SN Applied Sciences (Jul 2023)
Instant testing and non-contact diagnosis for photovoltaic cells using K-means clustering and associated hyperspectral imaging
Abstract
Abstract 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.
Keywords