Abstract
The silicon panel is the core component of photovoltaic power generation, whose surface quality is related to its service life and power generation efficiency. However, microcracks, fragments, incomplete welding, broken grids, and other defects often occur in industrial production. The edge detection algorithm is usually used to detect defects in silicon panels, but the common edge detection algorithm has an impact on defect detection because of the grid shadow of the panel. The current mainstream defect detection algorithm based on convolutional neural network requires a large number of positive and negative samples of image data sets for pretraining the model, which consumes a lot of time and GPU computing power, and the steps are cumbersome. To solve the problem, a defect detection method based on Prewitt and Canny operators is proposed in this article. In this method, Prewitt and Canny operators are combined to eliminate the effect of grids on the detection. The microcrack defects and their specific positions can be detected efficiently and intuitively, therefore improving the detection accuracy. The experimental results indicate that the purity and integrity of the defect profile of the image processed by the algorithm are greatly improved. The foreground edge is clear, and the defect recognition accuracy is higher, which effectively prevent the impact of grid shadow on weld testing.
Highlights
INTRODUCTIONThe development of renewable energy has become one of the hottest issues of global concern
Amid traditional energy declining, the development of renewable energy has become one of the hottest issues of global concern
In order to verify the effectiveness of the algorithm proposed in this paper, the solar panels which contain only micro-cracks are selected for comparison
Summary
The development of renewable energy has become one of the hottest issues of global concern. In order to better obtain the edge characteristics of the solar panel defects, this article proposes to use Prewitt and Canny operators which are sensitive to transverse and vertical margin lines to implement image edge extract, respectively. Grid and border part of the two images can be eliminated, leaving behind the defect edge image of the silicon panel
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have