CN111307818A - Visual online detection method for laser welding spot of lithium battery tab - Google Patents
Visual online detection method for laser welding spot of lithium battery tab Download PDFInfo
- Publication number
- CN111307818A CN111307818A CN202010114940.9A CN202010114940A CN111307818A CN 111307818 A CN111307818 A CN 111307818A CN 202010114940 A CN202010114940 A CN 202010114940A CN 111307818 A CN111307818 A CN 111307818A
- Authority
- CN
- China
- Prior art keywords
- image
- lug
- tab
- pcm
- battery cell
- 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.)
- Granted
Links
- 238000003466 welding Methods 0.000 title claims abstract description 146
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 44
- 230000000007 visual effect Effects 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 51
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 230000009466 transformation Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000001131 transforming effect Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 229910000679 solder Inorganic materials 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 2
- 238000005286 illumination Methods 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims 1
- 230000037303 wrinkles Effects 0.000 description 8
- 238000005452 bending Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 6
- 230000002950 deficient Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012858 packaging process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/10004—Still image; Photographic 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biochemistry (AREA)
- Theoretical Computer Science (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Connection Of Batteries Or Terminals (AREA)
Abstract
The invention discloses a visual online detection method for a laser welding spot of a lithium battery tab, which comprises the following steps: acquiring a PCM lug global image and a battery cell lug global image; dividing the global image to obtain a local image of the lithium battery tab; judging the contrast of the local image of the tab; obtaining a lug image from the local lug image by adopting a corresponding method according to the judged contrast result; detecting welding spots of the PCM tab image by adopting a corresponding method according to the judged contrast; mapping and pre-estimating welding spot coordinates in the battery cell lug image through the detected welding spot coordinates in the PCM lug image and pre-acquired calibration information; generating a square ROI (region of interest) by taking each obtained mapping pre-estimated welding spot coordinate as a center in the battery cell tab image; and detecting welding points in the square ROI to obtain actual welding point coordinates in the battery cell tab image. The method solves the problem that the welding spot of the folded tab is difficult to detect by the traditional visual algorithm, realizes the detection accuracy and meets the requirement of online detection.
Description
Technical Field
The invention relates to the field of laser welding spot detection in an automatic packaging process of a lithium battery, in particular to a visual online detection method for a laser welding spot of a lithium battery tab.
Background
With the continuous development of machine vision technology, visual defect detection is more and more widely applied in the industrial field. At present, a machine vision method is generally adopted in an automatic Pack packaging process of lithium batteries of digital products such as mobile phones and the like to perform defect online detection on welding spots of laser welding of a lithium battery cell lug and a PCM (circuit protection module) plate lug. However, since the material of the cell tab is very soft and thin, the cell tab is very easy to wrinkle and bend. The fold of the tab is easy to generate low contrast and local shadow imaging characteristics, and the bending and inclination of the tab is easy to cause the tab image to generate integral shadow characteristics. Therefore, the image characteristics of the battery cell tab seriously affect the welding spot identification of the traditional visual algorithm, and the problem that the welding spots cannot be identified or the number of the welding spots is omitted or increased is caused, so that the defective product is judged to be unqualified by mistake. Aiming at the problem, a detection equipment manufacturer adopts a method of adding a rolling and wrinkle removing process before a visual detection station, but the method has obvious defects: the production takt time is reduced, the production cost is improved, and the wrinkle removing effect is obviously reduced after the wrinkle removing agent is used for a period of time.
At present, the welding spot defect detection of the battery core lug and the PCM plate lug of the lithium battery adopts a traditional visual detection algorithm, and the main algorithm comprises the following steps: shape template matching, blob analysis, contour matching, etc.; the pretreatment algorithm typically has: gray scale linear transformation, erosion, dilation, etc. Once the image has local shadows or the whole image has low contrast characteristics, the welding spot detection methods such as the matching detection algorithm and the spot analysis are often disabled. It is still difficult to improve or solve the problem of image quality degradation caused by tab wrinkling and bending tilt in a universal manner. Therefore, the traditional visual detection algorithm is difficult to realize visual welding point identification under the conditions of tab folding and bending inclination.
Because the traditional visual detection method cannot effectively solve the detection problem caused by the wrinkles of the lithium battery tabs, the manual visual inspection method for the welding spots of the lithium battery is still largely used. However, the manual visual inspection method has the defects of low efficiency, unstable effect and the like. Therefore, it is very important to provide an effective visual welding point detection method for the image quality degradation caused by the wrinkle and bending inclination of the lithium battery tab.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a visual online detection method for a laser welding point of a lithium battery tab. The method solves the problem that the conventional detection method is difficult to detect the welding spot of the folded tab, and simultaneously meets the requirements on detection accuracy and online detection. According to the method, a specific detection algorithm is selected according to the contrast of the lug image, and the ROI is reduced and detected according to the positioning relation.
The purpose of the invention can be realized by the following technical scheme:
a visual online detection method for laser welding spots of a lithium battery tab comprises the following steps:
acquiring a PCM (circuit protection module) lug global image and a battery cell lug global image;
dividing the PCM plate lug global image and the battery cell lug global image to obtain a lithium battery lug local image;
judging the contrast of the obtained local image of the lithium battery tab;
extracting a lug ROI from the local lug image by adopting a corresponding method according to the judged contrast result to obtain a PCM lug image and a battery cell lug image;
detecting welding spots of the PCM tab image by adopting a corresponding method according to the judged contrast;
mapping and pre-estimating welding spot coordinates in the battery cell lug image through the detected welding spot coordinates in the PCM lug image and pre-acquired calibration information;
generating a square ROI (region of interest) by taking each obtained mapping pre-estimated welding spot coordinate as a center in the battery cell tab image;
and detecting welding points in the square ROI, and if the welding points are detected, compensating the pre-estimated welding point coordinates to obtain the actual welding point coordinates in the battery cell tab image.
Specifically, in the step of collecting the PCM tab global image and the cell tab global image, 2 groups of dome light sources and a black-and-white industrial camera module are adopted to collect the global image of the cell tab and the PCM plate tab of the lithium battery.
The light source adopts blue light for illumination; the two industrial cameras are oppositely arranged, and the lithium battery is positioned between the two industrial cameras during image acquisition; the two cameras respectively acquire a PCM plate lug global image and a battery cell lug global image; the lug global image covers the left lug and the right lug by 2; the two industrial camera modules (cameras and lenses) are completely the same, and the overlapped area of the view fields needs to completely cover the left lug and the right lug; the imaging effect that the exposure time of the camera and the light intensity of the light source are combined to achieve is that the gray value of the normal non-wrinkled lug in an image is 255.
Specifically, in the step of dividing the PCM plate lug global image and the cell lug global image, the cell lug global image is divided into a cell left lug local image and a cell right lug local image; the PCM lug global image is divided into a PCM plate left lug local image and a PCM plate right lug local image. Each lug local image is required to completely contain the lug outline, and the lug local image should cover all possible positions of the lithium battery lug in the global image due to lithium battery clamping errors.
