Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning

Photovoltaic (PV) systems are key renewable energy sources due to their ease of implementation, scalability, and global solar availability. Enhancing their lifespan and performance is vital for wider adoption. Identifying degradation root causes is essential for improving PV design and maintenance,...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohand Djeziri, Ndricim Ferko, Marc Bendahan, Hiba Al Sheikh, Nazih Moubayed
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/7684
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849419184145956864
author Mohand Djeziri
Ndricim Ferko
Marc Bendahan
Hiba Al Sheikh
Nazih Moubayed
author_facet Mohand Djeziri
Ndricim Ferko
Marc Bendahan
Hiba Al Sheikh
Nazih Moubayed
author_sort Mohand Djeziri
collection DOAJ
description Photovoltaic (PV) systems are key renewable energy sources due to their ease of implementation, scalability, and global solar availability. Enhancing their lifespan and performance is vital for wider adoption. Identifying degradation root causes is essential for improving PV design and maintenance, thus extending lifespan. This paper proposes a hybrid fault diagnosis method combining a bond graph-based PV cell model with empirical degradation models to simulate faults, and a deep learning approach for root-cause detection. The experimentally validated model simulates degradation effects on measurable variables (voltage, current, ambient, and cell temperatures). The resulting dataset trains an Optimized Feed-Forward Neural Network (OFFNN), achieving 75.43% accuracy in multi-class classification, which effectively identifies degradation processes.
format Article
id doaj-art-a735e0737b214e39be42bbdc0c7d86d6
institution Kabale University
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-a735e0737b214e39be42bbdc0c7d86d62025-08-20T03:32:12ZengMDPI AGApplied Sciences2076-34172025-07-011514768410.3390/app15147684Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep LearningMohand Djeziri0Ndricim Ferko1Marc Bendahan2Hiba Al Sheikh3Nazih Moubayed4Aix-Marseille University, Université de Toulon, CNRS, IM2NP, 13397 Marseille, FranceAix-Marseille University, Université de Toulon, CNRS, IM2NP, 13397 Marseille, FranceAix-Marseille University, Université de Toulon, CNRS, IM2NP, 13397 Marseille, FranceFaculty of Engineering, City University, Tripoli 1300, LebanonLaRGES-CRSI, Faculty of Engineering, Lebanese University, Tripoli 1300, LebanonPhotovoltaic (PV) systems are key renewable energy sources due to their ease of implementation, scalability, and global solar availability. Enhancing their lifespan and performance is vital for wider adoption. Identifying degradation root causes is essential for improving PV design and maintenance, thus extending lifespan. This paper proposes a hybrid fault diagnosis method combining a bond graph-based PV cell model with empirical degradation models to simulate faults, and a deep learning approach for root-cause detection. The experimentally validated model simulates degradation effects on measurable variables (voltage, current, ambient, and cell temperatures). The resulting dataset trains an Optimized Feed-Forward Neural Network (OFFNN), achieving 75.43% accuracy in multi-class classification, which effectively identifies degradation processes.https://www.mdpi.com/2076-3417/15/14/7684solar cellfault detection and identificationsimulationmonitoring
spellingShingle Mohand Djeziri
Ndricim Ferko
Marc Bendahan
Hiba Al Sheikh
Nazih Moubayed
Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning
Applied Sciences
solar cell
fault detection and identification
simulation
monitoring
title Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning
title_full Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning
title_fullStr Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning
title_full_unstemmed Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning
title_short Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning
title_sort detection and identification of degradation root causes in a photovoltaic cell based on physical modeling and deep learning
topic solar cell
fault detection and identification
simulation
monitoring
url https://www.mdpi.com/2076-3417/15/14/7684
work_keys_str_mv AT mohanddjeziri detectionandidentificationofdegradationrootcausesinaphotovoltaiccellbasedonphysicalmodelinganddeeplearning
AT ndricimferko detectionandidentificationofdegradationrootcausesinaphotovoltaiccellbasedonphysicalmodelinganddeeplearning
AT marcbendahan detectionandidentificationofdegradationrootcausesinaphotovoltaiccellbasedonphysicalmodelinganddeeplearning
AT hibaalsheikh detectionandidentificationofdegradationrootcausesinaphotovoltaiccellbasedonphysicalmodelinganddeeplearning
AT nazihmoubayed detectionandidentificationofdegradationrootcausesinaphotovoltaiccellbasedonphysicalmodelinganddeeplearning