CN117058047A - On-line monitoring method for edge burrs of lithium battery pole piece - Google Patents
On-line monitoring method for edge burrs of lithium battery pole piece Download PDFInfo
- Publication number
- CN117058047A CN117058047A CN202311307918.6A CN202311307918A CN117058047A CN 117058047 A CN117058047 A CN 117058047A CN 202311307918 A CN202311307918 A CN 202311307918A CN 117058047 A CN117058047 A CN 117058047A
- Authority
- CN
- China
- Prior art keywords
- burr
- lithium battery
- pole piece
- battery pole
- obtaining
- 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
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 87
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 230000003313 weakening effect Effects 0.000 claims abstract description 89
- 238000001914 filtration Methods 0.000 claims abstract description 62
- 238000009792 diffusion process Methods 0.000 claims abstract description 44
- 230000009467 reduction Effects 0.000 claims abstract description 35
- 230000011218 segmentation Effects 0.000 claims abstract description 14
- 230000007547 defect Effects 0.000 claims description 21
- 238000001514 detection method Methods 0.000 description 6
- 230000007797 corrosion Effects 0.000 description 5
- 238000005260 corrosion Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 239000003792 electrolyte Substances 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
-
- 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
- G06T2207/30232—Surveillance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to an on-line monitoring method for edge burrs of a lithium battery pole piece, which comprises the following steps: obtaining a gray level image of the lithium battery pole piece, obtaining a burr interference point according to the gray level value of a pixel point in the gray level image of the lithium battery pole piece, obtaining a primary filtering area of the burr interference point according to the burr interference point, obtaining a plurality of diffused filtering areas according to the primary filtering area of the burr interference point, obtaining weakening necessity of the burr interference point after diffusion, obtaining a weakening coefficient according to the weakening necessity of the burr interference point after diffusion, obtaining a Gaussian filter kernel of the burr interference point according to a weakening coefficient data set, obtaining the gray level image of the lithium battery pole piece after noise reduction according to the Gaussian filter kernel, and obtaining edge burrs by threshold segmentation. According to the invention, the Gaussian filter kernel of the burr interference point is obtained by analyzing the burr interference point and is subjected to filter processing, so that the edge Mao Cineng of the lithium battery in the image can be displayed more clearly.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an online monitoring method for edge burrs of a lithium battery pole piece.
Background
Pole pieces are an important component of lithium batteries, which directly affect the safety, chemical properties and life of the battery. Therefore, the defect rate of lithium battery products is reduced by detecting the burr defect at the edge of the lithium battery of the pole piece, and adjustment is timely made, so that the defect rate of the products is reduced, and the economic loss is reduced. The defect detection technology based on machine vision has the advantages of long working time, no influence of external factors and subjective factors and the like. Therefore, the method has extremely important practical significance for researching the defect detection technology based on machine vision.
Many burr interference points can exist at the edge of the lithium battery, the burr interference points are mainly generated because the electrolyte is possibly decomposed and reacted by water in the electrolyte under the high-temperature and high-humidity environment of the lithium battery pole piece, corrosion of the pole piece is caused, and then many burr interference points, namely corrosion defects caused by pole piece corrosion, can be generated, the existing noise reduction technology can not carry out good noise reduction treatment on the edge of the lithium battery, the edge burrs of the lithium battery can not be well distinguished, so that the safety performance, the chemical performance and the service life of the battery are influenced, and economic loss is caused, therefore, a filtering noise reduction method capable of well distinguishing the edge Mao Cineng of the lithium battery is required to be researched, and the edge Mao Cineng of the lithium battery in an image can be clearly displayed.
Disclosure of Invention
The invention provides an online monitoring method for edge burrs of a lithium battery pole piece, which aims to solve the existing problems.
The invention discloses an on-line monitoring method for edge burrs of a lithium battery pole piece, which adopts the following technical scheme:
the embodiment of the invention provides an on-line monitoring method for edge burrs of a lithium battery pole piece, which comprises the following steps:
acquiring a gray level image of a lithium battery pole piece;
according to the gray value of the pixel point in the gray image of the lithium battery pole piece, a burr interference point is obtained; obtaining a primary filtering area of the burr interference point according to the burr interference point;
obtaining a plurality of diffused filtering areas according to the primary filtering areas of the burr interference points; obtaining the weakening necessity of the burr interference point after diffusion according to the gray average value of the pixel point in the filtering area; obtaining a weakening coefficient of the diffused burr interference point according to the weakening necessity of the diffused burr interference point; obtaining a weakening coefficient data set according to the weakening coefficient;
obtaining a Gaussian filter kernel of the burr interference point according to the weakening coefficient data set; and obtaining a gray level image of the lithium battery pole piece after noise reduction according to the Gaussian filter kernel of the burr interference point, obtaining an edge burr defect image according to the gray level image of the lithium battery pole piece after noise reduction, and obtaining edge burrs according to the edge burr defect image.
