MultiSolSegment: Multi-channel segmentation of overlapping features in electroluminescence images of photovoltaic cells

TL;DR

This paper introduces a multi-channel U-Net model for pixel-level multi-label segmentation of electroluminescence images of photovoltaic cells, enabling accurate detection of overlapping defects and features.

Contribution

The paper presents a novel multi-channel segmentation architecture that can assign multiple labels to each pixel in EL images, improving defect detection in PV modules.

Findings

Achieved 98% accuracy in segmentation tasks.

Generalized well to unseen datasets.

Enabled accurate co-classification of overlapping features.

Abstract

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.