Research on Quality Control of Gigabit Network Transformers Based on Improved Transformer Neural Networks

Heng Xiao; Shengwei Liang; Zijie Zhou; Yu Wang; Hua Sun; Dongxu Yang

doi:10.47297/taposatWSP2633-456904.20260703

PDF
导出
分享
收藏
专辑

Research on Quality Control of Gigabit Network Transformers Based on Improved Transformer Neural Networks

7卷第3期

浏览量: 0 Downloads: 3

Research on Quality Control of Gigabit Network Transformers Based on Improved Transformer Neural Networks
Research on Quality Control of Gigabit Network Transformers Based on Improved Transformer Neural Networks
1.School of Mechanical Engineering, Xihua University, Chengdu, Sichuan, 610039, China
2.Deyang Zhida Precise Electronic Co.,Ltd., Deyang, Sichuan, 618500, China
2026年7卷第3期页码：20-25
纸质出版：2026-03-30
DOI：10.47297/taposatWSP2633-456904.20260703
Accepted：

Scan QR Code

Heng Xiao, Shengwei Liang, Zijie Zhou, Yu Wang, Hua Sun & Dongxu Yang. (2026). Research on Quality Control of Gigabit Network Transformers Based on Improved Transformer Neural Networks. 科技理论与实践（英文版）, 7(3), 20-25.

Xiao Heng,Liang Shengwei,Zhou Zijie,et al.Research on Quality Control of Gigabit Network Transformers Based on Improved Transformer Neural Networks[J].Theory and Practice of Science and Technology,2026,07(03):20-25.
Heng Xiao, Shengwei Liang, Zijie Zhou, Yu Wang, Hua Sun & Dongxu Yang. (2026). Research on Quality Control of Gigabit Network Transformers Based on Improved Transformer Neural Networks. 科技理论与实践（英文版）, 7(3), 20-25. DOI： 10.47297/taposatWSP2633-456904.20260703.

Xiao Heng,Liang Shengwei,Zhou Zijie,et al.Research on Quality Control of Gigabit Network Transformers Based on Improved Transformer Neural Networks[J].Theory and Practice of Science and Technology,2026,07(03):20-25. DOI： 10.47297/taposatWSP2633-456904.20260703.

摘要

Abstract

The structure of Gigabit network transformers is complex

with significant scale variations in defects such as pin skew and missing magnetic cores. This leads to low efficiency and high false detection rates in traditional manual inspection. To address this challenge and meet the industrial production line's demand for high speed and high precision

this study optimizes the YOLOv5s model with targeted improvements. First

to enhance detection speed

the original SPP module in the network is replaced with the more efficient simSPPF module

accelerating feature fusion and inference. Second

to improve the model's feature extraction capability for complex defects and its understanding of global context

some Conv and C3 modules in the backbone network are replaced with Transformer modules

thereby effectively enhancing the recognition accuracy for small targets and defects with variable morphologies. Experiments on the Gigabit network transformer dataset show that the optimized model significantly outperforms the baseline model in both detection accuracy and inference speed

achieving a balance between precision and efficiency. This provides an effective solution for the intelligent quality inspection of related electronic components.

关键词

Keywords

references

Golnaz Ghiasi, Yin Cui, Aravind Srinivas, Rui Qian, TsungYi Lin, Ekin D Cubuk, Quoc V Le, and Barret Zoph. Simple copy-paste is a strong data augmentation method for instance segmentation. In CVPR, 2021.

Yu Du, Fangyun Wei, Zihe Zhang, Miaojing Shi, Yue Gao, and Guoqi Li. Learning to prompt for open-vocabulary object detection with vision-language model. In CVPR, 2022.

Weicheng Kuo, Yin Cui, Xiuye Gu, AJ Piergiovanni, and Anelia Angelova. F-vlm: Open-vocabulary object detection upon frozen vision and language models. arXiv preprint arXiv: 2209.15639 , 2022.

Alireza Zareian, Kevin Dela Rosa, Derek Hao Hu, and ShihFu Chang. Open-vocabulary object detection using captions. In CVPR, 2021.

Ce Zhang and Azim Eskandarian. A quality index metric and method for online self-assessment of autonomous vehicles sensory perception arXiv preprint arXiv: 2203.02588 , 2022.

Zhiheng Wu, Yue Lu, Xingyu Chen, Zhengxing Wu, Liwen Kang, and Junzhi Yu. Uc-owod: Unknownclassified open world object detection. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part X, pages 193–210. Springer, 2022.

Zhong-Qiu Zhao, Peng Zheng, Shou-tao Xu, and Xindong Wu. Object detection with deep learning: A review. IEEE transactions on neural networks and learning systems, 30(11):3212–3232, 2019.

Ezra Fielding, Clement N Nyirenda, and Mattia Vaccari. 2022. The Classification of Optical Galaxy Morphology Using Unsupervised Learning Techniques. In Prceedings of the International Conference on Electrical, Computer and Energy Technologies (ICECET).

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 6 (2017), 84–90.

R Shirley, K Duncan, MC Campos Varillas, PD Hurley, K Małek, Y Roehlly, MWL Smith, H Aussel, T Bakx, V Buat, et al. 2021. HELP: the herschel extragalactic legacy project. Monthly Notices of the Royal Astronomical Society 507, 1 (2021), 129–155.

K. Cha, J. Seo, and T. Lee. A billion-scale foundation model for remote sensing images. arXiv preprint arXiv: 2304.05215 , 2023.

P. Akiva, M. Purri, and M. Leotta. Self-supervised material and texture representation learning for remote sensing tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8203–8215, 2022.

J. Ding, N. Xue, G.-S. Xia, and D. Dai. Decoupling zero-shot semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11583–11592, 2022.

K. Heidler, L. Mou, D. Hu, P. Jin, G. Li, C. Gan, J.-R. Wen, and X. X. Zhu. Self-supervised audiovisual representation learning for remote sensing data. International Journal of Applied Earth Observation and Geoinformation, 116:103130, 2023.

X. Lu, X. Sun, W. Diao, Y. Mao, J. Li, Y. Zhang, P. Wang, and K. Fu. Few-shot object detection in aerial imagery guided by textmodal knowledge. IEEE Transactions on Geoscience and Remote Sensing, 2023.

文章被引用时，请邮件提醒。

Submit

A Survey of Monocular Depth Estimation: Methodological Taxonomies, Technical Advances, and Future Trends

Exploration of the Real-Time Detection Model Transformer (UAV-DETR) for Small Object Detection in UAV Imagery

Human-centered Entrepreneurship in Assistive Robotics Optimization

Multi-Modal Fusion for 3D Object Detection in Autonomous Driving: A Review

Research and Application of Intelligent Manufacturing Technology for Financial Payment Products Based on Multi - Spectral Machine Vision Technology

Related Author

Yifan Li School of Physics, Sun Yat-sen University

Yican Yang School of Information Science and Engineering,Computer Science and Technology Major,Ocean University of China

Chaoqun Xiang Qingdao City University Gutenberg College

Mincong Kong Qingdao City University Gutenberg College

Haozhou Fei Nanjing University of Posts and Telecommunications

Yueqian Ke College of Physics and Information Engineering, QuanZhou Normal University

Yiqing Ye College of Physics and Information Engineering, QuanZhou Normal University

Wei Jiang College of Physics and Information Engineering, QuanZhou Normal University

Related Institution

School of Physics, Sun Yat-sen University

School of Information Science and Engineering,Computer Science and Technology Major,Ocean University of China

Qingdao City University Gutenberg College

Nanjing University of Posts and Telecommunications

College of Physics and Information Engineering, QuanZhou Normal University

⁰