QR-Code

Benchmarking Modern Deep Learning Models for Electroluminescence-Based Solar Cell Defect Detection

This study proposes a deep learning-based framework for the automated classification of photovoltaic solar cells as defective or normal using electroluminescence (EL) imaging. A balanced dataset containing 20,400 EL images, comprising 10,200 defective and 10,200 normal solar cells, was used for mode...

Ausführliche Beschreibung

Gespeichert in:
Hauptverfasser: Gökhan Şahin, Ali Cengiz Rüstemli, Ahmed Yaseen Bishree Al-Ani, Sabir Rüstemli, Erdal Akin
Format: Artigo
Sprache:Inglês
Veröffentlicht: MDPI AG 2026-07-01
Schriftenreihe:Sensors
Schlagworte:
deep learning
photovoltaic cells
electroluminescence imaging
defect detection
EfficientNet-B2
ConvNeXt-Tiny
Online-Zugang:https://www.mdpi.com/1424-8220/26/13/4256
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!

Ähnliche Einträge