Research on Defect Detection in Lightweight Photovoltaic Cells Using YOLOv8-FSD

Given the high computational complexity and poor real-time performance of current photovoltaic cell surface defect detection methods, this study proposes a lightweight model, YOLOv8-FSD, based on YOLOv8. By introducing the FasterNet network to replace the original backbone network, computational com...

Full description

Saved in:
Bibliographic Details
Main Authors: Chao Chen, Zhuo Chen, Hao Li, Yawen Wang, Guangzhou Lei, Lingling Wu
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/3/843
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199723480186880
author Chao Chen
Zhuo Chen
Hao Li
Yawen Wang
Guangzhou Lei
Lingling Wu
author_facet Chao Chen
Zhuo Chen
Hao Li
Yawen Wang
Guangzhou Lei
Lingling Wu
author_sort Chao Chen
collection DOAJ
description Given the high computational complexity and poor real-time performance of current photovoltaic cell surface defect detection methods, this study proposes a lightweight model, YOLOv8-FSD, based on YOLOv8. By introducing the FasterNet network to replace the original backbone network, computational complexity and memory access are reduced. A thin neck structure designed based on hybrid convolution technology is adopted to reduce model parameters and computational load further. A lightweight dynamic feature upsampling operator improves the feature map quality. Additionally, the regularized Gaussian distribution distance loss function is used to enhance the detection ability for small target defects. Experimental results show that the YOLOv8-FSD lightweight algorithm improves detection accuracy while significantly reducing the number of parameters and computational requirements compared to the original algorithm. This improvement provides an efficient, accurate, and lightweight solution for PV cell defect detection.
format Article
id doaj-art-4e6e185e54a34998a2db0245ef770eba
institution OA Journals
issn 1424-8220
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-4e6e185e54a34998a2db0245ef770eba2025-08-20T02:12:33ZengMDPI AGSensors1424-82202025-01-0125384310.3390/s25030843Research on Defect Detection in Lightweight Photovoltaic Cells Using YOLOv8-FSDChao Chen0Zhuo Chen1Hao Li2Yawen Wang3Guangzhou Lei4Lingling Wu5School of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643000, ChinaSchool of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643000, ChinaSchool of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643000, ChinaSchool of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643000, ChinaSchool of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643000, ChinaSchool of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643000, ChinaGiven the high computational complexity and poor real-time performance of current photovoltaic cell surface defect detection methods, this study proposes a lightweight model, YOLOv8-FSD, based on YOLOv8. By introducing the FasterNet network to replace the original backbone network, computational complexity and memory access are reduced. A thin neck structure designed based on hybrid convolution technology is adopted to reduce model parameters and computational load further. A lightweight dynamic feature upsampling operator improves the feature map quality. Additionally, the regularized Gaussian distribution distance loss function is used to enhance the detection ability for small target defects. Experimental results show that the YOLOv8-FSD lightweight algorithm improves detection accuracy while significantly reducing the number of parameters and computational requirements compared to the original algorithm. This improvement provides an efficient, accurate, and lightweight solution for PV cell defect detection.https://www.mdpi.com/1424-8220/25/3/843photovoltaic celldefect detectionYOLOv8lightweightingFasterNet
spellingShingle Chao Chen
Zhuo Chen
Hao Li
Yawen Wang
Guangzhou Lei
Lingling Wu
Research on Defect Detection in Lightweight Photovoltaic Cells Using YOLOv8-FSD
Sensors
photovoltaic cell
defect detection
YOLOv8
lightweighting
FasterNet
title Research on Defect Detection in Lightweight Photovoltaic Cells Using YOLOv8-FSD
title_full Research on Defect Detection in Lightweight Photovoltaic Cells Using YOLOv8-FSD
title_fullStr Research on Defect Detection in Lightweight Photovoltaic Cells Using YOLOv8-FSD
title_full_unstemmed Research on Defect Detection in Lightweight Photovoltaic Cells Using YOLOv8-FSD
title_short Research on Defect Detection in Lightweight Photovoltaic Cells Using YOLOv8-FSD
title_sort research on defect detection in lightweight photovoltaic cells using yolov8 fsd
topic photovoltaic cell
defect detection
YOLOv8
lightweighting
FasterNet
url https://www.mdpi.com/1424-8220/25/3/843
work_keys_str_mv AT chaochen researchondefectdetectioninlightweightphotovoltaiccellsusingyolov8fsd
AT zhuochen researchondefectdetectioninlightweightphotovoltaiccellsusingyolov8fsd
AT haoli researchondefectdetectioninlightweightphotovoltaiccellsusingyolov8fsd
AT yawenwang researchondefectdetectioninlightweightphotovoltaiccellsusingyolov8fsd
AT guangzhoulei researchondefectdetectioninlightweightphotovoltaiccellsusingyolov8fsd
AT linglingwu researchondefectdetectioninlightweightphotovoltaiccellsusingyolov8fsd