Further, the method comprises the following specific steps of:
and marking the pixel points with the gray values of the pixel points larger than the gray average value of all the pixel points in the gray image of the lithium battery pole piece as burr interference points.
Further, the primary filtering area for obtaining the glitch point according to the glitch point includes the following specific steps:
for any one burr interference point, the burr interference point is taken as the center to be establishedN is the width of a preset window, and the gray level image of the lithium battery pole piece is +.>Is noted as the primary filtering region of the glitch spot.
Further, the obtaining a plurality of diffused filtering areas according to the primary filtering area of the burr interference point comprises the following specific steps:
uniformly diffusing the primary filtering area of the burr interference point to the periphery, wherein the primary filtering area of the burr interference point is diffused to the periphery by one pixel unit when diffusing each time, so as to obtain a plurality of diffused filtering areas.
Further, the weakening necessity of the burr interference point after diffusion is obtained according to the gray average value of the pixel point in the filtering area, comprising the following specific steps:
the gray average value of the filtering area after the i-1 th diffusion is recorded asThe gray average value of the filter region after the ith diffusion is recorded as +.>The weakening necessity of the burr interference point after the ith diffusion is->When->And when the diffusion is smaller than 0, stopping the diffusion.
Further, the method for obtaining the weakening coefficient of the diffused burr interference point according to the weakening necessity of the diffused burr interference point comprises the following specific steps:
and (3) marking the ratio of the weakening necessity of the i-th diffusion post-burr interference point to the width of the i-th diffusion post-filter area as the weakening coefficient of the i-th diffusion post-burr interference point.
Further, the obtaining the weakening coefficient data set according to the weakening coefficient comprises the following specific steps:
all weakening coefficients not smaller than 0 are recorded as weakening coefficient data sets.
Further, the gaussian filter kernel for obtaining the glitch point according to the weakening coefficient data set includes the following specific steps:
acquiring variance of weakening coefficient data set, and weakening coefficient numberThe variance of the group is used as the Gaussian filter kernel variance of the glitch interference point, and the Gaussian filter kernel size of the glitch interference point is preset to beAnd obtaining the Gaussian filter kernel of the burr interference point according to the Gaussian filter kernel variance and the Gaussian filter kernel size of the burr interference point.
Further, the step of obtaining the gray level image of the lithium battery pole piece after noise reduction according to the Gaussian filter kernel of the burr interference point comprises the following specific steps:
and carrying out Gaussian filtering noise reduction according to the Gaussian filter kernel corresponding to the burr interference point to obtain the gray level image of the lithium battery pole piece after noise reduction.
Further, the edge burr defect image is obtained according to the gray level image of the lithium battery pole piece after noise reduction, and the edge burr is obtained according to the edge burr defect image, comprising the following specific steps:
and carrying out Ojin threshold segmentation on the lithium battery pole piece gray level image after noise reduction to obtain an optimal segmentation threshold value, setting the gray level value of a pixel point which is larger than the optimal segmentation threshold value in the lithium battery pole piece gray level image after noise reduction as 1, setting the gray level value of a pixel point which is smaller than or equal to the optimal segmentation threshold value as 0, and obtaining an edge burr defect image, wherein the area with the gray level value of 1 in the edge burr defect image is edge burr.
