CN117291882A - Pole piece defect detection method, device and storage medium - Google Patents
Pole piece defect detection method, device and storage medium Download PDFInfo
- Publication number
- CN117291882A CN117291882A CN202311216382.7A CN202311216382A CN117291882A CN 117291882 A CN117291882 A CN 117291882A CN 202311216382 A CN202311216382 A CN 202311216382A CN 117291882 A CN117291882 A CN 117291882A
- Authority
- CN
- China
- Prior art keywords
- pole piece
- battery
- determining
- key point
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 75
- 230000007547 defect Effects 0.000 title claims abstract description 53
- 230000011218 segmentation Effects 0.000 claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 50
- 230000008569 process Effects 0.000 abstract description 12
- 229910052744 lithium Inorganic materials 0.000 description 16
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 229910000733 Li alloy Inorganic materials 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 239000008151 electrolyte solution Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000001989 lithium alloy Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007773 negative electrode material Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000013072 incoming material Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application provides a pole piece defect detection method, a pole piece defect detection device and a storage medium. The method comprises the following steps: acquiring pole piece image information of a battery to be detected, wherein the battery to be detected comprises a plurality of pole pieces; inputting the pole piece image information into a key point model to obtain key point data in the pole piece image information, wherein the key point data is used for reflecting the end point positions of each pole piece in the battery to be detected; inputting the pole piece image information into a segmentation model to obtain segmentation areas in the pole piece image information, wherein the segmentation areas are used for reflecting areas where endpoints of each pole piece in the battery to be detected are located; determining endpoint coordinates of each pole piece in the battery to be detected according to the key point data and/or the segmentation areas; and performing defect detection on a plurality of pole pieces of the battery to be detected according to the endpoint coordinates. The method and the device do not need to be manually participated, the whole detection process is less influenced by artificial subjective factors, and the detection result is more accurate.
Description
Technical Field
The present disclosure relates to the field of batteries, and in particular, to a method and apparatus for detecting a defect of a pole piece, and a storage medium.
Background
The lithium battery is a battery using a non-electrolyte solution, and is made of lithium metal or a lithium alloy as a negative electrode material. In order to prevent the occurrence of lithium branching crystals, the negative electrode of a lithium battery is required to have a certain redundancy length than the positive electrode, and the electrodes should be aligned and cannot be bent and deformed to a large extent. In the manufacturing process of the lithium battery, the relative positions of the positive electrode and the negative electrode of the lithium battery can generate certain fluctuation due to winding or stacking, so that the boundary distance between the positive electrode and the negative electrode is changed, and the problems of overlarge redundancy or no redundancy of the negative electrode and the like occur.
In the related art, the redundancy and deformation of the positive pole piece and the negative pole piece of the lithium battery are generally judged through manual experience and visual observation, the influence of artificial subjective factors is great, and the accuracy of the defect detection of the pole piece of the lithium battery cannot be ensured.
Disclosure of Invention
Aspects of the application provide a pole piece defect detection method, a pole piece defect detection device and a storage medium, the whole detection process is less influenced by artificial subjective factors, and the detection result is more accurate.
The embodiment of the application provides a pole piece defect detection method, which comprises the following steps:
acquiring pole piece image information of a battery to be detected, wherein the battery to be detected comprises a plurality of pole pieces;
inputting the pole piece image information into a key point model to obtain key point data in the pole piece image information, wherein the key point data is used for reflecting the endpoint positions of each pole piece in the battery to be detected;
inputting the pole piece image information into a segmentation model to obtain segmentation areas in the pole piece image information, wherein the segmentation areas are used for reflecting areas where endpoints of each pole piece in the battery to be detected are located;
determining endpoint coordinates of each pole piece in the battery to be detected according to the key point data and/or the segmentation areas;
and performing defect detection on the plurality of pole pieces of the battery to be detected according to the endpoint coordinates.
In some embodiments of the present application, the determining, according to the keypoint data and/or the segmentation area, the endpoint coordinates of each pole piece in the battery to be detected includes:
acquiring the number of endpoints of the plurality of pole pieces, the number of key points in the key point data and the number of areas in the partitioned areas;
and determining the endpoint coordinates of each pole piece based on the endpoint number of the pole pieces, the key point number in the key point data and/or the area number in the partitioned area.
In some embodiments of the present application, the determining the endpoint coordinates of each pole piece based on the number of endpoints of the plurality of pole pieces, the number of keypoints in the keypoint data, and/or the number of regions in the partitioned region includes:
if the number of the endpoints of the pole pieces is equal to the number of the key points in the key point data and is unequal to the number of the areas in the partitioned areas, determining the endpoint coordinates of each pole piece according to the key point data;
if the number of the endpoints of the plurality of pole pieces is equal to the number of the areas in the dividing area and is unequal to the number of the key points in the key point data, determining the endpoint coordinates of each pole piece according to the dividing area;
and if the number of the endpoints of the plurality of pole pieces is different from the number of the key points in the key point data and the number of the areas in the dividing area, determining the endpoint coordinates of each pole piece according to the key point data and the dividing area.
