EUVIMEDEUVIMED entdecken
Crossref

Performance improvement of CNN-based model for multiclass hotspot severity classification in photovoltaic thermal imagery

Nurul Huda Ishak, Iza Sazanita Isa, Muhammad Khusairi Osman, Kamarulazhar Daud, Mohd Shawal Jadin, Noor Fadzilah Razali

ESTEEM Academic Journal · 01.04.2026 · 22 (March) · 58-72

DOI: 10.24191/esteem.v22imarch.10388 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ESTEEM Academic Journal, online erschienen am 01.04.2026. Verfasst von Nurul Huda Ishak und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intelligent diagnostic models that can identify and categorise thermal anomalies affecting efficiency and safety are essential for the reliable operation of photovoltaic (PV) systems. One of the most serious defects is thermal hotspots, which frequently result in energy loss and potential fire hazards. Convolutional Neural Networks (CNNs) have demonstrated promising performance when applied to aerial thermal images for PV fault detection. However, most existing models are limited to binary fault identification, thereby constraining their applicability for risk-based maintenance. Conventional CNN architectures also lack an optimised flatten-layer representation and fail to capture the full variability in hotspot severity. This study presents an enhanced CNN-based framework for multiclass classification of hotspot severity in PV modules. To improve feature abstraction and class separability across severity levels, the proposed model employs a staged architectural refinement strategy by progressively adding convolutional layers to a baseline CNN. Hotspot regions extracted from unmanned aerial vehicles (UAV)-acquired thermal imagery were categorised into low, medium, and high severity levels for model training and evaluation. The improved model achieved a 9.1% increase in accuracy and a 7.6% increase in F1-score, outperforming the baseline CNN, thus confirming its superior discriminative learning capability and diagnostic robustness. These findings demonstrate that architectural deepening and flatten-layer optimisation can advance automated thermographic inspection toward severity-aware predictive maintenance for PV systems.

Zitieren

APA

Ishak, N. H., Isa, I. S., Osman, M. K., Daud, K., Jadin, M. S., & Razali, N. F. (2026). Performance improvement of CNN-based model for multiclass hotspot severity classification in photovoltaic thermal imagery. ESTEEM Academic Journal, 22(March), 58-72. https://doi.org/10.24191/esteem.v22imarch.10388

Vancouver

Ishak NH, Isa IS, Osman MK, Daud K, Jadin MS, Razali NF. Performance improvement of CNN-based model for multiclass hotspot severity classification in photovoltaic thermal imagery. ESTEEM Academic Journal. 2026;22(March):58-72. doi:10.24191/esteem.v22imarch.10388

BibTeX
@article{Ishak2026,
  author = {Ishak, Nurul Huda and Isa, Iza Sazanita and Osman, Muhammad Khusairi and Daud, Kamarulazhar and Jadin, Mohd Shawal and Razali, Noor Fadzilah},
  title = {Performance improvement of CNN-based model for multiclass hotspot severity classification in photovoltaic thermal imagery},
  journal = {ESTEEM Academic Journal},
  year = {2026},
  volume = {22},
  number = {March},
  pages = {58--72},
  doi = {10.24191/esteem.v22imarch.10388}
}
Kostenlos starten →