Adaptive neuro fuzzy inference system based method for faults detection in the photovoltaic system

Abstract

As the case with all electrical and electronic systems, a photovoltaic (PV) system can be exposed to several failures causing it to malfunction; several studies have found that the reliability of the PV systems is highly dependent on the material used for the construction of the PV panels, temperature, humidity and solar radiation. A PV system can have several faults, whether construction type faults, or material and electrical faults caused by climatic conditions. This requires identification, the main objective of which is to provide a tool that can detect and locate these faults in order to guarantee optimal performance of the system, and thus reduce maintenance costs and above all increase productivity by increasing the availability rate facilities in order to have a better performance. The objective of this article is to propose a technique for detecting and locating faults in a PV system, the proposed algorithm is based on adaptive neuro fuzzy inference system (ANFIS). This algorithm is based on the technique of artificial neural networks and fuzzy logic. Nine faults will be examined with simulation results under MATLAB-Simulink in PV system (array, converter DC-DC and battery).