STMS-YOLOv5: A Lightweight Algorithm for Gear Surface Defect Detection
Sensors · 2023
DOI: 10.3390/s23135992 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Rui Yan und 6 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer C…. Hauptthemen laut MEDLINE: Algorithms, Industry. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shandong Province Natural Science Youth Foundation of China, 2020 Industrial Internet Innovation and Development Project.
Abstract (Originalsprache)
Most deep-learning-based object detection algorithms exhibit low speeds and accuracy in gear surface defect detection due to their high computational costs and complex structures. To solve this problem, a lightweight model for gear surface defect detection, namely STMS-YOLOv5, is proposed in this paper. Firstly, the ShuffleNetv2 module is employed as the backbone to reduce the giga floating-point operations per second and the number of parameters. Secondly, transposed convolution upsampling is used to enhance the learning capability of the network. Thirdly, the max efficient channel attention mechanism is embedded in the neck to compensate for the accuracy loss caused by the lightweight backbone. Finally, the SIOU_Loss is adopted as the bounding box regression loss function in the prediction part to speed up the model convergence. Experiments show that STMS-YOLOv5 achieves frames per second of 130.4 and 133.5 on the gear and NEU-DET steel surface defect datasets, respectively. The number of parameters and GFLOPs are reduced by 44.4% and 50.31%, respectively, while the mAP@0.5 reaches 98.6% and 73.5%, respectively. Extensive ablation and comparative experiments validate the effectiveness and generalization capability of the model in industrial defect detection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sc…
- Shandong Provincial Key Laboratory of Computer Networks, Shandong Fundamental Research Center for Computer Science, Jinan 250014, China.
ORCID-Profile: Rui Yan, Rangyong Zhang, Jinqiang Bai, Huijuan Hao, Wenjie Guo, Xiaoyan Gu, Qi Liu
Förderung
- National Natural Science Foundation of China
- Shandong Province Natural Science Youth Foundation of China
- 2020 Industrial Internet Innovation and Development Project
- Research project on big data analysis and intelligent fault diagnosis method of mechanical equipment based on industrial Internet platform
- Development and Application Demonstration of Data Acquisition and Processing System for Discrete Manufacturing Workshop
Zitieren
APA
Yan, R., Zhang, R., Bai, J., Hao, H., Guo, W., Gu, X., & Liu, Q. (2023). STMS-YOLOv5: A Lightweight Algorithm for Gear Surface Defect Detection. Sensors. https://doi.org/10.3390/s23135992
Vancouver
Yan R, Zhang R, Bai J, Hao H, Guo W, Gu X, et al. STMS-YOLOv5: A Lightweight Algorithm for Gear Surface Defect Detection. Sensors. 2023. doi:10.3390/s23135992
BibTeX
@article{Yan2023,
author = {Yan, Rui and Zhang, Rangyong and Bai, Jinqiang and Hao, Huijuan and Guo, Wenjie and Gu, Xiaoyan and Liu, Qi},
title = {STMS-YOLOv5: A Lightweight Algorithm for Gear Surface Defect Detection},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23135992}
}
EUVIMED