Deep Learning Model to Denoise Luminescence Images of Silicon Solar Cells
-
Published:2023-04-24
Issue:18
Volume:10
Page:
-
ISSN:2198-3844
-
Container-title:Advanced Science
-
language:en
-
Short-container-title:Advanced Science
Author:
Liu Grace1ORCID,
Dwivedi Priya1,
Trupke Thorsten1,
Hameiri Ziv1ORCID
Affiliation:
1. University of New South Wales (UNSW) Sydney NSW 2052 Australia
Abstract
AbstractLuminescence imaging is widely used to identify spatial defects and extract key electrical parameters of photovoltaic devices. To reliably identify defects, high‐quality images are desirable; however, acquiring such images implies a higher cost or lower throughput as they require better imaging systems or longer exposure times. This study proposes a deep learning‐based method to effectively diminish the noise in luminescence images, thereby enhancing their quality for inspection and analysis. The proposed method eliminates the requirement for extra hardware expenses or longer exposure times, making it a cost‐effective solution for image enhancement. This approach significantly improves image quality by >30% and >39% in terms of the peak signal‐to‐noise ratio and the structural similarity index, respectively, outperforming state‐of‐the‐art classical denoising algorithms.
Funder
Australian Renewable Energy Agency
Subject
General Physics and Astronomy,General Engineering,Biochemistry, Genetics and Molecular Biology (miscellaneous),General Materials Science,General Chemical Engineering,Medicine (miscellaneous)
Reference58 articles.
1. International Renewable Energy Agency Abu Dhabi UAE2019.
2. International Renewable Energy Agency Abu Dhabi UAE2020.
3. International Technology Roadmap for Photovoltaic VDMA Services GmbH Frankfurt Gremany2021.
4. Photographic Diagnosis of Crystalline Silicon Solar Cells by Electroluminescence