Monocrystalline silicon solar cell surface defect detection method based on grating detection

Abstract

The invention provides a monocrystalline silicon solar cell surface defect detection method based on grating detection. The method comprises the following steps: firstly, image scaling and median filtering are adopted to preprocess a monocrystalline silicon solar cell surface image; then, a grating detection method is provided for eliminating main gratings and auxiliary gratings in the monocrystalline silicon solar cell surface image; then, a method of combining super pixel segmentation and adaptive threshold processing is provided for detecting a defect area in a non-grating image and an initial detection result map is obtained; and finally, through image scaling, post processing is carried out on the initial detection result map, and a final detection result map is obtained. Monocrystalline silicon solar cell surface image acquisition quality requirements are relatively low, the detection speed is quick while high detection accuracy is kept, and great significance is achieved for improving the monocrystalline silicon solar cell quality detection efficiency and the ex-factory pass rate.

Description

technical field [0001] The invention relates to the technical field of surface defect detection based on machine vision, and mainly relates to a method for detecting surface defects of single crystal silicon solar cells based on grid line detection. Background technique [0002] The essence of surface defect detection of monocrystalline silicon solar cells is to judge whether there are defects on the surface of monocrystalline silicon solar cells and locate the defect area. In recent years, solar photovoltaic power generation has become one of the main solutions to the energy crisis. At the same time, the quality of solar cells directly affects the efficiency of photovoltaic power generation. Therefore, it is of great significance to detect defects on the surface of solar cells. [0003] The detection of defects on the surface of solar cells based on machine vision is the current main development trend. The existing technologies are based on the characteristics of defects to...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the technical problem that the existing machine vision-based solar cell surface defect detection method has insufficient generalization ability, the present invention proposes a single crystal silicon solar cell surface defect detection method based on grid line detection, according to the single crystal silicon solar cell surface defect detection method The characteristics of the texture, the main grid line and the sub-grid line in the surface image of the monocrystalline silicon solar cell are deleted by the grid line detection, and at the same time, the method of combining super pixel segmentation and adaptive threshold processing is used to detect in the grid line-free image defect area

Images