Instant testing and non-contact diagnosis for photovoltaic cells using K-means clustering and associated hyperspectral imaging

• Published in: SN applied sciences 2023-08, Vol.5 (8), p.207-16, Article 207
• Main Authors: Attia, Eslam Ali, Mahmoud, Alaaeldin, Fedawy, Mostafa, El-Sharkawy, Yasser H.
• Format: Article
• Language: English
• Subjects: Algorithms; Alternative energy sources; Applied and Technical Physics; Cameras; Chemistry/Food Science; Cluster analysis; Clustering; Contact; Contours; Defects; Earth Sciences; Efficiency; Electricity generation; Energy resources; Engineering; Environment; Hyperspectral imaging; Image processing; Image segmentation; Imaging techniques; Infrared imaging; Inspection; K-means clustering; Lasers; Life span; Light; Manufacturing; Materials Science; Measurement techniques; Non-contact diagnosis; Nondestructive testing; Optical properties; Panels; Peak frequency; Photoluminescence; Photons; Photovoltaic cells; Photovoltaics; Power; Quality control; Reflectance; Renewable energy; Renewable resources; Solar energy; Spectra; Spectral signatures; Vector quantization; Wavelength
• ISSN: 2523-3963; 2523-3971
• DOI: 10.1007/s42452-023-05431-7

Renewable energy, particularly solar energy, has experienced remarkable growth in recent years. However, the integrity of solar photovoltaic (PV) cells can degrade over time, necessitating non-destructive testing and evaluation (NDT-NDE) for quality control during production and in-service inspection. Hyperspectral (HS) imaging has emerged as a promising technique for defect identification in PV cells based on their spectral signatures. This study utilizes a HS imager to establish a diffuse reflectance spectra signature for two groups of PV cells: working and non-working. A non-contact photoluminescence imaging-based methodology is employed, using a halogen lamp as an illumination source to replicate sunlight. Our findings reveal that non-working PV regions can be differentiated from working regions within the 400–600 nm wavelength range, with an optimal candidate peak frequency of 450 nm. To accurately group active PV regions in the constructed HS images at 450 nm, we employ an image processing strategy that combines K-means clustering (K-mc) with contour delineation. Specifically, K-mc with K = 8 is used to efficiently and precisely group active PV regions. We demonstrate the effectiveness of this proposed approach and compare it with traditional infrared (IR) imaging techniques. This imaging clustering approach can be implemented using a conventional camera and a 450 nm wavelength filter for NDT-NDE on exterior-mounted PV panels. Overall, the proposed HS imaging technique, coupled with K-mc, offers a rapid and effective means of identifying defects in PV cells, outperforming conventional IR imaging techniques. This advancement contributes to increased efficiency and extended lifespan of solar PV panels. Article highlights The reflectance spectra of a PV panel may be captured via HS imaging even when the panel is not switched on, and this technique provides information on the optical properties and composition of the PV panel. Developing a technique for rapid and accurate image segmentation using contour mapping and (K = 8) K-mc in conjunction with our HS imaging strategy could determine the presence of PV working zones and outline their appearance remotely. For NDT-NDE on externally mounted PV panels, our image clustering method may be used with a standard camera and a filter that only operates at 450 nm in wavelength.