In some embodiments of the present application, the determining the endpoint coordinates of each pole piece according to the keypoint data and the segmentation area includes:
determining a first end point coordinate of each pole piece according to the key point data;
determining the second endpoint coordinates of each pole piece according to the segmentation areas;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates and the second endpoint coordinates.
In some embodiments of the present application, the determining the endpoint coordinates of each pole piece based on the first endpoint coordinates and the second endpoint coordinates includes:
determining a third end point coordinate of each pole piece based on a set skeleton algorithm;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates, the second endpoint coordinates and the third endpoint coordinates.
In some embodiments of the present application, before the determining, according to the keypoint data and/or the segmentation area, the endpoint coordinates of each pole piece in the battery to be detected, the method further includes:
determining whether redundant endpoints exist on each pole piece;
and if so, removing the redundant endpoint.
In some embodiments of the present application, before the inputting the pole piece image information into the keypoint model, the method further comprises:
inputting the pole piece image information into a deformation detection model to obtain deformation results of each pole piece in the battery to be detected;
and determining the deformation result as that each pole piece is not deformed.
In some embodiments of the present application, the battery to be detected includes a plurality of positive electrode pieces and negative electrode pieces that are disposed in a staggered manner; and performing defect detection on the plurality of pole pieces of the battery to be detected according to the endpoint coordinates, wherein the defect detection comprises the following steps:
determining the heights of a plurality of positive pole pieces and negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces according to the endpoint coordinates;
and performing defect detection on the plurality of pole pieces of the battery to be detected based on the heights of the plurality of positive pole pieces and the negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces.
The embodiment of the application also provides a pole piece defect detection device, which comprises:
the information acquisition module is used for acquiring pole piece image information of a battery to be detected, wherein the battery to be detected comprises a plurality of pole pieces;
the key point acquisition module is used for inputting the pole piece image information into a key point model to obtain key point data in the pole piece image information, wherein the key point data is used for reflecting the end point positions of each pole piece in the battery to be detected;
the region acquisition module is used for inputting the pole piece image information into a segmentation model to obtain segmentation regions in the pole piece image information, wherein the segmentation regions are used for reflecting regions where end points of each pole piece in the battery to be detected are located;
the determining module is used for determining the endpoint coordinates of each pole piece in the battery to be detected according to the key point data and/or the segmentation areas;
and the detection module is used for detecting the defects of the pole piece of the battery to be detected according to the endpoint coordinates.
In some embodiments of the present application, the determining module is specifically configured to:
acquiring the number of endpoints of the plurality of pole pieces, the number of key points in the key point data and the number of areas in the partitioned areas;
and determining the endpoint coordinates of each pole piece based on the endpoint number of the pole pieces, the key point number in the key point data and/or the area number in the partitioned area.
In some embodiments of the present application, the determining module is specifically configured to:
if the number of the endpoints of the pole pieces is equal to the number of the key points in the key point data and is unequal to the number of the areas in the partitioned areas, determining the endpoint coordinates of each pole piece according to the key point data;
if the number of the endpoints of the plurality of pole pieces is equal to the number of the areas in the dividing area and is unequal to the number of the key points in the key point data, determining the endpoint coordinates of each pole piece according to the dividing area;
and if the number of the endpoints of the plurality of pole pieces is different from the number of the key points in the key point data and the number of the areas in the dividing area, determining the endpoint coordinates of each pole piece according to the key point data and the dividing area.
In some embodiments of the present application, the determining module is specifically configured to:
determining a first end point coordinate of each pole piece according to the key point data;
determining the second endpoint coordinates of each pole piece according to the segmentation areas;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates and the second endpoint coordinates.
In some embodiments of the present application, the determining module is specifically configured to:
determining a third end point coordinate of each pole piece based on a set skeleton algorithm;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates, the second endpoint coordinates and the third endpoint coordinates.
In some embodiments of the present application, the apparatus further comprises:
the determining module is used for determining whether redundant endpoints exist on each pole piece;
and the removing module is used for removing the redundant endpoint when the redundant endpoint exists.
In some embodiments of the present application, the apparatus further comprises:
the deformation detection module is used for inputting the pole piece image information into a deformation detection model to obtain deformation results of each pole piece in the battery to be detected;
and the result determining module is used for determining that the deformation result is that each pole piece is not deformed.
In some embodiments of the present application, the battery to be detected includes a plurality of positive electrode pieces and negative electrode pieces that are disposed in a staggered manner; the detection module is specifically used for:
determining the heights of a plurality of positive pole pieces and negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces according to the endpoint coordinates;
and performing defect detection on the plurality of pole pieces of the battery to be detected based on the heights of the plurality of positive pole pieces and the negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces.