Specifically, the step of judging the contrast of the obtained local image of the lithium battery tab includes:
dividing the gray histogram statistical result of the local image of the lug into 3 intervals: a low gray value interval, a medium gray value interval and a high gray value interval;
the gray level of a background area, far away from light source irradiation, around the lithium battery in the local image of the tab is in a low gray level value interval, and the range is about 0 to 20; the gray level of the welding spot on the lug in the local image of the lug, the local shadow caused by the folded lug or the integral lug shadow caused by the bending and the inclination of the lug is in a middle gray level range, and the range is about 30 to 80; the gray level of a non-welding point area of a normal tab without wrinkles in a local image of the tab is in a high gray value interval, and the range is about 200 to 255;
by high gray value interval pixel sum ShAnd the sum of pixels and S in the interval of medium gray valuesmJudging the contrast of the local image of the tab:
if delta is larger than or equal to a preset constant const, judging the local image of the lug as normal contrast, otherwise, judging the local image of the lug as low contrast; the constant const refers to a quotient of the pixel number sum of the high gray value interval and the pixel number sum of the medium gray value interval of a wrinkle-free normal tab image, and can be continuously accumulated and averaged in real-time operation to reduce errors.
Specifically, in the step of extracting the electrode lug ROI from the electrode lug local image by adopting a corresponding method according to the judged contrast result, the electrode lug ROI extracted from the electrode lug local image needs to satisfy: the ROI left edge coincides with the left edge of the lug outline, the ROI right edge coincides with the right edge of the lug outline, and the ROI lower edge coincides with the lower edge of the lug outline.
Specifically, the step of extracting the tab ROI from the tab local image by a corresponding method according to the determined contrast result includes:
for a lug local image with normal contrast, thresholding is carried out by adopting an OTSU algorithm, and a method for searching a minimum external rectangle is adopted in a binary image, wherein the rectangle with the largest area in all external rectangles is a lug ROI;
for a local image of the lug with low contrast, thresholding is carried out by adopting an accumulated gray pixel number approximation method, and a method for searching a minimum circumscribed rectangle is adopted in a binary image, wherein the rectangle with the largest area in all circumscribed rectangles is the ROI of the lug;
and obtaining a tab ROI which is a tab image.
Furthermore, the thresholding by using the cumulative gray-scale pixel approximation method specifically includes: under normal conditions, the lug is 255 gray-scale values in the image, the pixel sum floats around an average value T, and the pixel length of the local image of the lug isl, the number of pixels corresponding to each gray value in the local image of the low-contrast tab is NiWherein i represents a gray value, N represents the number of pixels, S represents the sum of pixels accumulated by decreasing 1 from 255 gray level, when the sum is accumulated until S is greater than T for the first time, the accumulation is stopped and a gray value N is obtained, when the gray value is N, if the difference of subtracting T from S is greater than 2l, then 255 subtracting N is a threshold value T, if the difference of subtracting T from S is less than or equal to 2l, then 256 subtracting N is a threshold value T, and the thresholding operation is performed by taking T as a parameter. The parameter T is obtained by counting the number of 255 gray pixels of a normal image of the non-wrinkled battery cell tab and a normal image of the non-wrinkled PCM tab in advance, and can be continuously accumulated in real-time operation to calculate an average value and update the T.
The solving formula of the threshold t is as follows:
specifically, in the step of performing the welding point detection of the PCM tab image by adopting the corresponding method according to the judged contrast, the PCM tab image with the normal contrast is obtained after the local PCM tab image with the normal contrast is extracted, and the PCM tab image with the low contrast is obtained after the local PCM tab image with the low contrast is extracted. And detecting welding points of the PCM tab image with normal contrast by adopting a spot analysis or Hough circle transformation method.
Specifically, in the step of performing welding point detection on the PCM tab image by a corresponding method according to the determined contrast, for the PCM tab image with low contrast, the welding point detection step includes:
performing histogram equalization processing on the PCM tab image;
carrying out filtering processing by adopting a Log-Gabor even filter, and carrying out Hough circle transformation on a detection circle after the filtering processing;
varying the parameter σ of a Log-Gabor even filter0Repeating the filtering process and detecting the number of circlesSecondly;
and accumulating the circle results detected by Hough circle transformation after each Log-Gabor even filtering, and performing screening operation together, and finally reserving a real welding spot.
Further, the step of accumulating circle results detected by the hough circle transform after each Log-Gabor even filtering, and performing the screening operation includes:
circularly traversing from the first circle, combining circles with the coordinate distance of the circle center smaller than epsilon, wherein the circle center coordinate of the new circle is the average value of the circle center coordinates of the combined circles, and marking the number of the combined circles;
arranging all circles from small to large according to the x coordinate of the circle center, and if the x coordinate distance between two adjacent circles is less than epsilonxThen the two circular x-coordinates are considered to be identical;
counting the number sum of all merged circles under the same x coordinate, if the sum is more than or equal to CxKeeping all circles under the x coordinate, otherwise, deleting the circles;
arranging all circles reserved in the previous step from small to large according to the y coordinate of the circle center, and if the y coordinate distance between two adjacent circles is less than epsilonyThen the two circular y-coordinates are considered to be identical;
counting the number sum of all merged circles under the same y coordinate, if the sum is more than or equal to CyKeeping all circles under the y coordinate, otherwise, deleting the circles;
arranging all circles reserved in the previous step from small to large according to the x coordinate of the circle center, and if the x coordinate distance between two adjacent circles is less than epsilonxThen the two circular x-coordinates are considered to be identical;
counting the sum of all merged circles under the same x coordinate, if the sum is more than or equal to Cx' then keep all circles under the x coordinate, otherwise delete;
wherein C isx′>Cx。
Specifically, in the step of mapping and estimating the welding spot coordinates in the battery cell tab image through the welding spot coordinates in the detected PCM tab image and the pre-acquired calibration information, the welding spot coordinates of the PCM right tab image and the battery cell left tab image are transformed, and the transformation formula is as follows:
wherein, the { BL } is a battery cell left lug image coordinate system, the { FR } is a PCM right lug image coordinate system, the origin points of the coordinate systems are the upper left corners of the images, the right direction is the positive x direction, the downward direction is the positive y direction, and P isijRepresents a welding point coordinate vector, wherein i represents a row, j represents a column, and the PCM right tab image length w1High h is1Cell left tab image length w1', height h1', a ', b ' are pre-calibration information read from txt document, a is welding point P in PCM right tab imageCalibrationPixel length from left edge of image, b is P in PCM right tab imageCalibrationThe pixel length from the bottom edge of the image, a' is the welding point P corresponding to the left tab image of the battery cellCalibration'Pixel Length from right edge of image, b' is welding point P corresponding to left tab image of cellCalibration' pixel length from the bottom edge of the image.
