X-ray radiographs based fault detection and prediction for battery cells

Patent metadata

Field	Value
Publication number	US-12463263-B2
Application number	US-202217948841-A
Country	US
Kind code	B2
Filing date	Sep 20, 2022
Priority date	Sep 20, 2022
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

A method for detecting defects in battery cells includes receiving an X-Ray radiographic image of a battery cell and segmenting the X-Ray radiographic image into regions of interest using a classifier. The method includes processing the segmented X-Ray radiographic image using the classifier to identify features of the battery cell, detecting whether one or more of the features in the processed X-Ray radiographic image is defective using the classifier, and determining using the classifier whether the battery cell is defective based on whether one or more of the features in the processed X-Ray radiographic image is defective.

First claim

What is claimed is:

1 . A method for detecting defects in battery cells, the method comprising:
receiving an X-Ray radiographic image of a battery cell; segmenting the X-Ray radiographic image into regions of interest using a classifier; processing the segmented X-Ray radiographic image using the classifier to identify features of the battery cell; detecting whether one or more of the features in the processed X-Ray radiographic image is defective by using the classifier; and determining, using the classifier, whether the battery cell is defective based on whether one or more of the features in the processed X-Ray radiographic image is defective.

2 . The method of claim 1 , further comprises detecting an extraordinary condition in the battery cell using a unary classifier that is different than the classifier.

3 . The method of claim 1 , wherein the detecting comprises detecting one or more of a tear in a foil of an anode or a cathode in the battery cell, a fold in the foil, a defect in a first weld region comprising welded foils of anodes or cathodes of the battery cell, and a defect in a second weld region comprising the welded foils welded to a tab of the battery cell.

4 . The method of claim 1 , wherein the one or more of the features indicate one or more of a quality of welding of foils of anodes or cathodes of the battery cell and a quality of welding of the welded foils to a tab of the battery cell.

5 . The method of claim 1 , wherein the segmenting the X-Ray radiographic image comprises:
highlighting the regions of interest in the X-Ray radiographic image, separating the regions of interest from each other, and labeling the regions of interest.

6 . The method of claim 1 , further comprises using the segmenting to mask a selected one of the features for further processing.

7 . The method of claim 1 , further comprises using the segmenting to mask one of the features to facilitate the processing of another one of the features.

8 . The method of claim 1 , further comprises training the classifier by selectively augmenting one or more of the regions of interest without causing an artifact in the X-Ray radiographic image, wherein the augmenting comprises one or more of flipping, translating, and rotating the X-Ray radiographic image or a portion thereof.

9 . The method of claim 1 , wherein the detecting whether one or more of the features is defective comprises:
detecting, in the X-Ray radiographic image, an edge of a tab of the battery cell to which foils of anodes or cathodes of the battery cell are welded; measuring, relative to the edge of the tab, dimensions of a first weld region comprising the welded foils and a second weld region comprising the welded foils welded to the tab of the battery cell; and comparing the dimensions to respective thresholds.

10 . The method of claim 1 , wherein the detecting whether one or more of the features is defective comprises:
detecting, in the X-Ray radiographic image, an edge of a tab of the battery cell to which foils of anodes or cathodes of the battery cell are welded; fitting a line perpendicular to the edge of the tab; encapsulating a region of the welded foils between the edge and an end of the tab in a bounding box; scanning the line across the edge and the bounding box; measuring intersections of the line with the edge and two sides of the bounding box that are relatively parallel to the edge; and determining whether the welding of the foils is defective based on the measurements.

11 . The method of claim 8 , wherein the augmenting excludes contrast changes, adding noise, and blurring the X-Ray radiographic image or a portion thereof or any augmentation that obstructs features making it difficult to identify defects.

12 . A system comprising:
an X-Ray source configured to irradiate a portion of a battery cell, the portion of the battery cell comprising portions of foils of anodes or cathodes of the battery cell and a tab of the battery cell to which the foils are welded; a detector configured to record an X-Ray radiographic image of the portion of the battery cell generated by irradiating the portion of the battery cell; and a computing device coupled to the detector, wherein the computing device is configured to: receive the X-Ray radiographic image of the battery cell; segment the X-Ray radiographic image into regions of interest using a classifier; process the segmented X-Ray radiographic image using the classifier to identify features of the battery cell; detect whether one or more of the features in the processed X-Ray radiographic image is defective by using the classifier; and determine, using the classifier, whether the battery cell is defective based on whether one or more of the features in the processed X-Ray radiographic image is defective.

13 . The system of claim 12 , wherein the computing device is configured to detect an extraordinary condition in the battery cell using a unary classifier that is different than the classifier.

14 . The system of claim 12 , wherein the computing device is configured to detect one or more of a tear in a foil of an anode or a cathode in the battery cell, a fold in the foil, a defect in a first weld region comprising welded foils of anodes or cathodes of the battery cell, and a defect in a second weld region comprising the welded foils welded to a tab of the battery cell.

15 . The system of claim 12 , wherein the one or more of the features indicate one or more of a quality of welding of foils of anodes or cathodes of the battery cell and a quality of welding of the welded foils to a tab of the battery cell.

16 . The system of claim 12 , wherein the computing device is configured to segment the X-Ray radiographic image by highlighting the regions of interest in the X-Ray radiographic image, separating the regions of interest from each other, and labeling the regions of interest.

17 . The system of claim 12 , wherein the computing device is configured to use the segmentation to mask a selected one of the features to further segment the selected one of the features for further processing and to facilitate the processing of another one of the features.

18 . The system of claim 12 , wherein the computing device is configured to train the classifier by selectively augmenting one or more of the regions of interest by one or more of flipping, translating, and rotating the X-Ray radiographic image or a portion thereof without causing an artifact in the X-Ray radiographic image, and wherein the augmenting excludes contrast changes, adding noise, and blurring the X-Ray radiographic image or a portion thereof.

19 . The system of claim 12 , wherein the computing device is configured to detect whether one or more of the features is defective by:
detecting, in the X-Ray radiographic image, an edge of a tab of the battery cell to which foils of anodes or cathodes of the battery cell are welded; measuring, relative to the edge of the tab, dimensions of a first weld region comprising the welded foils and a second weld region comprising the welded foils welded to the tab of the battery cell; and comparing the dimensions to respective thresholds.

20 . The system of claim 12 , wherein the computing device is configured to detect whether one or more of the features is defective by:
detecting, in the X-Ray radiographic image, an edge of a tab of the battery cell to which foils of anodes or cathodes of the battery cell are welded; fitting a line perpendicular to the

Assignees

• Gm Global Tech Operations Llc

Inventors

• Wegner Diana M
• Mcgovern Megan E
• Bruder Dmitriy
• Wagner Sean Robert
• Ahmed Tanjina
• Schmitz Evan William

Classifications

• G01N23/083 Primary

  the radiation being X-rays · CPC title

• G01N2223/1016

  X-ray · CPC title

• G01N2223/646

  flaws, defects · CPC title

• G01N23/18

  Investigating the presence of flaws defects or foreign matter · CPC title

• H01M10/4285 Primary

  Testing apparatus · CPC title