A Deep Learning-Based Hybrid Approach to Detect Fastener Defects in Real-Time
A fastener is an important component used to fix the rail in railways. Defects in this component cause the rail and ballast to remain unstable. If the defective fasteners are not replaced in time, it is inevitable that the train will derail, and serious accidents will occur. Therefore, this componen...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
2023-01-01
|
| Series: | Tehnički Vjesnik |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/444169 |
| _version_ | 1797206383232286720 |
|---|---|
| author | Ilhan Aydin Mehmet Sevi Erhan Akin Emre Güçlü Mehmet Karaköse Hssen Aldarwich |
| author_facet | Ilhan Aydin Mehmet Sevi Erhan Akin Emre Güçlü Mehmet Karaköse Hssen Aldarwich |
| author_sort | Ilhan Aydin |
| collection | DOAJ |
| description | A fastener is an important component used to fix the rail in railways. Defects in this component cause the rail and ballast to remain unstable. If the defective fasteners are not replaced in time, it is inevitable that the train will derail, and serious accidents will occur. Therefore, this component should be inspected periodically. Conventional image processing-based control systems are affected by noise and different lighting conditions in the real environment. In this study, it is aimed to determine the defects of fasteners with a deep learning-based hybrid approach. The YOLOv4-Tiny method is used for fastener detection and localization. This method gives accurate results, especially for the detection of small objects. After the fastener position is determined, a new lightweight convolutional neural network model is used for defect classification. The proposed convolutional neural network for classification has a small network structure because it uses depth-wise and pointwise convolution layers. When the experimental results are compared with other known transfer learning methods, better results were obtained in terms of training/test time and accuracy. |
| first_indexed | 2024-04-24T09:06:08Z |
| format | Article |
| id | doaj.art-69b6d13bdff44b8393b52389012dfc0f |
| institution | Directory Open Access Journal |
| issn | 1330-3651 1848-6339 |
| language | English |
| last_indexed | 2024-04-24T09:06:08Z |
| publishDate | 2023-01-01 |
| publisher | Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek |
| record_format | Article |
| series | Tehnički Vjesnik |
| spelling | doaj.art-69b6d13bdff44b8393b52389012dfc0f2024-04-15T18:52:13ZengFaculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in OsijekTehnički Vjesnik1330-36511848-63392023-01-013051461146810.17559/TV-20221020152721A Deep Learning-Based Hybrid Approach to Detect Fastener Defects in Real-TimeIlhan Aydin0Mehmet Sevi1Erhan Akin2Emre Güçlü3Mehmet Karaköse4Hssen Aldarwich5Fırat University, Elazığ, TurkeyMuş Alparslan University, Muş, TurkeyFırat University, Elazığ, TurkeyFırat University, Elazığ, TurkeyFırat University, Elazığ, TurkeyFırat University, Elazığ, TurkeyA fastener is an important component used to fix the rail in railways. Defects in this component cause the rail and ballast to remain unstable. If the defective fasteners are not replaced in time, it is inevitable that the train will derail, and serious accidents will occur. Therefore, this component should be inspected periodically. Conventional image processing-based control systems are affected by noise and different lighting conditions in the real environment. In this study, it is aimed to determine the defects of fasteners with a deep learning-based hybrid approach. The YOLOv4-Tiny method is used for fastener detection and localization. This method gives accurate results, especially for the detection of small objects. After the fastener position is determined, a new lightweight convolutional neural network model is used for defect classification. The proposed convolutional neural network for classification has a small network structure because it uses depth-wise and pointwise convolution layers. When the experimental results are compared with other known transfer learning methods, better results were obtained in terms of training/test time and accuracy.https://hrcak.srce.hr/file/444169defect detectiondeep learningfastenerobject detectionrailway system |
| spellingShingle | Ilhan Aydin Mehmet Sevi Erhan Akin Emre Güçlü Mehmet Karaköse Hssen Aldarwich A Deep Learning-Based Hybrid Approach to Detect Fastener Defects in Real-Time Tehnički Vjesnik defect detection deep learning fastener object detection railway system |
| title | A Deep Learning-Based Hybrid Approach to Detect Fastener Defects in Real-Time |
| title_full | A Deep Learning-Based Hybrid Approach to Detect Fastener Defects in Real-Time |
| title_fullStr | A Deep Learning-Based Hybrid Approach to Detect Fastener Defects in Real-Time |
| title_full_unstemmed | A Deep Learning-Based Hybrid Approach to Detect Fastener Defects in Real-Time |
| title_short | A Deep Learning-Based Hybrid Approach to Detect Fastener Defects in Real-Time |
| title_sort | deep learning based hybrid approach to detect fastener defects in real time |
| topic | defect detection deep learning fastener object detection railway system |
| url | https://hrcak.srce.hr/file/444169 |
| work_keys_str_mv | AT ilhanaydin adeeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT mehmetsevi adeeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT erhanakin adeeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT emreguclu adeeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT mehmetkarakose adeeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT hssenaldarwich adeeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT ilhanaydin deeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT mehmetsevi deeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT erhanakin deeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT emreguclu deeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT mehmetkarakose deeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime AT hssenaldarwich deeplearningbasedhybridapproachtodetectfastenerdefectsinrealtime |