Battery Module Image Analysis for Pseudo Soldering Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting pseudo soldering faults in solar battery modules are costly, labor-intensive, prone to human error, and suffer from low accuracy due to variations in human assessment criteria and visual fatigue, and threshold-based methods lead to overkill issues and difficulty in setting gray level thresholds.
Innovation Solution
An image processing method that divides images of solar battery modules into regions corresponding to solder joints, calculates image difference information between adjacent regions, and uses this information to accurately identify pseudo soldering faults using artificial intelligence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual detection methods are used for fault detection in solar batteries, then detection can be performed with simple equipment, but detection accuracy is low and employee turnover is high due to visual fatigue
Solution Approach 1:
The patent replaces manual visual inspection with an automated image processing system that captures images of solar battery modules and uses algorithms to detect faults. This substitution eliminates visual fatigue and improves detection accuracy while maintaining operational simplicity through automated processing pipelines.
Solution Approach 2:
The patent creates digital copies (images) of the solar battery modules for analysis instead of requiring direct visual inspection. These image copies can be processed repeatedly without degradation, enabling accurate fault detection while reducing reliance on human operators and minimizing turnover associated with manual detection work.
2Reliability
If gray-level thresholding is used for fault detection, then the detection process is simple to implement, but detection accuracy is low due to inconsistencies in gray level differences between battery modules
Solution Approach 1:
The patent moves beyond fixed gray-level thresholding to a more sophisticated parameter-based analysis that compares image differences between adjacent regions. This approach adapts to variations in gray levels between different battery modules by using relative comparisons rather than absolute thresholds, significantly improving fault detection accuracy.
Solution Approach 2:
The patent applies local quality analysis by dividing the image into multiple regions and performing localized comparisons between adjacent areas. This region-by-region approach accounts for local variations in image characteristics while maintaining overall detection accuracy, overcoming the limitations of global thresholding methods.
3Measurement precision
If image difference comparison between adjacent regions is performed, then fault detection accuracy is improved despite gray level variations, but computational complexity increases
Solution Approach 1:
The patent segments the solar battery module image into multiple distinct regions corresponding to different cell areas. By performing difference comparisons only between adjacent segmented regions rather than analyzing the entire image globally, the method achieves high measurement precision while managing computational complexity through divide-and-conquer processing.
Data Source
AI summary
An image processing method, apparatus, and device, and a storage medium relate to the field of artificial intelligence. The method may include: obtaining an image corresponding to a target battery module, the target battery module including N solder joints, and the N solder joints being respectively mapped to N solder joint fields in the image; dividing the image according to the N solder joint fields to obtain N image regions in one-to-one correspondence with the N solder joint fields; calculating image difference information between each pair of adjacent image regions among the N image regions to obtain an image difference information set; and performing fault recognition on the target battery module based on the image difference information set. The accuracy for recognizing a preset fault in a battery module can be improved by the method.