FAULT PREDICTION AND ANALYSIS TECHNIQUES OF SOLAR CELLS AND PV MODULES

The photovoltaic market has quickly increasing over a couple of years. One of the main reasons for this high growth in PV industry is the reduction of PV production costs. The output power obtained from the PV module is mainly depend upon the two parameters named as irradiance and temperature. There are number of factors that affects the performance of the PV array, such as diode and connection loss, mismatch loss, DC/AC wring loss, sun tracking loss, shading loss, soiling loss and material loss. From the above mentioned techniques, in the proposed research work, we have considered three faults named as shading loss, soiling loss and material loss. When these faults occur in the network, the power loss of the module decreases. In this research work, we have presented a simulation model fault detection procedure for PV systems, based on the power losses analysis. This automatic supervision system has been developed in MATLAB (MATrix Laboratory) &in Simulink environment. It includes parameter extraction techniques to calculate main PV system parameters for monitoring data in real conditions of work, taking into account the environmental irradiance and module temperature evolution, allowing simulation of the PV system behaviour in real time. The automatic supervision method has analysed the output power losses in the DC side of the PV generator, capture losses. Also, a classification technique named as ANN (Artificial neural network) is used to classify the type of error and to know the level of power loss. ANN is also used to reduce the power loss occurred in the PV array. The performance parameters named as power loss, Idc and Vdc are measured. The power loss is measured without ANN and with ANN to know the efficiency of the system