CN115963114B - Lithium battery production quality inspection system - Google Patents
Lithium battery production quality inspection system Download PDFInfo
- Publication number
- CN115963114B CN115963114B CN202310176798.4A CN202310176798A CN115963114B CN 115963114 B CN115963114 B CN 115963114B CN 202310176798 A CN202310176798 A CN 202310176798A CN 115963114 B CN115963114 B CN 115963114B
- Authority
- CN
- China
- Prior art keywords
- image
- quality inspection
- lithium battery
- production
- sub
- 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.)
- Active
Links
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 106
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 106
- 238000007689 inspection Methods 0.000 title claims abstract description 86
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 71
- 230000007547 defect Effects 0.000 claims abstract description 67
- 230000001502 supplementing effect Effects 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Classifications
-
- 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
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Secondary Cells (AREA)
Abstract
The invention belongs to the field of quality inspection, and discloses a lithium battery production quality inspection system, which comprises a shooting device and a computing device; the shooting device is used for shooting the lithium battery needing appearance identification to obtain a shooting image; the computing device is used for judging whether the production batch of the lithium battery corresponding to the current shot image is the same as that of the lithium battery corresponding to the previous shot image, if the production batch is the same, judging whether the previous shot image has defects, if so, adopting a first image recognition mode to carry out quality inspection on the current shot image, and if not, adopting a second image recognition mode to carry out quality inspection on the current shot image; and if the production batches are different, adopting a second image recognition mode to carry out quality inspection on the current shooting image. The invention improves the quality inspection efficiency of the lithium battery.
Description
Technical Field
The invention relates to the field of quality inspection, in particular to a quality inspection system for lithium battery production.
Background
The lithium battery needs to carry out quality inspection to the outward appearance in the production process, judges whether there is the surface of lithium battery to scratch, characteristics that the swell etc. do not accord with the quality inspection requirement, and traditional quality inspection mode is artifical quality inspection, but artifical quality inspection has the inefficiency problem, consequently, the prior art generally all adopts image recognition's mode to carry out quality inspection. In the existing system for quality inspection of the appearance of the lithium battery, in the quality inspection process, all pixels of an image A of the lithium battery to be inspected and an image B of a standard lithium battery are required to be compared one by one in sequence, so that whether the appearance of the lithium battery meets the quality inspection requirement can be known, and the pixels in the image A and the pixels in the image B are compared one by one in sequence from left to right and from top to bottom. When the pixel ordering of the defective part in the appearance image of the lithium battery is later, for example, when the defective part is positioned at the lower right corner of the image A, the comparison of the previous pixel belongs to invalid comparison, so that the judgment result of whether the quality inspection requirement is met or not is difficult to obtain quickly, and the efficiency of quality inspection on the appearance of the lithium battery is reduced.
Disclosure of Invention
The invention aims to disclose a lithium battery production quality inspection system, which solves the problem of how to improve the efficiency of quality inspection on the appearance of a lithium battery.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a lithium battery production quality inspection system comprises a shooting device and a computing device;
the shooting device is used for shooting the lithium battery needing appearance identification to obtain a shooting image;
the computing device is used for judging whether the production batch of the lithium battery corresponding to the current shot image is the same as that of the lithium battery corresponding to the previous shot image, if the production batch is the same, judging whether the previous shot image has defects, if so, adopting a first image recognition mode to carry out quality inspection on the current shot image, and if not, adopting a second image recognition mode to carry out quality inspection on the current shot image;
if the production batches are different, adopting a second image recognition mode to carry out quality inspection on the current shooting image;
the first image recognition mode comprises the following steps:
partitioning the current shooting image to obtain a plurality of sub-images with the same size;
sorting different sub-images in the current shooting image according to the defect position of the previous shooting image to obtain a sorting result;
performing image recognition on the sub-images according to the sorting result, stopping performing image recognition when the defects in the sub-images are recognized, and outputting a quality inspection result;
the second image recognition method comprises the following steps:
comparing pixel points in the current shooting image with pixel points in the standard lithium battery appearance image one by one according to the sequence from left to right and from top to bottom to obtain a comparison image;
and obtaining a quality inspection result according to the comparison image.
Optionally, the lithium battery production quality inspection system further comprises a storage device, wherein the storage device is used for storing the total number of lithium batteries in different production batches.
