Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems

Abdellahi  Moulaye Rchid; Moussa Attia; Mohamed Elmamy  MOHAMED MAHMOUD; Vatma Elvally; Zoubir Aoulmi; Abdelkader  Ould Mahmoud

doi:10.51646/jsesd.v14i1.419

المؤلفون

Abdellahi Moulaye Rchid Applied Research Unit for Renewable Energies in Water and Environment (URA3E), University of Nouakchott, Nouakchott BP 880, Mauritania. https://orcid.org/0009-0004-2899-6820
Moussa Attia Environment Laboratory, Institute of Mines, Echahid Cheikh Larbi Tebessi University, Tebessa, 12002, Algeria https://orcid.org/0000-0003-3700-7049
Mohamed Elmamy MOHAMED MAHMOUD Applied Research Unit for Renewable Energies in Water and Environment (URA3E), University of Nouakchott, Nouakchott BP 880, Mauritania.
Vatma Elvally Applied Research Laboratory for Renewable Energies, Department of Physic, Faculty of Sciences and Technics, University of Nouakchott, Nouakchott, Mauritania. https://orcid.org/0009-0009-4456-0003
Zoubir Aoulmi Environment Laboratory, Institute of Mines, Echahid Cheikh Larbi Tebessi University, Tebessa 12002, Algeria. https://orcid.org/0000-0001-7212-7332
Abdelkader Ould Mahmoud Mauritanian Society of Renewable Energies and Green Hydrogen (2SMERHV), Mauritania; and Applied Research Unit for Renewable Energies in Water and Environment (URA3E), University of Nouakchott, Nouakchott BP 880, Mauritania.. https://orcid.org/0000-0002-9368-8232

DOI:

https://doi.org/10.51646/jsesd.v14i1.419

الكلمات المفتاحية:

Photovoltaic systems، machine learning، fault detection، maintenance optimization، Renewable energy.

الملخص

مع تزايد شعبية أنظمة الطاقة الكهروضوئية، أصبحت تقنيات الكشف عن المشكلات وصيانتها فعّالة، مما يتطلب ضمان أقصى قدر من الأداء. يقارن هذا البحث بين أداء خمسة نماذج متطورة للتعلم الآلي - الغابة العشوائية، وXGBoost، والشبكات العصبية الاصطناعية (ANN)، والشبكات العصبية التلافيفية (CNN)، وآلات المتجهات الداعمة (SVM) - لتحديد العيوب وتحسين صيانة أنظمة الطاقة الكهروضوئية. تم تقييم النماذج باستخدام مجموعات البيانات التشغيلية بناءً على دقتها وإحكامها واستدعائها ودرجة F1. تكشف النتائج أن XGBoost حصل على أكبر قدر من الدقة (88٪)، مما يجعله الخيار الأفضل للصيانة التنبؤية في الوقت الفعلي. كان أداء الغابة العشوائية جيدًا، خاصة في الظروف الصاخبة. تفوقت ANN وCNN في اكتشاف التدهور البطيء وتحسين تدابير الصيانة الوقائية. تركز هذه الدراسة على الاستخدام العملي للتعلم الآلي في أنظمة الطاقة المتجددة، مما يوفر رؤى قابلة للتنفيذ لتحسين موثوقية النظام، وتقليل وقت التوقف، وتحسين عمليات الصيانة، وتعزيز استدامة الطاقة الشمسية في نهاية المطاف.

التنزيلات

بيانات التنزيل غير متوفرة بعد.

المقاييس

يتم تحميل المقاييس...

