Genetic-Algorithm-Based Neural Network for Fault Detection and Diagnosis: Application to Grid-Connected Photovoltaic Systems

Modern photovoltaic (PV) systems have received significant attention regarding fault detection and diagnosis (FDD) for enhancing their operation by boosting dependability, availability, necessary safety. As a result, the problem of FDD in grid-connected PV (GCPV) is discussed this work. Tools feature extraction selection classification are applied developed approach to monitor GCPV system under various operating conditions. This addressed such that genetic algorithm (GA) technique used selecting best features artificial neural network (ANN) classifier diagnosis. Only most important selected be supplied ANN classifier. The performance determined via different metrics GA-based classifiers using data extracted from healthy faulty system. A thorough analysis 16 faults on module performed. In general terms, observed classified three categories: simple, multiple, mixed. obtained results confirm feasibility effectiveness with low computation time proposed