Optionally, the calculating device is configured to count the shot images of lithium batteries in the same production lot, and when the accumulated number is greater than the total number of lithium batteries in the corresponding production lot stored in the storage device, the accumulated number is cleared, and the counting is performed again.
Optionally, determining whether the production lot of the lithium battery corresponding to the current shot image and the production lot of the lithium battery corresponding to the previous shot image are the same includes:
if the accumulated number corresponding to the current shooting image is smaller than or equal to the total number of lithium batteries in the production lot corresponding to the current shooting image, the lithium batteries corresponding to the current shooting image are identical to the production lot of the lithium batteries corresponding to the previous shooting image;
if the accumulated number corresponding to the current shooting image is greater than the total number of lithium batteries of the production lot corresponding to the current shooting image, the lithium batteries corresponding to the current shooting image are different from the production lot of the lithium batteries corresponding to the previous shooting image.
Optionally, the shooting device comprises a camera and a light supplementing device;
the light supplementing device is used for supplementing light for the camera when the illumination intensity of the environment where the camera is located is lower than a set intensity threshold value;
the camera is used for shooting the lithium battery to obtain a shooting image.
Optionally, the lithium battery production quality inspection system further comprises a conveyor belt device, wherein the conveyor belt device is used for conveying the lithium battery needing appearance identification to the position right below the camera.
Optionally, sorting different sub-images in the current shot image according to the defect position of the previous shot image to obtain a sorting result, including:
respectively calculating the distance between the center of each sub-image and the defect position;
and sequencing the sub-images according to the sequence from small to large to obtain a sequencing result.
Optionally, the quality inspection result meets the quality inspection requirement or does not meet the quality inspection requirement.
Optionally, in the first image recognition mode, if the quality inspection result does not meet the quality inspection requirement, the center of the sub-image with the defect is identified as the defect position;
in the second image recognition mode, if the quality inspection result does not meet the quality inspection requirement, the average coordinates of the pixel points corresponding to the defects with the largest area are taken as defect positions.
Compared with the prior art, the method has the advantages that the quality of the lithium batteries subjected to appearance quality inspection is inspected according to whether the production batches are the same or not in different modes, and the lithium batteries in the same production batch are identified according to whether the previous lithium batteries have defects or not in different identification modes. For lithium batteries in the same production batch, if production defects exist, the types and positions of the defects are always the same, so that after the sub-images are ordered, the probability of defects in the front sub-images is relatively high, even if the positions of the defects are positioned at the lower right corner of the images, the identification result can be obtained by carrying out image identification on a small number of pixel points, and therefore the quality inspection efficiency is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention.
Fig. 1 is a schematic diagram of a lithium battery production quality inspection system according to the present invention.
Fig. 2 is another schematic diagram of a lithium battery production quality inspection system according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. In addition, the embodiments of the present invention and the features in the embodiments may be combined with each other without collision. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than within the scope of the description, and the scope of the invention is therefore not limited to the specific embodiments disclosed below.
In one embodiment shown in fig. 1, the invention provides a lithium battery production quality inspection system, which comprises a shooting device 1 and a computing device 2;
the shooting device 1 is used for shooting a lithium battery which needs appearance recognition to obtain a shooting image;
the computing device 2 is configured to determine whether a production lot of a lithium battery corresponding to a current captured image is the same as a production lot of a lithium battery corresponding to a previous captured image, if the production lot is the same, determine whether a defect exists in the previous captured image, if yes, perform quality inspection on the current captured image by using a first image recognition mode, and if not, perform quality inspection on the current captured image by using a second image recognition mode;
if the production batches are different, adopting a second image recognition mode to carry out quality inspection on the current shooting image;
the first image recognition mode comprises the following steps:
partitioning the current shooting image to obtain a plurality of sub-images with the same size;
sorting different sub-images in the current shooting image according to the defect position of the previous shooting image to obtain a sorting result;
performing image recognition on the sub-images according to the sorting result, stopping performing image recognition when the defects in the sub-images are recognized, and outputting a quality inspection result; in addition, after all the sub-images are identified, if no defect is found, a quality inspection result is also output;
the second image recognition method comprises the following steps:
comparing pixel points in the current shooting image with pixel points in the standard lithium battery appearance image one by one according to the sequence from left to right and from top to bottom to obtain a comparison image;
and obtaining a quality inspection result according to the comparison image.