Transforming the welding spot coordinates of the PCM left lug image and the battery cell right lug image, wherein the transformation formula is as follows:
wherein, the { BR } is a battery cell right lug image coordinate system, the { FL } is a PCM left lug image coordinate system, the origin points of the coordinate systems are the upper left corners of the images, the right direction is the positive x direction, the downward direction is the positive y direction, and P ismnRepresents a welding point coordinate vector, wherein m represents a row, n represents a column, and the PCM left tab image length w2High h, h2Battery cell right electrode ear image length w2', high h2', c ', d ' are pre-calibration information read from txt document, c is welding point P in PCM left tab imageCalibrationPixel length from right edge of image, d is P in PCM left tab imageCalibrationPixel length from bottom edge of imageDegree, c' is the corresponding welding point P of the battery cell right lug imageCalibration'Pixel Length from left edge of image, d' is welding Point P corresponding to right tab image of cellCalibration' pixel length from the bottom edge of the image.
Furthermore, in the process of transforming the welding point coordinates of the PCM right tab image and the battery cell left tab image, the obtaining of the pre-calibration information is obtained in advance through an additional program, specifically:
inputting a PCM plate lug global image and a battery cell lug global image of a normal non-wrinkled lug;
obtaining a PCM right lug image and a battery cell left lug image through contrast judgment and lug ROI extraction;
(ii) specifying a solder point location in the PCM right tab imageFRx,FRy), solving a and b, and calculating the formula as follows:
(a position corresponding to the welding point of the PCM right lug is appointed in the image of the left lug of the battery cellBLx,BLy), solving a 'and b', and calculating the formula as follows:
the values of a, b, a ', b' are saved in an xml or txt file.
Furthermore, in the process of transforming the welding point coordinates of the PCM left tab image and the battery cell right tab image, the obtaining of the pre-calibration information is obtained in advance through an additional program, specifically:
inputting a PCM plate lug global image and a battery cell lug global image of a normal non-wrinkled lug;
obtaining a PCM right lug image and a battery cell left lug image through contrast judgment and lug ROI extraction;
specifying a solder point location in the PCM left tab imageFLx, FLy), solving for c, d, and countingThe calculation formula is as follows:
(a position corresponding to the welding point of the PCM left lug is appointed in the image of the battery cell right lugBRx,BRy), solving c ', d', and calculating the formula as follows:
the values of c, d, c ', d' are saved in an xml or txt file.
The pre-calibration information read from the txt file can only use a, b, a ', b' or only use c, d, c ', d'; when only a, b, a ', b' are used, use
Instead of the former
By using
Instead of the former
When only c, d, c ', d' are used, use
Instead of the former
By using
Instead of the former
And can be accumulated and averaged by repeatedly recording a, b, a ', b', c, d, c 'and d' in real-time operation,thereby reducing the error.
Specifically, in the step of detecting the welding spot in the square ROI to obtain the actual welding spot coordinate in the image of the battery cell tab, the welding spot is searched for the square ROI by adopting a spot analysis method, if the welding spot cannot be searched by the spot analysis, histogram equalization processing is carried out on the image, and then the welding spot is detected and searched by using the Hoff circle. The formula for compensating the mapped coordinates of the welding points of the electrode lugs of the battery cell through the search result in the square ROI is as follows (the origin of an image coordinate system is in the upper left corner):
wherein J is the welding point coordinate under the actual battery core tab image coordinate system, (x)temp,ytemp) The coordinates of the weld points in the Square ROI image coordinate system Square, l the length of the Square ROI, only the one closest to the center of the rectangle if multiple circles are detected. Wherein the side length l of the ROI is a preset parameter and is related to the installation position and model selection type of the image acquisition mechanism, and the length of the pixel is about 2 times of the diameter of the circle of the welding spot
Compared with the prior art, the invention has the following beneficial effects:
(1) on the basis of not increasing hardware cost, the problem that a traditional algorithm is unqualified in good product misjudgment caused by folded tab image detection is solved.
(2) The invention meets the real-time requirement of actual automatic production.
Drawings
FIG. 1 is a flow chart of a visual online detection method for laser welding spots of a lithium battery tab;
fig. 2 is a flowchart of local tab image contrast determination in an embodiment of the present invention;
FIG. 3 is a flow chart of low contrast PCM tab image processing in an embodiment of the present invention;
fig. 4 is a schematic diagram of obtaining calibration information in the step of mapping the welding point coordinates of the battery tab image from the welding point coordinates of the PCM tab image according to the embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a laser welding spot visual online detection system for a lithium battery tab in an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples and drawings, but the embodiments of the present invention are not limited thereto.
Examples
In this embodiment, a visual online detection system for laser welding spots of a tab of a lithium battery is provided, and the structure of the system is shown in fig. 5. In the system, a lithium battery 113 is conveyed to a visual detection station by a feeding mechanism 112 and is fixedly held by a clamp 114, and the visual detection station comprises dome light sources 106 and 108, industrial cameras 107 and 110, a light source controller 104, an image acquisition card 105, an operation processing and control unit 102 and a display device 101; after the lithium battery 113 is placed, the visual inspection method of the present invention starts.
As shown in fig. 1, a flow chart of a visual online detection method for a laser welding spot of a lithium battery tab includes the steps:
(1) acquiring a PCM (circuit protection module) lug global image and a battery cell lug global image;
in this embodiment, 2 sets of dome light sources 106, 108 and industrial cameras 107, 110 are employed for acquisition. The PCM tab global image and the cell tab global image with the size of 2592 × 1944 are obtained, 2 tabs on the left and right in each global image are shot, the tab without folds in the image is high-brightness, and the tab with folds has most shadows.
(2) Dividing the global image to obtain 4 local images of the lithium battery tabs;
the battery cell lug global image is divided into a battery cell left lug local image and a battery cell right lug local image; and the PCM lug global image is divided into a PCM plate left lug local image and a PCM plate right lug local image.
In the present embodiment, a rectangular region with a starting point (0,450), a length of 800, and a width of 600 is set as a local image of the left tab in the global image, and a rectangular region with a starting point (1700,600), a length of 800, and a width of 600 is set as a local image of the right tab. Therefore, the obtained lug outlines of the local image of the PCM left lug, the local image of the PCM right lug, the local image of the battery left lug and the local image of the battery right lug are completely positioned in the local images.
