Image processing and detection of discontinuities in battery cells

Patent metadata

Field	Value
Publication number	US-12203880-B2
Application number	US-202217665829-A
Country	US
Kind code	B2
Filing date	Feb 7, 2022
Priority date	Feb 7, 2022
Publication date	Jan 21, 2025
Grant date	Jan 21, 2025

Abstract

A system for evaluating a battery cell includes an imaging device configured to take an image of at least part of the battery cell, and a processor. The processor is configured to perform: determining a region of interest in the acquired image, reducing a sharpness of the acquired image to generate a reference image, comparing the acquired image and the reference image, and identifying a discontinuity of the battery cell based on a difference between the acquired image and the reference image.

First claim

What is claimed is:

1. A system for evaluating a battery cell, comprising:
an imaging device configured to take an image of at least part of the battery cell; and
a processor configured to acquire the image and perform:
determining a region of interest in the acquired image, the region of interest being a portion of the acquired image, wherein determining the region of interest is based on at least one of a rule-based algorithm that includes a location-based rule, an image attribute threshold and a machine learning algorithm;
reducing a sharpness of the region of interest of the acquired image to generate a reference image;
comparing the region of the interest of the acquired image and the reference image; and
identifying a discontinuity of the battery cell based on a difference between the region of the interest of the acquired image and the reference image.

2. The system of claim 1 , further comprising a deformation assembly configured to elastically deform the at least part of the battery cell.

3. The system of claim 2 , wherein the imaging device is configured to take a plurality of images of the at least part of the battery cell in a plurality of deformation states, and verify the identified discontinuity based on the plurality of images.

4. The system of claim 1 , wherein the comparing includes subtracting an image attribute of the reference image from an image attribute of the region of interest of the acquired image to generate a subtracted image, the subtracted image providing an enhanced view of the discontinuity.

5. The system of claim 4 , wherein the image attribute is selected from at least one of a brightness, a contrast and a gray scale.

6. The system of claim 4 , wherein the comparing includes at least one of applying a derivative in a selected direction on the subtracted image, and applying a filter to the subtracted image.

7. The system of claim 1 , wherein the location-based rule specifies a location of a section of the image that includes one or more features of interest, the image attribute threshold is associated with the one or more features of interest; and
the machine learning algorithm is configured to identify the region of interest based on training images of the battery cell and/or one or more similar battery cells.

8. A method of evaluating a battery cell, comprising:
acquiring an image of at least part of the battery cell;
determining a region of interest in the acquired image, the region of interest being a portion of the acquired image, wherein determining the region of interest is based on at least one of a rule-based algorithm that includes a location-based rule, an image attribute threshold and a machine learning algorithm;
reducing a sharpness of the region of interest of the acquired image to generate a reference image;
comparing the region of interest of the acquired image and the reference image; and
identifying a discontinuity of the battery cell based on a difference between the region of interest of the acquired image and the reference image.

9. The method of claim 8 , wherein the acquired image is acquired using direct x-ray radiography.

10. The method of claim 8 , wherein the comparing includes subtracting an image attribute of the reference image from an image attribute of the region of interest of the acquired image to generate a subtracted image, the subtracted image providing an enhanced view of the discontinuity.

11. The method of claim 10 , wherein the image attribute is selected from at least one of a brightness, a contrast and a gray scale.

12. The method of claim 10 , wherein the comparing includes at least one of: applying a derivative in a selected direction on the subtracted image, and applying a filter to the subtracted image.

13. The method of claim 8 , wherein determining the region of interest is determined based on a rule-based algorithm configured to identify the region of interest based on a rule that specifies a location of a section of the image that includes one or more features of interest, and/or an image attribute threshold associated with the one or more features of interest.

14. The method of claim 8 , wherein determining the region of interest is based on a machine learning algorithm configured to identify the region of interest based on training images of at least one of: the battery cell and one or more similar battery cells.

15. The method of claim 8 , wherein acquiring the acquired image is performed in-line during a process of manufacturing the battery cell.

16. A system for evaluating a battery cell, comprising:
an imaging device configured to automatically take one or more images of at least part of the battery cell in conjunction with a process of manufacturing the battery cell, the imaging device including an x-ray source and an x-ray detector mounted on a support structure, the support structure disposed on at least one of a battery cell manufacturing station and a battery cell inspection station; and
a processor configured to acquire the image and process a portion of the acquired image to identify a discontinuity of the battery cell, the portion of the acquired image being a region of interest in the acquired image, the processor configured to determine the region of interest based on at least one of a rule-based algorithm that includes a location-based rule, an image attribute threshold and a machine learning algorithm.

17. The system of claim 16 , wherein the processor is configured to perform:
reducing a sharpness of the portion of the acquired image to generate a reference image;
comparing the portion of the acquired image and the reference image; and
identifying the discontinuity of the battery cell based on a difference between the portion of the acquired image and the reference image.

18. The system of claim 17 , wherein the comparing includes subtracting an image attribute of the reference image from an image attribute of the portion of the acquired image to generate a subtracted image, the subtracted image providing an enhanced view of the discontinuity.

19. The system of claim 18 , wherein the comparing includes at least one of: applying a derivative in a selected direction on the subtracted image, and applying a filter to the subtracted image.

20. The system of claim 16 , wherein the imaging device is configured to automatically take the one or more images in-line during the process of manufacturing the battery cell.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Wagner Sean Robert
• Mcgovern Megan E
• Bruder Dmitriy
• Kukreja Ratandeep Singh
• Balogh Michael P
• Sekol Ryan Curtis

Classifications

• G01N23/083

  the radiation being X-rays · CPC title

• G01N2223/401

  image processing · CPC title

• G06T2207/20224

  Image subtraction · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10116

  X-ray image · CPC title