The technical scheme of the invention has the beneficial effects that: according to the gray value of the pixel point in the gray image of the lithium battery pole piece, a burr interference point is obtained; the primary filtering area of the burr interference point is obtained according to the burr interference point, and the obtained primary filtering area can perform better noise reduction on the burr interference point; according to the primary filtering area of the burr interference point, a plurality of diffused filtering areas are obtained, the association condition of the burr interference point and surrounding pixel points can be better reflected by the diffused filtering areas, and the burr interference point is prevented from being more abrupt with the surrounding pixel points after noise reduction; obtaining the weakening necessity of the burr interference point after diffusion according to the gray average value of the pixel point in the filtering area; obtaining a weakening coefficient of the diffused burr interference point according to the weakening necessity of the diffused burr interference point; obtaining a weakening coefficient data set according to the weakening coefficient; according to the weakening coefficient data set, a Gaussian filter kernel of the burr interference point is obtained, the Gaussian filter kernel can perform better filtering noise reduction on the burr interference point, and different burr interference points have different Gaussian filter kernels, so that the condition that the filtering effect is poor due to the fact that the same Gaussian filter kernel is used is avoided; and obtaining a gray image of the lithium battery pole piece after noise reduction according to the Gaussian filter kernel, and finally dividing to obtain edge burrs.
According to the invention, the burr interference points are analyzed to obtain the Gaussian filter kernel of the burr interference points and filter the burr interference points, so that the burr interference points in the gray level image of the lithium battery pole piece can be removed better, and the edge Mao Cineng of the lithium battery in the image can be displayed more clearly.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of steps of a method for on-line monitoring edge burrs of a lithium battery pole piece according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the method for on-line monitoring edge burrs of a lithium battery pole piece according to the invention, which is provided by the invention, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of an on-line monitoring method for edge burrs of a lithium battery pole piece, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for on-line monitoring edge burrs of a lithium battery pole piece according to an embodiment of the invention is shown, the method includes the following steps:
and S001, collecting a lithium battery pole piece image, and graying to obtain a lithium battery pole piece gray image.
It should be noted that, in this embodiment, the edge burrs of the lithium battery pole piece are analyzed and processed based on image processing, and first, a corresponding image needs to be acquired and a certain pretreatment is performed.
Specifically, an industrial camera is utilized to acquire images of the lithium battery pole pieces to obtain images of the lithium battery pole pieces, and the fact that the images of the lithium battery pole pieces contain a plurality of edge burrs and burr interference points is required to be described, and the imaging of the edge burrs is not clear due to the existence of the burr interference points, so that the detection of the edge burrs is not facilitated.
And carrying out graying treatment on the lithium battery pole piece image to obtain a lithium battery pole piece gray level image.
And thus, obtaining the gray level image of the lithium battery pole piece.
Step S002, obtaining a primary filtering area of the burr interference point according to the gray value of the pixel point in the gray image of the lithium battery pole piece.
It should be noted that, under the high-temperature and high-humidity environment, the moisture in the electrolyte may cause decomposition and reaction of the electrolyte, so that the electrode plate is corroded, and a plurality of burr interference points are generated in the gray level image of the lithium battery electrode plate, namely corrosion blemishes caused by the electrode plate corrosion, the burr interference points can cause inaccurate detection results when detecting edge burrs, and the gray level value of the burr interference points is higher than that of surrounding areas through analyzing the gray level image of the lithium battery electrode plate, so that the influence of the burr interference points on the edge burrs is reduced for better noise reduction of the gray level image of the lithium battery electrode plate, and meanwhile, the burr interference points are provided with larger bumps with surrounding pixel points after noise reduction, so that the gray level value of a central pixel point is adjusted by combining with the neighborhood of the pixel points, and a primary filtering area is established, so that a better noise reduction effect is achieved.
Specifically, pixel points with the gray values of the pixel points larger than the gray average value of all the pixel points in the gray image of the lithium battery pole piece are marked as burr interference points, a plurality of burr interference points are finally obtained, and for any one burr interference point, the burr interference point is taken as the center to be establishedN is the size of the preset window, in this embodiment, n=3 is described, and may be set to other values during implementation, so as to add +_in the gray level image of the lithium battery pole piece>The window of (2) is marked as the primary filtering area of the glitch point, and the primary filtering area of each glitch point can be obtained in the same way.
Thus, a primary filtering area of the glitch point is obtained.
Step S003, a plurality of diffused filtering areas are obtained according to the primary filtering areas of the burr interference points, the weakening necessity of the burr interference points after diffusion is obtained according to the gray average value of the pixel points in the filtering areas, the weakening coefficient is obtained according to the weakening necessity of the burr interference points after diffusion, and a weakening coefficient data set is obtained.
It should be noted that, in step S002, the primary filtering area of the glitch point is obtained, and since the gray value of the glitch point in the image is higher, and there may be a case where the gray values of the pixel points in the primary filtering area are all very high, in order to make the effect of weakening the glitch point optimal, it is necessary to weaken each glitch point to different degrees according to different situations of each glitch point.
Specifically, uniformly diffusing the primary filtering area of the burr interference point to the periphery, and diffusing the primary filtering area of the burr interference point to the periphery by one pixel unit during each diffusion to obtain a plurality of diffused areasThe primary filtering area of the (C) is, for example, the primary filtering area of the glitch pointThe size of the filter area of the burr interference point after diffusion once is +.>Size of the product.
It should be noted that, the primary filtering area is uniformly diffused around, and the weakening necessity is obtained according to the difference value of the gray average value, when the gray difference value between the burr interference point and the surrounding pixel point is larger, at this time, in the image, the more the interference point protrudes relative to the surrounding pixel point, the more the weakening is required, so the larger the difference value is, the greater the weakening necessity is, and the higher the weakening degree of the center is; and conversely, the smaller the difference value is, the smaller the weakening necessity is, and the smaller the weakening degree of the center is.
Further, the weakening necessity of the burr interference point after diffusion is obtained according to the gray average value of the pixel point in the filtering area, and the method is specifically as follows:
the gray average value of the pixel points of the primary filtering area is recorded asThe gray average value of the filter region after the ith diffusion is recorded as +.>The gray average value of the filtering area after the i-1 th diffusion is recorded as +.>The weakening necessity of the burr interference point after the ith diffusion is->The greater the weakening necessity, the greater the degree of weakening of the glitch spot, and vice versa, it is to be noted that, when + ->Stopping diffusion when the concentration is less than 0, if +.>And when the diffusion is not less than 0 but exceeds the boundary of the lithium battery pole piece gray level image, continuing to diffuse, and only calculating the gray level average value of the filtering area in the lithium battery pole piece gray level image.
As the distance of diffusion increases, the correlation between the diffused pixel point and the center pixel point (burr interference point) becomes weaker, and therefore, the weakening coefficient is obtained according to the diffusion distance and the weakening necessity.
Further, the weakening coefficient is obtained according to the weakening necessity of the burr interference point after diffusion, and specifically the weakening coefficient is as follows:
in the method, in the process of the invention,in order to weaken the interference point of the burr after the ith diffusion, when the gray level difference between the interference point of the burr and the surrounding pixel points is larger, the more the interference point is protruded relative to the surrounding pixel points in the image, the more the interference point needs to be weakened, and the more the interference point is required to be weakened>For the width of the filter region after the ith diffusion, is->The larger the diffusion range, and the weaker the correlation between the diffused pixel point and the burr interference point is, so the distance characteristic is introduced to better reflect the weakening coefficient of the burr interference point, and the diffusion range is increased>Is the weakening coefficient of the burr interference point after the ith diffusion.
It should be noted that, only when the gray average value of the diffused area is lower than the filtering area, the burr interference point can be weakened, along with continuous diffusion, the weakening necessity can have a negative value, when the weakening necessity is negative, the weakening effect on the burr interference point can not be achieved after diffusion, the weakening coefficient is also negative, the filtering area stops diffusion, and in order to obtain the weakening coefficient data set according to the weakening coefficient, all weakening coefficients before the weakening coefficient is smaller than 0 need to be obtained.
Specifically, all the weakening coefficients not smaller than 0 are recorded as weakening coefficient data sets.
To this end, all weakening coefficients and weakening coefficient data sets before weakening coefficients smaller than 0 are obtained.
And S004, obtaining a Gaussian filter kernel of the burr interference point according to the weakening coefficient data set, obtaining a lithium battery pole piece gray level image after noise reduction according to the Gaussian filter kernel, and performing threshold segmentation on the lithium battery pole piece gray level image after noise reduction to obtain edge burrs.
It should be noted that, in step S003, all weakening coefficients before the weakening coefficient is smaller than 0 are obtained, and the gaussian filter kernel of the burr interference point can be obtained through the weakening coefficients.
Specifically, the variance of the weakening coefficient data set is obtained, the variance of the weakening coefficient data set is used as the gaussian filter kernel variance of the glitch interference point, after the gaussian filter kernel variance of the glitch interference point is determined, the size of the gaussian filter kernel of the glitch interference point is also required to be determined, and the size of the gaussian filter kernel of the glitch interference point is preset to beThe implementation is->For example, the Gaussian filter kernel size is +.>The Gaussian filter kernel of the burr interference points is obtained according to the Gaussian filter kernel variance and the Gaussian filter kernel size of the burr interference points, the burr interference points are filtered and noise reduction is carried out by utilizing the Gaussian filter kernel, and as the step is to analyze any burr interference point, each gray level image of the lithium battery pole piece is obtainedAnd Gaussian filtering kernels corresponding to the burr interference points are used for Gaussian filtering and noise reduction according to the Gaussian filtering kernels corresponding to the burr interference points, and finally, the gray level image of the lithium battery pole piece after noise reduction is obtained.
