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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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!
|
| Summary: | 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%. |
|---|---|
| ISSN: | 2460-8122 |