Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 5, 2026

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

1.2K

A Hybrid CNN-Transformer Approach for Photovoltaic Cell Defect Classification Using Electroluminescence Imaging.

Miktat Aktaş1,2, Ferdi Doğan3, İbrahim Türkoğlu4

  • 1Software Engineering, GTC Gunes Sanayi ve Ticaret AS, Adiyaman 02040, Türkiye.

Sensors (Basel, Switzerland)
|May 4, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A DNA-Local, Constraint-Aware Dual-Head Transformer for Pseudorandom Stream Generation.

Entropy (Basel, Switzerland)·2026
Same author

Machine Learning-Based Human Detection Using Active Non-Line-of-Sight Laser Sensing.

Sensors (Basel, Switzerland)·2026
Same author

Material Classification from Non-Line-of-Sight Acoustic Echoes Using Wavelet-Acoustic Hybrid Feature Fusion.

Sensors (Basel, Switzerland)·2026
See all related articles

A new PVELNet model accurately classifies photovoltaic cell defects using electroluminescent images. This lightweight deep learning approach achieved 95.71% accuracy, showing potential for solar panel production line control.

Area of Science:

  • Materials Science
  • Electrical Engineering
  • Computer Science

Background:

  • Photovoltaic cell defects impact solar panel efficiency and reliability.
  • Automated defect detection is crucial for quality control in solar panel manufacturing.
  • Electroluminescent imaging provides detailed insights into cell-level defects.

Purpose of the Study:

  • To develop and evaluate a novel deep learning model for automatic classification of photovoltaic cell defects.
  • To compare the proposed model's performance against existing deep learning models.
  • To assess the model's suitability for real-time process control in solar panel production.

Main Methods:

  • A dataset of 37,538 electroluminescent images was curated, featuring eight defect classes.
Keywords:
CNN–Transformerelectroluminescence imagingmulti-class defectphotovoltaic cell defect classificationsolar cell defect detection

Related Experiment Videos

Last Updated: May 5, 2026

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

1.2K
  • Automated cell segmentation using Run-Length Smoothing Algorithm (RLSA) and morphological processing was applied.
  • A novel CNN-Transformer model, PVELNet, incorporating a self-attention mechanism, was proposed for defect classification.
  • Performance was evaluated using F1-Score, Precision, Recall, and Accuracy metrics against 16 other deep learning models.

    • Main Results:

    • PVELNet achieved a high accuracy of 95.71%, surpassing other evaluated models.
    • The model demonstrated strong performance across various defect classes, as indicated by confusion matrix analysis.
    • PVELNet is a relatively lightweight model with 1.79 million parameters and 46.1 MB memory footprint.

    Conclusions:

    • The proposed PVELNet model offers a highly accurate and efficient solution for photovoltaic cell defect classification.
    • Its lightweight nature and high performance suggest practical applicability in automated quality control for solar panel production lines.
    • PVELNet shows significant potential for enhancing process control and ensuring the reliability of solar energy technology.