AI-Driven Fault Detection and Classification in Photovoltaic Systems using High-Frequency Data
Keywords:
Keywords: Photovoltaic Systems, Fault Detection, Artificial Intelligence, Cat Boost, LGBM, RFC, High-Frequency Data, Machine LearningAbstract
The rising global demand for sustainable energy has accelerated the adoption of photovoltaic (PV)systems as clean, renewable power sources. However, PV systems are prone to various faults, includingMaximum Power Point Tracking (MPPT) failures, Low Power Point Tracking (LPPT) issues, partialshading, and hardware degradation. These issues can significantly impact system efficiency andlifespan. Accurate, timely fault detection and classification are crucial for improving reliability andreducing maintenance costs
References
Mantel C, Villebro F, Alves dos Reis Benatto G, Rajesh Parikh H, Wendlandt S, Hossain K, Poulsen PB, Spataru S, Séra D, Forchhammer S (2019) Machine learning prediction of defect types for electroluminescence images of photovoltaic panels. Appl Mach Learn. https://doi.org/10.1117/12.2528440
Köntges M, Kurtz S, Packard C, Jahn U, Berger K, Kato K, Friesen T, Liu H, Iseghem MV, Wohlgemuth J, Miller D, Kempe M, Hacke P, Reil F, Bogdansk N, Herrmann W, Buerhop-Lutz C, Razongles G, Friesen G (2014) Review of failures of photovoltaic modules—iea-pvps [www document]. https://iea-pvps.org