Compared with the prior art, the method has the advantages that the quality of the lithium batteries subjected to appearance quality inspection is inspected according to whether the production batches are the same or not in different modes, and the lithium batteries in the same production batch are identified according to whether the previous lithium batteries have defects or not in different identification modes. For lithium batteries in the same production batch, if production defects exist, the types and positions of the defects are always the same, so that after the sub-images are ordered, the probability of defects in the front sub-images is relatively high, even if the positions of the defects are positioned at the lower right corner of the images, the identification result can be obtained by carrying out image identification on a small number of pixel points, and therefore the quality inspection efficiency is improved.
Optionally, performing image recognition on the sub-image includes:
respectively calculating the difference value between each pixel point in the sub-image and the pixel point in the appearance image of the standard lithium battery;
calculating a defect estimation value of the sub-image according to the difference value;
if the defect estimated value is larger than the set defect threshold value, the defect estimated value indicates that the defect possibly exists in the sub-image, and the sub-image is input into a pre-trained neural network for recognition.
Specifically, because the time required for image recognition is relatively long, only the sub-images with relatively large defect estimation values are subjected to image recognition, so that the image recognition of all the sub-images can be avoided, the recognition efficiency of the first image recognition mode is improved, and the quality inspection efficiency of the lithium battery is improved.
Specifically, the standard image is an image obtained by the photographing device 1 photographing a lithium battery having no defect. The photographing conditions of the photographed image and the standard image are the same. The shooting conditions include the placement direction of the lithium battery, the distance between the lithium battery and the shooting device 1, the illumination intensity of the shooting environment, and the like. The same shooting conditions are kept, and the region with the changed pixel value can be obtained rapidly in the mode of image difference in the subsequent image recognition, so that whether defects exist or not is judged.
Optionally, calculating a difference between each pixel point in the sub-image and a pixel point in the appearance image of the standard lithium battery includes:
the sitting of the pixel point q in the sub-image in the photographed image is marked as (x) q ,y q )；
The coordinates (x) are obtained from the external image of the standard lithium battery q ,y q ) Is defined as pixel q';
the calculation function of the difference is:
diff q ＝pho(x q ,y q )-std(x q ,y q )
wherein diff is q Is the difference value corresponding to the pixel point q, pho (x q ,y q ) For the gradation value of the pixel point q in the captured image pho, std (x q ,y q ) In the external image std which is a standard lithium battery, the coordinates are (x q ,y q ) Pixel values of the pixel points of (c).
Specifically, the larger the difference value is, the greater the possibility of defects is, and therefore, the subsequent calculation of the defect estimation value can be performed after the difference value is calculated.
Optionally, calculating the defect estimation value of the sub-image according to the difference value includes:
for sub-image simg, defect estimates for simg are calculated using the following function:
in the above function, the defest simg For defect estimation of simg, λ is the sum weight, simcu is the set of pixel points in simg, diff i For the difference corresponding to pixel i in the set simcu, nsimigu is the total number of pixels in simcu, stdif is the set first comparison mean, stdch is the set second comparison mean, pho i The gray value of the pixel point i in the photographed image pho; pho i,lf The pixel value of the pixel point lf corresponding to the pixel point i in the comparison image is obtained.
Specifically, the defect estimation value considers not only the average value of the difference value of the gray values of the pixel points between the sub-image simg and the appearance image of the standard lithium battery, but also the average value of the difference value between the pixel points in the sub-image simg and the comparison image, if only the gray value difference value between the sub-image simg and the appearance image of the standard lithium battery is considered, the difference value of partial pixel points is likely to be higher, the difference value of partial pixel points is smaller, and finally the left numerical value of the calculation function of the defect estimation value is smaller, so that the sub-image is misjudged.
Optionally, in the first case, if the left boundary of the simg coincides with the left boundary of the captured image and the upper boundary of the simg coincides with the upper boundary of the captured image, the comparison image corresponding to the simg is a sub-image directly below the simg;
in the second case, if the left boundary of the simg coincides with the left boundary of the photographed image and the lower boundary of the simg coincides with the lower boundary of the photographed image, the comparison image corresponding to the simg is a sub-image directly above the simg;
in the third case, if the left boundary of the simg coincides with the left boundary of the photographed image and the upper boundary of the simg does not coincide with the upper boundary of the photographed image, the comparison image corresponding to the simg is a sub-image directly above the simg;
in the fourth case, if the simg does not match the above three cases, the comparative image corresponding to the simg is a sub-image on the left side of the simg.