It should be noted that, since the above steps are performed on any one burr interference point, the gaussian filter kernels of different burr interference points may be different, and the gaussian filter kernels for obtaining the burr interference points according to the gaussian filter kernel variance and the gaussian filter kernel size of the burr interference points are the existing method, which is not repeated in this embodiment, the edge burrs in the gray level image of the lithium battery pole piece after noise reduction are clearer, and the detection of the edge burrs is more beneficial.
Further, the gray level image of the lithium battery pole piece after noise reduction is subjected to Ojin threshold segmentation to obtain an optimal segmentation threshold, the gray level value of a pixel point which is larger than the optimal segmentation threshold in the gray level image of the lithium battery pole piece after noise reduction is set to be 1, the gray level value of a pixel point which is smaller than or equal to the optimal segmentation threshold is set to be 0, and an edge burr defect image is obtained, namely the edge burr defect image is a binary image, the area with the gray level value of 1 in the edge burr defect image is edge burr, and the area with the gray level value of 0 is the normal area of the lithium battery pole piece. Therefore, the detection of the edge burrs of the lithium battery pole piece is completed, and the edge burrs of the lithium battery pole piece can be monitored on line by the method.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. The on-line monitoring method for the edge burrs of the lithium battery pole piece is characterized by comprising the following steps of:
acquiring a gray level image of a lithium battery pole piece;
according to the gray value of the pixel point in the gray image of the lithium battery pole piece, a burr interference point is obtained; obtaining a primary filtering area of the burr interference point according to the burr interference point;
obtaining a plurality of diffused filtering areas according to the primary filtering areas of the burr interference points; obtaining the weakening necessity of the burr interference point after diffusion according to the gray average value of the pixel point in the filtering area; obtaining a weakening coefficient of the diffused burr interference point according to the weakening necessity of the diffused burr interference point; obtaining a weakening coefficient data set according to the weakening coefficient;
obtaining a Gaussian filter kernel of the burr interference point according to the weakening coefficient data set; and obtaining a gray level image of the lithium battery pole piece after noise reduction according to the Gaussian filter kernel of the burr interference point, obtaining an edge burr defect image according to the gray level image of the lithium battery pole piece after noise reduction, and obtaining edge burrs according to the edge burr defect image.
2. The method for on-line monitoring of edge burrs of a lithium battery pole piece according to claim 1, wherein the method comprises the following specific steps of:
and marking the pixel points with the gray values of the pixel points larger than the gray average value of all the pixel points in the gray image of the lithium battery pole piece as burr interference points.
3. The method for on-line monitoring of the burr on the edge of the lithium battery pole piece according to claim 1, wherein the primary filtering area of the burr interference point is obtained according to the burr interference point, comprises the following specific steps:
for any one burr interference point, the burr interference point is taken as the center to be establishedN is the width of a preset window, and the gray level image of the lithium battery pole piece is +.>Is noted as the primary filtering region of the glitch spot.
4. The method for on-line monitoring of the edge burrs of the lithium battery pole piece according to claim 1, wherein the method for obtaining a plurality of diffused filter areas according to the primary filter areas of the burr interference points comprises the following specific steps:
uniformly diffusing the primary filtering area of the burr interference point to the periphery, wherein the primary filtering area of the burr interference point is diffused to the periphery by one pixel unit when diffusing each time, so as to obtain a plurality of diffused filtering areas.
5. The method for on-line monitoring of burrs at edges of lithium battery pole pieces according to claim 1, wherein the weakening necessity of the burrs after diffusion interference points is obtained according to the gray average value of pixel points in a filtering area, comprises the following specific steps:
the gray average value of the filtering area after the i-1 th diffusion is recorded asThe gray average value of the filter region after the ith diffusion is recorded as +.>The weakening necessity of the burr interference point after the ith diffusion is->When->And when the diffusion is smaller than 0, stopping the diffusion.
