Transfer Learning-based Enhanced Detection of Hotspot and Bypass Diode Faults in Photovoltaic Arrays

Zahra Mohammadi; Aref Eskandari; Gevork B. Gharepetian; Amir Nedaei; Rodrigo Del Prado Santamaria; Gisele A. Dos Reis Benatto; Mohammadreza Aghaei

doi:10.1109/PVSC59419.2025.11132955

Transfer Learning-based Enhanced Detection of Hotspot and Bypass Diode Faults in Photovoltaic Arrays

Zahra Mohammadi
, Aref Eskandari
, Gevork B. Gharepetian
, Amir Nedaei
, Rodrigo Del Prado Santamaria
, Gisele A. Dos Reis Benatto
, Mohammadreza Aghaei

Amirkabir University of Technology
Iran University of Science and Technology
Norwegian University of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Due to the increasing importance of solar systems and their growing role in the world, ensuring their proper and flawless operation is of utmost importance. Solar photovoltaic (PV) systems are susceptible to various faults, making early fault detection a critical task. Persistent faults in PV systems can lead to irreversible damages. In this regard, this paper focuses on PV fault detection and classification using the transfer learning method. Initially, a dataset of thermographic images from PV arrays was collected. Subsequently, fine-tuning was performed, and finally, fault detection and classification were carried out using a pre-trained model. The model achieved 100% accuracy in detecting and classifying bypass diode and hotspot faults, as well as distinguishing healthy modules.

Original language	English
Title of host publication	Proceedings of IEEE 53^rd Photovoltaic Specialists Conference (PVSC 2025)
Publisher	IEEE
Publication date	2025
Pages	969-973
Article number	11132955
ISBN (Print)	979-8-3315-3445-5
DOIs	https://doi.org/10.1109/PVSC59419.2025.11132955
Publication status	Published - 2025
Event	2025 IEEE 53^rd Photovoltaic Specialists Conference - Palais des congres de Montreal, Montreal, Canada Duration: 8 Jun 2025 → 13 Jun 2025

Conference

Conference	2025 IEEE 53^rd Photovoltaic Specialists Conference
Location	Palais des congres de Montreal
Country/Territory	Canada
City	Montreal
Period	08/06/2025 → 13/06/2025

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Access to Document

10.1109/PVSC59419.2025.11132955

OpenUrl availability

Check availability in DTU Findit

Cite this

Mohammadi, Z., Eskandari, A., Gharepetian, G. B., Nedaei, A., Santamaria, R. D. P., Benatto, G. A. D. R., & Aghaei, M. (2025). Transfer Learning-based Enhanced Detection of Hotspot and Bypass Diode Faults in Photovoltaic Arrays. In Proceedings of IEEE 53^rd Photovoltaic Specialists Conference (PVSC 2025) (pp. 969-973). Article 11132955 IEEE. https://doi.org/10.1109/PVSC59419.2025.11132955

@inproceedings{ee26aeaa1d804efdb8769396123b53d9,

title = "Transfer Learning-based Enhanced Detection of Hotspot and Bypass Diode Faults in Photovoltaic Arrays",

abstract = "Due to the increasing importance of solar systems and their growing role in the world, ensuring their proper and flawless operation is of utmost importance. Solar photovoltaic (PV) systems are susceptible to various faults, making early fault detection a critical task. Persistent faults in PV systems can lead to irreversible damages. In this regard, this paper focuses on PV fault detection and classification using the transfer learning method. Initially, a dataset of thermographic images from PV arrays was collected. Subsequently, fine-tuning was performed, and finally, fault detection and classification were carried out using a pre-trained model. The model achieved 100\% accuracy in detecting and classifying bypass diode and hotspot faults, as well as distinguishing healthy modules.",

author = "Zahra Mohammadi and Aref Eskandari and Gharepetian, \{Gevork B.\} and Amir Nedaei and Santamaria, \{Rodrigo Del Prado\} and Benatto, \{Gisele A. Dos Reis\} and Mohammadreza Aghaei",

year = "2025",

doi = "10.1109/PVSC59419.2025.11132955",

language = "English",

isbn = "979-8-3315-3445-5",

pages = "969--973",

booktitle = "Proceedings of IEEE 53rd Photovoltaic Specialists Conference (PVSC 2025)",

publisher = "IEEE",

address = "United States",

note = "2025 IEEE 53<sup>rd</sup> Photovoltaic Specialists Conference, PVSC53 ; Conference date: 08-06-2025 Through 13-06-2025",

