Electrode Assembly Image Segmentation for Dark-Region Defect Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing electrode assembly inspection methods struggle to accurately detect defects due to regions in the image being unduly dark, making it difficult to obtain complete image information and determine defects effectively.

Innovation Solution

A method involving different preset thresholds to segment images of the electrode assembly body and tab, allowing for the determination of defect status based on these segmented images, including the use of inflection points and pixel sum statistics to enhance detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a single threshold is used for image segmentation, then the processing is simple, but the detection accuracy is insufficient due to varying brightness in different regions

Engineering Contradiction:
Improvedefect detection accuracyVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the image segmentation process into two distinct stages: first segmentation using a first threshold to extract the electrode assembly body, and second segmentation using a second threshold to extract the tab. This multi-stage segmentation approach allows different regions with different brightness characteristics to be processed appropriately, improving defect detection accuracy while managing processing complexity through systematic division of the segmentation task.

Inventive Principle:
Principle #1Segmentation

2Loss of information

If ambient light conditions are not controlled, then the inspection process is simple, but some regions become unduly dark making complete image information unobtainable

Engineering Contradiction:
Improveimage information completenessVSAvoidambient light interference
Core Design Contradiction:
Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent changes the parameter of threshold values based on the brightness characteristics of different image regions. By setting a first threshold for the electrode assembly body and a second threshold for the tab region, the system adapts to the varying brightness conditions caused by ambient light, ensuring complete image information is captured without requiring strict control of ambient light conditions.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If the tab region is not properly segmented, then the processing is simpler, but the defect detection accuracy is reduced due to inability to analyze inflection points

Engineering Contradiction:
Improvedefect detection accuracyVSAvoidsegmentation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent specifically segments the tab region from the electrode assembly body through second segmentation using a second threshold. This enables subsequent analysis of inflection points in the tab region, which are critical for detecting defects such as separator protrusions. The segmentation complexity is justified by the significant improvement in defect detection accuracy that results from being able to analyze these specific geometric features.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4361950B1Method and device for detecting defect of electrode assembly, and computer-readable storage medium
Publication Date: 2025.11.26 CONTEMPORARY AMPEREX TECHNOLOGY (HONG KONG) LIMITED
  • EP4361950B1 patent drawingFigure 1~2
  • EP4361950B1 patent drawingFigure 3~4
  • EP4361950B1 patent drawingFigure 5~6

AI summary

An embodiment of this application discloses a method and device for detecting a defect of an electrode assembly, and a computer-readable storage medium. The method includes: determining a first segmented image of an electrode assembly body in an electrode assembly image based on a first preset threshold; determining a second segmented image of a tab in the electrode assembly image based on a second preset threshold, where the second preset threshold is less than the first preset threshold; and determining defect status of the electrode assembly based on the first segmented image and the second segmented image. In this way, the complete image information of the electrode assembly can be obtained, so as to detect defects of the electrode assembly accurately.