.
format Article
id doaj-art-b09d0ac1caea407bb56ba8e294c00ac0
institution Kabale University
issn 2460-8122
language English
publishDate 2023-09-01
publisher Departement of Electrical Engineering, Faculty of Engineering, Universitas Brawijaya
record_format Article
series Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems)
spelling doaj-art-b09d0ac1caea407bb56ba8e294c00ac02024-12-14T10:28:29ZengDepartement of Electrical Engineering, Faculty of Engineering, Universitas BrawijayaJurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems)2460-81222023-09-01172667110.21776/jeeccis.v17i2.16552088Advancing Fault Diagnosis for Parallel Misalignment Detection in Induction Motors Based on Convolutional Neural NetworksHanif Adi Rahmawan0Bambang Lelono Widjianto1Katherin Indriawati2Rizki Mendung Ariefianto3Institut Teknologi Sepuluh NopemberInstitut Teknologi Sepuluh NopemberInstitut Teknologi Sepuluh NopemberUniversitas BrawijayaMaintenance of machines is highly necessary to prolong the operational lifespan of induction motors. Prioritizing preventive measures is crucial in order to prevent more significant damage to the machinery. One of these measures includes detecting abnormalities, such as misalignment, in the motor shaft. This research is aimed to detect the misalignment of induction motor experimentally by varying the coupling between normal and parallel misalignment. The signal readings were analyzed in the frequency domain using Fast Fourier Transform (FFT). The results revealed that in the case of coupling misalignment, a peak appeared at f = 13.5 Hz, whereas in the parallel misalignment condition with a 1 cm misalignment, a peak was found at f+fr = 20 Hz. By utilizing the Convolutional Neural Network (CNN) system, normal and parallel conditions can be detected with an accuracy level of 87.5%.https://jurnaleeccis.ub.ac.id/index.php/eeccis/article/view/1655induction motormisalignmentfftcnn
spellingShingle Hanif Adi Rahmawan
Bambang Lelono Widjianto
Katherin Indriawati
Rizki Mendung Ariefianto
Advancing Fault Diagnosis for Parallel Misalignment Detection in Induction Motors Based on Convolutional Neural Networks
Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems)
induction motor
misalignment
fft
cnn
title Advancing Fault Diagnosis for Parallel Misalignment Detection in Induction Motors Based on Convolutional Neural Networks
title_full Advancing Fault Diagnosis for Parallel Misalignment Detection in Induction Motors Based on Convolutional Neural Networks
title_fullStr Advancing Fault Diagnosis for Parallel Misalignment Detection in Induction Motors Based on Convolutional Neural Networks
title_full_unstemmed Advancing Fault Diagnosis for Parallel Misalignment Detection in Induction Motors Based on Convolutional Neural Networks
title_short Advancing Fault Diagnosis for Parallel Misalignment Detection in Induction Motors Based on Convolutional Neural Networks
title_sort advancing fault diagnosis for parallel misalignment detection in induction motors based on convolutional neural networks
topic induction motor
misalignment
fft
cnn
url https://jurnaleeccis.ub.ac.id/index.php/eeccis/article/view/1655
work_keys_str_mv AT hanifadirahmawan advancingfaultdiagnosisforparallelmisalignmentdetectionininductionmotorsbasedonconvolutionalneuralnetworks
AT bambanglelonowidjianto advancingfaultdiagnosisforparallelmisalignmentdetectionininductionmotorsbasedonconvolutionalneuralnetworks
AT katherinindriawati advancingfaultdiagnosisforparallelmisalignmentdetectionininductionmotorsbasedonconvolutionalneuralnetworks
AT rizkimendungariefianto advancingfaultdiagnosisforparallelmisalignmentdetectionininductionmotorsbasedonconvolutionalneuralnetworks