YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8
Aiming at the demand for defect detection accuracy and efficiency under the trend of high-density and integration in printed circuit board (PCB) manufacturing, this paper proposes an improved YOLOv8n model (YOLO-SUMAS), which enhances detection performance through multi-module collaborative optimiza...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/16/5/509 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711886886502400 |
|---|---|
| author | Ying Tang Runhao Liu Sheng Wang |
| author_facet | Ying Tang Runhao Liu Sheng Wang |
| author_sort | Ying Tang |
| collection | DOAJ |
| description | Aiming at the demand for defect detection accuracy and efficiency under the trend of high-density and integration in printed circuit board (PCB) manufacturing, this paper proposes an improved YOLOv8n model (YOLO-SUMAS), which enhances detection performance through multi-module collaborative optimization. The model introduces the SCSA attention mechanism, which improves the feature expression capability through spatial and channel synergistic attention; adopts the Unified-IoU loss function, combined with the dynamic bounding box scaling and bi-directional weight allocation strategy, to optimize the accuracy of high-quality target localization; integrates the MobileNetV4 lightweight architecture and its MobileMQA attention module, which reduces the computational complexity and improves the inference speed; and combines ASF-SDI Neck structure with weighted bi-directional feature pyramid and multi-level semantic detail fusion to strengthen small target detection capability. The experiments are based on public datasets, and the results show that the improved model achieves 98.8% precision and 99.2% recall, and mAP@50 reached 99.1%, significantly better than the original YOLOv8n and other mainstream models. YOLO-SUMAS provides a highly efficient industrial-grade PCB defect detection solution by considering high precision and real-time performance while maintaining lightweight characteristics. |
| format | Article |
| id | doaj-art-d0ab457fdd024a12bc5af44a155631a9 |
| institution | DOAJ |
| issn | 2072-666X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj-art-d0ab457fdd024a12bc5af44a155631a92025-08-20T03:14:29ZengMDPI AGMicromachines2072-666X2025-04-0116550910.3390/mi16050509YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8Ying Tang0Runhao Liu1Sheng Wang2School of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, ChinaSchool of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, ChinaSchool of Computer and Network Security, Chengdu University of Technology, Chengdu 610059, ChinaAiming at the demand for defect detection accuracy and efficiency under the trend of high-density and integration in printed circuit board (PCB) manufacturing, this paper proposes an improved YOLOv8n model (YOLO-SUMAS), which enhances detection performance through multi-module collaborative optimization. The model introduces the SCSA attention mechanism, which improves the feature expression capability through spatial and channel synergistic attention; adopts the Unified-IoU loss function, combined with the dynamic bounding box scaling and bi-directional weight allocation strategy, to optimize the accuracy of high-quality target localization; integrates the MobileNetV4 lightweight architecture and its MobileMQA attention module, which reduces the computational complexity and improves the inference speed; and combines ASF-SDI Neck structure with weighted bi-directional feature pyramid and multi-level semantic detail fusion to strengthen small target detection capability. The experiments are based on public datasets, and the results show that the improved model achieves 98.8% precision and 99.2% recall, and mAP@50 reached 99.1%, significantly better than the original YOLOv8n and other mainstream models. YOLO-SUMAS provides a highly efficient industrial-grade PCB defect detection solution by considering high precision and real-time performance while maintaining lightweight characteristics.https://www.mdpi.com/2072-666X/16/5/509defect detectionYOLOv8nPCBdeep learningmulti-scale feature fusion |
| spellingShingle | Ying Tang Runhao Liu Sheng Wang YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8 Micromachines defect detection YOLOv8n PCB deep learning multi-scale feature fusion |
| title | YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8 |
| title_full | YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8 |
| title_fullStr | YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8 |
| title_full_unstemmed | YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8 |
| title_short | YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8 |
| title_sort | yolo sumas improved printed circuit board defect detection and identification research based on yolov8 |
| topic | defect detection YOLOv8n PCB deep learning multi-scale feature fusion |
| url | https://www.mdpi.com/2072-666X/16/5/509 |
| work_keys_str_mv | AT yingtang yolosumasimprovedprintedcircuitboarddefectdetectionandidentificationresearchbasedonyolov8 AT runhaoliu yolosumasimprovedprintedcircuitboarddefectdetectionandidentificationresearchbasedonyolov8 AT shengwang yolosumasimprovedprintedcircuitboarddefectdetectionandidentificationresearchbasedonyolov8 |