Edge device for ultraviolet fluorescence inspection of photovoltaic panels

Regular inspection of photovoltaic panels plays a key role in maximizing performance, ensuring safety, and extending the life of solar plants. This paper presents the construction of a 6W 365 nm ultraviolet light source for ultraviolet fluorescence (UVF) inspections coupled with an edge device used to capture and process the fluorescence images. In addition, an artificial intelligence (AI) algorithm was applied to identify and classify automatically healthy and defective cells in the captured images. The trained AI presents a precision of 89%, and this result shows that the development of an ultraviolet light source coupled with an edge device for automatic cell classification could help with the maintenance staff to make routine UVF inspections to identify possible defects in cell structure, which is the main contribution of the presented work.