Detection and Diagnosis in Photovoltaic Panels Using Artificial Intelligence Techniques Based on Random Forest and LSTM Neural Networks
This paper investigates the use of artificial intelligence techniques for monitoring photovoltaic systems and for fault detection and diagnosis. The proposed methodology uses approximately 1.37 million records collected over 16 days, including electrical variables, such as the voltage and DC current of the two photovoltaic strings, as well as meteorological parameters, such as solar irradiation and module temperature. The analysis process is structured in two stages: a binary detection stage, which differentiates normal from faulty operation, and a multiclass diagnostic stage, which identifies the type of fault: short circuit, degradation, open circuit or shading. Random Forest, LSTM and CNN-LSTM models are implemented and compared, to capitalize on both the nonlinear relationships between variables and the temporal dependencies in sequential data. Random Forest provides interpretability by analyzing the importance of features, LSTM captures the temporal evolution of signals, and the CNN-LSTM hybrid architecture combines automatic local feature extraction with temporal modeling. Evaluation based on accuracy, F1 score, and confusion matrices demonstrates high classification performance, with the CNN-LSTM model standing out for its increased robustness in identifying complex and transient photovoltaic defects.