EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Approach to Automated Monitoring of Defects and Soiling on Solar Panels

Ahmed Hamdi, Hassan N. Noura, Joseph Azar

Future Internet · 23.09.2025 · 17 (10) · 433

DOI: 10.3390/fi17100433 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 23.09.2025. Verfasst von Ahmed Hamdi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bourgogne-Franche-Comté Region, EIPHI Graduate School.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The reliable operation of photovoltaic (PV) systems is often compromised by surface soiling and structural damage, which reduce energy efficiency and complicate large-scale monitoring. To address this challenge, we propose a two-tiered image-classification framework that combines Vision Transformer (ViT) models, lightweight convolutional neural networks (CNNs), and knowledge distillation (KD). In Tier 1, a DINOv2 ViT-Base model is fine-tuned to provide robust high-level categorization of solar-panel images into three classes: Normal, Soiled, and Damaged. In Tier 2, two enhanced EfficientNetB0 models are introduced: (i) a KD-based student model distilled from a DINOv2 ViT-S/14 teacher, which improves accuracy from 96.7% to 98.67% for damage classification and from 90.7% to 92.38% for soiling classification, and (ii) an EfficientNetB0 augmented with Multi-Head Self-Attention (MHSA), which achieves 98.73% accuracy for damage and 93.33% accuracy for soiling. These results demonstrate that integrating transformer-based representations with compact CNN architectures yields a scalable and efficient solution for automated monitoring of the condition of PV systems, offering high accuracy and real-time applicability in inspections on solar farms.

Förderung

  • Bourgogne-Franche-Comté Region
  • EIPHI Graduate School

Zitieren

APA

Hamdi, A., Noura, H. N., & Azar, J. (2025). Deep Learning-Based Approach to Automated Monitoring of Defects and Soiling on Solar Panels. Future Internet, 17(10), 433. https://doi.org/10.3390/fi17100433

Vancouver

Hamdi A, Noura HN, Azar J. Deep Learning-Based Approach to Automated Monitoring of Defects and Soiling on Solar Panels. Future Internet. 2025;17(10):433. doi:10.3390/fi17100433

BibTeX
@article{Hamdi2025,
  author = {Hamdi, Ahmed and Noura, Hassan N. and Azar, Joseph},
  title = {Deep Learning-Based Approach to Automated Monitoring of Defects and Soiling on Solar Panels},
  journal = {Future Internet},
  year = {2025},
  volume = {17},
  number = {10},
  pages = {433},
  doi = {10.3390/fi17100433}
}
Kostenlos starten →