Specifically, for sub-images at different positions, the above embodiment sets different acquisition modes of the comparison images, so that the invention can adaptively select the comparison images, and effectively avoid error calculation of the defect estimation value. If the peripheral boundary of the photographed image is filled as in the conventional image processing method, the calculation area is enlarged, and the values of the filled pixels are the same, so that the defect estimation values of the sub-images in the first case, the second case and the third case are larger, and an erroneous estimation result is obtained.
Alternatively, the comparison image is noted as simg', and the pixel point lf is determined as follows:
respectively taking the lower left corners of simg' and simg as the origin of coordinates to establish a rectangular coordinate system;
in the simg', the pixel point with the same coordinate as the pixel point i in the simg is the pixel point lf.
Optionally, partitioning the current captured image to obtain a plurality of sub-images with the same size, including:
n represents the serial number of the current shooting image;
if the shot image with the sequence number of n-1 is judged to have defects through the first image recognition mode, R is used n-1 Representing the size of a sub-image in the photographed image with the sequence number n-1;
the size R of the sub-image in the photographed image with the sequence number n n The calculation function of (2) is:
where ur is the single change in size of the sub-image, sg n Is the variance of pixel values of pixel points in a photographed image with a sequence number n, sg n-1 The variance of pixel values of pixel points in a shot image with the sequence number of n-1 is shown, wherein lsthre is a variance threshold; when R is n-1 When +ur is greater than the set maximum value mar, then R n When R is =mar n-1 When ur is smaller than the set minimum mir, then R n ＝mir；
Using R n Partitioning the current shooting image to obtain a plurality of sub-images with the same size;
if the shot image with the sequence number of n-1 is not judged to have defects through the first image recognition mode, the shot image is partitioned by the set size of the sub-image, and a plurality of sub-images with the same size are obtained.
In the prior art, the fixed sub-image size is generally adopted to partition the image, but in the invention, the position of the defect can be offset in different lithium batteries, so that the time for obtaining a quality inspection result can be prolonged by utilizing the sub-image with the fixed size, therefore, the invention sets the calculation function, when the difference value of the pixel value variance between the shooting image with the sequence number of n and the shooting image with the sequence number of n-1 is larger, the effective information amount in the shooting image with the sequence number of n is larger than that of the shooting image with the sequence number of n, the defect can be detected more easily, at the moment, the invention enlarges the size of the sub-image, so that the defect can be detected only by calculating fewer sub-images, and the defect can be detected more quickly, otherwise, the probability of detecting the defect can be improved by reducing the size of the sub-image.
Optionally, comparing the pixel points in the current photographed image with the pixel points in the standard lithium battery appearance image one by one according to the sequence from left to right and from top to bottom to obtain a comparison image, including:
and calculating the absolute value of the difference of the gray value between the pixel point in the current shooting image and the pixel point in the standard lithium battery appearance image one by one according to the sequence from left to right and from top to bottom, and taking the pixel point with the absolute value larger than the set absolute value threshold value in the current shooting image as the pixel point of the contrast image.
Optionally, obtaining the quality inspection result according to the comparison image includes:
and inputting the comparison image into a pre-trained neural network for recognition to obtain a quality inspection result.
Optionally, as shown in fig. 2, the lithium battery production quality inspection system further comprises a storage device 3, where the storage device 3 is used for storing the total number of lithium batteries in different production batches.
Optionally, the calculating device 2 is configured to count the shot images of lithium batteries in the same production lot, and when the accumulated number is greater than the total number of lithium batteries in the corresponding production lot stored in the storage device 3, the accumulated number is cleared, and the counting is performed again.
Specifically, the total number of lithium batteries in different production batches can be input into the storage device 3 in advance for storage by a manual input mode.
Optionally, determining whether the production lot of the lithium battery corresponding to the current shot image and the production lot of the lithium battery corresponding to the previous shot image are the same includes:
if the accumulated number corresponding to the current shooting image is smaller than or equal to the total number of lithium batteries in the production lot corresponding to the current shooting image, the lithium batteries corresponding to the current shooting image are identical to the production lot of the lithium batteries corresponding to the previous shooting image;
if the accumulated number corresponding to the current shooting image is greater than the total number of lithium batteries of the production lot corresponding to the current shooting image, the lithium batteries corresponding to the current shooting image are different from the production lot of the lithium batteries corresponding to the previous shooting image.