المراجع

M. Attia, N. Belghar, Z. Driss, and K. Soltani, "Automated Hydroponic System Measurement for Smart Greenhouses in Algeria," Solar Energy and Sustainable Development Journal, vol. 14, no. 1, pp. 111-130, 2025. DOI: https://doi.org/10.51646/jsesd.v14i1.306

D. Gielen, F. Boshell, D. Saygin, M. D. Bazilian, N. Wagner, and R. Gorini, "The role of renewable energy in the global energy transformation," Energy strategy reviews, vol. 24, pp. 38-50, 2019. DOI: https://doi.org/10.1016/j.esr.2019.01.006

M. Attia, M. Bechouat, M. Sedraoui, and Z. Aoulmi, "An Optimal Linear Quadratic Regulator in Closed Loop with Boost Converter for Current Photovoltaic Application," European Journal of Electrical Engineering/Revue Internationale de Génie Electrique, vol. 24, no. 2, 2022. DOI: https://doi.org/10.18280/ejee.240204

G. Di Lorenzo, R. Araneo, M. Mitolo, A. Niccolai, and F. Grimaccia, "Review of O&M practices in PV plants: Failures, solutions, remote control, and monitoring tools," IEEE Journal of Photovoltaics, vol. 10, no. 4, pp. 914-926, 2020. DOI: https://doi.org/10.1109/JPHOTOV.2020.2994531

M. Del-Coco, M. Leo, and P. Carcagnì, "Machine learning for smart irrigation in agriculture: How far along are we?," Information, vol. 15, no. 6, p. 306, 2024. DOI: https://doi.org/10.3390/info15060306

C. Saiprakash, S. R. Kumar Joga, A. Mohapatra, and B. Nayak, "Improved fault detection and classification in PV arrays using stockwell transform and data mining techniques," Results in Engineering, vol. 23, p. 102808, 2024/09/01/ 2024, doi: https://doi.org/10.1016/j.rineng.2024.102808. DOI: https://doi.org/10.1016/j.rineng.2024.102808

N. Gokmen, E. Karatepe, S. Silvestre, B. Celik, and P. Ortega, "An efficient fault diagnosis method for PV systems based on operating voltage-window," Energy Conversion and Management, vol. 73, pp. 350-360, 2013/09/01/ 2013, doi: https://doi.org/10.1016/j.enconman.2013.05.015. DOI: https://doi.org/10.1016/j.enconman.2013.05.015

A. Moussa and Z. Aoulmi, "Improving Electric Vehicle Maintenance by Advanced Prediction of Failure Modes Using Machine Learning Classifications," Eksploatacja i Niezawodność – Maintenance and Reliability, journal article 2025, doi: 10.17531/ein/201372. DOI: https://doi.org/10.17531/ein/201372

D. d. S. M. Freire, "Cellular Time Activation Networks, a novel approach applied to photovoltaic anomaly detection," Universidade do Porto (Portugal), 2023.

B. Taghezouit, F. Harrou, Y. Sun, and W. Merrouche, "Model-based fault detection in photovoltaic systems: A comprehensive review and avenues for enhancement," Results in Engineering, vol. 21, p. 101835, 2024/03/01/ 2024, doi: https://doi.org/10.1016/j.rineng.2024.101835. DOI: https://doi.org/10.1016/j.rineng.2024.101835

E. H. Sepúlveda-Oviedo, L. Travé-Massuyès, A. Subias, M. Pavlov, and C. Alonso, "Fault diagnosis of photovoltaic systems using artificial intelligence: A bibliometric approach," Heliyon, vol. 9, no. 11, p. e21491, 2023/11/01/ 2023, doi: https://doi.org/10.1016/j.heliyon.2023.e21491. DOI: https://doi.org/10.1016/j.heliyon.2023.e21491

T. Kavzoglu and A. Teke, "Predictive Performances of Ensemble Machine Learning Algorithms in Landslide Susceptibility Mapping Using Random Forest, Extreme Gradient Boosting (XGBoost) and Natural Gradient Boosting (NGBoost)," Arabian Journal for Science and Engineering, vol. 47, no. 6, pp. 7367-7385, 2022/06/01 2022, doi: 10.1007/s13369-022-06560-8. DOI: https://doi.org/10.1007/s13369-022-06560-8

