Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plants

Although aerial infrared (aIRT) imagery-based solutions for diagnostics of PV plants demonstrate impressive time-efficiency and spatial resolution, they also suffer from considerable drawbacks: limited automation (hence, expert dependence) and insufficient quantitative insights. In this paper, we in...

Full description

Saved in:
Bibliographic Details
Main Authors: Tsanakas John Ioannis A., Marechal Philippe
Format: Article
Language:English
Published: EDP Sciences 2025-01-01
Series:EPJ Photovoltaics
Subjects:
Online Access:https://www.epj-pv.org/articles/epjpv/full_html/2025/01/pv20240066/pv20240066.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730691022979072
author Tsanakas John Ioannis A.
Marechal Philippe
author_facet Tsanakas John Ioannis A.
Marechal Philippe
author_sort Tsanakas John Ioannis A.
collection DOAJ
description Although aerial infrared (aIRT) imagery-based solutions for diagnostics of PV plants demonstrate impressive time-efficiency and spatial resolution, they also suffer from considerable drawbacks: limited automation (hence, expert dependence) and insufficient quantitative insights. In this paper, we introduce a software prototype, evolved from an innovative diagnostics framework researched and developed by CEA-INES over the last years, which integrates aIRT imagery with deep learning-based algorithms and physical/electrical modeling. With such an approach, unlike conventional ones, we worked on reaching both qualitative fault detection and quantitative (power loss) insights, with a focus on various spatial granularity levels within PV systems. Leveraging advanced deep learning techniques, first results show that we can achieve automated PV module detection and fault identification/classification, with associated power loss analysis at PV system, string/inverter, or module level. Further real-life validation efforts are underway, in utility-scale PV plants. Future developments aim to enhance further enhance our PV diagnostic framework, through data fusion with SCADA outputs and integration with maintenance and end-of-life (EoL) management tools.
format Article
id doaj-art-ef3371d4f21344b2bd919175cc1571f4
institution DOAJ
issn 2105-0716
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series EPJ Photovoltaics
spelling doaj-art-ef3371d4f21344b2bd919175cc1571f42025-08-20T03:08:47ZengEDP SciencesEPJ Photovoltaics2105-07162025-01-01162410.1051/epjpv/2025013pv20240066Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plantsTsanakas John Ioannis A.0https://orcid.org/0000-0002-8230-4635Marechal Philippe1CEA, Liten, Univ. Grenoble Alpes Campus INESCEA, Liten, Univ. Grenoble Alpes Campus INESAlthough aerial infrared (aIRT) imagery-based solutions for diagnostics of PV plants demonstrate impressive time-efficiency and spatial resolution, they also suffer from considerable drawbacks: limited automation (hence, expert dependence) and insufficient quantitative insights. In this paper, we introduce a software prototype, evolved from an innovative diagnostics framework researched and developed by CEA-INES over the last years, which integrates aIRT imagery with deep learning-based algorithms and physical/electrical modeling. With such an approach, unlike conventional ones, we worked on reaching both qualitative fault detection and quantitative (power loss) insights, with a focus on various spatial granularity levels within PV systems. Leveraging advanced deep learning techniques, first results show that we can achieve automated PV module detection and fault identification/classification, with associated power loss analysis at PV system, string/inverter, or module level. Further real-life validation efforts are underway, in utility-scale PV plants. Future developments aim to enhance further enhance our PV diagnostic framework, through data fusion with SCADA outputs and integration with maintenance and end-of-life (EoL) management tools.https://www.epj-pv.org/articles/epjpv/full_html/2025/01/pv20240066/pv20240066.htmlpv systemsfault diagnosticsdeep learningthermal imagery
spellingShingle Tsanakas John Ioannis A.
Marechal Philippe
Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plants
EPJ Photovoltaics
pv systems
fault diagnostics
deep learning
thermal imagery
title Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plants
title_full Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plants
title_fullStr Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plants
title_full_unstemmed Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plants
title_short Decoding pixels: A modular software prototype for cognitive image-based diagnostics of PV plants
title_sort decoding pixels a modular software prototype for cognitive image based diagnostics of pv plants
topic pv systems
fault diagnostics
deep learning
thermal imagery
url https://www.epj-pv.org/articles/epjpv/full_html/2025/01/pv20240066/pv20240066.html
work_keys_str_mv AT tsanakasjohnioannisa decodingpixelsamodularsoftwareprototypeforcognitiveimagebaseddiagnosticsofpvplants
AT marechalphilippe decodingpixelsamodularsoftwareprototypeforcognitiveimagebaseddiagnosticsofpvplants