The distinction of production batches is mainly because the probability of the same defect occurrence position is larger for the same batch of products, so that the quality inspection result can be obtained more quickly by combining the quality inspection method.
Optionally, the photographing apparatus 1 includes a camera and a light supplementing device;
the light supplementing device is used for supplementing light for the camera when the illumination intensity of the environment where the camera is located is lower than a set intensity threshold value;
the camera is used for shooting the lithium battery to obtain a shooting image.
In particular, the light supplementing device may be a light supplementing lamp arranged around the camera.
Optionally, the lithium battery production quality inspection system further comprises a conveyor belt device, wherein the conveyor belt device is used for conveying the lithium battery needing appearance identification to the position right below the camera.
The quality inspection efficiency can be improved by conveying through the conveyor belt.
Optionally, sorting different sub-images in the current shot image according to the defect position of the previous shot image to obtain a sorting result, including:
respectively calculating the distance between the center of each sub-image and the defect position;
and sequencing the sub-images according to the sequence from small to large to obtain a sequencing result.
Specifically, the closer the defect position of the previous shot image is, the greater the possibility of defects is, and the greater the possibility of defects is in the process of identifying the sub-images arranged in front after the sorting.
Optionally, the quality inspection result meets the quality inspection requirement or does not meet the quality inspection requirement.
Optionally, in the first image recognition mode, if the quality inspection result does not meet the quality inspection requirement, the center of the sub-image with the defect is identified as the defect position;
in the second image recognition mode, if the quality inspection result does not meet the quality inspection requirement, the average coordinates of the pixel points corresponding to the defects with the largest area are taken as defect positions.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. The lithium battery production quality inspection system is characterized by comprising a shooting device and a calculating device;
the shooting device is used for shooting the lithium battery which needs appearance recognition to obtain a shooting image;
the computing device is used for judging whether the production batch of the lithium battery corresponding to the current shot image is the same as that of the lithium battery corresponding to the previous shot image, if the production batch is the same, judging whether the previous shot image has defects, if so, adopting a first image recognition mode to carry out quality inspection on the current shot image, and if not, adopting a second image recognition mode to carry out quality inspection on the current shot image;
if the production batches are different, adopting a second image recognition mode to carry out quality inspection on the current shooting image;
the first image recognition mode comprises the following steps:
partitioning the current shooting image to obtain a plurality of sub-images with the same size;
sorting different sub-images in the current shooting image according to the defect position of the previous shooting image to obtain a sorting result;
performing image recognition on the sub-images according to the sorting result, stopping performing image recognition when the defects in the sub-images are recognized, and outputting a quality inspection result;
the second image recognition method comprises the following steps:
comparing pixel points in the current shooting image with pixel points in the standard lithium battery appearance image one by one according to the sequence from left to right and from top to bottom to obtain a comparison image;
obtaining a quality inspection result according to the comparison image;
sorting different sub-images in the current shooting image according to the defect position of the previous shooting image to obtain a sorting result, wherein the sorting result comprises the following steps:
respectively calculating the distance between the center of each sub-image and the defect position;
and sequencing the sub-images according to the sequence from small to large to obtain a sequencing result.
2. The lithium battery production quality inspection system of claim 1, further comprising a storage device for storing a total number of lithium batteries of different production lots.
3. The lithium battery production quality inspection system according to claim 2, wherein the computing device is configured to count the shot images of lithium batteries of the same production lot, and when the accumulated number is greater than the total number of lithium batteries of the corresponding production lot stored in the storage device, the accumulated number is cleared, and the counting is performed again.
4. A lithium battery production quality inspection system according to claim 3, wherein determining whether a production lot of a lithium battery corresponding to a current captured image and a production lot of a lithium battery corresponding to a previous captured image are the same comprises:
if the accumulated number corresponding to the current shooting image is smaller than or equal to the total number of lithium batteries in the production lot corresponding to the current shooting image, the lithium batteries corresponding to the current shooting image are identical to the production lot of the lithium batteries corresponding to the previous shooting image;
if the accumulated number corresponding to the current shooting image is greater than the total number of lithium batteries of the production lot corresponding to the current shooting image, the lithium batteries corresponding to the current shooting image are different from the production lot of the lithium batteries corresponding to the previous shooting image.
