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

• URL: http://arxiv.org/abs/2604.23662v1
• Date: Sun, 26 Apr 2026 11:33:07 GMT
• Title: SolarFCD: A Large-Scale Dataset and Benchmark for Solar Fault Classification in Photovoltaic Systems
• Abstract summary: We introduce SolarFCD, an extensive dataset of solar panel defects created by combining and reconciling three publicly accessible datasets.<n>The dataset consist of 4,435 images arranged under four unified defect classes such as: healthy images, Surface Obstruction, structural fault, and electrical fault.<n>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.
• Score: 5.4998857381465465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• TinyViT: Field Deployable Transformer Pipeline for Solar Panel Surface Fault and Severity Screening [0.0]
  This work demonstrates that deep learning and classical machine learning may be judiciously combined to achieve robust surface anomaly categorization and severity estimation.<n>We introduce TinyViT which is a compact pipeline integrating Transformer based segmentation, spectral-spatial feature engineering, and ensemble regression.
  arXiv  Detail & Related papers  (2025-11-27T17:35:57Z)
• Vision-Based Object Detection for UAV Solar Panel Inspection Using an Enhanced Defects Dataset [0.0]
  This study presents a comprehensive evaluation of five state-of-the-art object detection models: YOLOv3, Faster R-CNN, RetinaNet, EfficientDet, and Swin Transformer.<n>A custom dataset, annotated in the COCO format and specifically designed for solar panel defect and contamination detection, was developed.<n>The results demonstrate the trade-offs between detection accuracy and computational efficiency, highlighting the relative strengths and limitations of each model.
  arXiv  Detail & Related papers  (2025-09-02T14:41:31Z)
• Power Battery Detection [91.99787495748218]
  Power batteries are essential components in electric vehicles, where internal structural defects can pose serious safety risks.<n>We conduct a comprehensive study on power battery detection (PBD), which aims to localize the dense endpoints of cathode and anode plates from X-ray images for quality inspection.<n>We present PBD5K, the first large-scale benchmark for this task, consisting of 5,000 X-ray images from nine battery types with fine-grained annotations and eight types of real-world visual interference.
  arXiv  Detail & Related papers  (2025-08-11T09:35:25Z)
• Solar Photovoltaic Assessment with Large Language Model [5.156484100374059]
  We investigate how large language models (LLMs) can be leveraged to overcome solar panel detection challenges.<n>LLMs face several challenges in solar panel detection, including difficulties with multi-step logical processes.<n>We propose the PV Assessment with LLMs framework, which incorporates task decomposition for more efficient output standardization.
  arXiv  Detail & Related papers  (2025-07-25T10:26:29Z)
• One-Shot Learning for Periocular Recognition: Exploring the Effect of Domain Adaptation and Data Bias on Deep Representations [59.17685450892182]
  We investigate the behavior of deep representations in widely used CNN models under extreme data scarcity for One-Shot periocular recognition. We improved state-of-the-art results that made use of networks trained with biometric datasets with millions of images. Traditional algorithms like SIFT can outperform CNNs in situations with limited data.
  arXiv  Detail & Related papers  (2023-07-11T09:10:16Z)
• A Comparative Study on Generative Models for High Resolution Solar Observation Imaging [59.372588316558826]
  This work investigates capabilities of current state-of-the-art generative models to accurately capture the data distribution behind observed solar activity states. Using distributed training on supercomputers, we are able to train generative models for up to 1024x1024 resolution that produce high quality samples indistinguishable to human experts.
  arXiv  Detail & Related papers  (2023-04-14T14:40:32Z)
• A Fault Detection Scheme Utilizing Convolutional Neural Network for PV Solar Panels with High Accuracy [0.0]
  This paper proposes a trained convolutional neural network based fault detection scheme. For binary classification, the algorithm classifies the input images of PV cells into two categories. The success rate for the proposed CNN model is 91.1% for binary classification and 88.6% for multi-classification.
  arXiv  Detail & Related papers  (2022-10-14T14:19:33Z)
• CellDefectNet: A Machine-designed Attention Condenser Network for Electroluminescence-based Photovoltaic Cell Defect Inspection [67.99623869339919]
  A big challenge faced by industry in photovoltaic cell visual inspection is the fact that it is currently done manually by human inspectors. In this work, we introduce CellDefectNet, a highly efficient attention condenser network designed via machine-driven design exploration. We demonstrate the efficacy of CellDefectNet on a benchmark dataset comprising of a diversity of photovoltaic cells captured using electroluminescence imagery.
  arXiv  Detail & Related papers  (2022-04-25T16:35:19Z)
• Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning [4.409996772486956]
  We train a ResNet-34 convolutional neural network with a supervised contrastive loss to detect anomalies in infrared images. Our method converges quickly and reliably detects unknown types of anomalies making it well suited for practice. Our work serves the community with a more realistic view on PV module fault detection using unsupervised domain adaptation.
  arXiv  Detail & Related papers  (2021-12-06T10:42:28Z)
• A Multi-Stage model based on YOLOv3 for defect detection in PV panels based on IR and Visible Imaging by Unmanned Aerial Vehicle [65.99880594435643]
  We propose a novel model to detect panel defects on aerial images captured by unmanned aerial vehicle. The model combines detections of panels and defects to refine its accuracy. The proposed model has been validated on two big PV plants in the south of Italy.
  arXiv  Detail & Related papers  (2021-11-23T08:04:32Z)
• Chest x-ray automated triage: a semiologic approach designed for clinical implementation, exploiting different types of labels through a combination of four Deep Learning architectures [83.48996461770017]
  This work presents a Deep Learning method based on the late fusion of different convolutional architectures. We built four training datasets combining images from public chest x-ray datasets and our institutional archive. We trained four different Deep Learning architectures and combined their outputs with a late fusion strategy, obtaining a unified tool.
  arXiv  Detail & Related papers  (2020-12-23T14:38:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.