Fotovoltaik sistemlerde ariza ve hata tespiti için yapay zeka tabanli karar destek sistemi gelistirilmesi ve uygulamasi

Gunes enerji santrallerinin (GES) verimli ve guvenli isletilmesi, fotovoltaik (PV) arizalarin otonom saptanmasina baglidir. Bu tez calismasinda, Van/Baskale bolgesinde kurulu 10 kWp kapasiteli evsel bir PV sisteminden farkli mevsimsel kosullar ve operasyonel senaryolar altinda elde edilen cok boyutlu kronolojik sensor verileri islenerek; elektriksel analitik ve bilgisayarli goru tabanli, cok modlu (multimodal) ozgun bir karar destek sistemi (KDS) tasarlanmistir. Ilk asamada, sensor verileri uzerinde makine ogrenmesi (ML) ve derin ogrenme (DL) mimarilerinin ariza tespit performanslari karsilastirilmistir. Denetimsiz on suzme icin Isolation Forest algoritmasi, denetimli guc tahmini icin ise HistGradientBoosting (HGB) modeli kullanilarak istatistiksel kalinti analiziyle hafif (lightweight) bir ML katmani kurgulanmistir. Bu altyapi, zamansal ve uzaysal oznitelikleri hiyerarsik olarak ogrenen 1D-CNN-LSTM Hibrit Autoencoder mimarisiyle dogruluk, F1-Skoru ve hesaplama maliyeti kriterlerine gore kiyaslanmistir. Derin ogrenme modelinin "kara kutu" yapisini aciklamak amaciyla sisteme SHAP algoritmasi entegre edilerek aciklanabilir yapay zeka (XAI) katmani olusturulmustur. Ikinci asamada, elektriksel anomalilerin fiziksel nedenlerini (mikro-catlak, kirik, kirlenme, golgelenme) otonom dogrulamak icin sahadan alinan panel goruntuleri Roboflow'da etiketlenmis ve Transformer tabanli RF-DETR nesne tespiti mimarisiyle egitilmistir. Fiziksel deformasyonlar %95'in uzerinde bir guven skoruyla basariyla haritalandirilmistir. Son asamada, tum yapay zeka modelleri Antigravity altyapisi kullanilarak butunlesik bir kullanici arayuzune donusturulmustur. Gelistirilen KDS, iki farkli veri kaynagini fuzyonlayarak operatore anlik "Tahmin Edilen Yuzdesel Verimlilik Kaybi (Loss %)" ve aksiyona yonelik "Bakim Onerileri" sunmaktadir. Ampirik bulgular, onerilen KDS altyapisinin evsel GES projelerinde kestirimci bakim guvenilirligini artirirken, operasyonel ariza surelerini ve teknik bakim maliyetlerini onemli olcude dusurdugunu kanitlamaktadir.

The efficient and safe operation of Solar Power Plants (SPP) depends on the autonomous detection of photovoltaic (PV) faults. In this thesis, an original multimodal Decision Support System (DSS) based on electrical analytics and computer vision was designed by processing multidimensional chronological sensor data obtained from a 10 kWp domestic PV system installed in the Van/Başkale region under varying seasonal conditions and operational scenarios. In the first stage, the fault detection performances of Machine Learning (ML) and Deep Learning (DL) architectures were compared on sensor data. A lightweight ML layer was constructed through statistical residual analysis, utilizing the Isolation Forest algorithm for unsupervised pre-filtering and the HistGradientBoosting (HGB) model for supervised power estimation. This infrastructure was benchmarked against a 1D-CNN-LSTM Hybrid Autoencoder architecture, which hierarchically learns temporal and spatial features, based on accuracy, F1-Score, and computational cost criteria. To clarify the "black box" nature of the deep learning model, an Explainable AI (XAI) layer was established by integrating the SHAP algorithm into the system. In the second stage, to autonomously verify the physical causes of electrical anomalies (such as micro-cracks, fractures, soiling, and shading), panel images collected from the field were labeled on Roboflow and trained using the Transformer-based RF-DETR object detection architecture. Physical deformations were successfully mapped with a confidence score exceeding 95%. In the final stage, all analytical and visual models were integrated into a unified user interface using the Antigravity infrastructure. The developed DSS fuses two different data sources to provide the operator with instantaneous "Predicted Percentage of Efficiency Loss (%)" and action-oriented "Maintenance Recommendations." Empirical findings demonstrate that the proposed DSS infrastructure significantly enhances predictive maintenance reliability in domestic SPP projects while substantially reducing operational downtime and technical maintenance costs.