(3) Judging the contrast of the obtained local image of the lithium battery tab;
fig. 2 is a flowchart for determining the contrast of the obtained local image of the tab of the lithium battery, which includes the following steps:
(3-1) dividing the gray histogram statistical result of the local image of the lug into 3 intervals: a low gray value interval, a medium gray value interval and a high gray value interval;
the gray level of a background area, far away from light source irradiation, around the lithium battery in the local image of the tab is in a low gray level value interval, and the range is about 0 to 20; the gray level of the welding spot on the lug in the local image of the lug, the local shadow caused by the folded lug or the integral lug shadow caused by the bending and the inclination of the lug is in a middle gray level range, and the range is about 30 to 80; the gray level of a non-welding point area of a normal tab without wrinkles in a local image of the tab is in a high gray value interval, and the range is about 200 to 255;
(3-2) passing the high gray value interval pixel and ShAnd the sum of pixels and S in the interval of medium gray valuesmJudging the contrast of the local image of the lug:
if delta is larger than or equal to a preset constant const, judging the local image of the lug as normal contrast, otherwise, judging the local image of the lug as low contrast; the constant const refers to a quotient of the pixel number sum of the high gray value interval and the pixel number sum of the medium gray value interval of a wrinkle-free normal tab image, and can be continuously accumulated and averaged in real-time operation to reduce errors.
In this embodiment, a constant const is taken as 3, a gray histogram of the PCM left tab local image is counted, the sum of the number of pixels in the high gray value interval is 10 times of the sum of the number of pixels in the medium gray value interval, the tab image with normal contrast is determined, and the sum of the number of pixels in the high gray value interval in the PCM right tab local image is 1.5 times of the sum of the number of pixels in the medium gray value interval, and the tab image with low contrast is determined; similarly, the battery cell left tab is judged to be low in contrast, and the battery cell right tab is judged to be normal in contrast.
(4) Extracting a tab ROI from the partial image of the tab by adopting a corresponding method according to the judged contrast result to obtain a tab image;
the electrode lug ROI extracted from the electrode lug local image meets the following requirements: the ROI left edge is coincided with the pole lug outline left edge, the ROI right edge is coincided with the pole lug outline right edge, and the ROI lower edge is coincided with the pole lug outline lower edge.
In the embodiment, different threshold parameters are adopted to perform threshold image segmentation to extract the tab ROI according to the contrast judgment result; the local image of the PCM left lug is normal in contrast, so that the OTSU threshold value is adopted for binarization, and the minimum circumscribed rectangle of the largest connected domain in the binarized image is extracted to obtain the PCM left lug image; the PCM right lug image has low contrast, the pixel number summation is accumulated from 255 gray values, when the accumulated sum reaches 85000, the accumulation is stopped, the gray value at the moment is 35, so that the binarization operation with the threshold value of 35 is carried out on the partial image of the PCM right lug, and the circumscribed rectangle with the largest area is extracted from the binary image to obtain the PCM right lug image; similarly, a battery cell left tab image and a battery cell right tab image are obtained.
(5) Detecting welding spots of the PCM tab image by adopting a corresponding method according to the judged contrast;
in this embodiment, different methods are adopted to detect the welding point of the PCM tab image according to different contrasts: detecting all 6 welding points by adopting a spot analysis method for the PCM left lug image; for the PCM right tab image with low contrast, the welding spot detection step is shown in fig. 3, and includes:
(5-1) carrying out histogram equalization processing on the PCM tab image;
(5-2) filtering by adopting a Log-Gabor even filter, and detecting a circle by Hough circle transformation after processing;
(5-3) changing parameter σ of Log-Gabor even filter0Repeating the step (5-2)10 times, sigma0From 0.01 to 0.10;
(5-4) performing circle results detected by Hough circle transformation after each Log-Gabor even filtering, and accumulating the circle results together to perform 3 screening operations based on repeated times in different directions: the X direction, the Y direction and the X direction are sequentially arranged, the result of each screening is used as the input of the next screening, and finally the true welding spot is reserved.
The Log-Gabor even filter expression is as follows:
wherein ω is0The central wavelength is 45, ω ═ ωx,ωy)T，σ0Determining parameters of bandwidth, performing Hough circle transformation to detect circles after each filtering, accumulating all the circle results together, and screening according to the following steps:
(5-4-1) starting to cycle through from the first circle, merging circles with the circle center coordinate distance smaller than 3, wherein the circle center coordinate of the new circle is the average value of the circle center coordinates of the merged circles, and marking the number of the merged circles;
(5-4-2) firstly, arranging all circles from small to large according to the x coordinates of the circle centers, and if the x pixel coordinate distance of two adjacent circles is less than 6, considering the x coordinates of the two circles to be the same;
(5-4-3) counting the number of all circles in the same x coordinate, if the number is greater than or equal to 14, keeping all circles in the x coordinate, and if not, deleting all circles in the x coordinate;
(5-4-4) arranging all circles reserved in the previous step from small to large according to the y coordinate of the circle center, and if the distance between the y coordinates of two adjacent circles is less than 5, considering the y coordinates of the two circles to be the same;
(5-4-5) counting the number of all circles in the same y coordinate, if the number is more than or equal to 25, keeping all circles in the y coordinate, and if not, deleting all circles in the y coordinate;
(5-4-6) arranging all circles reserved in the previous step from small to large according to the x coordinate of the circle center, and if the x coordinate distance between two adjacent circles is less than 5, considering the x coordinates of the two circles to be the same;
(5-4-7) counting the number of all circles in the same x coordinate, if the number is greater than or equal to 16, keeping all circles in the x coordinate, and if not, deleting all circles in the x coordinate.
And obtaining all 6 welding points in the PCM right lug image after screening.
(6) Mapping and pre-estimating welding spot coordinates in the battery cell lug image through the detected welding spot coordinates in the PCM lug image and pre-acquired calibration information;
transforming the welding spot coordinates of the PCM right lug image and the battery cell left lug image, wherein the transformation formula is as follows:
wherein, the { BL } is a battery cell left lug image coordinate system, the { FR } is a PCM right lug image coordinate system, the origin points of the coordinate systems are the upper left corners of the images, the right direction is the positive x direction, the downward direction is the positive y direction, and P isijRepresents a welding point coordinate vector, wherein i represents a row, j represents a column, and the PCM right tab image length w1High h is1Cell left tab image length w1', height h1', a ', b ' are pre-calibration information read from txt document, a is welding point P in PCM right tab imageCalibrationPixel length from left edge of image, b is P in PCM right tab imageCalibrationThe pixel length from the bottom edge of the image, a' is the welding point P corresponding to the left tab image of the battery cellCalibration'Pixel Length from right edge of image, b' is welding point P corresponding to left tab image of cellCalibration' pixel length from the bottom edge of the image.
