MDD-DETR: Lightweight Detection Algorithm for Printed Circuit Board Minor Defects
Electronics · 13.11.2024 · 13 (22) · 4453
DOI: 10.3390/electronics13224453 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 13.11.2024. Verfasst von Jinmin Peng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fuxiaquan National Independent Innovation Demonstration Zone High end Flexible Intelligent Packaging Equipment Collaborative Innovation Platform Project, 2022 Fujian Provincial Key Project for Science and Technology Innovation.
Abstract (Originalsprache)
PCBs (printed circuit boards) are the core components of modern electronic devices, and inspecting them for defects will have a direct impact on the performance, reliability and cost of the product. However, the performance of current detection algorithms in identifying minor PCB defects (e.g., mouse bite and spur) still requires improvement. This paper presents the MDD-DETR algorithm for detecting minor defects in PCBs. The backbone network, MDDNet, is used to efficiently extract features while significantly reducing the number of parameters. Simultaneously, the HiLo attention mechanism captures both high- and low-frequency features, transmitting a broader range of gradient information to the neck. Additionally, the proposed SOEP neck network effectively fuses scale features, particularly those rich in small targets, while INM-IoU loss function optimization enables more effective distinction between defects and background, further improving detection accuracy. Experimental results on the PCB_DATASET show that MDD-DETR achieves a 99.3% mAP, outperforming RT-DETR by 2.0% and reducing parameters by 32.3%, thus effectively addressing the challenges of detecting minor PCB defects.
Förderung
- Fuxiaquan National Independent Innovation Demonstration Zone High end Flexible Intelligent Packaging Equipment Collaborative Innovation Platform Project
- 2022 Fujian Provincial Key Project for Science and Technology Innovation
Zitieren
APA
Peng, J., Fan, W., Lan, S., & Wang, D. (2024). MDD-DETR: Lightweight Detection Algorithm for Printed Circuit Board Minor Defects. Electronics, 13(22), 4453. https://doi.org/10.3390/electronics13224453
Vancouver
Peng J, Fan W, Lan S, Wang D. MDD-DETR: Lightweight Detection Algorithm for Printed Circuit Board Minor Defects. Electronics. 2024;13(22):4453. doi:10.3390/electronics13224453
BibTeX
@article{Peng2024,
author = {Peng, Jinmin and Fan, Weipeng and Lan, Song and Wang, Dingran},
title = {MDD-DETR: Lightweight Detection Algorithm for Printed Circuit Board Minor Defects},
journal = {Electronics},
year = {2024},
volume = {13},
number = {22},
pages = {4453},
doi = {10.3390/electronics13224453}
}
EUVIMED