SolarFCD: A Large-Scale Dataset and Benchmark for Solar Fault Classification in Photovoltaic Systems

TL;DR

SolarFCD is a comprehensive dataset and benchmark for classifying solar panel defects using multi-modal images, enabling improved automated inspection of photovoltaic systems.

Contribution

This work introduces SolarFCD, a large-scale, multi-modal dataset with benchmark results for solar fault classification, addressing the lack of publicly available annotated datasets in this domain.

Findings

ResNet101V2 achieved 86.68% accuracy on the dataset.

Balanced detection across defect classes with less than 1.2% performance variation.

Open release of dataset, annotations, and baseline code to support research.

Abstract

The increasing global deployment of solar photovoltaic (PV) systems needs robust, scalable, and automated inspection technologies capable of detecting a wide range of panel flaws under a variety of operating situations. The lack of large-scale, multi-modal, publicly available annotated datasets is a major obstacle preventing advancement in this field. We introduce SolarFCD, an extensive dataset of solar panel defects created by methodically combining and reconciling three publicly accessible datasets covering two imaging modalities: RGB/Drone images and Thermal Infrared. The dataset consist of 4,435 images arranged under four unified defect classes such as: healthy images, Surface Obstruction, structural fault, and electrical fault. The dataset was divided into training, validation, and test splits at an 80:10:10 ratio through methodical label mapping, near-duplicate removal, and targeted augmentation of minority classes. Sixteen classification architectures from five design families were trained and assessed on the dataset to provide repeatable benchmark baselines. With an accuracy of 86.68%, precision of 88.65%, recall of 88.62%, and F1-score of 88.17%, ResNet101V2 performed the best overall. Per-class results showed balanced detection across all four defect categories within a narrow performance band of less than 1.2 percentage points. To promote open and repeatable research in automated PV inspection and solar energy operations and maintenance, the dataset, annotation files, and baseline code are made openly available.