Comparison of Recognition Techniques to Classify Wear Particle Texture
Wear particle analysis, which identifies failure modes caused by the wear of various machine components, is an essential technique for monitoring machinery conditions. This analysis plays a vital role in predictive maintenance by revealing component degradation in machinery. This study proposes an a...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Eng |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4117/6/6/107 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839654176712294400 |
|---|---|
| author | Mohammad Laghari Ahmed Hassan Mahmoud Haggag Addy Wahyudie Motaz Tayfor Abdallah Elsayed |
| author_facet | Mohammad Laghari Ahmed Hassan Mahmoud Haggag Addy Wahyudie Motaz Tayfor Abdallah Elsayed |
| author_sort | Mohammad Laghari |
| collection | DOAJ |
| description | Wear particle analysis, which identifies failure modes caused by the wear of various machine components, is an essential technique for monitoring machinery conditions. This analysis plays a vital role in predictive maintenance by revealing component degradation in machinery. This study proposes an automated framework to classify four standard wear particle textures—rough, striated, pitted, and fatigued—using artificial neural networks (ANNs) combined with advanced image processing techniques. Images acquired via Charged-Coupled Device (CCD) microscopy were preprocessed using sharpening, histogram stretching, and four edge detection algorithms: Sobel, Laplacian, Boie–Cox, and Canny. The Laplacian and Canny methods yielded the highest classification accuracies of 97.9% and 98.9%, respectively. By minimizing human subjectivity, this automated approach enhances diagnostic consistency and represents a scalable solution for industrial condition monitoring. |
| format | Article |
| id | doaj-art-da8ac5acb72c44d6ac3dfad7c79fd18f |
| institution | Matheson Library |
| issn | 2673-4117 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Eng |
| spelling | doaj-art-da8ac5acb72c44d6ac3dfad7c79fd18f2025-06-25T13:46:02ZengMDPI AGEng2673-41172025-05-016610710.3390/eng6060107Comparison of Recognition Techniques to Classify Wear Particle TextureMohammad Laghari0Ahmed Hassan1Mahmoud Haggag2Addy Wahyudie3Motaz Tayfor4Abdallah Elsayed5Department of Electrical and Communication Engineering, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab EmiratesDepartment of Architectural Engineering, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab EmiratesDepartment of Architectural Engineering, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab EmiratesDepartment of Electrical and Communication Engineering, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab EmiratesDepartment of Electrical and Communication Engineering, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab EmiratesDepartment of Electrical and Communication Engineering, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab EmiratesWear particle analysis, which identifies failure modes caused by the wear of various machine components, is an essential technique for monitoring machinery conditions. This analysis plays a vital role in predictive maintenance by revealing component degradation in machinery. This study proposes an automated framework to classify four standard wear particle textures—rough, striated, pitted, and fatigued—using artificial neural networks (ANNs) combined with advanced image processing techniques. Images acquired via Charged-Coupled Device (CCD) microscopy were preprocessed using sharpening, histogram stretching, and four edge detection algorithms: Sobel, Laplacian, Boie–Cox, and Canny. The Laplacian and Canny methods yielded the highest classification accuracies of 97.9% and 98.9%, respectively. By minimizing human subjectivity, this automated approach enhances diagnostic consistency and represents a scalable solution for industrial condition monitoring.https://www.mdpi.com/2673-4117/6/6/107wear particlestexture identificationimage processingartificial neural networks |
| spellingShingle | Mohammad Laghari Ahmed Hassan Mahmoud Haggag Addy Wahyudie Motaz Tayfor Abdallah Elsayed Comparison of Recognition Techniques to Classify Wear Particle Texture Eng wear particles texture identification image processing artificial neural networks |
| title | Comparison of Recognition Techniques to Classify Wear Particle Texture |
| title_full | Comparison of Recognition Techniques to Classify Wear Particle Texture |
| title_fullStr | Comparison of Recognition Techniques to Classify Wear Particle Texture |
| title_full_unstemmed | Comparison of Recognition Techniques to Classify Wear Particle Texture |
| title_short | Comparison of Recognition Techniques to Classify Wear Particle Texture |
| title_sort | comparison of recognition techniques to classify wear particle texture |
| topic | wear particles texture identification image processing artificial neural networks |
| url | https://www.mdpi.com/2673-4117/6/6/107 |
| work_keys_str_mv | AT mohammadlaghari comparisonofrecognitiontechniquestoclassifywearparticletexture AT ahmedhassan comparisonofrecognitiontechniquestoclassifywearparticletexture AT mahmoudhaggag comparisonofrecognitiontechniquestoclassifywearparticletexture AT addywahyudie comparisonofrecognitiontechniquestoclassifywearparticletexture AT motaztayfor comparisonofrecognitiontechniquestoclassifywearparticletexture AT abdallahelsayed comparisonofrecognitiontechniquestoclassifywearparticletexture |