SOLAR CELL DEFECT DETECTION NETWORK BASED ON MULTI-SCALE ASYMPTOTIC PYRAMID

被引：0

作者：

Zhu, Lei ^{[1
]}

Geng, Cuicui ^{[1
]}

Li, Botao ^{[1
]}

Pan, Yang ^{[1
]}

Zhang, Bo ^{[1
]}

Yao, Li'na ^{[1
]}

机构：

[1] School of Electronic and Information, Xi’an Polytechnic University, Xi’an

来源：

Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2025年 / 46卷 / 05期

关键词：

deep learning; defect detection; hierarchical feature fusion structure; multi-scale asymptotic pyramid; solar cells; spatial attention mechanism;

D O I：

10.19912/j.0254-0096.tynxb.2024-0064

中图分类号：

学科分类号：

摘要：

A multi-scale asymptotic pyramid network called MSANet is proposed based on the YOLOv8 network. Initially,we replace conventional convolution layers with feature extraction blocks(M-Block)containing a hierarchical feature fusion structure to enhance the network′s capability multi-scale feature extraction. Subsequently,we introduce the spatial attention mechanism SRU to suppress feature redundancy in background regions,allowing the network to focus more on crucial areas while reducing the introduction of parameters. Finally,we propose an improved asymptotic pyramid network structure,AFPNa,to mitigate information loss or degradation during the feature fusion process,thereby enhancing defect detection accuracy. Experimental results demonstrate that compared to the original YOLOv8 model and seven other advanced detection networks,including RTMDET,MSANet achieves higher detection accuracy,with a 5.7% improvement in mean average precision compared to the original model. © 2025 Science Press. All rights reserved.

引用

页码：267 / 274

页数：7

共 17 条

[1]

ZHOU Y, WANG R Y, YUAN Z T, Et al., An efficient dual-path attention solar cell defect detection network, Acta energiae solaris sinica, 44, 4, pp. 407-413, (2023)

[2]

ZHANG Z, ZOU P H, LIU Z F, Et al., Influence of emitter doping process on performance of industrial IBC solar cell [J], Acta energiae solaris sinica, 43, 3, pp. 158-162, (2022)

[3]

WANG Y L, HOU T, ZHANG X, Et al., Surface defect detection of solar cell based on similarity non-maximum suppression mechanism[J], Signal, image and video processing, 17, 5, pp. 2583-2593, (2023)

[4]

JIANG S J, YI H, LI H T, Et al., Defect detection method of solar cells based on transfer learning and ResNet, Acta energiae solaris sinica, 44, 7, pp. 116-121, (2023)

[5]

PENG T, WEN F., Photovoltaic panel fault detection based on improved mask R-CNN[C], 2023 IEEE International Conference on Control, Electronics and Computer Technology(ICCECT), pp. 1187-1191, (2023)

[6]

XU M Y., Solar cell defect detection based on improved G-SSD Network[J], International journal of energy, 2, 1, pp. 68-71, (2023)

[7]

WANG D L, LI M S, YAO Y, Et al., Method of hotspot detection of photovoltaic panels modules on improved SSD [J], Acta energiae solaris sinica, 44, 4, pp. 420-425, (2023)

[8]

CHEN Y M, YUAN X B, WU R Q, Et al., YOLO-MS: rethinking multi-scale representation learning for real-time object detection

[9]

LI J F, WEN Y, HE L H., SCConv:spatial and channel reconstruction convolution for feature redundancy, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), pp. 6153-6162, (2023)

[10]

YANG G Y, LEI J, ZHU Z K, Et al., AFPN:asymptotic feature pyramid network for object detection, 2023 IEEE International Conference on Systems,Man,and Cybernetics(SMC), pp. 2184-2189, (2023)

← 1 2 →