Electroluminescence (EL) imaging is widely used to detect defects in photovoltaic (PV) modules, and machine learning methods have been applied to enable large-scale analysis of EL images. However, existing methods cannot assign multiple labels to the same pixel, limiting their ability to capture overlapping degradation features. We present a multi-channel U-Net architecture for pixel-level multi-label segmentation of EL images. The model outputs independent probability maps for cracks, busbars, dark areas, and non-cell regions, enabling accurate co-classification of interacting features such as cracks crossing busbars. The model achieved an accuracy of 98% and has been shown to generalize to unseen datasets. This framework offers a scalable, extensible tool for automated PV module inspection, improving defect quantification and lifetime prediction in large-scale PV systems. • Developed multi-channel U-Net for pixel-level multi-label segmentation of EL images. • New model enables co-classification of overlapping PV degradation features. • Prepared a diverse set of labeled 2,340 mono-Si images, with categories: dark-area, crack, busbar and no cell. • Bench-marked against another widely used segmentation model for solar cells with better results.
Sanghi et al. (Wed,) studied this question.