Embodiments of the present application also provide a non-transitory machine-readable storage medium having executable code stored thereon, which when executed by a processor of an electronic device, causes the processor to perform the pole piece defect detection method described above.
In the embodiment of the application, the key point data and the segmentation area in the electrode slice image information are respectively obtained by acquiring the electrode slice image information of the battery to be detected and inputting the electrode slice image information into the key point model and the segmentation model. And determining the endpoint coordinates of each pole piece in the battery to be detected based on the key point data and/or the segmentation areas, and further finishing defect detection of a plurality of pole pieces of the battery to be detected according to the endpoint coordinates. In summary, the method and the device can automatically acquire the key point data for reflecting the end point positions of the pole pieces and the segmentation areas for reflecting the end point areas of the pole pieces according to the key point model and the segmentation model, can quickly obtain the end point coordinates of the pole pieces according to the key point data and/or the segmentation areas without manual participation, further finish defect detection of a plurality of pole pieces of the battery to be detected according to the end point coordinates, and the whole detection process is less influenced by artificial subjective factors and has more accurate detection results.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a flow chart of a method for detecting defects of a pole piece according to an exemplary embodiment of the present application;
FIG. 2 is a specific exemplary diagram of pole piece image information for different angles provided in accordance with an exemplary embodiment of the present application;
FIG. 3 is a specific exemplary diagram of pole piece image information provided in an exemplary embodiment of the present application;
FIG. 4 is a flowchart of a method for determining endpoint coordinates for each pole piece according to an exemplary embodiment of the present application;
fig. 5 is a schematic structural diagram of a pole piece defect detecting device according to an exemplary embodiment of the present application.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The lithium battery is a battery using a non-electrolyte solution, and is made of lithium metal or a lithium alloy as a negative electrode material. In order to prevent the occurrence of lithium branching crystals, the negative electrode of a lithium battery is required to have a certain redundancy length than the positive electrode, and the electrodes should be aligned and cannot be bent and deformed to a large extent. In the manufacturing process of the lithium battery, the relative positions of the positive electrode and the negative electrode of the lithium battery can generate certain fluctuation due to winding or stacking, so that the boundary distance between the positive electrode and the negative electrode is changed, and the problems of overlarge redundancy or no redundancy of the negative electrode and the like occur. In the related art, the redundancy and deformation of the positive pole piece and the negative pole piece of the lithium battery are generally judged through manual experience and visual observation, the influence of artificial subjective factors is great, and the accuracy of the defect detection of the pole piece of the lithium battery cannot be ensured. In view of this, the embodiment of the application provides a pole piece defect detection method.
Fig. 1 is a flowchart of a method for detecting a defect of a pole piece according to an embodiment of the present application, as shown in fig. 1, where the method includes:
step 101, obtaining pole piece image information of a battery to be detected, wherein the battery to be detected comprises a plurality of pole pieces.
It should be understood that a battery to be detected includes a plurality of positive electrode plates and a plurality of negative electrode plates, where the positive electrode plates and the negative electrode plates are paired two by two, and are distributed in a cross-stacked manner, for example, the number of the plates may be 59, where there may be 29 positive electrode plates and 30 negative electrode plates.
Step 102, inputting pole piece image information into a key point model to obtain key point data in the pole piece image information, wherein the key point data is used for reflecting the end point positions of each pole piece in the battery to be detected.
Step 103, inputting the pole piece image information into a segmentation model to obtain segmentation areas in the pole piece image information, wherein the segmentation areas are used for reflecting areas where end points of the pole pieces in the battery to be detected are located.
And 104, determining the endpoint coordinates of each pole piece in the battery to be detected according to the key point data and/or the segmentation areas.
And 105, performing defect detection on a plurality of pole pieces of the battery to be detected according to the endpoint coordinates.
In practical application, an X-ray generator (also called Xray generator) can be used to emit X-rays, penetrate through the inside of a plurality of pole pieces of the battery, and the flat panel detector receives the X-rays for imaging, so as to obtain the pole piece image information. In implementation, four flat panel detectors may be disposed at four corners of the plurality of pole pieces, to collect pole piece image information respectively, see fig. 2. For convenience of description, the following description will be made by taking one of the four pole piece image information as an example:
after the pole piece image information is obtained, the obtained pole piece image information can be preprocessed to eliminate background interference in order to improve the accuracy of pole piece endpoint finding in the follow-up process. Inputting the preprocessed pole piece image information into a key point model and a segmentation model respectively, and obtaining key point data in the pole piece image information through the key point model; and obtaining a segmentation area in the pole piece image information through the segmentation model. The key point data are used for reflecting the positions of the end points of the pole pieces in the battery to be detected, and the dividing areas are used for reflecting the areas where the end points of the pole pieces in the battery to be detected are located.
