Automated fault classification of photovoltaic modules from thermal images using autoencoder-compressed CNN features
PRZEGLĄD ELEKTROTECHNICZNY · 27.05.2026 · 1 (5) · 172-177
DOI: 10.15199/48.2026.05.22 ↗Kurz gefasst
Fachartikel in der Zeitschrift PRZEGLĄD ELEKTROTECHNICZNY, online erschienen am 27.05.2026. Verfasst von Chutinun PHUNGKET und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben.
Abstract (Originalsprache)
This paper presents a compact pipeline for automated thermal photovoltaic module fault classification combining CNN feature extraction, autoencoder-based compression, and multi-class SVM inference. Using ResNet-101 fixed features, dimensionality is reduced from 2048 to 256 while achieving 96.67% accuracy on a benchmark test set. Leakage-safe protocols ensure valid model selection. External validation on 1,800 UAV-acquired field images yields 89.33% accuracy, evidencing domain-shift degradation yet supporting deployment for three-class thermal PV fault detection (No-Anomaly, Cracking, and Soiling) in resource-constrained inspection systems.
Zitieren
APA
PHUNGKET, C., & NANGTIN, P. (2026). Automated fault classification of photovoltaic modules from thermal images using autoencoder-compressed CNN features. PRZEGLĄD ELEKTROTECHNICZNY, 1(5), 172-177. https://doi.org/10.15199/48.2026.05.22
Vancouver
PHUNGKET C, NANGTIN P. Automated fault classification of photovoltaic modules from thermal images using autoencoder-compressed CNN features. PRZEGLĄD ELEKTROTECHNICZNY. 2026;1(5):172-177. doi:10.15199/48.2026.05.22
BibTeX
@article{PHUNGKET2026,
author = {PHUNGKET, Chutinun and NANGTIN, Prasit},
title = {Automated fault classification of photovoltaic modules from thermal images using autoencoder-compressed CNN features},
journal = {PRZEGLĄD ELEKTROTECHNICZNY},
year = {2026},
volume = {1},
number = {5},
pages = {172--177},
doi = {10.15199/48.2026.05.22}
}
EUVIMED