Paper
5 June 2024 Defect detection of solar cells based on improved YOLOv5s
Bin Liao, Hao Wang, Mingzhe Zhang, Peidong Shen
Author Affiliations +
Proceedings Volume 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024); 131631Y (2024) https://doi.org/10.1117/12.3030136
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 2024, Xi'an, China
Abstract
This study proposes an improved lightweight YOLOv5s neural network model for efficiently identifying various defects on the surface of solar cells. Firstly, ShuffleNetv2 is used as the backbone feature extraction network in the YOLOv5s network. Secondly, the Triplet Attention attention mechanism is introduced into the backbone network of YOLOv5s.Lastly,the two-dimensional activation function FReLU is used to replace Leaky ReLu. The experimental results show that the improved YOLOv5s model has an average accuracy value of 94.1%, ensuring the detection accuracy of defect targets; At the same time, the floating-point operation amount was reduced by 78.7%, and the model size was reduced by 64.8%, effectively improving the model's lightweight performance.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Bin Liao, Hao Wang, Mingzhe Zhang, and Peidong Shen "Defect detection of solar cells based on improved YOLOv5s", Proc. SPIE 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 131631Y (5 June 2024); https://doi.org/10.1117/12.3030136
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Solar cells

Defect detection

Performance modeling

Convolution

Object detection

Target detection

Data modeling

RELATED CONTENT


Back to Top