The invention provides a photovoltaic
cell panel grid line defect detection method and
system based on
artificial intelligence, and relates to the field of
artificial intelligence. The method comprises the following steps: acquiring an image of a single photovoltaic
cell panel; constructing an image matrix according to prior color features in the photovoltaic
cell panel image, and performing sliding window calculation on the image matrix to obtain a single-channel image; obtaining a compression value of each column of pixels of the single-channel image as a one-dimensional sequence representing the photovoltaic
cell panel image; and inputting the one-dimensional sequence into a time
convolution network to obtain the periodicity of the grid line in the photovoltaic
cell panel image, and judging the defect position of the grid line according to the abnormal point. According to the invention, the semantic segmentation network type is adopted to identify the content of each column in the image, the
image processing mode does not need to debug parameters, the periodicity of the content of the photovoltaic
cell panel is utilized to adapt to cell panel images of various sizes, the preprocessing process is simplified, and the generalization ability is high. According to the invention, the influence of camera parameters and illumination intensity can be eliminated,
automation is realized, and the detection efficiency and accuracy are improved.