S. F. Ahmed et al., "Deep learning modelling techniques: current progress, applications, advantages, and challenges," Artificial Intelligence Review, vol. 56, no. 11, pp. 13521-13617, 2023/11/01 2023, doi: 10.1007/s10462-023-10466-8. DOI: https://doi.org/10.1007/s10462-023-10466-8

K. Devi and M. Srivenkatesh, "Convolutional Neural Networks for Fault Detection in Grid-Connected Photovoltaic Panels," Ingenierie des Systemes d'Information, vol. 28, no. 6, 2023. DOI: https://doi.org/10.18280/isi.280619

N. Franić, I. Pivac, and F. Barbir, "A review of machine learning applications in hydrogen electrochemical devices," International Journal of Hydrogen Energy, vol. 102, pp. 523-544, 2025/02/10/ 2025, doi: https://doi.org/10.1016/j.ijhydene.2025.01.070. DOI: https://doi.org/10.1016/j.ijhydene.2025.01.070

A. A. Soomro et al., "Insights into modern machine learning approaches for bearing fault classification: A systematic literature review," Results in Engineering, p. 102700, 2024. DOI: https://doi.org/10.1016/j.rineng.2024.102700

S. Ghoneim, A. E. Rashed, and N. I. Elkalashy, "Fault detection algorithms for achieving service continuity in photovoltaic farms," Intelligent Automation & Soft Computing, vol. 30, no. 2, pp. 467-479, 2021. DOI: https://doi.org/10.32604/iasc.2021.016681

S. Kumar, V. Kumar, S. Sarangi, and O. P. Singh, "Gearbox fault diagnosis: A higher order moments approach," Measurement, vol. 210, p. 112489, 2023. DOI: https://doi.org/10.1016/j.measurement.2023.112489

O. A. Youssef, "An optimised fault classification technique based on Support-Vector-Machines," in 2009 IEEE/PES Power Systems Conference and Exposition, 2009: IEEE, pp. 1-8. DOI: https://doi.org/10.1109/PSCE.2009.4839949

A. N. Boruah, S. K. Biswas, and S. Bandyopadhyay, "Transparent rule generator random forest (TRG-RF): an interpretable random forest," Evolving Systems, vol. 14, no. 1, pp. 69-83, 2023. DOI: https://doi.org/10.1007/s12530-022-09434-4

A. H. Elsheikh, S. W. Sharshir, M. Abd Elaziz, A. E. Kabeel, W. Guilan, and Z. Haiou, "Modeling of solar energy systems using artificial neural network: A comprehensive review," Solar Energy, vol. 180, pp. 622-639, 2019. DOI: https://doi.org/10.1016/j.solener.2019.01.037

M. Jalal, I. U. Khalil, and A. u. Haq, "Deep learning approaches for visual faults diagnosis of photovoltaic systems: State-of-the-Art review," Results in Engineering, vol. 23, p. 102622, 2024/09/01/ 2024, doi: https://doi.org/10.1016/j.rineng.2024.102622. DOI: https://doi.org/10.1016/j.rineng.2024.102622

J. Verma, L. Sandys, A. Matthews, and S. Goel, "Readiness of artificial intelligence technology for managing energy demands from renewable sources," Engineering Applications of Artificial Intelligence, vol. 135, p. 108831, 2024/09/01/ 2024, doi: https://doi.org/10.1016/j.engappai.2024.108831. DOI: https://doi.org/10.1016/j.engappai.2024.108831

A. Mellit, O. Herrak, C. Rus Casas, and A. Massi Pavan, "A machine learning and internet of things-based online fault diagnosis method for photovoltaic arrays," Sustalani, A. Ghennioui, and M. El Aroussi, "A photovoltaic power prediction approach enhanced by feature engineering and stacked machine learning model," Energy Reports, vol. 8, pp. 1288-1300, 2022.

G. Naidu, T. Zuva, and E. M. Sibanda, "A review of evaluation metrics in machine learning algorithms," in Computer science on-line conference, 2023: Springer, pp. 15-25. DOI: https://doi.org/10.1007/978-3-031-35314-7_2