Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet's computer vision in aerial infrared imagery analysis

The rapid growth of the solar photovoltaic industry underlines the importance of effective operation and maintenance strategies, particularly for large-scale systems. Aerial infrared thermography has become an essential tool for detecting anomalies in photovoltaic modules due to its cost-effectivene...

Full description

Saved in:
Bibliographic Details
Main Authors: Gallmetzer Sandra, Sondoqah Mousa, Turri Evelyn, Koester Lukas, Louwen Atse, Moser David
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/pv20240079/pv20240079.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730658047361024
author Gallmetzer Sandra
Sondoqah Mousa
Turri Evelyn
Koester Lukas
Louwen Atse
Moser David
author_facet Gallmetzer Sandra
Sondoqah Mousa
Turri Evelyn
Koester Lukas
Louwen Atse
Moser David
author_sort Gallmetzer Sandra
collection DOAJ
description The rapid growth of the solar photovoltaic industry underlines the importance of effective operation and maintenance strategies, particularly for large-scale systems. Aerial infrared thermography has become an essential tool for detecting anomalies in photovoltaic modules due to its cost-effectiveness and scalability. Continuous monitoring through advanced fault detection and classification methods can maintain optimal system performance and extend the life of PV modules. This study investigates the application of advanced artificial intelligence methods for fault detection and classification comparing the performance of GPT-4o, a multimodal large language model, and ResNet, a convolutional neural network renowned for image classification tasks. Our research evaluates the effectiveness of both models using infrared images, focusing on binary defect detection and multiclass classification. ResNet demonstrated advantages in terms of computational efficiency and ease of implementation. Conversely, GPT-4o offered superior adaptability and interpretability, effectively analysing multimodal data to identify and explain subtle anomalies in thermal imagery. However, its higher computational requirements limit its feasibility in resource-limited settings. The results highlight the complementary strengths of these models and provide valuable insights into their role in advancing automated fault diagnosis in photovoltaic systems.
format Article
id doaj-art-834934d2f0034d4ca577ecefd05771ea
institution DOAJ
issn 2105-0716
language English
publishDate 2025-01-01
publisher EDP Sciences
record_format Article
series EPJ Photovoltaics
spelling doaj-art-834934d2f0034d4ca577ecefd05771ea2025-08-20T03:08:47ZengEDP SciencesEPJ Photovoltaics2105-07162025-01-01162310.1051/epjpv/2025010pv20240079Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet's computer vision in aerial infrared imagery analysisGallmetzer Sandra0https://orcid.org/0000-0002-6660-6115Sondoqah Mousa1Turri Evelyn2https://orcid.org/0009-0005-5668-0839Koester Lukas3Louwen Atse4Moser David5Institute for Renewable Energy, Eurac ResearchInstitute for Renewable Energy, Eurac ResearchInstitute for Renewable Energy, Eurac ResearchInstitute for Renewable Energy, Eurac ResearchInstitute for Renewable Energy, Eurac ResearchInstitute for Renewable Energy, Eurac ResearchThe rapid growth of the solar photovoltaic industry underlines the importance of effective operation and maintenance strategies, particularly for large-scale systems. Aerial infrared thermography has become an essential tool for detecting anomalies in photovoltaic modules due to its cost-effectiveness and scalability. Continuous monitoring through advanced fault detection and classification methods can maintain optimal system performance and extend the life of PV modules. This study investigates the application of advanced artificial intelligence methods for fault detection and classification comparing the performance of GPT-4o, a multimodal large language model, and ResNet, a convolutional neural network renowned for image classification tasks. Our research evaluates the effectiveness of both models using infrared images, focusing on binary defect detection and multiclass classification. ResNet demonstrated advantages in terms of computational efficiency and ease of implementation. Conversely, GPT-4o offered superior adaptability and interpretability, effectively analysing multimodal data to identify and explain subtle anomalies in thermal imagery. However, its higher computational requirements limit its feasibility in resource-limited settings. The results highlight the complementary strengths of these models and provide valuable insights into their role in advancing automated fault diagnosis in photovoltaic systems.https://www.epj-pv.org/articles/epjpv/full_html/2025/01/pv20240079/pv20240079.htmlinspectionperformancefailure detection and classificationphotovoltaicsmultimodal large language modelsprompt engineering
spellingShingle Gallmetzer Sandra
Sondoqah Mousa
Turri Evelyn
Koester Lukas
Louwen Atse
Moser David
Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet's computer vision in aerial infrared imagery analysis
EPJ Photovoltaics
inspection
performance
failure detection and classification
photovoltaics
multimodal large language models
prompt engineering
title Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet's computer vision in aerial infrared imagery analysis
title_full Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet's computer vision in aerial infrared imagery analysis
title_fullStr Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet's computer vision in aerial infrared imagery analysis
title_full_unstemmed Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet's computer vision in aerial infrared imagery analysis
title_short Redefining failure detection in PV Systems: a comparative study of GPT-4o and ResNet's computer vision in aerial infrared imagery analysis
title_sort redefining failure detection in pv systems a comparative study of gpt 4o and resnet s computer vision in aerial infrared imagery analysis
topic inspection
performance
failure detection and classification
photovoltaics
multimodal large language models
prompt engineering
url https://www.epj-pv.org/articles/epjpv/full_html/2025/01/pv20240079/pv20240079.html
work_keys_str_mv AT gallmetzersandra redefiningfailuredetectioninpvsystemsacomparativestudyofgpt4oandresnetscomputervisioninaerialinfraredimageryanalysis
AT sondoqahmousa redefiningfailuredetectioninpvsystemsacomparativestudyofgpt4oandresnetscomputervisioninaerialinfraredimageryanalysis
AT turrievelyn redefiningfailuredetectioninpvsystemsacomparativestudyofgpt4oandresnetscomputervisioninaerialinfraredimageryanalysis
AT koesterlukas redefiningfailuredetectioninpvsystemsacomparativestudyofgpt4oandresnetscomputervisioninaerialinfraredimageryanalysis
AT louwenatse redefiningfailuredetectioninpvsystemsacomparativestudyofgpt4oandresnetscomputervisioninaerialinfraredimageryanalysis
AT moserdavid redefiningfailuredetectioninpvsystemsacomparativestudyofgpt4oandresnetscomputervisioninaerialinfraredimageryanalysis