The key point model and the segmentation model are both trained neural network models, specifically, when the key point model is trained, a plurality of acquired pole piece images can be used as training samples, and key points marked on the pole piece images are used as labels to carry out model training. And when the segmentation model is trained, a plurality of acquired pole piece images can be used as training samples, and the segmentation areas marked on the pole piece images are used as labels to carry out model training.
After the key point data and the segmentation areas are obtained through the key point model and the segmentation model, the endpoint coordinates of each pole piece in the battery to be detected can be determined according to the key point data and/or the segmentation areas, and then defect detection is carried out on a plurality of pole pieces of the battery to be detected according to the endpoint coordinates. The specific method for determining the endpoint coordinates can be found in the following embodiments, and will not be described in detail herein.
It should be noted that, before determining the endpoint coordinates of each pole piece in the battery to be detected according to the key point data and/or the segmentation area, the method further includes: determining whether redundant endpoints exist on each pole piece; if so, the redundant endpoint is removed.
It should be understood that in the process of finding points through the key point model and the segmentation model, the situation of misidentification of the end points may occur, and a plurality of end points appear on one pole piece, and at this time, the accuracy of finding points of the end points of each pole piece is ensured by removing redundant end points.
In this embodiment, the battery to be detected includes a plurality of anode plates and cathode plates that are disposed in a staggered manner; performing defect detection on a plurality of pole pieces of a battery to be detected according to the endpoint coordinates, including:
and determining the heights of the positive pole pieces and the negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces according to the endpoint coordinates.
And performing defect detection on a plurality of pole pieces of the battery to be detected based on the heights of the plurality of positive pole pieces and the negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces.
For ease of understanding, the specific method of defect detection is described below in conjunction with fig. 2 and 3:
in fig. 3, the box-framed portion is the end point of the found pole piece, and the 4 panels in fig. 2 are the pole piece image information at 4 angles, in fig. 2, there are 29 positive pole pieces and 30 negative pole pieces, and the "L1, L2..l29" marked in fig. 2 indicates the distance from each positive end point to the negative end point, and under normal conditions, the negative end point is a certain distance (herein referred to as a standard distance) higher than the positive end point, and by comparing whether "L1, L2..l29" is greater than or less than the standard distance by a certain range, if yes, it is proved that the redundancy of the pole piece is problematic, and the pole piece has defects.
The "upper limit" in fig. 2 indicates the highest point phase difference degree of all positive pole pieces, if the phase difference degree is within the set range, the positive pole pieces have no particularly high or particularly low end points, and the requirements are met, otherwise, the defect of the positive pole pieces is proved. Similarly, the "lower limit" indicates the highest point phase difference degree of all the negative pole pieces, if the phase difference degree is within the set range, the positive pole pieces have no particularly high or particularly low end points, and the requirements are met, otherwise, the defect of the pole pieces is proved.
The "negative electrode fall" in fig. 2 refers to the fall between two adjacent negative electrode terminals, and if the fall is within the set fall range, the pole piece is proved to meet the requirements, otherwise, the pole piece is proved to have defects. Similarly, the positive electrode fall refers to the fall between two adjacent positive electrode endpoints, and if the fall is within the set fall range, the pole piece meets the requirements, otherwise, the defect of the pole piece is proved.
As can be seen from the above examples, the parameters of defect detection ("upper limit", "lower limit", "negative electrode fall", "positive electrode fall", etc.) can be determined based on the heights of the positive electrode plates and the negative electrode plates and the distance between every two adjacent positive electrode plates or negative electrode plates, so that defect detection of multiple electrode plates of the battery to be detected can be completed according to the heights of the positive electrode plates and the negative electrode plates and the distance between every two adjacent positive electrode plates or negative electrode plates.
According to the pole piece defect detection method, the pole piece image information of the battery to be detected is obtained, and the pole piece image information is input into the key point model and the segmentation model, so that key point data and the segmentation area in the pole piece image information are obtained respectively. And determining the endpoint coordinates of each pole piece in the battery to be detected based on the key point data and/or the segmentation areas, and further finishing defect detection of a plurality of pole pieces of the battery to be detected according to the endpoint coordinates. In summary, the method and the device can automatically acquire the key point data for reflecting the end point positions of the pole pieces and the segmentation areas for reflecting the end point areas of the pole pieces according to the key point model and the segmentation model, can quickly obtain the end point coordinates of the pole pieces according to the key point data and/or the segmentation areas without manual participation, further finish defect detection of a plurality of pole pieces of the battery to be detected according to the end point coordinates, and the whole detection process is less influenced by artificial subjective factors and has more accurate detection results.
With the foregoing in mind, a specific method for determining endpoint coordinates of each pole piece is described below, and fig. 4 is a flowchart of a method for determining endpoint coordinates of each pole piece, as shown in fig. 4, the method comprising:
step 401, if the number of end points of the plurality of pole pieces is equal to the number of key points in the key point data and is unequal to the number of areas in the partitioned areas, determining the end point coordinates of each pole piece according to the key point data.
