A Comparative Study of Image Representation for Roller Bearing Fault Diagnosis Using Pretrained Networks
Roller bearings are critical components in many types of machinery, and their failure may cause significant downtime and maintenance costs. Fault diagnosis of roller bearings is thus crucial for detecting potential problems before they cause catastrophic failure and for planning maintenance and repa...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Journal of Engineering |
| Online Access: | http://dx.doi.org/10.1155/je/4707723 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850219903345229824 |
|---|---|
| author | M. Arun Balaji S. Naveen Venkatesh V. Sugumaran K. I. Ramachandran |
| author_facet | M. Arun Balaji S. Naveen Venkatesh V. Sugumaran K. I. Ramachandran |
| author_sort | M. Arun Balaji |
| collection | DOAJ |
| description | Roller bearings are critical components in many types of machinery, and their failure may cause significant downtime and maintenance costs. Fault diagnosis of roller bearings is thus crucial for detecting potential problems before they cause catastrophic failure and for planning maintenance and repair operations ahead of time. Early detection of roller bearing failures can help to minimize costly machine downtime and save maintenance costs. This study uses the help of deep learning models for roller bearing fault diagnosis, which can help to minimize machinery downtime and maintenance costs. The study utilizes 12 deep learning modules, and they were evaluated using various image generation methods such as vibration plot, radar plot, polar plot, Hilbert–Huang transforms, spectrogram, and scalogram. From the experimental findings, the ResNet18 model has achieved a 100.00% accuracy when the spectrogram image generation method was employed. The findings highlight the importance of selecting and optimizing deep learning models for a specific maintenance application and contribute valuable insights for researchers and practitioners in reliability engineering. |
| format | Article |
| id | doaj-art-af53bb2f8b4a4436b83e8b668c582e6e |
| institution | OA Journals |
| issn | 2314-4912 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Engineering |
| spelling | doaj-art-af53bb2f8b4a4436b83e8b668c582e6e2025-08-20T02:07:13ZengWileyJournal of Engineering2314-49122025-01-01202510.1155/je/4707723A Comparative Study of Image Representation for Roller Bearing Fault Diagnosis Using Pretrained NetworksM. Arun Balaji0S. Naveen Venkatesh1V. Sugumaran2K. I. Ramachandran3School of Mechanical Engineering (SMEC)Division of Operation and Maintenance EngineeringSchool of Mechanical Engineering (SMEC)Department of Mechanical EngineeringRoller bearings are critical components in many types of machinery, and their failure may cause significant downtime and maintenance costs. Fault diagnosis of roller bearings is thus crucial for detecting potential problems before they cause catastrophic failure and for planning maintenance and repair operations ahead of time. Early detection of roller bearing failures can help to minimize costly machine downtime and save maintenance costs. This study uses the help of deep learning models for roller bearing fault diagnosis, which can help to minimize machinery downtime and maintenance costs. The study utilizes 12 deep learning modules, and they were evaluated using various image generation methods such as vibration plot, radar plot, polar plot, Hilbert–Huang transforms, spectrogram, and scalogram. From the experimental findings, the ResNet18 model has achieved a 100.00% accuracy when the spectrogram image generation method was employed. The findings highlight the importance of selecting and optimizing deep learning models for a specific maintenance application and contribute valuable insights for researchers and practitioners in reliability engineering.http://dx.doi.org/10.1155/je/4707723 |
| spellingShingle | M. Arun Balaji S. Naveen Venkatesh V. Sugumaran K. I. Ramachandran A Comparative Study of Image Representation for Roller Bearing Fault Diagnosis Using Pretrained Networks Journal of Engineering |
| title | A Comparative Study of Image Representation for Roller Bearing Fault Diagnosis Using Pretrained Networks |
| title_full | A Comparative Study of Image Representation for Roller Bearing Fault Diagnosis Using Pretrained Networks |
| title_fullStr | A Comparative Study of Image Representation for Roller Bearing Fault Diagnosis Using Pretrained Networks |
| title_full_unstemmed | A Comparative Study of Image Representation for Roller Bearing Fault Diagnosis Using Pretrained Networks |
| title_short | A Comparative Study of Image Representation for Roller Bearing Fault Diagnosis Using Pretrained Networks |
| title_sort | comparative study of image representation for roller bearing fault diagnosis using pretrained networks |
| url | http://dx.doi.org/10.1155/je/4707723 |
| work_keys_str_mv | AT marunbalaji acomparativestudyofimagerepresentationforrollerbearingfaultdiagnosisusingpretrainednetworks AT snaveenvenkatesh acomparativestudyofimagerepresentationforrollerbearingfaultdiagnosisusingpretrainednetworks AT vsugumaran acomparativestudyofimagerepresentationforrollerbearingfaultdiagnosisusingpretrainednetworks AT kiramachandran acomparativestudyofimagerepresentationforrollerbearingfaultdiagnosisusingpretrainednetworks AT marunbalaji comparativestudyofimagerepresentationforrollerbearingfaultdiagnosisusingpretrainednetworks AT snaveenvenkatesh comparativestudyofimagerepresentationforrollerbearingfaultdiagnosisusingpretrainednetworks AT vsugumaran comparativestudyofimagerepresentationforrollerbearingfaultdiagnosisusingpretrainednetworks AT kiramachandran comparativestudyofimagerepresentationforrollerbearingfaultdiagnosisusingpretrainednetworks |