YOLOv11‐DDP: An Accuracy‐Enhanced PCB Defect Detection Algorithm Featuring Dynamic Feature Fusion and DAT Attention Mechanism.
Saved in:
| Title: | YOLOv11‐DDP: An Accuracy‐Enhanced PCB Defect Detection Algorithm Featuring Dynamic Feature Fusion and DAT Attention Mechanism. |
|---|---|
| Authors: | Zhang, Lianlian1 (AUTHOR), Liu, Qi1 (AUTHOR), Cao, Xiaorui1 (AUTHOR), Zhang, Yujin2 (AUTHOR) zyj1219@hebiace.edu.cn, Sun, Jie3 (AUTHOR), Cui, Mengmeng4 (AUTHOR), Ren, Xiaoru1 (AUTHOR), Wu, Di1 (AUTHOR), Bansal, Shonak (AUTHOR) shonakk@gmail.com |
| Source: | Journal of Electrical & Computer Engineering. 7/6/2026, Vol. 2026, p1-12. 12p. |
| Subjects: | Manufacturing defects, Object recognition (Computer vision), Industrial applications |
| Abstract: | With the rapid development of the electronic manufacturing industry, printed circuit boards (PCBs) are critical components in electronic systems, and the accuracy of their defect detection directly determines product quality and production efficiency. However, existing mainstream methods still exhibit several key limitations in PCB defect detection, including poor adaptability to multiscale defects, high computational complexity of attention mechanisms, and high missed detection rates for small targets. These limitations lead to insufficient detection accuracy in complex industrial scenarios, failing to meet the requirements of modern production. To address the above problems, this paper proposes a PCB defect detection algorithm based on YOLOv11‐DDP. The algorithm introduces a dynamic feature fusion module to improve model generalization, embeds the DAT attention mechanism to effectively balance accuracy and efficiency, and adopts a P2 detection head to enhance the perception ability of tiny defects. Experimental results show that the proposed algorithm achieves an mAP@0.5 of 94.1% on the PCB defect dataset, representing a 3.7% improvement over the original YOLOv11 model. Meanwhile, mAP@0.5:0.95 is increased by 1.8%, precision by 5.3%, and recall by 2.6%. The proposed method effectively mitigates the problem of insufficient detection accuracy in PCB defect detection and can meet the high‐precision detection requirements in complex industrial scenarios. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Electrical & Computer Engineering is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | With the rapid development of the electronic manufacturing industry, printed circuit boards (PCBs) are critical components in electronic systems, and the accuracy of their defect detection directly determines product quality and production efficiency. However, existing mainstream methods still exhibit several key limitations in PCB defect detection, including poor adaptability to multiscale defects, high computational complexity of attention mechanisms, and high missed detection rates for small targets. These limitations lead to insufficient detection accuracy in complex industrial scenarios, failing to meet the requirements of modern production. To address the above problems, this paper proposes a PCB defect detection algorithm based on YOLOv11‐DDP. The algorithm introduces a dynamic feature fusion module to improve model generalization, embeds the DAT attention mechanism to effectively balance accuracy and efficiency, and adopts a P2 detection head to enhance the perception ability of tiny defects. Experimental results show that the proposed algorithm achieves an mAP@0.5 of 94.1% on the PCB defect dataset, representing a 3.7% improvement over the original YOLOv11 model. Meanwhile, mAP@0.5:0.95 is increased by 1.8%, precision by 5.3%, and recall by 2.6%. The proposed method effectively mitigates the problem of insufficient detection accuracy in PCB defect detection and can meet the high‐precision detection requirements in complex industrial scenarios. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20900147 |
| DOI: | 10.1155/jece/2638110 |
