ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire Connectors
With the rapid growth of China’s new energy vehicle industry, the quality of crimped wire connectors directly impacts the performance of wiring harnesses, which are critical to the overall vehicle quality. At present, reliable methods for inspecting crimped wire connectors are still prima...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10820347/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550763916001280 |
|---|---|
| author | Xiaojian Zhou Jicheng Kan Nur Fatin Liyana Mohd Rosely Xu Duan Jiajing Cai Zihan Zhou |
| author_facet | Xiaojian Zhou Jicheng Kan Nur Fatin Liyana Mohd Rosely Xu Duan Jiajing Cai Zihan Zhou |
| author_sort | Xiaojian Zhou |
| collection | DOAJ |
| description | With the rapid growth of China’s new energy vehicle industry, the quality of crimped wire connectors directly impacts the performance of wiring harnesses, which are critical to the overall vehicle quality. At present, reliable methods for inspecting crimped wire connectors are still primarily based on image recognition evaluations. To address this, we propose an Improved Lightweight Network based on YOLOv8 (ILN-YOLOv8) to achieve high-precision and high-efficiency detection of crimped wire connectors. Taking the original YOLOv8 model as a baseline, the new model enhances the ability to extract shallow features from small targets by increasing the P2 detection layer and improving the Feature Pyramid Network(FPN) and Path Aggregation Network(PAN) structures. Next, the improved Selective Boundary Aggregation(SBA) module replaces the Concat module in the Neck, enhancing the fusion of deep and shallow features. Additionally, the Efficient Local Attention(ELA) attention mechanism is introduced into the Cryptographic Service Provider(CSP) bottleneck with 2 convolutions(C2F) module in the Backbone, improving feature localization accuracy without increasing network complexity. The Minimum Point Distance based IoU(MPDIoU) loss function is used to calculate localization loss, improving detection accuracy while preventing gradient explosion. Finally, lightweighting of the ILN-YOLOv8 model is achieved using the slim-neck network, the backbone with Depthwise Separable Convolution (DWConv), and Lightweight Convolution (LightConv) modules. After pruning and knowledge distillation, the model’s complexity and computational load significantly decreased while accuracy improved, meeting the industry’s requirements for crimped wire connectors detection and achieves superior performance. Experimental results show that, compared to the original YOLOv8 model, the proposed method achieved 96.2% accuracy on a real-world crimped wire connectors dataset, with mAP@0.5 and mAP@.5:.95 improving by 6.1% and 7.4%, respectively, while Parameters and FLOPs decreased by 66.7% and 34.6%. |
| format | Article |
| id | doaj-art-58802c57f46c4c399dd3bc25d8e23877 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-58802c57f46c4c399dd3bc25d8e238772025-01-10T00:01:14ZengIEEEIEEE Access2169-35362025-01-01135193520210.1109/ACCESS.2025.352556410820347ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire ConnectorsXiaojian Zhou0https://orcid.org/0009-0005-8264-1059Jicheng Kan1https://orcid.org/0000-0002-1142-4293Nur Fatin Liyana Mohd Rosely2https://orcid.org/0000-0003-0289-0337Xu Duan3Jiajing Cai4https://orcid.org/0000-0002-4751-3028Zihan Zhou5College of Information Engineering, Hainan Vocational University of Science and Technology, Haikou, Hainan, ChinaCollege of Information Engineering, Hainan Vocational University of Science and Technology, Haikou, Hainan, ChinaFaculty of Data Science and Information Technology, INTI International University, Nilai, Negeri Sembilan, MalaysiaCollege of Information Engineering, Hainan Vocational University of Science and Technology, Haikou, Hainan, ChinaCollege of Information Engineering, Hainan Vocational University of Science and Technology, Haikou, Hainan, ChinaUniversity of International Business and Economics, Chaoyang, Beijing, ChinaWith the rapid growth of China’s new energy vehicle industry, the quality of crimped wire connectors directly impacts the performance of wiring harnesses, which are critical to the overall vehicle quality. At present, reliable methods for inspecting crimped wire connectors are still primarily based on image recognition evaluations. To address this, we propose an Improved Lightweight Network based on YOLOv8 (ILN-YOLOv8) to achieve high-precision and high-efficiency detection of crimped wire connectors. Taking the original YOLOv8 model as a baseline, the new model enhances the ability to extract shallow features from small targets by increasing the P2 detection layer and improving the Feature Pyramid Network(FPN) and Path Aggregation Network(PAN) structures. Next, the improved Selective Boundary Aggregation(SBA) module replaces the Concat module in the Neck, enhancing the fusion of deep and shallow features. Additionally, the Efficient Local Attention(ELA) attention mechanism is introduced into the Cryptographic Service Provider(CSP) bottleneck with 2 convolutions(C2F) module in the Backbone, improving feature localization accuracy without increasing network complexity. The Minimum Point Distance based IoU(MPDIoU) loss function is used to calculate localization loss, improving detection accuracy while preventing gradient explosion. Finally, lightweighting of the ILN-YOLOv8 model is achieved using the slim-neck network, the backbone with Depthwise Separable Convolution (DWConv), and Lightweight Convolution (LightConv) modules. After pruning and knowledge distillation, the model’s complexity and computational load significantly decreased while accuracy improved, meeting the industry’s requirements for crimped wire connectors detection and achieves superior performance. Experimental results show that, compared to the original YOLOv8 model, the proposed method achieved 96.2% accuracy on a real-world crimped wire connectors dataset, with mAP@0.5 and mAP@.5:.95 improving by 6.1% and 7.4%, respectively, while Parameters and FLOPs decreased by 66.7% and 34.6%.https://ieeexplore.ieee.org/document/10820347/Crimped wire connectorILN-YOLOv8lightweightpruningknowledge distillation |
| spellingShingle | Xiaojian Zhou Jicheng Kan Nur Fatin Liyana Mohd Rosely Xu Duan Jiajing Cai Zihan Zhou ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire Connectors IEEE Access Crimped wire connector ILN-YOLOv8 lightweight pruning knowledge distillation |
| title | ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire Connectors |
| title_full | ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire Connectors |
| title_fullStr | ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire Connectors |
| title_full_unstemmed | ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire Connectors |
| title_short | ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire Connectors |
| title_sort | iln yolov8 a lightweight image recognition model for crimped wire connectors |
| topic | Crimped wire connector ILN-YOLOv8 lightweight pruning knowledge distillation |
| url | https://ieeexplore.ieee.org/document/10820347/ |
| work_keys_str_mv | AT xiaojianzhou ilnyolov8alightweightimagerecognitionmodelforcrimpedwireconnectors AT jichengkan ilnyolov8alightweightimagerecognitionmodelforcrimpedwireconnectors AT nurfatinliyanamohdrosely ilnyolov8alightweightimagerecognitionmodelforcrimpedwireconnectors AT xuduan ilnyolov8alightweightimagerecognitionmodelforcrimpedwireconnectors AT jiajingcai ilnyolov8alightweightimagerecognitionmodelforcrimpedwireconnectors AT zihanzhou ilnyolov8alightweightimagerecognitionmodelforcrimpedwireconnectors |