Article Dans Une Revue Energy and AI Année : 2025

Artificial intelligence in photovoltaic fault diagnosis: A Natural Language-Based Topic-tSNE Fusion analysis

Résumé

Timely fault detection in photovoltaic systems is critical for ensuring energy efficiency, reliability, and cost-effectiveness. However, the nonlinear and weather-dependent behavior of photovoltaic systems poses challenges for accurate diagnosis. This study presents a large-scale review of 983 scientific publications on artificial intelligence-based photovoltaic fault detection, using a novel methodology called Topic-tSNE Fusion. This approach integrates topic modeling, dimensionality reduction, and expert analysis to extract and visualize dominant research themes. Four key machine learning paradigms are identified: supervised, unsupervised, semi-supervised, and reinforcement learning. Among them, supervised methods, particularly neural networks and support vector machines, are the most frequently applied, showing accuracies above 95% in controlled conditions. The analysis also reveals growing use of semi-supervised and hybrid approaches to overcome data scarcity. Commonly monitored variables include irradiance, voltage, and current, while the most studied faults are shading, open-circuit, and degradation. Several open-access datasets supporting fault diagnosis research are catalogued. Overall, the proposed method enables a more objective and scalable review process and uncovers emerging trends, such as the shift toward lightweight artificial intelligence for edge deployment and frugal diagnostic architectures. The methodology is scalable and adaptable to other domains facing similar challenges in knowledge synthesis and system monitoring.

Fichier principal
Vignette du fichier
1-s2.0-S2666546825000904-main (1).pdf (3.05 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence
DOI

Cite 10.17632/z93gzbptf7.1 Jeu de données kalaimohan T S. (2021). PV Panel: Irradiance, Temperature, Partial Shading - IV Curves [Data set]. Mendeley. https://doi.org/10.17632/Z93GZBPTF7.1

PV Panel: Irradiance, Temperature, Partial Shading — I–V Curves
DOI

Cite 10.17632/n76t439f65.1 Jeu de données Bakdi, A. (2020). GPVS-Faults: Experimental Data for fault scenarios in grid-connected PV systems under MPPT and IPPT modes [Data set]. Mendeley. https://doi.org/10.17632/N76T439F65.1

GPVS-Faults
DOI

Cite 10.17632/3fr92f4xy9.1 Jeu de données Rakeshkumar Mahto. (2022). Simulation Dataset of Partial Shading and Fault of a Photovoltaic Module [Data set]. Mendeley. https://doi.org/10.17632/3FR92F4XY9.1

Partial Shading in a Photovoltaic Module (simulation)
DOI

Cite 10.5281/zenodo.6386767 Jeu de données Rico-Garcia, M., Ceballos, J. P. V., & Paja, C. A. R. (2022). Dataset for detecting the electrical behavior of photovoltaic panels from RGB images [Data set]. Zenodo. https://doi.org/10.5281/ZENODO.6386767

Electrical Behavior of Photovoltaic Panels from RGB Images
DOI

Cite 10.1038/sdata.2016.106 Autre Bradbury, K., Saboo, R., L. Johnson, T., Malof, J. M., Devarajan, A., Zhang, W., M. Collins, L., & G. Newell, R. (2016). Distributed solar photovoltaic array location and extent dataset for remote sensing object identification. Scientific Data, 3(1). https://doi.org/10.1038/sdata.2016.106

Distributed Solar PV Array Location & Extent
DOI

Cite 10.5281/zenodo.5171712 Jeu de données Hou, J., Ling, Y., & Yujun, L. (2021). Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery (Version v1.0) [Data set]. Zenodo. https://doi.org/10.5281/ZENODO.5171712

Multi-Resolution Dataset for PV Panel Segmentation
DOI

Cite 10.5281/zenodo.7868082 Jeu de données Manso Callejo, M. Á., & Calimanut-Ionut, C. (2023). SPVPANELEX: Dataset containing aerial orthoimages (covering 257.93 km2 of the Spanish territory, with a spatial resolution of 0.5 m) labelled with photovoltaic panel information for binary recognition and semantic segmentation (Version 1) [Data set]. Zenodo. https://doi.org/10.5281/ZENODO.7868082

SPVPANELEX
DOI

Cite 10.17632/mmwhkt7whb.3 Jeu de données Motahhir, S. (2020). MATLAB/Simulink Model of Photovoltaic Cell, Panel and Array [Data set]. Mendeley. https://doi.org/10.17632/MMWHKT7WHB.3

MATLAB/Simulink model of PV cell, panel and array
DOI

Cite 10.21227/f0nc-hc38 Jeu de données Arnaudo, E. A. (2023). Piedmont Photovoltaic Panels Dataset [Data set]. IEEE DataPort. https://doi.org/10.21227/F0NC-HC38

Piedmont Photovoltaic Panels Dataset

Dates et versions

hal-05251841 , version 1 (12-09-2025)

Licence

Identifiants

Citer

Edgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, Marko Pavlov, Corinne Alonso. Artificial intelligence in photovoltaic fault diagnosis: A Natural Language-Based Topic-tSNE Fusion analysis. Energy and AI, 2025, 21, pp.100558. ⟨10.1016/j.egyai.2025.100558⟩. ⟨hal-05251841⟩
1394 Consultations
295 Téléchargements

Altmetric

Partager

  • More