Defect-Specific Physical-Prior-Guided Synthesis of Photovoltaic RGB Defect Images with Pixel-Level Annotations
Open Access
- 20 September 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (18) , 9338
Abstract
Reliable visual inspection of photovoltaic modules is limited by the scarcity of diverse defect images and pixel-level annotations. This study proposes a defect-specific RGB image synthesis framework combining local feature disentanglement and physical-prior-guided modeling for shadow, debris, dust, and broken defects, while simultaneously generating spatially aligned pixel-level masks. The generated samples are evaluated in terms of image quality, distribution consistency, structural preservation, and downstream utility. Compared with CycleGAN, MUNIT, and SDXL Inpainting, the proposed method achieves the lowest BRISQUE scores across all four categories, the lowest class-wise Defect-aware Fréchet Distance (DFD) for shadow, debris, and broken, and the lowest MMD2-RBF values across all categories. With generated samples added to real training data, the five-run average classification Accuracy and Macro-F1 reach 88.96% and 87.83%, respectively, while detection performance is also improved. Moreover, a segmentation model trained solely on generated image–mask pairs achieves an mIoU of 60.15% on unseen real images. These results demonstrate that the proposed framework provides structurally consistent, task-useful defect samples and directly usable pixel-level supervision for photovoltaic visual inspection.Keywords
Funding Information
- Department of Science and Technology of Inner Mongolia Autonomous Region (2025YFDZ0034)
This publication has 47 references indexed in Scilit:
- Open data sets for assessing photovoltaic system reliabilityApplied Energy, 2025
- PVF-10: A high-resolution unmanned aerial vehicle thermal infrared image dataset for fine-grained photovoltaic fault classificationApplied Energy, 2024
- Towards more reliable photovoltaic energy conversion systems: A weakly-supervised learning perspective on anomaly detectionEnergy Conversion and Management, 2024
- Weakly-semi supervised extraction of rooftop photovoltaics from high-resolution images based on segment anything model and class activation mapApplied Energy, 2024
- Compound fault diagnosis for photovoltaic arrays based on multi-label learning considering multiple faults couplingEnergy Conversion and Management, 2023
- Automatic detection, classification and localization of defects in large photovoltaic plants using unmanned aerial vehicles (UAV) based infrared (IR) and RGB imagingEnergy Conversion and Management, 2022
- An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural networkEngineering Applications of Artificial Intelligence, 2022
- Automatic soiling and partial shading assessment on PV modules through RGB images analysisApplied Energy, 2022
- Dataset for recognition of snail trails and hot spot failures in monocrystalline Si solar panelsData in Brief, 2019
- Multimodal Unsupervised Image-to-Image Translation2018