6. The method for on-line monitoring of the edge burrs of the lithium battery pole piece according to claim 1, wherein the weakening coefficient of the diffused burr interference point is obtained according to the weakening necessity of the diffused burr interference point, comprising the following specific steps:
and (3) marking the ratio of the weakening necessity of the i-th diffusion post-burr interference point to the width of the i-th diffusion post-filter area as the weakening coefficient of the i-th diffusion post-burr interference point.
7. The method for on-line monitoring of edge burrs of a lithium battery pole piece according to claim 1, wherein the step of obtaining the weakening coefficient data set according to the weakening coefficient comprises the following specific steps:
all weakening coefficients not smaller than 0 are recorded as weakening coefficient data sets.
8. The method for on-line monitoring of burrs on edges of lithium battery pole pieces according to claim 1, wherein the gaussian filter kernel for obtaining the burrs interference points according to the weakening coefficient data set comprises the following specific steps:
acquiring variance of the weakening coefficient data set, taking the variance of the weakening coefficient data set as Gaussian filter kernel variance of the glitch interference point, and presetting the Gaussian filter kernel size of the glitch interference point to beAnd obtaining the Gaussian filter kernel of the burr interference point according to the Gaussian filter kernel variance and the Gaussian filter kernel size of the burr interference point.
9. The method for on-line monitoring of the edge burrs of the lithium battery pole piece according to claim 1, wherein the method for obtaining the gray level image of the lithium battery pole piece after noise reduction according to the Gaussian filter kernel of the burr interference point comprises the following specific steps:
and carrying out Gaussian filtering noise reduction according to the Gaussian filter kernel corresponding to the burr interference point to obtain the gray level image of the lithium battery pole piece after noise reduction.
10. The method for on-line monitoring of edge burrs of a lithium battery pole piece according to claim 1, wherein the step of obtaining an edge burr defect image according to the gray level image of the lithium battery pole piece after noise reduction and obtaining the edge burrs according to the edge burr defect image comprises the following specific steps:
and carrying out Ojin threshold segmentation on the lithium battery pole piece gray level image after noise reduction to obtain an optimal segmentation threshold value, setting the gray level value of a pixel point which is larger than the optimal segmentation threshold value in the lithium battery pole piece gray level image after noise reduction as 1, setting the gray level value of a pixel point which is smaller than or equal to the optimal segmentation threshold value as 0, and obtaining an edge burr defect image, wherein the area with the gray level value of 1 in the edge burr defect image is edge burr.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311307918.6A CN117058047B (en) | 2023-10-11 | 2023-10-11 | On-line monitoring method for edge burrs of lithium battery pole piece |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311307918.6A CN117058047B (en) | 2023-10-11 | 2023-10-11 | On-line monitoring method for edge burrs of lithium battery pole piece |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117058047A true CN117058047A (en) | 2023-11-14 |
| CN117058047B CN117058047B (en) | 2023-12-22 |
Family
ID=88655704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311307918.6A Active CN117058047B (en) | 2023-10-11 | 2023-10-11 | On-line monitoring method for edge burrs of lithium battery pole piece |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117058047B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7203245B1 (en) * | 2003-03-31 | 2007-04-10 | 3Com Corporation | Symbol boundary detector method and device for OFDM systems |
| CN101789080A (en) * | 2010-01-21 | 2010-07-28 | 上海交通大学 | Detection method for vehicle license plate real-time positioning character segmentation |
| US20130077840A1 (en) * | 2011-06-14 | 2013-03-28 | Radnostics, LLC | Automated Vertebral Body Image Segmentation for Medical Screening |
| CN103839268A (en) * | 2014-03-18 | 2014-06-04 | 北京交通大学 | Method for detecting fissure on surface of subway tunnel |
| JP2015046678A (en) * | 2013-08-27 | 2015-03-12 | キヤノン株式会社 | Image processing device, image processing method and imaging device |
