Solar cells may possess defects during the manufacturing process in photovoltaic (PV) industries. To precisely evaluate the effectiveness of solar PV modules, manufacturing defects are required to be identified. Conventional defect inspection in industries mainly depends on manual defect inspection by highly skilled inspectors, which may still give inconsistent, subjective identification results. In order to automatize the visual defect inspection process, an automatic cell segmentation technique and a convolutional neural network (CNN)-based defect detection system with pseudo-colorization of defects is designed in this paper. High-resolution Electroluminescence (EL) images of single-crystalline silicon (sc-Si) solar PV modules are used in our study for the detection of defects and their quality inspection. Firstly, an automatic cell segmentation methodology is developed to extract cells from an EL image. Secondly, defect detection can be actualized by CNN-based defect detector and can be visualized with pseudo-colors. We used contour tracing to accurately localize the panel region and a probabilistic Hough transform to identify gridlines and busbars on the extracted panel region for cell segmentation. A cell-based defect identification system was developed using state-of-the-art deep learning in CNNs. The detected defects are imposed with pseudo-colors for enhancing defect visualization using K-means clustering. Our automatic cell segmentation methodology can segment cells from an EL image in about $2.71$ s. The average segmentation errors along the x-direction and y-direction are only $1.6$ pixels and $1.4$ pixels, respectively. The defect detection approach on segmented cells achieves $99.8\%$ accuracy. Along with defect detection, the defect regions on a cell are furnished with pseudo-colors to enhance the visualization.

In this study, a self-developed atmospheric pressure atomic layer deposition (APALD) system is used to deposit Al₂O₃ passivation film, along with the use of precursor combinations of Al(CH₃)₃/H₂O to improve its passivation characteristics through a short-time microwave post-annealing process. Comparing the unannealed and microwave-annealed samples whose temperature is controlled at 200–500 °C, APALD non-vacuum deposited film can be realized with a higher film deposition rate, which is beneficial for increasing the production throughput while at the same time reducing the operating cost of vacuum equipment at hand. Since the microwave has a greater penetration depth during the process, the resultant thermal energy provided can be spread out evenly to the entire wafer, thereby achieving the effect of rapid annealing. The film thickness is subsequently analyzed by TEM, whereas the chemical composition is verified by EDS and XPS. The negative fixed charge and interface trap density are analyzed by the C-V measurement method. Finally, the three major indicators of τ_eff, SRV, and IVoc are analyzed by QSSPC to duly verify the excellent passivation performance.