Step 402, if the number of end points of the plurality of pole pieces is equal to the number of areas in the segmented area and is different from the number of key points in the key point data, determining the end point coordinates of each pole piece according to the segmented area.
Step 403, if the number of end points of the plurality of pole pieces is different from the number of key points in the key point data and the number of areas in the segmented area, determining the end point coordinates of each pole piece according to the key point data and the segmented area.
In particular, for example, it is assumed that the number of end points corresponding to the plurality of pole pieces is 59. Then:
as one implementation: if the number of keypoints is equal to 59 and the number of regions in the partitioned area is less than 59, the keypoint data is taken as the final output endpoint coordinates.
As another implementation: if the number of areas in the divided area is equal to 59 and the number of key points is less than 59, the coordinates of the specified points in the divided area are used as the final output end point coordinates, and various methods for determining the end point coordinates in the divided area are possible, for example, the center point coordinates of the divided area may be used as the end point coordinates, or the point at a certain position in the divided area may be set as the end point coordinates according to an empirical value.
As yet another implementation: the first end point coordinates of each pole piece can be determined according to the key point data; determining the second endpoint coordinates of each pole piece according to the segmentation areas; and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates and the second endpoint coordinates.
In specific implementation, for example, if the number of key points is 57, and the number of areas in the partitioned area is 58, that is, the number of the key points and the partitioned area is smaller than the number of end points 59 corresponding to the pole pieces, coordinate comparison and complementation are performed on the key point data and the partitioned area, and 59 coordinate points are complemented. Specifically, the coordinates (first endpoint coordinates) corresponding to 57 key points may be determined first, then the coordinates (second endpoint coordinates) of the specified points corresponding to 58 divided regions may be determined, the coordinates of the 57 key points and the coordinates of the specified points corresponding to the divided regions may be compared, if the coordinates of the key points and the coordinates of the specified points corresponding to the divided regions are the same, the same point may be determined as the final endpoint, if the coordinates of the key points are not found in the divided regions, the coordinates of the key points may be fed into the divided regions, and if 59 coordinate points may be fed in at this time, the fed-in image may be output as the final endpoint finding result.
In the embodiment, the number of the endpoints of the pole pieces, the number of the key points in the key point data and the number of the areas in the partitioned areas are compared, so that the endpoint coordinates of the whole pole pieces can be obtained without manual participation, and the accuracy is high.
Of course, after the coordinate comparison and complementation are performed on the key point data and the segmented region, there may be a situation of few points, and in order to further improve the accuracy of finding points, in the embodiment of the present application, the determining endpoint coordinates of each pole piece based on the first endpoint coordinate and the second endpoint coordinate includes:
determining a third end point coordinate of each pole piece based on a set skeleton algorithm;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates, the second endpoint coordinates and the third endpoint coordinates.
In specific implementation, based on the above example, assuming that 59 points are still complemented by the key point data and the segmentation area, the set skeleton algorithm is continuously used to find the points, that is, the coordinates of the third end point of each pole piece are obtained, and the coordinates of the first end point coordinate, the second end point coordinate and the third end point coordinate are compared and complemented (in short, the skeleton is arranged between two points with far distances, the search area is roughly determined according to the positions of the skeleton and the left and right points), if 59 coordinate points can be successfully complemented, the complemented images are output as the final end point finding result. If the patches are still not uniform, an "error" or "end" result is output.
The specific steps of finding points by using a skeleton algorithm can be as follows: and convolving the first-order and second-order partial derivatives of the Gaussian smoothing kernel with the image, establishing a Hessian matrix to obtain the normal direction of the skeleton line, and applying Taylor polynomial expansion on the normal direction of the skeleton line to calculate the sub-pixel position of the skeleton line.
By using the key point model, the segmentation area model and the skeleton algorithm, three point finding results (a first end point coordinate, a second end point coordinate and a third end point coordinate) are obtained, and the three point finding results are comprehensively analyzed, so that the point finding efficiency and accuracy of each pole piece end point can be improved.
In addition, it should be understood that the pole pieces will be severely deformed after being extruded, and if the pole pieces are deformed, it is meaningless to find the end points of each pole piece through the key point model, the segmentation model and the skeleton algorithm, so as to be definitely inaccurate. Thus, the method further comprises, prior to inputting the pole piece image information into the keypoint model
Inputting the electrode plate image information into a deformation detection model to obtain deformation results of all electrode plates in the battery to be detected;
and determining the deformation result as that each pole piece is not deformed.