5. The lithium battery production quality inspection system of claim 1, wherein the photographing device comprises a camera and a light supplementing device;
the light supplementing device is used for supplementing light for the camera when the illumination intensity of the environment where the camera is located is lower than a set intensity threshold value;
the camera is used for shooting the lithium battery to obtain a shooting image.
6. The lithium battery production quality inspection system of claim 5, further comprising a conveyor belt device for transporting the lithium battery to be visually identified to a position directly below the camera.
7. The lithium battery production quality inspection system according to claim 1, wherein the quality inspection result is a quality inspection requirement or a quality inspection non-requirement.
8. The system according to claim 7, wherein in the first image recognition mode, if the quality inspection result is not in accordance with the quality inspection requirement, the center of the sub-image in which the defect is recognized is taken as the defect position;
in the second image recognition mode, if the quality inspection result does not meet the quality inspection requirement, the average coordinates of the pixel points corresponding to the defects with the largest area are taken as defect positions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310176798.4A CN115963114B (en) | 2023-02-28 | 2023-02-28 | Lithium battery production quality inspection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310176798.4A CN115963114B (en) | 2023-02-28 | 2023-02-28 | Lithium battery production quality inspection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115963114A CN115963114A (en) | 2023-04-14 |
| CN115963114B true CN115963114B (en) | 2023-07-28 |
Family
ID=85889868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310176798.4A Active CN115963114B (en) | 2023-02-28 | 2023-02-28 | Lithium battery production quality inspection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115963114B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152236B (en) * | 2023-04-18 | 2023-07-07 | 钛玛科（北京）工业科技有限公司 | Visual detection method and system for lithium battery adhesive tape |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103149215B (en) * | 2013-02-27 | 2016-04-13 | 中国计量学院 | A kind of toughened glass insulator defect inspection method and device |
| CN103499585B (en) * | 2013-10-22 | 2015-07-29 | 常州工学院 | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision |
| CN104777172B (en) * | 2015-04-30 | 2018-10-09 | 重庆理工大学 | A kind of quick, intelligent detection device of optical lens substandard products and method |
| CN114387233A (en) * | 2021-12-29 | 2022-04-22 | 山东大学 | Sand mold defect detection method and system based on machine vision |
-
2023
- 2023-02-28 CN CN202310176798.4A patent/CN115963114B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115963114A (en) | 2023-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105608671B (en) | A kind of image split-joint method based on SURF algorithm | |
| CN103903005B (en) | License plate image identification system and method | |
| US20200134857A1 (en) | Determining positions and orientations of objects | |
| CN115963114B (en) | Lithium battery production quality inspection system | |
| US20060193511A1 (en) | Object determining apparatus | |
| CN111192326B (en) | Method and system for visually identifying direct-current charging socket of electric automobile | |
| CN111062938B (en) | Plate expansion plug detection system and method based on machine learning | |
| CN112052782B (en) | Method, device, equipment and storage medium for recognizing parking space based on looking around | |
| CN114820773A (en) | Silo transport vehicle carriage position detection method based on computer vision | |
| CN113012157B (en) | Visual detection method and system for equipment defects | |
| Willamowski et al. | Probabilistic automatic red eye detection and correction | |
| CN116559183A (en) | Method and system for improving defect judging efficiency | |
| CN111539311A (en) | Living body distinguishing method, device and system based on IR and RGB double photographing | |
| CN112881430A (en) | Display screen defect monitoring system based on image recognition and detection method thereof | |
| CN115953398A (en) | Defect identification method for strip steel surface | |
| CN109344758B (en) | Face recognition method based on improved local binary pattern | |
| US11530993B2 (en) | Deposit detection device and deposit detection method | |
| CN114004858A (en) | Method and device for identifying aviation cable surface code based on machine vision | |
| CN115532620B (en) | Pulp molding product quality inspection device and method | |
| WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium | |
| CN112338898A (en) | Image processing method and device of object sorting system and object sorting system | |
| CN115330710B (en) | Cloud computing-based automobile wire harness quality inspection system | |
| CN114972317B (en) | Square grain placement planning method | |
| CN109934817A (en) | The external contouring deformity detection method of one seed pod | |
| US20220076428A1 (en) | Product positioning method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Quality Inspection System for Lithium Battery Production Granted publication date: 20230728 Pledgee: Bank of China Co.,Ltd. Dongguan Branch Pledgor: Guangdong Kunpeng Environmental Protection Technology Co.,Ltd. Registration number: Y2024980011988 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |