DCGAN-Driven Minority Class Augmentation for Lightweight YOLO-Based Photovoltaic Defect Localization Suitable for Edge Deployment

Abstract

This study presents YOLOv11n-GhostLite, an innovative lightweight deep learning architecture optimized for real-time localization of photovoltaic (PV) faults in electroluminescence (EL) images, specifically designed for edge deployment. A Deep Convolutional Generative Adversarial Network (DCGAN)-based synthetic augmentation pipeline is presented to address the issues of class imbalance and limited resource availability, generating high-fidelity, class-conditional EL images that include realistic banding artifacts. This method enhances the representation of minority defect categories by more than 150%, elevating the mean Average Precision (mAP@50) by 4% and decreasing false negatives by 5%. The proposed model incorporates GhostConv for efficient early feature extraction, C3k2 residual blocks for deep representation learning, GhostSPPF for multi-scale context aggregation, C2PSA attention for adaptive feature refinement, and an anchor-free detection head, achieving high performance with only 2.34 million parameters and 6.2 GFLOPs. Detailed experiments on two benchmark datasets PVEL-AD and PV Multi-Defect exhibit the model’s efficacy, attaining 97.2% mAP@50 on PVEL-AD, and 96.4% mAP@50 on PV Multi-Defect, outperforming larger models in both accuracy and speed. The model is further deployed on a Google Coral Edge TPU, demonstrating its real-time functionality with minimal power consumption (~2W) and suitable latency for drone-based solar inspections. YOLOv11n-GhostLite’s integration of efficient architecture and data-driven augmentation renders it an effective solution for scalable, real-time photovoltaic fault detection in resource-limited settings.