In practical application, based on a plurality of training samples (images of a plurality of pole pieces) acquired in advance, a label (deformed pole piece) trains the neural network model to obtain a trained deformation detection model. And inputting the pole piece image information into the trained deformation detection model to obtain the deformation result of each pole piece in the battery to be detected, and inputting the pole piece image information into the key point model and the segmentation model only when the deformation result is determined to be that each pole piece is not deformed, and continuing the subsequent steps.
In summary, the method and the device for detecting the electrode slice image of the battery obtain electrode slice image information of the battery to be detected, input the electrode slice image information into the key point model and the segmentation model, and further obtain key point data and segmentation areas in the electrode slice image information respectively. And determining the endpoint coordinates of each pole piece in the battery to be detected based on the key point data and/or the segmentation areas, and further finishing defect detection of a plurality of pole pieces of the battery to be detected according to the endpoint coordinates. In summary, the method and the device can automatically acquire the key point data for reflecting the end point positions of the pole pieces and the segmentation areas for reflecting the end point areas of the pole pieces according to the key point model and the segmentation model, can quickly obtain the end point coordinates of the pole pieces according to the key point data and/or the segmentation areas without manual participation, further finish defect detection of a plurality of pole pieces of the battery to be detected according to the end point coordinates, and the whole detection process is less influenced by artificial subjective factors and has more accurate detection results.
The advantages of the present application are summarized below:
1. the efficiency is higher: manual detection is inefficient, whereas the X-ray detection speed of the present application is much faster.
2. The overall cost is lower: the machine is more efficient than manual detection and in the long term the cost of machine X-ray detection is lower.
3. Information integration: the X-ray detection apparatus can measure a plurality of technical parameters such as the alignment degree of a product to be detected, the length of the positive electrode, the bending angle of the negative electrode, etc. at one time by a multi-station detection method (four-angle simultaneous detection).
4. Digital statistical management: SPC data statistics. In short, a mark is made for each battery, so that the subsequent call inquiry is facilitated.
5. More objective and stable: in the manual detection process, the detection result is influenced by factors such as personal standards, emotion, energy and the like. The machine strictly conforms to the set standard, and the detection result is more objective, reliable and stable.
6. Avoiding secondary pollution: manual operation sometimes results in an uncertain source of contamination, and a contaminated workpiece.
7. The maintenance is simple: low technical requirements on operators, long service life and the like.
8. The method has high adaptability to incoming materials with different forms, can be compatible with images with poor imaging effects, and can accurately find points.
Fig. 5 is a schematic structural diagram of a pole piece defect detecting device provided in an embodiment of the present application, as shown in fig. 5, the device includes: an information acquisition module 51, a key point acquisition module 52, an area acquisition module 53, a determination module 54, and a detection module 55.
The information obtaining module 51 is configured to obtain pole piece image information of a battery to be detected, where the battery to be detected includes a plurality of pole pieces.
The key point obtaining module 52 is configured to input the pole piece image information to the key point model, and obtain key point data in the pole piece image information, where the key point data is used to reflect the endpoint positions of each pole piece in the battery to be detected.
The region obtaining module 53 is configured to input the pole piece image information to the segmentation model, and obtain a segmentation region in the pole piece image information, where the segmentation region is configured to reflect a region where an endpoint of each pole piece in the battery to be detected is located.
The determining module 54 is configured to determine endpoint coordinates of each pole piece in the battery to be detected according to the key point data and/or the segmentation area.
The detection module 55 is configured to detect a defect of a pole piece of the battery to be detected according to the endpoint coordinates.
In some embodiments of the present application, the determining module 54 is specifically configured to:
acquiring the number of endpoints of the plurality of pole pieces, the number of key points in the key point data and the number of areas in the partitioned areas;
and determining the endpoint coordinates of each pole piece based on the endpoint number of the pole pieces, the key point number in the key point data and/or the area number in the partitioned area.
In some embodiments of the present application, the determining module 54 is specifically configured to:
if the number of the endpoints of the pole pieces is equal to the number of the key points in the key point data and is unequal to the number of the areas in the partitioned areas, determining the endpoint coordinates of each pole piece according to the key point data;
if the number of the endpoints of the plurality of pole pieces is equal to the number of the areas in the dividing area and is unequal to the number of the key points in the key point data, determining the endpoint coordinates of each pole piece according to the dividing area;
and if the number of the endpoints of the plurality of pole pieces is different from the number of the key points in the key point data and the number of the areas in the dividing area, determining the endpoint coordinates of each pole piece according to the key point data and the dividing area.
In some embodiments of the present application, the determining module 54 is specifically configured to:
determining a first end point coordinate of each pole piece according to the key point data;
determining the second endpoint coordinates of each pole piece according to the segmentation areas;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates and the second endpoint coordinates.
In some embodiments of the present application, the determining module 54 is specifically configured to:
determining a third end point coordinate of each pole piece based on a set skeleton algorithm;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates, the second endpoint coordinates and the third endpoint coordinates.
In some embodiments of the present application, the apparatus further comprises:
the determining module is used for determining whether redundant endpoints exist on each pole piece;
and the removing module is used for removing the redundant endpoint when the redundant endpoint exists.
In some embodiments of the present application, the apparatus further comprises:
the deformation detection module is used for inputting the pole piece image information into a deformation detection model to obtain deformation results of each pole piece in the battery to be detected;
and the result determining module is used for determining that the deformation result is that each pole piece is not deformed.
In some embodiments of the present application, the battery to be detected includes a plurality of positive electrode pieces and negative electrode pieces that are disposed in a staggered manner; the detection module 55 is specifically configured to:
determining the heights of a plurality of positive pole pieces and negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces according to the endpoint coordinates;
and performing defect detection on the plurality of pole pieces of the battery to be detected based on the heights of the plurality of positive pole pieces and the negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces.
Embodiments of the present application also provide a non-transitory machine-readable storage medium having executable code stored thereon, which when executed by a processor of an electronic device, causes the processor to perform the pole piece defect detection method described above.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. The pole piece defect detection method is characterized by comprising the following steps of:
acquiring pole piece image information of a battery to be detected, wherein the battery to be detected comprises a plurality of pole pieces;
inputting the pole piece image information into a key point model to obtain key point data in the pole piece image information, wherein the key point data is used for reflecting the endpoint positions of each pole piece in the battery to be detected;
inputting the pole piece image information into a segmentation model to obtain segmentation areas in the pole piece image information, wherein the segmentation areas are used for reflecting areas where endpoints of each pole piece in the battery to be detected are located;
determining endpoint coordinates of each pole piece in the battery to be detected according to the key point data and/or the segmentation areas;
and performing defect detection on the plurality of pole pieces of the battery to be detected according to the endpoint coordinates.
2. The method according to claim 1, wherein determining the endpoint coordinates of each pole piece in the battery to be detected according to the keypoint data and/or the segmented region comprises:
acquiring the number of endpoints of the plurality of pole pieces, the number of key points in the key point data and the number of areas in the partitioned areas;
and determining the endpoint coordinates of each pole piece based on the endpoint number of the pole pieces, the key point number in the key point data and/or the area number in the partitioned area.
3. The method of claim 2, wherein the determining endpoint coordinates for each pole piece based on the number of endpoints of the plurality of pole pieces, the number of keypoints in the keypoint data, and/or the number of regions in the partitioned region comprises:
if the number of the endpoints of the pole pieces is equal to the number of the key points in the key point data and is unequal to the number of the areas in the partitioned areas, determining the endpoint coordinates of each pole piece according to the key point data;
if the number of the endpoints of the plurality of pole pieces is equal to the number of the areas in the dividing area and is unequal to the number of the key points in the key point data, determining the endpoint coordinates of each pole piece according to the dividing area;
and if the number of the endpoints of the plurality of pole pieces is different from the number of the key points in the key point data and the number of the areas in the dividing area, determining the endpoint coordinates of each pole piece according to the key point data and the dividing area.
4. A method according to claim 3, wherein said determining endpoint coordinates of each pole piece from said keypoint data and said segmented region comprises:
determining a first end point coordinate of each pole piece according to the key point data;
determining the second endpoint coordinates of each pole piece according to the segmentation areas;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates and the second endpoint coordinates.
5. The method of claim 4, wherein the determining endpoint coordinates for each pole piece based on the first endpoint coordinates and the second endpoint coordinates comprises:
determining a third end point coordinate of each pole piece based on a set skeleton algorithm;
and determining the endpoint coordinates of each pole piece based on the first endpoint coordinates, the second endpoint coordinates and the third endpoint coordinates.
6. The method according to claim 1, wherein before determining the end point coordinates of each pole piece in the battery to be detected based on the keypoint data and/or the segmentation area, the method further comprises:
determining whether redundant endpoints exist on each pole piece;
and if so, removing the redundant endpoint.
7. The method of claim 1, wherein prior to the inputting the pole piece image information to a keypoint model, the method further comprises:
inputting the pole piece image information into a deformation detection model to obtain deformation results of each pole piece in the battery to be detected;
and determining the deformation result as that each pole piece is not deformed.
8. The method according to claim 1, wherein the battery to be detected comprises a plurality of positive electrode pieces and negative electrode pieces which are arranged in a staggered manner; and performing defect detection on the plurality of pole pieces of the battery to be detected according to the endpoint coordinates, wherein the defect detection comprises the following steps:
determining the heights of a plurality of positive pole pieces and negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces according to the endpoint coordinates;
and performing defect detection on the plurality of pole pieces of the battery to be detected based on the heights of the plurality of positive pole pieces and the negative pole pieces and the distance between every two adjacent positive pole pieces or negative pole pieces.