Transforming the welding spot coordinates of the PCM left lug image and the battery cell right lug image, wherein the transformation formula is as follows:
wherein, the { BR } is a battery cell right lug image coordinate system, the { FL } is a PCM left lug image coordinate system, the origin points of the coordinate systems are the upper left corners of the images, and the right is the positive xDirection, downwards being the positive y-direction, PmnRepresents a welding point coordinate vector, wherein m represents a row, n represents a column, and the PCM left tab image length w2High h, h2Battery cell right electrode ear image length w2', high h2', c ', d ' are pre-calibration information read from txt document, c is welding point P in PCM left tab imageCalibrationPixel length from right edge of image, d is P in PCM left tab imageCalibrationC' is the corresponding welding point P of the right electrode lug image of the battery cellCalibration'Pixel Length from left edge of image, d' is welding Point P corresponding to right tab image of cellCalibration' pixel length from the bottom edge of the image.
In the process of transforming the welding spot coordinates of the PCM right tab image and the battery cell left tab image, the pre-calibration information is obtained in advance through an additional program, and an obtaining schematic diagram is shown in fig. 4, and specifically includes:
(6-1-1) inputting a PCM plate lug global image and a battery cell lug global image which are normal and have no folded lug;
(6-1-2) obtaining a PCM right lug image and a battery cell left lug image through the steps (2) - (5);
(6-1-3) specifying a welding point position in the PCM right tab imageFRx,FRy), solving a and b, and calculating the formula as follows:
(6-1-4) appointing the position of the welding spot corresponding to the PCM right lug image in the left lug image of the battery cell (BLx,BLy), solving a ', b', and calculating the formula as follows:
(6-1-5) save the values of a, b, a ', b' in an xml or txt file.
In the process of transforming the welding spot coordinates of the PCM left lug image and the battery cell right lug image, the acquisition of the pre-calibration information is obtained in advance through an additional program, which specifically comprises the following steps:
(6-2-1) inputting a PCM plate lug global image and a battery cell lug global image which are normal and have no folded lug;
(6-2-2) obtaining a PCM right lug image and a battery cell left lug image through the steps (2) - (5);
(6-2-3) specifying a welding point position in the PCM left tab imageFLx,FLy), solving c and d, wherein the calculation formula is as follows:
(6-2-4) appointing the position of the welding spot corresponding to the PCM left lug image in the battery cell right lug image (BRx,BRy), solving c ', d', and calculating the formula as follows:
(6-2-5) save the values of c, d, c ', d' in an xml or txt file.
The coordinates of the 6 mapped welding points in the image of the left electrode lug of the battery cell and the coordinates of the 6 mapped welding points in the image of the right electrode lug of the battery cell are obtained.
(7) Generating a square ROI by taking each obtained mapping pre-estimated welding point coordinate as a center;
in this embodiment, the square ROI is 20 pixels on a side.
(8) And detecting welding points in the square ROI, and if the welding points are detected, compensating the estimated welding point coordinates to obtain the actual welding point coordinates in the battery cell tab image.
Specifically, in the step (8), welding points are searched for in a square ROI by using a spot analysis method, and if welding points cannot be searched for by using the spot analysis, histogram equalization processing is performed on the image, and then welding points are searched for by using hough circle detection. The compensation formula for the mapped coordinates of the welding points of the electrode lugs of the battery cell through the search result in the square ROI is as follows (the origin of an image coordinate system is in the upper left corner):
wherein J is the welding point coordinate under the actual battery core tab image coordinate system, (x)temp,ytemp) For the coordinates of the weld points in the Square ROI image coordinate system Square, l is 20, and only the one closest to the center of the rectangle is used if multiple circles are detected.
The welding spot detection of all PCM lug images and battery core lug images is completed, and whether the welding spot welding of the lithium battery 113 is good or defective is marked according to the detection result. If the lithium batteries are good products, the lithium batteries 113 are conveyed to a good product blanking conveyer belt 103 by a blanking mechanism 109; if the defective products are found, the lithium battery 113 is conveyed to the defective product blanking conveyer 111 by the blanking mechanism 109.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. A visual online detection method for laser welding spots of a lithium battery tab is characterized by comprising the following steps:
acquiring a PCM lug global image and a battery cell lug global image;
dividing the PCM plate lug global image and the battery cell lug global image to obtain a lithium battery lug local image;
judging the contrast of the obtained local image of the lithium battery tab;
extracting a lug ROI from the local lug image by adopting a corresponding method according to the judged contrast result to obtain a PCM lug image and a battery cell lug image;
detecting welding spots of the PCM tab image by adopting a corresponding method according to the judged contrast;
mapping and pre-estimating welding spot coordinates in the battery cell lug image through the detected welding spot coordinates in the PCM lug image and pre-acquired calibration information;
generating a square ROI (region of interest) by taking each obtained mapping pre-estimated welding spot coordinate as a center in the battery cell tab image;
and detecting welding points in the square ROI, and if the welding points are detected, compensating the pre-estimated welding point coordinates to obtain the actual welding point coordinates in the battery cell tab image.
2. The method of claim 1, wherein in the step of collecting the PCM tab global image and the cell tab global image, 2 groups of dome light sources and black and white industrial camera modules are adopted to perform global image collection on the cell tab and the PCM plate tab of the lithium battery;
the light source adopts blue light for illumination; the two industrial cameras are oppositely arranged, and the lithium battery is positioned between the two industrial cameras during image acquisition; the two cameras respectively acquire a PCM lug global image and a battery cell lug global image; the lug global image covers the left lug and the right lug by 2; the two industrial camera modules are completely the same, and the overlapped area of the view fields needs to completely cover the left and right lugs; the imaging effect that the exposure time of the camera and the light intensity of the light source are combined to achieve is that the gray value of the normal non-wrinkled lug in an image is 255.
3. The method of claim 1, wherein in the step of dividing the PCM plate tab global image and the cell tab global image, the cell tab global image is divided into a cell left tab local image and a cell right tab local image; dividing the PCM lug global image into a PCM plate left lug local image and a PCM plate right lug local image; each lug local image is required to completely contain the lug outline, and the lug local image should cover all possible positions of the lithium battery lug in the global image due to lithium battery clamping errors.
4. The method as claimed in claim 1, wherein the step of determining the contrast of the obtained local image of the lithium battery tab comprises:
dividing the gray histogram statistical result of the local image of the lug into 3 intervals: a low gray value interval, a medium gray value interval and a high gray value interval;
by high gray value interval pixel sum ShAnd the sum of pixels and S in the interval of medium gray valuesmJudging the contrast of the local image of the tab:
if delta is larger than or equal to a preset constant const, judging the local image of the lug as normal contrast, otherwise, judging the local image of the lug as low contrast; the constant const refers to a quotient of the pixel number sum of the high gray value interval and the pixel number sum of the medium gray value interval of a wrinkle-free normal tab image, and can be continuously accumulated and averaged in real-time operation to reduce errors.
5. The method as claimed in claim 1, wherein in the step of extracting the ROI of the tab from the partial image of the tab by using a corresponding method according to the determined contrast result, the ROI of the tab extracted from the partial image of the tab is required to satisfy: the ROI left edge coincides with the pole lug outline left edge, the ROI right edge coincides with the pole lug outline right edge, and the ROI lower edge coincides with the pole lug outline lower edge.
