Application of Artificial Intelligence Techniques for Fault Identification in Photovoltaic Modules
Solar Energy; Photovoltaic Modules; PV Systems Faults; Fault Detection; Artificial Intelligence.
Photovoltaic solar energy has proven to be a viable alternative that contributes to sustainable development and ensures energy supply around the world. However, the exponential growth of installed capacity in recent years has highlighted the need to ensure the safe operation and reliability of photovoltaic systems. In this context, faults in such systems are a crucial issue, since they can significantly impact the generated power, reduce the useful life, and cause potential risks in operation. Thus, this research applied artificial intelligence techniques to detect and diagnose faults in photovoltaic modules. The faults identified by the proposed methods are short-circuit modules, string disconnection and partial shading. In addition, multilayer perceptron neural network algorithms, probabilistic neural networks, and a neuro-fuzzy method were developed, combining a neural network with fuzzy logic. All trained algorithms were used from simulated and tested experimental data from three different photovoltaic systems. Moreover, training situations in which the dataset is contaminated by random noise were also considered. The results indicated maximum accuracy of 99.1% for the lack of short-circuited modules, 100% for string disconnection and 82.2% for the lack of partial shading. Furthermore, the analyzes allowed to reaffirm the robustness of the multi-layer perceptron network for fault detection in photovoltaic systems, even with the presence of noise in the training data.