A Lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological Reasoning
Bearing as a critical component of machinery and equipment, its state of health directly affects the operating efficiency and security of the equipment. Therefore, the quality control of bearings must be very strict. Aiming at the different sizes and textures of the defect types on the surface of th...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11072476/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849319912137293824 |
|---|---|
| author | Xiaolin Shi Haisong Xu Han Zhang Yi Li Xinshuo Li Fan Yang |
| author_facet | Xiaolin Shi Haisong Xu Han Zhang Yi Li Xinshuo Li Fan Yang |
| author_sort | Xiaolin Shi |
| collection | DOAJ |
| description | Bearing as a critical component of machinery and equipment, its state of health directly affects the operating efficiency and security of the equipment. Therefore, the quality control of bearings must be very strict. Aiming at the different sizes and textures of the defect types on the surface of the outer ring of the bearing, and the fact that most of the target detection algorithms relying on deep learning show low speed and low precision in the detection of defects on the surface of the bearing, this paper presents a lightweight method for detecting the defects on the surface of the bearing based on deep learning and ontological reasoning. In this paper, YOLOv5s is chosen as the baseline model. First, the dynamic convolution is fused with the Ghost module and the combined structure is embedded into the C3 module, thus constructing a new module named C3-GhostDynamicConv (C3-GDConv) module, which achieves network lightweighting while maintaining efficient computation. Secondly, adding the lightweight attention mechanism SGE (Spatial Group-wise Enhancement) to the neck network almost eliminates the need to add additional parameters and computation. Without adding significant computational burden, it can significantly enhance the model’s performance and realize the efficient identification of bearing surface defects. Finally, a knowledge ontology of bearing defects is constructed by combining ontological reasoning techniques to give reasoning results on whether bearing defects can be repaired or not. The experimental results show that the frame rate per second (FPS) value of the improved model GDS-YOLOv5s for bearing defect recognition in this paper is 130, which is an improvement of 11% compared to the original YOLOv5s model. GFLOPs and the number of parameters decreased by 7% and 10% respectively, and mAP@0.5 reached 92.4%. The recognition accuracy is ensured while keeping the model lightweight. Combined with ontological reasoning, it is able to determine the repairability of defects, which provides a reliable basis for the maintenance decision of bearings. This study offers an efficient and intelligent scheme for bearing defect inspection and subsequent processes, which has important engineering application value. |
| format | Article |
| id | doaj-art-68146bb6ceef412e95fece2d0021fedf |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-68146bb6ceef412e95fece2d0021fedf2025-08-20T03:50:16ZengIEEEIEEE Access2169-35362025-01-011311721011722310.1109/ACCESS.2025.358661911072476A Lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological ReasoningXiaolin Shi0https://orcid.org/0000-0001-7022-7882Haisong Xu1https://orcid.org/0009-0007-4598-1024Han Zhang2https://orcid.org/0009-0001-7347-865XYi Li3https://orcid.org/0009-0001-9331-9322Xinshuo Li4Fan Yang5College of Mechanical Engineering and Automation, Liaoning University of Technology, Jinzhou, ChinaCollege of Mechanical Engineering and Automation, Liaoning University of Technology, Jinzhou, ChinaCollege of Mechanical Engineering and Automation, Liaoning University of Technology, Jinzhou, ChinaCollege of Mechanical Engineering and Automation, Liaoning University of Technology, Jinzhou, ChinaCollege of Mechanical Engineering and Automation, Liaoning University of Technology, Jinzhou, ChinaInstitute of Intelligent Manufacturing, School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an, ChinaBearing as a critical component of machinery and equipment, its state of health directly affects the operating efficiency and security of the equipment. Therefore, the quality control of bearings must be very strict. Aiming at the different sizes and textures of the defect types on the surface of the outer ring of the bearing, and the fact that most of the target detection algorithms relying on deep learning show low speed and low precision in the detection of defects on the surface of the bearing, this paper presents a lightweight method for detecting the defects on the surface of the bearing based on deep learning and ontological reasoning. In this paper, YOLOv5s is chosen as the baseline model. First, the dynamic convolution is fused with the Ghost module and the combined structure is embedded into the C3 module, thus constructing a new module named C3-GhostDynamicConv (C3-GDConv) module, which achieves network lightweighting while maintaining efficient computation. Secondly, adding the lightweight attention mechanism SGE (Spatial Group-wise Enhancement) to the neck network almost eliminates the need to add additional parameters and computation. Without adding significant computational burden, it can significantly enhance the model’s performance and realize the efficient identification of bearing surface defects. Finally, a knowledge ontology of bearing defects is constructed by combining ontological reasoning techniques to give reasoning results on whether bearing defects can be repaired or not. The experimental results show that the frame rate per second (FPS) value of the improved model GDS-YOLOv5s for bearing defect recognition in this paper is 130, which is an improvement of 11% compared to the original YOLOv5s model. GFLOPs and the number of parameters decreased by 7% and 10% respectively, and mAP@0.5 reached 92.4%. The recognition accuracy is ensured while keeping the model lightweight. Combined with ontological reasoning, it is able to determine the repairability of defects, which provides a reliable basis for the maintenance decision of bearings. This study offers an efficient and intelligent scheme for bearing defect inspection and subsequent processes, which has important engineering application value.https://ieeexplore.ieee.org/document/11072476/Defect detectionbearing surfacedeep learninglightweightingontological reasoning |
| spellingShingle | Xiaolin Shi Haisong Xu Han Zhang Yi Li Xinshuo Li Fan Yang A Lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological Reasoning IEEE Access Defect detection bearing surface deep learning lightweighting ontological reasoning |
| title | A Lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological Reasoning |
| title_full | A Lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological Reasoning |
| title_fullStr | A Lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological Reasoning |
| title_full_unstemmed | A Lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological Reasoning |
| title_short | A Lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological Reasoning |
| title_sort | lightweight method for detecting bearing surface defects based on deep learning and ontological reasoning |
| topic | Defect detection bearing surface deep learning lightweighting ontological reasoning |
| url | https://ieeexplore.ieee.org/document/11072476/ |
| work_keys_str_mv | AT xiaolinshi alightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT haisongxu alightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT hanzhang alightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT yili alightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT xinshuoli alightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT fanyang alightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT xiaolinshi lightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT haisongxu lightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT hanzhang lightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT yili lightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT xinshuoli lightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning AT fanyang lightweightmethodfordetectingbearingsurfacedefectsbasedondeeplearningandontologicalreasoning |