MultiSolSegment: Multi-channel segmentation of overlapping features in electroluminescence images of photovoltaic cells
This provides a scalable tool for automated inspection of photovoltaic modules, improving defect quantification and lifetime prediction in large-scale systems.
The paper tackled the problem of overlapping degradation features in electroluminescence images of photovoltaic cells by developing a multi-channel U-Net architecture for multi-label segmentation, achieving 98% accuracy and generalization to unseen datasets.
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.