6. The method as claimed in claim 1, wherein the step of extracting the tab ROI from the tab local image by using a corresponding method according to the determined contrast result comprises:
for a lug local image with normal contrast, thresholding is carried out by adopting an OTSU algorithm, and a method for searching a minimum external rectangle is adopted in a binary image, wherein the rectangle with the largest area in all external rectangles is a lug ROI;
for a local image of the lug with low contrast, thresholding is carried out by adopting an accumulated gray pixel number approximation method, and a method for searching a minimum external rectangle is adopted in a binary image, wherein the rectangle with the largest area in all the external rectangles is the ROI of the lug;
obtaining a tab ROI which is a tab image;
thresholding is carried out by adopting an accumulative gray pixel approximation method, and the solving formula of the threshold t is as follows:
wherein, the tab is 255 gray scale values in the image under normal conditions, the pixel sum of the tab floats around an average value T, l is the pixel length of the local image of the tab, and N is the pixel length of the local image of the tabiThe number of pixels corresponding to each gray value in the local image of the low-contrast tab is represented by i; s denotes the sum of pixels accumulated in decreasing 1 starting from 255 gradations, and n denotes the gradation value obtained when S is accumulated until it is first larger than T.
7. The method as claimed in claim 1, wherein in the step of performing the welding spot detection of the PCM tab image according to the judged contrast by a corresponding method, for the PCM tab image with low contrast, the welding spot detection step comprises:
performing histogram equalization processing on the PCM tab image;
carrying out filtering processing by adopting a Log-Gabor even filter, and carrying out Hough circle transformation detection circle after processing;
varying the parameter σ of a Log-Gabor even filter0Repeating the filtering process and the circle detection for a plurality of times;
and accumulating circle results detected by Hough circle transformation after each Log-Gabor even filtering, and performing screening operation, and finally reserving a real welding spot.
8. The method of claim 7, wherein the step of accumulating circle results detected by the hough circle transform after each Log-Gabor even filtering comprises:
circularly traversing from the first circle, combining circles with the coordinate distance of the circle center smaller than epsilon, wherein the coordinate of the circle center of the new circle is the average value of the coordinate of the circle center of the combined circles, and marking the number of the combined circles;
arranging all circles from small to large according to the x coordinate of the circle center, and if the x coordinate distance between two adjacent circles is less than epsilonxThen the two circular x-coordinates are considered to be identical;
counting the number sum of all merged circles under the same x coordinate, if the sum is more than or equal to CxKeeping all circles under the x coordinate, otherwise, deleting the circles;
arranging all circles reserved in the previous step from small to large according to the y coordinate of the circle center, and if the y coordinate distance between two adjacent circles is less than epsilonyThen the two circular y-coordinates are considered to be identical;
counting the number sum of all merged circles under the same y coordinate, if the sum is more than or equal to CyKeeping all circles under the y coordinate, otherwise, deleting the circles;
arranging all circles reserved in the previous step from small to large according to the x coordinate of the circle center, and if the x coordinate distance between two adjacent circles is less than epsilonxThen the two circular x-coordinates are considered to be identical;
counting the sum of all merged circles under the same x coordinate, if the sum is more than or equal to Cx' then all circles in that x coordinate are retained, otherwise they are deleted;
wherein C isx′>Cx。
9. The method of claim 1, wherein in the step of mapping and estimating the coordinates of the welding spot in the image of the battery cell tab through the coordinates of the welding spot in the detected PCM tab image and the pre-obtained calibration information, the coordinates of the welding spot in the image of the battery cell tab are transformed, and a transformation formula is as follows:
wherein, the { BL } is the coordinate system of the left tab image of the cell,{ FR } is a PCM right lug image coordinate system, the origin points of the coordinate system are the upper left corner of the image, the right direction is the positive x direction, the downward direction is the positive y direction, and PijRepresents a welding point coordinate vector, wherein i represents a row, j represents a column, and the PCM right tab image length w1High h is1Cell left tab image length w1', height h1', a ', b ' are pre-calibration information read from txt document, a is welding point P in PCM right tab imageCalibrationPixel length from left edge of image, b is P in PCM right tab imageCalibrationThe pixel length from the bottom edge of the image, a' is the welding point P corresponding to the left tab image of the battery cellCalibration'Pixel Length from right edge of image, b' is welding point P corresponding to left tab image of cellCalibration' pixel length from bottom edge of image;
transforming the welding spot coordinates of the PCM left lug image and the battery cell right lug image, wherein the transformation formula is as follows:
wherein, the { BR } is a battery cell right lug image coordinate system, the { FL } is a PCM left lug image coordinate system, the origin points of the coordinate systems are the upper left corners of the images, the right direction is the positive x direction, the downward direction is the positive y direction, and P ismnRepresents a welding point coordinate vector, wherein m represents a row, n represents a column, and the PCM left tab image length w2High h, h2Battery cell right electrode ear image length w2', high h2', c ', d ' are pre-calibration information read from txt document, and c is a welding point P in the PCM left tab imageCalibrationPixel length from right edge of image, d is P in PCM left tab imageCalibrationC' is the corresponding welding point P of the right electrode lug image of the battery cellCalibration'Pixel Length from left edge of image, d' is welding Point P corresponding to right tab image of cellCalibration' pixel length from bottom edge of image;
in the process of transforming the welding spot coordinates of the PCM right lug image and the battery cell left lug image, the acquisition of the pre-calibration information is obtained in advance through an additional program, which specifically comprises the following steps:
inputting a PCM plate lug global image and a battery cell lug global image of a normal non-wrinkled lug;
obtaining a PCM right lug image and a battery cell left lug image through contrast judgment and ROI extraction;
(ii) specifying a solder point location in the PCM right tab imageFRx,FRy), solving a and b, and calculating the formula as follows:
(a position corresponding to the PCM right lug image in the battery cell left lug image is designated with a welding pointBLx,BLy), solving a ', b', and calculating the formula as follows:
saving the values of a, b, a 'and b' in an xml or txt file;
in the process of transforming the welding spot coordinates of the PCM left lug image and the battery cell right lug image, the acquisition of the pre-calibration information is obtained in advance through an additional program, which specifically comprises the following steps:
inputting a PCM plate lug global image and a battery cell lug global image of a normal non-wrinkled lug;
obtaining a PCM right lug image and a battery cell left lug image through contrast judgment and ROI extraction;
specifying a solder point location in the PCM left tab imageFLx,FLy), solving c and d, wherein the calculation formula is as follows:
(a position corresponding to the welding point of the PCM left lug image is appointed in the battery cell right lug imageBRx,BRy), solving c ', d', and calculating the formula as follows:
the values of c, d, c ', d' are saved in an xml or txt file.
