Monitoring apparatus and operation method thereof
A monitoring apparatus according to an example embodiment disclosed in this document may include an image acquisition unit configured to acquire an image of at least one process processing device related to manufacturing of a battery cell, an analyzer configured to input the acquired image into an artificial intelligence model for determining a welding state of the battery cell to generate a first determination result of determining whether the battery cell is defective, and a determination unit configured to determine whether the battery cell is defective based on the first determination result.
1 . A monitoring apparatus, comprising:
an image acquirer configured to acquire an image of at least one process processing device in manufacturing of a battery cell;
an analyzer configured to input the acquired image into an artificial intelligence model for determining a welding state of the battery cell to generate a first determination result of determining whether the battery cell is defective; and
a determinator configured to determine whether the battery cell is defective based on the first determination result.
2 . The apparatus of claim 1 , wherein the determinator is further configured to generate a second determination result of determining whether the battery cell is defective based on gray level information of the acquired image.
3 . The apparatus of claim 2 , wherein the determinator is further configured to determine whether the battery cell is defective based on the first and second determination results.
4 . The apparatus of claim 2 , wherein the determinator is further configured to generate the second determination result by determining at least one of a presence or absence of a can of the battery cell, a presence or absence of a top cap of the battery cell, a center distance between the can and the top cap of the battery cell, a position of a cathode tab of the battery cell, and whether the cathode tab is over-welded, based on the gray level information of the acquired image.
5 . The apparatus of claim 1 , wherein the artificial intelligence model comprises an artificial intelligence model configured to detect a welding area of the battery cell based on the acquired image and an artificial intelligence model configured to analyze a welding state of the welding area.
6 . The apparatus of claim 5 , wherein the artificial intelligence model configured to analyze the welding state of the welding area is further configured to classify the welding state into a state having a welding length within a reference length range, a state having a welding length less than the reference length, and a state having other defects.
7 . The apparatus of claim 1 , wherein the artificial intelligence model comprises an artificial intelligence model configured to determine a state of a can assembly of the battery cell based on the acquired image and an artificial intelligence model configured to detect and/or crop a welding position in the acquired image in response to the state of the can assembly being normal.
8 . An operation method of a monitoring apparatus, the method comprising:
acquiring an image of at least one process processing device in manufacturing of a battery cell;
generating a first determination result of determining whether the battery cell is defective by inputting the acquired image to an artificial intelligence model configured to determine a welding state of the battery cell;
generating a second determination result of determining whether the battery cell is defective based gray level information of the acquired image; and
determining whether the battery cell is defective based on the first and second determination results.
9 . The method of claim 8 , wherein the artificial intelligence model comprises an artificial intelligence model configured to detect a welding area of the battery cell based on the acquired image and an artificial intelligence model configured to analyze a welding state of the welding area.
10 . The method of claim 9 , wherein the artificial intelligence model configured to analyze the welding state of the welding area is further configured to classify the welding state into a state having a welding length within a reference length range, a state having a welding length less than a reference length range, and a state having other defects.
11 . The method of claim 9 , wherein the generating of the second determination result comprises generating the second determination result by determining at least one of a presence or absence of a can of the battery cell, a presence or absence of a top cap of the battery cell, a center distance between the can and the top cap of the battery cell, a position of a cathode tab of the battery cell, and whether the cathode tab is over-welded, based on the gray level information of the acquired image.
12 . The method of claim 8 , wherein the artificial intelligence model comprises an artificial intelligence model configured to determine a state of a can assembly of the battery cell based on the acquired image and an artificial intelligence model configured to detect and/or crop a welding position in the acquired image in response to the state of the can assembly being normal.