Photovoltaic panel identification method diagram

What is fault identification in photovoltaic (PV) panels?

Fault identification in Photovoltaic (PV) panels is of prime importance during the regular operation and maintenance of PV power plants. An extensive fault identification process that employs Image Processing, Machine Learning, and Electrical-based techniques has been analyzed comprehensively.

How can we detect and classify PV panel faults using infrared images?

One method that particularly stands out is the use of Convolutional Neural Networks (CNNs) to detect and classify PV panel faults via infrared images . Further exploring the image-based techniques, the utilization of thermographic images taken by Unmanned Aerial Vehicles (UAVs) has proven beneficial in inspecting and classifying PV faults .

Can a PV system detect faults among modules with different array configurations?

This PV system is capable of studying faults among modules with different array configurations. In order to test the ability of the proposed approach to detect and locate the faults and identify the fault types, a series of line-line faults within the string are used in the simulations.

Can a fault detection model accurately classify PV arrays based on PNN?

This paper developed an intelligent fault detection model for PV arrays based on PNN for accurately classifying the fault types. The model was trained with a large dataset containing different data values under different environmental conditions in the summer and the winter season.

What are the thermal patterns of photovoltaic faults?

The thermal patterns of the main photovoltaic faults (hot spot, fault cell, open circuit, bypass diode, and polarization) are studied in real photovoltaic panels. Different scenarios are considered, analyzing online the main patterns of the faults by Internet of Things.

Which technique is used for analyzing PV module degradation?

The I–V curve measurement was the dominant technique for analyzing the PV module degradation, accounting for about 33%. This is because this technique is fast and reliable and also provides instant feedback for fault diagnosis.