9. A pole piece defect detection device, comprising:
the information acquisition module is used for acquiring pole piece image information of a battery to be detected, wherein the battery to be detected comprises a plurality of pole pieces;
the key point acquisition module is used for inputting the pole piece image information into a key point model to obtain key point data in the pole piece image information, wherein the key point data is used for reflecting the end point positions of each pole piece in the battery to be detected;
the region acquisition module is used for inputting the pole piece image information into a segmentation model to obtain segmentation regions in the pole piece image information, wherein the segmentation regions are used for reflecting regions where end points of each pole piece in the battery to be detected are located;
the determining module is used for determining the endpoint coordinates of each pole piece in the battery to be detected according to the key point data and/or the segmentation areas;
and the detection module is used for detecting the defects of the pole piece of the battery to be detected according to the endpoint coordinates.
10. A non-transitory machine-readable storage medium having stored thereon executable code which, when executed by a processor of an electronic device, causes the processor to perform the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311216382.7A CN117291882A (en) | 2023-09-19 | 2023-09-19 | Pole piece defect detection method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311216382.7A CN117291882A (en) | 2023-09-19 | 2023-09-19 | Pole piece defect detection method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117291882A true CN117291882A (en) | 2023-12-26 |
Family
ID=89256577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311216382.7A Pending CN117291882A (en) | 2023-09-19 | 2023-09-19 | Pole piece defect detection method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117291882A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611591A (en) * | 2024-01-24 | 2024-02-27 | 俐玛精密测量技术(苏州)有限公司 | Industrial CT detection method and device for battery cell defects, electronic equipment and storage medium |
| CN117974632A (en) * | 2024-03-28 | 2024-05-03 | 大连理工大学 | Lithium battery CT cathode-anode alignment detection method based on segmentation large model |
-
2023
- 2023-09-19 CN CN202311216382.7A patent/CN117291882A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611591A (en) * | 2024-01-24 | 2024-02-27 | 俐玛精密测量技术(苏州)有限公司 | Industrial CT detection method and device for battery cell defects, electronic equipment and storage medium |
| CN117611591B (en) * | 2024-01-24 | 2024-05-14 | 俐玛精密测量技术(苏州)有限公司 | Industrial CT detection method and device for battery cell defects, electronic equipment and storage medium |
| CN117974632A (en) * | 2024-03-28 | 2024-05-03 | 大连理工大学 | Lithium battery CT cathode-anode alignment detection method based on segmentation large model |
| CN117974632B (en) * | 2024-03-28 | 2024-06-07 | 大连理工大学 | Lithium battery CT cathode-anode alignment detection method based on segmentation large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117291882A (en) | Pole piece defect detection method, device and storage medium | |
| CN106934800B (en) | Metal plate strip surface defect detection method and device based on YOLO9000 network | |
| CN114723942B (en) | Method, device and equipment for detecting size of lithium battery pole piece and storage medium | |
| TW202217750A (en) | Systems and methods of optimal metrology guidance | |
| KR101667471B1 (en) | Defect determination device, radiography system, and defect determination method | |
| CN115731165B (en) | Detection system and method for on-line size spot inspection of lithium battery | |
| CN103606221A (en) | Fault automatic diagnostic method of counter and device | |
| CN115035061A (en) | Method for extracting cathode and anode points of battery cell electrode group and detecting alignment degree of cathode and anode sheets | |
| CN115018902A (en) | Method and processor for determining inventory of media piles | |
| CN117611591B (en) | Industrial CT detection method and device for battery cell defects, electronic equipment and storage medium | |
| CN116773559A (en) | Laminated lithium ion battery detection method and device and image processing equipment | |
| CN114581446B (en) | Battery core abnormity detection method and system of laminated battery | |
| CN110426395B (en) | Method and device for detecting surface of solar EL battery silicon wafer | |
| JP2017096943A (en) | Inspection apparatus, computer apparatus, and inspection method | |
| Guo et al. | Machine vision-based intelligent manufacturing using a novel dual-template matching: a case study for lithium battery positioning | |
| US11176351B2 (en) | Fingerprint identification method and apparatus, storage medium and terminal | |
| CN108037503B (en) | Laser radar-based planar multi-plate positioning method for feeding and discharging of household plates | |
| CN111256609B (en) | Method and device for detecting USB interface depth | |
| CN115020174A (en) | Method for measuring and monitoring actual pixel size of charged particle beam scanning imaging equipment | |
| CN108053404B (en) | Efficient positioning method for lithium battery coating boundary | |
| CN116012330B (en) | Pole piece defect detection method, device, equipment and computer storage medium | |
| CN114240946B (en) | Locator abnormality detection method, system, storage medium and computing device | |
| CN116586925B (en) | Large-scale bearing retainer production method, equipment and medium based on images | |
| CN114782429B (en) | Image-based lithium battery defect detection method, device, equipment and storage medium | |
| CN116793245B (en) | Tunnel detection method, equipment and medium based on track robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |