Solar Cell EL Image Classification for Internal Crack Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for inspecting solar battery cells are inadequate in detecting invisible internal cracks and are inefficient for mass-produced cells, as they require extensive time and cannot handle the analysis of unique electroluminescence (EL) images from millions of cells daily.
Innovation Solution
A method and apparatus that classify solar battery cell defects based on EL images using a pre-trained defect classification model, primarily by determining the percentage of black spots and secondarily identifying defect types through image processing techniques like histogram homogenization, bus-bar line removal, edge-based perspective transform, and contour extraction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional current-voltage characteristic analysis is used to inspect solar battery cells, then inspection of visible defects is possible, but inspection of invisible internal cracks and mass-produced cells is inefficient and time-consuming
Solution Approach 1:
The patent replaces conventional electrical measurement methods (current-voltage analysis) with optical imaging technology (electroluminescence imaging). This substitution enables simultaneous detection of both visible and invisible defects through image capture, while the automated image processing system handles mass-produced cells efficiently, resolving the contradiction between measurement precision and productivity
Solution Approach 2:
The patent creates digital copies (EL images) of solar battery cells for analysis. These image copies capture the electrical characteristics and defect information of each cell, allowing rapid automated analysis without physical manipulation. The copying approach enables high-speed processing of millions of cells while maintaining detailed defect detection capability
2Measurement precision
If each unique EL image is analyzed individually to detect all defects, then detection accuracy is improved, but processing time increases significantly for mass-produced cells
Solution Approach 1:
The patent segments the defect detection process into distinct stages: EL image capture, pre-processing (noise reduction, enhancement), defect detection, and classification. This segmentation allows parallel processing of multiple cells through the same pipeline, maintaining high detection accuracy while reducing overall processing time for mass-produced cells
Solution Approach 2:
The patent applies pre-processing operations (noise reduction, image enhancement, feature extraction) to EL images before detailed defect analysis. This preliminary action prepares the images for rapid automated processing, enabling accurate defect detection to be performed quickly on millions of cells without sacrificing detection accuracy
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables quick and accurate classification of solar battery cell defects, minimizing human error and allowing for the analysis of over a million EL images per day, thereby improving efficiency and accuracy in defect detection.
Implementation Method 1
A solar battery cell is a device that converts incident sunlight into electrical energy and outputs the same
Implementation Method 2
a method and apparatus for quickly and accurately classifying the defect and type of a solar battery cell based on an electroluminescence image (EL image) of the solar battery cell
Data Source
AI summary
The present invention relates to a method and apparatus for classifying images of solar battery cells. The method according to an exemplary embodiment of the present invention is performed by an electronic apparatus, and is a method for determining whether a solar battery cell being inspected is defective, based on an electroluminescence (EL) image of the solar battery cell being inspected. The method comprises: a step of classifying an EL image of a solar battery cell being inspected, according to whether a black spot occupies a certain percentage or more of the EL image of the solar battery cell being inspected, namely, primarily classifying the EL image of the solar battery cell being inspected into a first type in which a black spot occupies a certain percentage or more, or a second type in which a black spot occupies less than the certain percentage; and a step of secondarily classifying the type of defect of the solar battery cell being inspected, based on the EL image of the solar battery cell being inspected, by using a pre-trained defect classification model, if the EL image of the solar battery cell being inspected is primarily classified into the first type.