IP Library Granted Patent US 12,725,846
Granted Patent B2
US 12,725,846 · App. 18/430,850 · Granted Sep 1, 2026

Method and device for detecting abnormality in alignment of battery cell type electrodes

Inventors: Dong Whan Shin (Daejeon, KR); Kang San Kim (Daejeon, KR); Yun Jae Kim (Daejeon, KR); Seung Han Lee (Daejeon, KR); Hye Ju Jang (Daejeon, KR)
Assignee: SK On Co., Ltd.
H01M10/484G01N21/88G06T7/0004H01M10/4285H01M10/48H01M10/488G06T7/0006G06T2207/10081G06T2207/20081
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,725,846
App. No.
18/430,850
Granted
Sep 1, 2026
Kind
B2
Abstract

According to various embodiments, there may be provides a method for detecting an abnormality in battery cell type electrodes, which includes: acquiring a 3-dimensional image by imaging a specimen including one or more battery cell type electrodes; determining an arrangement state of the electrodes of the specimen by processing the 3-dimensional image as an input to one or more determination models comprising a deep learning-based determination model or a rule-based determination model; and detecting an abnormality in the electrodes of the specimen based on determination results for each of one or more determination models, and a device therefor.

Claims (31)

1 . A method for detecting an abnormality in battery cell type electrodes, the method comprising:

acquiring a 3-dimensional image by imaging a specimen including one or more battery cell type electrodes;

determining an arrangement state of the electrodes of the specimen by processing the 3-dimensional image as an input to one or more determination models comprising a deep learning-based determination model or a rule-based determination model; and

detecting an abnormality in the electrodes of the specimen based on determination results for each of one or more determination models,

wherein the one or more determination models is configured to extract electrodes from a plurality of tomography images included in the 3-dimensional image, extract endpoint positions for each of the extracted electrodes, and determine the arrangement state of the electrodes based on endpoint positions of pairs of electrodes, and

wherein the arrangement state includes at least one of whether an electrode alignment is abnormal, whether an electrode is omitted, whether electrodes are duplicated, and whether an electrode is deformed.

2 . The method according to claim 1 , wherein in the acquiring a 3-dimensional image, the 3-dimensional image is generated by integrating a plurality of images, which are obtained by tomography of cross-sections of the electrodes inside the specimen in a specific region of edges of the specimen, where the electrodes are disposed, by means of CT.

3 . The method according to claim 2 , wherein the specific region includes a region where an extension line of a first edge formed in a first axis direction and an extension line of a second edge formed in a second axis direction of the specimen meet, and

the plurality of images include a first tomography image obtained by tomography of a first cross-section of the specimen perpendicular to the first edge in the specific region, and a second tomography image obtained by tomography of a second cross-section of the specimen perpendicular to the second edge in the specific region.

4 . The method according to claim 1 , wherein in the detecting an abnormality in the electrodes, each of the deep learning-based determination model and the rule-based determination model is configured to determine an abnormality in the electrodes of the specimen based on at least some of whether the electrode alignment is abnormal, whether the electrode is omitted, whether the electrodes are duplicated, and whether the electrode is deformed in the acquired 3-dimensional image.

5 . The method according to claim 4 , wherein the determination of whether an electrode alignment is abnormal is configured to perform according to:

in the determining an arrangement state of the electrodes, by using the deep learning-based determination model and the rule-based determination model, whether a gap between endpoints of two electrodes disposed in the 3-dimensional image is greater than a preset reference gap; whether a slope formed based on the endpoints of the two electrodes is greater than a preset reference slope; or whether an endpoint of one electrode from the 3-dimensional image is greater than a preset threshold distance from a preset reference point.

6 . The method according to claim 1 , wherein the one or more determination models comprise:

i) two or more of the same deep learning-based determination models;

ii) two or more different deep learning-based determination models; or

iii) at least one of the deep learning-based determination model and at least one rule-based determination model.

