- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
AIP Conference Proceedings [AIP Publishing 15th International Conference on Concentrator Photovoltaic Systems (CPV-15) - Fes, Morocco (25–27 March 2019)] 15th International Conference on Concentrator Photovoltaic Systems (CPV-15) - Comparison of magnetic field imaging (MFI) and magnetic field simulation of silicon solar cells
摘要： In solar cells, electric currents are generated by electric injection or light flow distributed over the whole area. Each flowing current generates a magnetic field depending on the strength and the direction of the electric current. Recently, a new measuring technology, called magnetic field imaging (MFI) was presented showing the potential to measure the electric current strength and direction by imaging the resulting magnetic fields. The method was applied to various defects, e.g. missing or defect solder point between solar cell interconnector and cross-connector. Here, MFI measurements of various solar cell configurations and solar cell defects are compared with a finite elemental magnetic field simulation. The results are qualitatively and quantitatively interpreted and discussed. The model is used to obtain limits in resolution depending on measuring height and measurable defects (connector brakeage or defect soldering point) of the MFI method. The variation of geometry and material parameters (within reasonable boundaries) on the current flow and the corresponding magnetic field distribution show negligible influence of manufacturing tolerances regarding layer thicknesses and ribbon/connector width as well as material fluctuations resulting in variation of electrical resistance. Measuring height and electrical current have the biggest influence on magnetic field strength and are therefore starting points for process and product optimization.
关键词： magnetic field imaging,FEM,finite element method,MFI,solar cell defects,silicon solar cells
更新于2025-09-16 10:30:52
-
[IEEE 2019 IEEE International Conference on Big Knowledge (ICBK) - Beijing, China (2019.11.10-2019.11.11)] 2019 IEEE International Conference on Big Knowledge (ICBK) - U-Net Based Defects Inspection in Photovoltaic Electroluminecscence Images
摘要： Efficient defects segmentation from photovoltaic (PV) electroluminescence (EL) images is a crucial process due to the random inhomogeneous background and unbalanced crack non-crack pixel distribution. The automatic defect inspection of solar cells greatly influences the quality of photovoltaic cells, so it is necessary to examine defects efficiently and accurately. In this paper we propose a novel end to end deep learning-based architecture for defects segmentation. In the proposed architecture we introduce a novel global attention to extract rich context information. Further, we modified the U-net by adding dilated convolution at both encoder and decoder side with skip connections from early layers to later layers at encoder side. Then the proposed global attention is incorporated into the modified U-net. The model is trained and tested on Photovoltaic electroluminescence 512x512 images dataset and the results are recorded using mean Intersection over union (IOU). In experiments, we reported the results and made comparison between the proposed model and other state of the art methods. The mean IOU of proposed method is 0.6477 with pixel accuracy 0.9738 which is better than the state-of-the-art methods. We demonstrate that the proposed method can give effective results with smaller dataset and is computationally efficient.
关键词： cracks detection,electroluminescence images,U-net,Solar cell defects detection
更新于2025-09-16 10:30:52