| WO2015061128A1 (en) * | 2013-10-21 | 2015-04-30 | Bae Systems Information And Electronic Systems Integration Inc. | Medical thermal image processing for subcutaneous detection of veins, bones and the like |
| CN110637227A (en) * | 2017-03-29 | 2019-12-31 | 深圳配天智能技术研究院有限公司 | Detection parameter determining method and detection device |
| CN113989168A (en) * | 2021-11-02 | 2022-01-28 | 华北电力大学（保定） | Self-adaptive non-local mean filtering method for salt and pepper noise |
| CN115330784A (en) * | 2022-10-13 | 2022-11-11 | 南通金百福纺织品有限公司 | Cloth surface defect detection method |
| CN115330791A (en) * | 2022-10-13 | 2022-11-11 | 江苏东晨机械科技有限公司 | Part burr detection method |
-
2023
- 2023-10-11 CN CN202311307918.6A patent/CN117058047B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7203245B1 (en) * | 2003-03-31 | 2007-04-10 | 3Com Corporation | Symbol boundary detector method and device for OFDM systems |
| CN101789080A (en) * | 2010-01-21 | 2010-07-28 | 上海交通大学 | Detection method for vehicle license plate real-time positioning character segmentation |
| US20130077840A1 (en) * | 2011-06-14 | 2013-03-28 | Radnostics, LLC | Automated Vertebral Body Image Segmentation for Medical Screening |
| JP2015046678A (en) * | 2013-08-27 | 2015-03-12 | キヤノン株式会社 | Image processing device, image processing method and imaging device |
| WO2015061128A1 (en) * | 2013-10-21 | 2015-04-30 | Bae Systems Information And Electronic Systems Integration Inc. | Medical thermal image processing for subcutaneous detection of veins, bones and the like |
| CN103839268A (en) * | 2014-03-18 | 2014-06-04 | 北京交通大学 | Method for detecting fissure on surface of subway tunnel |
| CN110637227A (en) * | 2017-03-29 | 2019-12-31 | 深圳配天智能技术研究院有限公司 | Detection parameter determining method and detection device |
| CN113989168A (en) * | 2021-11-02 | 2022-01-28 | 华北电力大学（保定） | Self-adaptive non-local mean filtering method for salt and pepper noise |
| CN115330784A (en) * | 2022-10-13 | 2022-11-11 | 南通金百福纺织品有限公司 | Cloth surface defect detection method |
| CN115330791A (en) * | 2022-10-13 | 2022-11-11 | 江苏东晨机械科技有限公司 | Part burr detection method |
Non-Patent Citations (1)
| Title |
|---|
| 孙畅: "基于小波域的非局部均值医学图像降噪研究", 《中国优秀硕士学位论文全文数据库》, no. 01, pages 080 - 2 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117058047B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115294140A (en) | Hardware part defect detection method and system | |
| CN115953398B (en) | Defect identification method for strip steel surface | |
| CN110544231A (en) | lithium battery electrode surface defect detection method based on background standardization and centralized compensation algorithm | |
| CN115965623B (en) | Surface flaw detection method and system in transformer production | |
| CN116523921B (en) | Detection method, device and system for tab turnover condition | |
| CN116309599B (en) | Water quality visual monitoring method based on sewage pretreatment | |
| CN113834816A (en) | Machine vision-based photovoltaic cell defect online detection method and system | |
| CN117058047B (en) | On-line monitoring method for edge burrs of lithium battery pole piece | |
| CN115601368A (en) | Method for detecting defects of sheet metal parts of building material equipment | |
| CN114581446A (en) | Battery core abnormity detection method and system of laminated battery | |
| CN117314925A (en) | Metal workpiece surface defect detection method based on computer vision | |
| CN117437238B (en) | Visual inspection method for surface defects of packaged IC | |
| CN111812292B (en) | Water pollution type tracing method, device, equipment and readable storage medium | |
| CN116452581B (en) | Intelligent voltage source state detection system and method based on machine vision | |
| CN112597865A (en) | Intelligent identification method for edge defects of hot-rolled strip steel | |
| CN110288540B (en) | Carbon fiber wire X-ray image online imaging standardization method | |
| CN116385390A (en) | Method and device for detecting rubberizing quality, electronic equipment and storage medium | |
| CN114764861A (en) | Sewage treatment verification method based on computer vision | |
| CN111669575B (en) | Method, system, electronic device, medium and terminal for testing image processing effect | |
| CN114465681A (en) | Multi-node cooperative spectrum sensing method and device for power Internet of things | |
| CN113628203B (en) | Image quality detection method and detection system | |
| CN115170446B (en) | Self-adaptive metal plate image enhancement method based on morphological processing | |
| CN117094912B (en) | Welding image enhancement method and system for low-voltage power distribution cabinet | |
| CN112614069B (en) | Face picture dimension reduction fuzzy preprocessing method | |
| CN115311300B (en) | Saw blade defect detection 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 |