7 . A device for detecting an abnormality in battery cell type electrodes, the device comprising:

an image acquisition apparatus configured to acquire a 3-dimensional image by imaging a specimen including one or more battery cell type electrodes;

an image determination apparatus configured to determine an arrangement state of the electrodes of the specimen by processing the 3-dimensional image as an input to one or more determination models comprising a deep learning-based determination model or a rule-based determination model; and

an electrode state determination apparatus configured to detect an abnormality in the electrodes of the specimen based on determination results for each of one or more determination models,

wherein the one or more determination models is configured to extract electrodes from a plurality of tomography images included in the 3-dimensional image, extract endpoint positions for each of the extracted electrodes, and determine the arrangement state of the electrodes based on endpoint positions of pairs of electrodes, and

wherein the arrangement state includes at least one of whether an electrode alignment is abnormal, whether an electrode is omitted, whether electrodes are duplicated, and whether an electrode is deformed.

8 . The device according to claim 7 , wherein the image acquisition apparatus generates the 3-dimensional image by integrating a plurality of images, which are obtained by tomography of cross-sections of the electrodes inside the specimen in a specific region of edges of the specimen, where the electrodes are disposed, by means of CT.

9 . The device according to claim 8 , wherein the specific region includes a region where an extension line of a first edge formed in a first axis direction and an extension line of a second edge formed in a second axis direction of the specimen meet, and

the image acquisition apparatus acquires the plurality of images including a first tomography image obtained by tomography of a first cross-section of the specimen perpendicular to the first edge in the specific region, and a second tomography image obtained by tomography of a second cross-section of the specimen perpendicular to the second edge in the specific region.

10 . The device according to claim 7 , wherein each of the deep learning-based determination model and the rule-based determination model is configured to determine an abnormality in the electrodes of the specimen based on at least some of whether the electrode alignment is abnormal, whether the electrode is omitted, whether the electrodes are duplicated, and whether the electrode is deformed in the acquired 3-dimensional image.

11 . The device according to claim 10 , wherein the image determination apparatus determines whether the electrode alignment is abnormal according to: by using the deep learning-based determination model and the rule-based determination model, whether a gap between endpoints of two electrodes disposed in the 3-dimensional image is greater than a preset reference gap; whether a slope formed based on the endpoints of the two electrodes is greater than a preset reference slope; or whether an endpoint of one electrode from the 3-dimensional image is greater than a preset threshold distance from a preset reference point.

12 . The device according to claim 7 , wherein the one or more determination models comprises:

i) two or more of the same deep learning-based determination models;

ii) two or more different deep learning-based determination models; or

iii) at least one of the deep learning-based determination model and at least one rule-based determination model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 6, 2024
From: SHIN, DONG WHAN; KIM, KANG SAN; KIM, YUN JAE; LEE, SEUNG HAN; JANG, HYE JU
To: SK ON CO., LTD.
Reel/Frame 066394/0447 →
Priority Claims (2)
KR 10-2023-0016436 · Feb 7, 2023 · national
KR 10-2023-0089839 · Jul 11, 2023 · national
Continuity (1)
Related Publication 20240265519A1 · Aug 8, 2024
References Cited (11)
US 20210153825A1 · Shizukuishi · 2021 [cited by examiner]
US 20210234207A1 · Chae · 2021 [cited by examiner]
US 20220231300A1 · Yun · 2022 [cited by examiner]
US 20230207815A1 · Ai · 2023 [cited by examiner]
US 20240354932A1 · Lee · 2024 [cited by examiner]
US 20250329900A1 · Wu · 2025 [cited by examiner]
CN 113466706B · 2022 [cited by examiner]
JP 2001203003A · 2001 [cited by applicant]
KR 20200088222A · 2020 [cited by applicant]
KR 20220086871A · 2022 [cited by applicant]
Google Patents Translation of CN-113466706-B, First published Oct. 1, 2021, Date Accessed: Jan. 10, 2026, Available Online at: https://patents.google.com/patent/CN113466706B/en?oq=CN113466706B (Year: 2021). [cited by examiner]