}

Mohammadi, Z, Eskandari, A, Gharepetian, GB, Nedaei, A, Santamaria, RDP , Benatto, GADR & Aghaei, M 2025, Transfer Learning-based Enhanced Detection of Hotspot and Bypass Diode Faults in Photovoltaic Arrays. in Proceedings of IEEE 53^rd Photovoltaic Specialists Conference (PVSC 2025)., 11132955, IEEE, pp. 969-973, 2025 IEEE 53^rd Photovoltaic Specialists Conference, Montreal, Quebec, Canada, 08/06/2025. https://doi.org/10.1109/PVSC59419.2025.11132955

Transfer Learning-based Enhanced Detection of Hotspot and Bypass Diode Faults in Photovoltaic Arrays. / Mohammadi, Zahra; Eskandari, Aref; Gharepetian, Gevork B. et al.
Proceedings of IEEE 53^rd Photovoltaic Specialists Conference (PVSC 2025). IEEE, 2025. p. 969-973 11132955.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Transfer Learning-based Enhanced Detection of Hotspot and Bypass Diode Faults in Photovoltaic Arrays

AU - Mohammadi, Zahra

AU - Eskandari, Aref

AU - Gharepetian, Gevork B.

AU - Nedaei, Amir

AU - Santamaria, Rodrigo Del Prado

AU - Benatto, Gisele A. Dos Reis

AU - Aghaei, Mohammadreza

PY - 2025

Y1 - 2025

N2 - Due to the increasing importance of solar systems and their growing role in the world, ensuring their proper and flawless operation is of utmost importance. Solar photovoltaic (PV) systems are susceptible to various faults, making early fault detection a critical task. Persistent faults in PV systems can lead to irreversible damages. In this regard, this paper focuses on PV fault detection and classification using the transfer learning method. Initially, a dataset of thermographic images from PV arrays was collected. Subsequently, fine-tuning was performed, and finally, fault detection and classification were carried out using a pre-trained model. The model achieved 100% accuracy in detecting and classifying bypass diode and hotspot faults, as well as distinguishing healthy modules.

AB - Due to the increasing importance of solar systems and their growing role in the world, ensuring their proper and flawless operation is of utmost importance. Solar photovoltaic (PV) systems are susceptible to various faults, making early fault detection a critical task. Persistent faults in PV systems can lead to irreversible damages. In this regard, this paper focuses on PV fault detection and classification using the transfer learning method. Initially, a dataset of thermographic images from PV arrays was collected. Subsequently, fine-tuning was performed, and finally, fault detection and classification were carried out using a pre-trained model. The model achieved 100% accuracy in detecting and classifying bypass diode and hotspot faults, as well as distinguishing healthy modules.

U2 - 10.1109/PVSC59419.2025.11132955

DO - 10.1109/PVSC59419.2025.11132955

M3 - Article in proceedings

SN - 979-8-3315-3445-5

SP - 969

EP - 973

BT - Proceedings of IEEE 53rd Photovoltaic Specialists Conference (PVSC 2025)

PB - IEEE

T2 - 2025 IEEE 53<sup>rd</sup> Photovoltaic Specialists Conference

Y2 - 8 June 2025 through 13 June 2025

ER -

Transfer Learning-based Enhanced Detection of Hotspot and Bypass Diode Faults in Photovoltaic Arrays

Abstract

Conference

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this