Salvato in:
Dettagli Bibliografici
Autori principali: Sanghi, Ojas, Jost, Norman, Pierce, Benjamin G., Cooper, Emma, Deane, Isaiah H., Braid, Jennifer L.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.13337
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910052513742848
author Sanghi, Ojas
Jost, Norman
Pierce, Benjamin G.
Cooper, Emma
Deane, Isaiah H.
Braid, Jennifer L.
author_facet Sanghi, Ojas
Jost, Norman
Pierce, Benjamin G.
Cooper, Emma
Deane, Isaiah H.
Braid, Jennifer L.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13337
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MultiSolSegment: Multi-channel segmentation of overlapping features in electroluminescence images of photovoltaic cells
Sanghi, Ojas
Jost, Norman
Pierce, Benjamin G.
Cooper, Emma
Deane, Isaiah H.
Braid, Jennifer L.
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title MultiSolSegment: Multi-channel segmentation of overlapping features in electroluminescence images of photovoltaic cells
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.13337