SolarFCD unifies RGB and thermal solar panel images from prior datasets into 4,435 samples across healthy, surface obstruction, structural fault, and electrical fault classes, with ResNet101V2 reaching 86.68% accuracy as the strongest baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
SolarFCD: A Large-Scale Dataset and Benchmark for Solar Fault Classification in Photovoltaic Systems
SolarFCD unifies RGB and thermal solar panel images from prior datasets into 4,435 samples across healthy, surface obstruction, structural fault, and electrical fault classes, with ResNet101V2 reaching 86.68% accuracy as the strongest baseline.