10. The method according to claim 1, wherein in the step of detecting the welding spot in the square ROI to obtain the coordinates of the welding spot in the actual battery cell tab image, the welding spot is searched for the square ROI by a spot analysis method, if the welding spot cannot be searched by the spot analysis, histogram equalization processing is performed on the image, and then the welding spot is searched by Hough circle transformation; the formula for compensating the coordinates of the welding points of the electrode lugs of the mapped battery cell through the search result in the square ROI is as follows:
wherein J is the welding point coordinate under the actual battery core tab image coordinate system, (x)temp,ytemp) The coordinates of the weld points in the rectangular ROI image coordinate system Square, l is the length of the rectangular ROI, and only the nearest one from the center of the rectangle is used if multiple circles are detected.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010114940.9A CN111307818B (en) | 2020-02-25 | 2020-02-25 | Visual online detection method for laser welding spot of lithium battery tab |
| PCT/CN2020/122843 WO2021169335A1 (en) | 2020-02-25 | 2020-10-22 | Visual online detection method for laser welding point of lithium battery tab |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010114940.9A CN111307818B (en) | 2020-02-25 | 2020-02-25 | Visual online detection method for laser welding spot of lithium battery tab |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111307818A true CN111307818A (en) | 2020-06-19 |
| CN111307818B CN111307818B (en) | 2021-07-20 |
Family
ID=71156802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010114940.9A Expired - Fee Related CN111307818B (en) | 2020-02-25 | 2020-02-25 | Visual online detection method for laser welding spot of lithium battery tab |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111307818B (en) |
| WO (1) | WO2021169335A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111976151A (en) * | 2020-08-06 | 2020-11-24 | 漳浦金盛智能科技有限公司 | Plane gauze mask machine |
| CN112184816A (en) * | 2020-09-28 | 2021-01-05 | 珠海博明视觉科技有限公司 | Lithium battery flexible positioning method based on battery tabs |
| CN112363069A (en) * | 2020-09-18 | 2021-02-12 | 万向一二三股份公司 | Lithium ion battery tab fracture detection method |
| WO2021169335A1 (en) * | 2020-02-25 | 2021-09-02 | 华南理工大学 | Visual online detection method for laser welding point of lithium battery tab |
| CN113469991A (en) * | 2021-07-15 | 2021-10-01 | 广东奥普特科技股份有限公司 | Visual online detection method for laser welding spot of lithium battery tab |
| CN113552133A (en) * | 2021-06-30 | 2021-10-26 | 广东利元亨智能装备股份有限公司 | Cell skirt edge cracking detection method and visual detection device |
| CN115825070A (en) * | 2022-08-10 | 2023-03-21 | 宁德时代新能源科技股份有限公司 | Battery cell detection method and device, computer equipment and medium |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113744244B (en) * | 2021-09-03 | 2022-05-13 | 广东奥普特科技股份有限公司 | Online visual detection system for measuring distance from edge of lithium battery pole piece to edge of pole lug |
| CN114037657A (en) * | 2021-10-12 | 2022-02-11 | 上海电机学院 | Lithium battery tab defect detection method combining region growth and annular correction |
| CN114549531B (en) * | 2022-04-26 | 2022-07-15 | 广州市易鸿智能装备有限公司 | Centering and deviation-correcting control system and method for lithium battery winding OverHang |
| CN117078580A (en) * | 2022-05-10 | 2023-11-17 | 广州镭晨智能装备科技有限公司 | Solder joint detection method, device and computer readable storage medium |
| CN115178909B (en) * | 2022-07-11 | 2023-10-27 | 苏州汇川控制技术有限公司 | Welding quality detection method and device, terminal equipment and medium |
| CN115829913B (en) * | 2022-08-10 | 2024-05-17 | 宁德时代新能源科技股份有限公司 | Bare cell appearance detection method, bare cell appearance detection device, bare cell appearance detection computer equipment and bare cell appearance storage medium |
| CN115082504B (en) * | 2022-08-23 | 2022-11-11 | 菏泽学院 | Light spot identification method for solar photovoltaic panel |
| CN115360319B (en) * | 2022-09-20 | 2023-04-14 | 楚能新能源股份有限公司 | Multi-tab battery cell pole piece information tracing method |
| CN115841451B (en) * | 2022-09-27 | 2023-11-17 | 宁德时代新能源科技股份有限公司 | Method and device for detecting number of lugs |
| CN115661040B (en) * | 2022-09-28 | 2023-07-14 | 广州市易鸿智能装备有限公司 | Lithium battery cell gluing detection method and device and electronic equipment |
| CN116008294B (en) * | 2022-12-13 | 2024-03-08 | 无锡微准科技有限公司 | Key cap surface particle defect detection method based on machine vision |
| CN116596932B (en) * | 2023-07-18 | 2024-02-09 | 北京阿丘机器人科技有限公司 | Method, device, equipment and storage medium for detecting appearance of battery top cover pole |
| CN117109447B (en) * | 2023-10-24 | 2024-01-05 | 钛玛科（北京）工业科技有限公司 | Self-adaptive tab width detection method, device and equipment |
| CN117309889B (en) * | 2023-11-27 | 2024-05-14 | 宁德时代新能源科技股份有限公司 | Pole piece edge detection device and method |
| CN117570852B (en) * | 2024-01-15 | 2024-03-26 | 钛玛科（北京）工业科技有限公司 | Method, device and equipment for detecting polar lug vertex coordinates |
| CN117593309B (en) * | 2024-01-19 | 2024-03-19 | 常熟理工学院 | Method, system and storage medium for detecting chip welding spots based on stereo reconstruction |
| CN117718593A (en) * | 2024-02-01 | 2024-03-19 | 宁德时代新能源科技股份有限公司 | Welding method and welding system for pole |
| CN117723491A (en) * | 2024-02-07 | 2024-03-19 | 宁德时代新能源科技股份有限公司 | Detection system and detection method for battery cell explosion-proof valve |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104439727A (en) * | 2014-11-20 | 2015-03-25 | 东莞市德尔能新能源科技有限公司 | Clamp for battery laser welding |
| CN106825958A (en) * | 2017-03-16 | 2017-06-13 | 深圳市光大激光科技股份有限公司 | Integrated welding is agreed to play and takes the photograph structure and battery core automatic welding detection means and method |
| CN108280837A (en) * | 2018-01-25 | 2018-07-13 | 电子科技大学 | BGA soldered balls contour extraction method in radioscopic image based on transformation |
| CN109187547A (en) * | 2018-07-23 | 2019-01-11 | 广州超音速自动化科技股份有限公司 | Lithium battery pole ear solder joint welds broken detection method and tab welding detection system |
| CN109187546A (en) * | 2018-07-23 | 2019-01-11 | 广州超音速自动化科技股份有限公司 | Lithium battery pole ear mixes detection method and tab welding detection system |
| CN110135521A (en) * | 2019-05-28 | 2019-08-16 | 陕西何止网络科技有限公司 | Pole-piece pole-ear defects detection model, detection method and system based on convolutional neural networks |
| CN110910363A (en) * | 2019-11-15 | 2020-03-24 | 上海交通大学 | Insufficient solder joint detection method, system and medium based on machine vision and deep learning |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05109858A (en) * | 1991-10-15 | 1993-04-30 | Nec Corp | Tab soldering inspecting device |
| CN103846538A (en) * | 2012-11-29 | 2014-06-11 | 上海航天设备制造总厂 | Image recognition device and battery array welding system utilizing same |
| CN103487440B (en) * | 2013-08-28 | 2015-11-18 | 东莞市三瑞自动化科技有限公司 | A kind of battery pole ear detection method based on machine vision and detection system thereof |
| KR101678662B1 (en) * | 2013-09-24 | 2016-11-22 | 주식회사 엘지화학 | Method of vision measuring optimization concerning ultrasonic welding state in rechargeable battery and apparatus thereof |
| CN108355981B (en) * | 2018-01-08 | 2020-03-17 | 西安交通大学 | Battery connector quality detection method based on machine vision |
| CN109142368A (en) * | 2018-07-23 | 2019-01-04 | 广州超音速自动化科技股份有限公司 | Lithium battery pole slice is crumpled detection method and tab welding detection system |
| CN111307818B (en) * | 2020-02-25 | 2021-07-20 | 华南理工大学 | Visual online detection method for laser welding spot of lithium battery tab |
-
2020
- 2020-02-25 CN CN202010114940.9A patent/CN111307818B/en not_active Expired - Fee Related
- 2020-10-22 WO PCT/CN2020/122843 patent/WO2021169335A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104439727A (en) * | 2014-11-20 | 2015-03-25 | 东莞市德尔能新能源科技有限公司 | Clamp for battery laser welding |
| CN106825958A (en) * | 2017-03-16 | 2017-06-13 | 深圳市光大激光科技股份有限公司 | Integrated welding is agreed to play and takes the photograph structure and battery core automatic welding detection means and method |
| CN108280837A (en) * | 2018-01-25 | 2018-07-13 | 电子科技大学 | BGA soldered balls contour extraction method in radioscopic image based on transformation |
| CN109187547A (en) * | 2018-07-23 | 2019-01-11 | 广州超音速自动化科技股份有限公司 | Lithium battery pole ear solder joint welds broken detection method and tab welding detection system |
| CN109187546A (en) * | 2018-07-23 | 2019-01-11 | 广州超音速自动化科技股份有限公司 | Lithium battery pole ear mixes detection method and tab welding detection system |
| CN110135521A (en) * | 2019-05-28 | 2019-08-16 | 陕西何止网络科技有限公司 | Pole-piece pole-ear defects detection model, detection method and system based on convolutional neural networks |
| CN110910363A (en) * | 2019-11-15 | 2020-03-24 | 上海交通大学 | Insufficient solder joint detection method, system and medium based on machine vision and deep learning |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021169335A1 (en) * | 2020-02-25 | 2021-09-02 | 华南理工大学 | Visual online detection method for laser welding point of lithium battery tab |
| CN111976151A (en) * | 2020-08-06 | 2020-11-24 | 漳浦金盛智能科技有限公司 | Plane gauze mask machine |
| CN112363069A (en) * | 2020-09-18 | 2021-02-12 | 万向一二三股份公司 | Lithium ion battery tab fracture detection method |
| CN112363069B (en) * | 2020-09-18 | 2023-07-07 | 万向一二三股份公司 | Method for detecting breakage of tab of lithium ion battery |
| CN112184816A (en) * | 2020-09-28 | 2021-01-05 | 珠海博明视觉科技有限公司 | Lithium battery flexible positioning method based on battery tabs |
| CN112184816B (en) * | 2020-09-28 | 2024-03-22 | 珠海博明视觉科技有限公司 | Lithium battery flexible positioning method based on battery lugs |
| CN113552133A (en) * | 2021-06-30 | 2021-10-26 | 广东利元亨智能装备股份有限公司 | Cell skirt edge cracking detection method and visual detection device |
| CN113469991A (en) * | 2021-07-15 | 2021-10-01 | 广东奥普特科技股份有限公司 | Visual online detection method for laser welding spot of lithium battery tab |
| CN113469991B (en) * | 2021-07-15 | 2022-03-18 | 广东奥普特科技股份有限公司 | Visual online detection method for laser welding spot of lithium battery tab |
| CN115825070A (en) * | 2022-08-10 | 2023-03-21 | 宁德时代新能源科技股份有限公司 | Battery cell detection method and device, computer equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111307818B (en) | 2021-07-20 |
| WO2021169335A1 (en) | 2021-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111307818B (en) | Visual online detection method for laser welding spot of lithium battery tab | |
| CN110717872B (en) | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning | |
| CN108229475B (en) | Vehicle tracking method, system, computer device and readable storage medium | |
| CN110390677B (en) | Defect positioning method and system based on sliding self-matching | |
| CN115115644A (en) | Vehicle welding defect detection method based on artificial intelligence | |
| CN116559183B (en) | Method and system for improving defect judging efficiency | |
| CN113834816A (en) | Machine vision-based photovoltaic cell defect online detection method and system | |
| US20110199491A1 (en) | Calibration index determination device, calibration device, calibration performance evaluation device, system, method, and program | |
| CN110567965A (en) | Smartphone glass cover plate edge visual defect detection method | |
| CN114594114A (en) | Full-automatic online nondestructive detection method for lithium battery cell | |
| CN116416268B (en) | Method and device for detecting edge position of lithium battery pole piece based on recursion dichotomy | |
| CN111915485B (en) | Rapid splicing method and system for feature point sparse workpiece images | |
| CN114612410A (en) | Novel clothing detects device | |
| CN117058411B (en) | Method, device, medium and equipment for identifying edge appearance flaws of battery | |
| CN113705564A (en) | Pointer type instrument identification reading method | |
| CN113129260A (en) | Automatic detection method and device for internal defects of lithium battery cell | |
| CN116681677A (en) | Lithium battery defect detection method, device and system | |
| CN114881878B (en) | Depth image enhancement method, device, equipment and storage medium | |
| CN115984197A (en) | Defect detection method based on standard PCB image and related device | |
| CN115194323A (en) | Positioning welding method of laser welding machine | |
| CN115035071A (en) | Visual detection method for black spot defect of PAD light guide plate | |
| CN114359414A (en) | Lens smudge identification method and device, computer equipment and storage medium | |
| CN114494142A (en) | Mobile terminal middle frame defect detection method and device based on deep learning | |
| CN117593302B (en) | Defective part tracing method and system | |
| CN116448666B (en) | Detection device and detection method for lithium battery box based on machine vision |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210720 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |