A method and system for detecting burrs on a pole piece

Abstract

The present invention proposes a method and system for detecting burrs on a pole piece. The method comprises: obtaining a pole piece image and selecting an ROI; calculating the row coordinates of the actual foil center point of each column in the ROI column by column to extract the center line of the foil in the ROI; determining the pixel points of the coating area column by column based on the grayscale value of each area in the ROI, taking the maximum value of the row coordinates corresponding to the pixel points of the coating area in any column as the lower boundary of the coating, and the minimum value as the upper boundary of the coating; calculating the difference between the row coordinates of the center line of the foil in any column and the upper boundary of the coating in the current column and the lower boundary of the coating in the current column, respectively, to determine the burr type of the current column. The method disclosed in the present application realizes the extraction of the center line of the foil and the determination of the boundary of the coating area at the same time according to the grayscale value distribution characteristics of the pole piece image, so as to use the difference between the row coordinates of the center line of the foil and the boundary of the coating area as the basis for judging the burr type. The calculation method is simple and fast, effectively resists noise interference, and the detection result is highly accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial detection, and in particular to a pole piece burr detection method and system. Background Art

[0002] Pole sheet production is the basic process for manufacturing lithium-ion power batteries. The positive electrode is coated on both sides of copper foil, and the negative electrode is coated on both sides of aluminum foil. The positive and negative pole sheets are separated by a diaphragm. Pole sheet slitting and die-cutting is the process of slitting the rolled battery pole sheets according to the battery specifications, including hardware slitting, die-cutting and laser slitting and die-cutting. The pole sheet coating is a composite material composed of layered metal salt particles or layered carbon particles such as petroleum coke, which has almost no plastic deformation ability. When the internal stress generated by the upper and lower disc knives or the high temperature of the laser is greater than the bonding force between the coating particles, cracks will appear in the coating and eventually expand and separate. This is the pole sheet slitting process. The pole sheets after slitting should not have wrinkles, powder loss, burrs, or dimensional deviations; if the length of the burr exceeds half of the diaphragm, it is possible to pierce the diaphragm to form a short circuit between the positive and negative electrodes, causing a battery safety accident.

[0003] In order to prevent burrs from being generated during the electrode slitting process, which may lead to safety accidents, the end face burr detection process is added after slitting. Currently, electrode burr detection usually adopts manual sampling, which has the disadvantages of strong subjectivity, low efficiency, poor real-time performance, and is very easy to miss detection, resulting in serious consequences. It is difficult to be competent in complex and high-speed industrial production environments.

[0004] Chinese patent CN118570188A proposes a battery pole piece burr recognition method, device, equipment and storage medium, which implements a series of image processing methods on the battery pole piece burr image to achieve high accuracy and high precision detection of pole piece burrs. This is different from the technical problem solved by this solution.

[0005] Chinese patent CN116579972A discloses a battery pole piece burr detection method, which uses segmented histogram statistics to quickly screen out effective edges, calculates regional features as screening conditions, and combines the effective edges of the active layer and the regional features of the metal layer to accurately and quickly screen out burrs, greatly improving the detection efficiency. This is different from the technical means of this solution. Summary of the invention

[0006] The present invention provides a pole piece burr detection method and system, which can solve at least one of the above-mentioned technical problems.

[0007] To achieve the above object, the present invention proposes the following technical solutions:

[0008] A method for detecting burrs on a pole piece, comprising:

[0009] Get the electrode image and select ROI, which includes background area, coating area and foil area;

[0010] Calculate the row coordinates of the actual foil center point of each column in the ROI column by column to extract the center line of the foil in the ROI;

[0011] Based on the grayscale value of each area in the ROI, the pixel points of the coating area are determined column by column, and the maximum value of the row coordinates corresponding to the pixel points of any column of the coating area is used as the lower boundary of the coating, and the minimum value is used as the upper boundary of the coating;

[0012] The differences between the row coordinates of the center line of any column of foil and the upper boundary of the coating of the current column and the lower boundary of the coating of the current column are calculated to determine the burr type of the current column.

[0013] Further, the extracting the center line of the foil in the ROI includes: calculating the row coordinates of the center point of the foil in each column of the ROI column by column; if there is only one row coordinate of the center point of the foil in the current column, using the row coordinate of the center point of the foil as the actual row coordinate of the center point of the foil, as the row coordinate of the center line of the foil in the current column, for extracting the center line of the foil in the ROI.

[0014] Further, the extracting the center line of the foil in the ROI includes: calculating the row coordinates of the center point of the foil and the reference center row coordinates of each column in the ROI column by column, determining the actual row coordinates of the center point of the foil in the current column as the row coordinates of the center line of the foil in the current column, and extracting the center line of the foil in the ROI.

[0015] Furthermore, the actual foil center row coordinates include: if there are two or more foil center row coordinates in the current column, then the difference between the reference center row coordinates of the current column and each foil center row coordinate is calculated, and the foil center row coordinates with the smallest distance are selected as the actual foil center row coordinates of the current column; if there are no foil center row coordinates in the current column, then the reference center row coordinates of the current row are used as the actual foil center row coordinates.

[0016] Furthermore, it also includes: if it is the first column, according to the position relationship between the foil area and the ROI row of the first column, based on the number of rows of the ROI, the default row coordinates of the first column are calculated; if there are no row coordinates of the center point of the foil in the first column, the default row coordinates are used as the row coordinates of the center of the foil, the row coordinates of the reference center, and the row coordinates of the actual center of the foil; if there are two or more row coordinates of the center point of the foil in the first column, the default row coordinates are used as the reference center row coordinates.

[0017] Furthermore, the row coordinates of the center point of the foil material include: filtering the image data of the ROI column by column, selecting at least three consecutive pixel points whose grayscale values ​​are greater than the grayscale threshold of the foil material in any column to form a point set; and taking the mean of the row coordinates in the point set as the row coordinates of the center point of the foil material in the current column.

[0018] Further, the reference center row coordinates include: taking the actual foil center point row coordinates of the first column of image data as the reference center row coordinates of the first column; setting every T columns as a calculation cycle, and the average of the actual foil center point row coordinates from the (i-1)th column to the (iT)th column as the reference center row coordinates of the i-th column of image data; if it is less than one calculation cycle, calculating the average of the actual foil center point row coordinates from the (i-1)th column to the first column as the reference center row coordinates of the i-th column; wherein, i>T≥2.

[0019] Further, the pixel points of the coating area are determined column by column, including: if the grayscale mean value of a consecutive pixel points in the current column is greater than a first threshold value, and the maximum value of the grayscale values ​​corresponding to the a consecutive pixel points is less than a second threshold value, then the a consecutive pixel points are in the coating area of ​​the current column; traverse the pixel points of the current column to obtain all pixel points of the coating area of ​​the current column; wherein the first threshold value is the mean value of the grayscale value of the background area and the grayscale value of the coating area; the second threshold value is the mean value of the grayscale value of the coating area and the grayscale value of the foil area; a is a positive integer, a≥3.

[0020] Further, the determining of the burr type of the current column includes: calculating a first difference between the row coordinates of the center line of the foil in any column and the upper boundary of the coating in the current column, and a second difference between the row coordinates of the lower boundary of the coating in the current column and the center line of the foil in the current column; if the first difference or the second difference is less than zero, it is determined to be a Class A burr; if the first difference or the second difference is greater than zero and less than a burr threshold, it is determined to be a Class B burr.

[0021] Based on the same inventive concept, the present invention also proposes a pole piece burr detection system, comprising:

[0022] An acquisition module is used to acquire the electrode image and select ROI, which includes the background area, coating area, and foil area;

[0023] A centerline extraction module is used to calculate the row coordinates of the actual foil center point of each column in the ROI column by column to extract the centerline of the foil in the ROI;

[0024] The coating boundary determination module is used to determine the pixel points of the coating area column by column based on the grayscale value of each area in the ROI, and the maximum grayscale value corresponding to the pixel points of the coating area is used as the lower boundary of the coating, and the minimum grayscale value is used as the upper boundary of the coating;

[0025] The burr determination module is used to calculate the difference between the row coordinates of the center line of any column of foil and the upper boundary of the coating of the current column and the lower boundary of the coating of the current column, and determine the burr type of the current column.

[0026] The beneficial effects of the present invention are as follows:

[0027] The electrode burr detection method disclosed in the present invention combines the gray value distribution characteristics of the electrode image, utilizes the gray threshold of the foil area, quickly determines the pixel points in the foil area, and calculates the row coordinates of the actual foil center point to extract the foil center line in the ROI, and quickly determines the boundary of the coating area, thereby quickly realizing the burr detection process and effectively avoiding safety accidents caused by burrs.

[0028] In the present invention, the extraction of the foil centerline and the boundary of the coating area can be realized simultaneously, and the calculation is fast.

[0029] The calculation process of foil centerline extraction in the present invention can not only effectively resist the interference of foil centerline extraction caused by noise, but also interpolate the missing coordinates of the actual foil center point, so that the calculation result of the foil centerline finally extracted has high accuracy, thereby improving the accuracy of the detection result.

[0030] In the present invention, the difference between the row coordinates of the center line of the foil and the boundary of the coating area is used as the basis for judging the burr type. The calculation method is simple and fast, and the damage degree of the current burr can be judged intuitively. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic flow chart of the pole piece burr detection method in the present invention;

[0032] Figure 2 is the pole piece image obtained in the present invention;

[0033] Figure 3 is the pole piece image with burrs obtained in the present invention;

[0034] Figure 4 is a schematic diagram of a grayscale histogram of a pole piece image in the present invention;

[0035] Figure 5 It is a schematic diagram of the row coordinates of the three foil center points in the present invention;

[0036] Figure 6 is a schematic diagram of a type A burr in the present invention;

[0037] Figure 7 Schematic diagram of Class B burrs in the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0039] like Figure 1As shown, the present invention proposes a method for detecting burrs on a pole piece, comprising:

[0040] Acquire the electrode image and select ROI, which includes the background area, coating area, and foil area.

[0041] The pole piece image obtained in the present invention is an image of the cut end surface of the lithium battery pole piece, so as to detect whether there are burrs on the cut end surface.

[0042] like Figure 2 As shown in the figure, the ROI includes the background area, coating area, and foil area. Figure 2 From top to bottom, the distribution order is background area, coating area, foil area, coating area, and background area.

[0043] like Figure 3 As shown in the figure, the ROI includes the background area, coating area, and foil area, and there are burrs in the coating area. Figure 3 From top to bottom, the distribution order is background area, coating area, foil area, coating area, background area. The foil area extends upward to form a protrusion (i.e., burr), and the highest point of the protrusion is close to the boundary of the coating area.

[0044] According to the IEEE1725 battery safety performance review and testing standards, burrs are metal protrusions that extend upward or downward from the foil to the outside of the pole piece with the foil (i.e., the uncoated area) as the baseline; or metal protrusions that extend upward or downward from the coating to the outside of the pole piece in the coated area; the burr size is measured by measuring the vertical height of the burr. If the burr is too large, it is easy to pierce the diaphragm, and then the positive and negative electrodes contact and cause a short circuit. If a short circuit occurs when the battery is fully charged, a large amount of heat will be released immediately inside, causing an explosion, seriously endangering the lives and property of consumers.

[0045] The method further includes: setting a foil grayscale threshold to screen the pixels of the foil area. In this embodiment, the average grayscale value of the foil area in the ROI is used as the foil grayscale threshold.

[0046] There are two ways to obtain the grayscale threshold of foil:

[0047] Method 1: Use the statistical results of the gray value histogram to obtain the gray threshold of the foil. The details are as follows:

[0048] like Figure 4 As shown, the grayscale histogram of the statistical pole piece image is obtained.

[0049] According to the grayscale histogram, the grayscale mean of the background interval in the grayscale histogram is used as the grayscale value of the background area in the electrode image; the grayscale mean of the coating interval in the grayscale histogram is used as the grayscale value of the coating area in the electrode image; the grayscale mean of the foil interval in the grayscale histogram is used as the grayscale value of the foil area in the electrode image, that is, the foil grayscale threshold.

[0050] Grayscale histogram is a function of grayscale distribution, which is a statistic of grayscale distribution in the image of the tested area (pole image). The grayscale histogram of an image describes the statistical characteristics of the image at 256 grayscale levels. Its row coordinates represent the grayscale values ​​corresponding to the 256 grayscale levels and are 0-255 from left to right. The ordinate represents the number of pixels or the frequency of occurrence of pixels at each grayscale value (in this article, the ordinate represents the number of pixels at each grayscale value).

[0051] If the vertical axis represents the frequency of occurrence of pixels at each grayscale value in the image, the grayscale histogram calculation formula is: p(rk) = nk / MN. Among them, rk is the grayscale level (grayscale value) of the pixel, nk is the number of pixels with grayscale rk (number of pixels), and MN is the total number of pixels in the image.

[0052] In this paper, the ordinate represents the number of pixels of the image at each grayscale value. It is only necessary to count the number of pixels at a certain grayscale value, and there is no need to determine the grayscale histogram of the pole image through this formula.

[0053] Method 2: Preferably, the grayscale threshold of the foil material can be obtained by artificially setting it based on experience, without using the above-mentioned grayscale histogram calculation process.

[0054] Generally, in order to facilitate the observation of burr detection, when obtaining the pole piece image, the pole piece image is adjusted to the center of the field of view; at the same time, the area where the foil material is located in the center is selected as the ROI. Therefore, the grayscale mean value of the pixel point at the center of the pole piece image (or ROI) is used to estimate the grayscale threshold of the foil material.

[0055] According to the number of pixels in the theoretical foil interval and the pixel accuracy of the imaging system, the grayscale mean G of several pixels at the center of the pole piece image (or ROI) is calculated. According to the empirical criteria, the grayscale value of the foil area (foil grayscale threshold) GT=G×80% is set.

[0056] In addition, the grayscale value GP of the coating area and the grayscale value GB of the background area can also be set manually.

[0057] The number of pixels in the theoretical foil interval is the product of the theoretical number of foil rows and the image width, and the theoretical number of foil rows is the ratio of the foil thickness to the pixel accuracy. The image width is the number of pixels in the horizontal direction of the image actually collected.

[0058] The pixel accuracy of the current electrode image acquisition device is p um / pixel, and the foil thickness is q um, so the theoretical number of rows of foil is q / p. For example, if the image is 4000 wide and 200 high, the theoretical number of rows of foil is generally 3, and the theoretical number of pixels in the foil interval is 12000.

[0059] The pole piece burr detection method proposed by the present invention also includes:

[0060] The row coordinates of the actual foil center point of each column in the ROI are calculated column by column to extract the foil center line in the ROI.

[0061] There are two calculation methods for extracting the center line of the foil in ROI:

[0062] Method 1: Calculate the row coordinates of the center point of the foil in each column of the ROI column by column; if there is only one row coordinate of the center point of the foil in the current column, use the row coordinate of the center point of the foil as the actual row coordinate of the center point of the foil and the row coordinate of the center line of the foil in the current column to extract the center line of the foil in the ROI.

[0063] Method 2: Calculate the row coordinates of the center point of the foil and the reference center of each column in the ROI column by column, determine the actual row coordinates of the center point of the foil in the current column, and use them as the row coordinates of the center line of the foil in the current column to extract the center line of the foil in the ROI. Method 2 is for the case where there is more than one row coordinate of the center point of the foil in the current column, such as no row coordinates of the center point of the foil or multiple row coordinates of the center point of the foil, as follows:

[0064] If there are two or more foil center row coordinates in the current column, the difference between the reference center row coordinate of the current column and each foil center row coordinate is calculated, and the foil center row coordinate with the smallest distance is selected as the actual foil center row coordinate of the current column;

[0065] If the row coordinates of the center point of the foil material do not exist in the current column, the row coordinates of the reference center point of the current row are used as the row coordinates of the actual center point of the foil material.

[0066] The reference center row coordinates include: taking the actual foil center row coordinates of the first column of image data as the reference center row coordinates of the first column; setting every T columns as a calculation cycle, and taking the average of the actual foil center row coordinates from the (i-1)th column to the (iT)th column as the reference center row coordinates of the i-th column of image data; if it is less than one calculation cycle, then calculating the average of the actual foil center row coordinates from the (i-1)th column to the first column as the reference center row coordinates of the i-th column; wherein, i>T≥2.

[0067] If the calculation process of method 2 is used to obtain the row coordinates of the center line of the foil in the first column, the calculation process of the row coordinates of the actual foil center point in the first column is as follows:

[0068] If it is the first column, the default row coordinates of the first column are calculated based on the position relationship between the foil area and the ROI row in the first column and the number of rows of ROI; if there are no row coordinates of the foil center point in the first column, the default row coordinates are used as the foil center row coordinates, the reference center row coordinates, and the actual foil center row coordinates; if there are two or more foil center row coordinates in the first column, the default row coordinates are used as the reference center row coordinates.

[0069] In the above two calculation methods for extracting the center line of the foil, the coordinates of the center point of the foil include:

[0070] The image data of ROI is screened column by column, and at least three consecutive pixels with grayscale values ​​greater than the grayscale threshold of the foil are selected in any column to form a point set; the mean of the row coordinates in the point set is used as the row coordinate of the center point of the foil in the current column.

[0071] In this embodiment, the calculation process of the row coordinates of the actual foil center point of the first column of image data in the ROI is as follows:

[0072] At least three consecutive pixel points whose grayscale values ​​of the first column of pixels are greater than the grayscale threshold of the foil material are selected to form a point set; and the row coordinate mean of the point set is used as the row coordinate of the center point of the foil material in the first column.

[0073] If there is only one row coordinate of the center point of the foil material, the row coordinate of the center point of the foil material is used as the actual row coordinate of the center point of the foil material.

[0074] If there are multiple row coordinates of the center point of the foil, since the image data of the first column is not in the previous column, the reference center row coordinates of the first column cannot be calculated based on the actual row coordinates of the center point of the foil in the previous column. Therefore, for the above situation where multiple row coordinates of the center point of the foil appear, this embodiment proposes to use the row position relationship of the foil area in the first column in the ROI as the reference center row coordinates of the first column.

[0075] Generally, in order to facilitate the observation of burr detection, when acquiring the pole piece image, the pole piece image is adjusted to the center of the field of view; at the same time, the area where the foil area is located at the center is selected as the ROI.

[0076] In this embodiment, the row position relationship of the foil area in any column of the ROI is that the foil area is located at the center of the ROI. Assuming that the ROI has m rows, the default row coordinates of the foil area are m / 2. At this time, the row position relationship of the foil area in the first column in the ROI is also the default row coordinates.

[0077] Then the reference center row coordinates C of the first column are 1,ref =m / 2.

[0078] Preferably, the foil area may also be set to be one-third or one-quarter of the ROI row coordinates, or other positions.

[0079] If the first column cannot filter out continuous pixel points that meet the foil grayscale threshold, refer to the calculation process of the reference center row coordinates of the first column, and use the default row coordinates as the foil center row coordinates, reference center row coordinates, and actual foil center row coordinates of the row.

[0080] Referring to the calculation process of the row coordinates of the actual foil center point of the first column, the row coordinates of the actual foil center point of the i-th (i≥2) column of image data are calculated as follows:

[0081] Among them, the reference center row coordinates of the i-th column include:

[0082] The actual foil center row coordinates of the first column of image data are used as the reference center row coordinates of the first column; each T column is set as a calculation cycle, and the average of the actual foil center row coordinates from the (i-1)th column to the (iT)th column is used as the reference center row coordinates of the i-th column of image data; if it is less than one calculation cycle, the average of the actual foil center row coordinates from the (i-1)th column to the first column is calculated as the reference center row coordinates of the i-th column; wherein, i>T≥2.

[0083] In order to facilitate the processing of image data in the ROI and improve calculation efficiency, in this embodiment, every T (i>T≥2) columns of image data are set as a column period, which serves as the calculation basis for the reference center point coordinates of the first column after the column period.

[0084] In this embodiment, every 8 columns of image data are set as one column period, that is, T=8.

[0085] Preferably, T=32 or T=64, or other values, may be set according to factors such as the resolution and size of the current polar image (or ROI).

[0086] Preferably, the calculation cycle may not be set.

[0087] In this embodiment, according to the calculation method of the foil center row coordinates of the first column of image data, the foil center row coordinates of each column are calculated column by column. Based on the actual foil center row coordinates of the previous column, the reference center row coordinates of the current column are calculated as follows:

[0088] In the first column cycle, if the second column of image data, its previous column is the first column (less than one calculation cycle), the actual foil center row coordinate C1 of the first column is the foil center row coordinate of this row. Then the reference center row coordinate C of the second column 2,ref =sum(C1) / (2-1)=C1.

[0089] If there are two or more foil center point row coordinates in the second column, the difference between the reference center row coordinates in the second column and the multiple foil center point row coordinates in the column is calculated respectively, and the distance C is selected. 2,ref The row coordinate of the nearest foil center point is used as the row coordinate C2 of the actual foil center point in the second column and as the row coordinate of the foil center line in the second column for subsequent extraction of the foil center line.

[0090] like Figure 5 As shown, taking the case where there are three foil center point row coordinates as an example, the example is explained as follows:

[0091] The row coordinates of the three foil center points are: i,1 , candidate point 2 row coordinates C i,2 , the candidate point 3 row coordinates C i,3 .

[0092] Calculate the reference center row coordinate C of the current column i,ref The row coordinates of each foil center point (candidate point 1 row coordinates C i,1 , candidate point 2 row coordinates C i,2 , the candidate point 3 row coordinates C i,3 ) and select the row coordinate of the center point of the foil with the smallest distance (row coordinate of candidate point 2 C i,2 ), as the row coordinate C of the actual foil center point of the current column i =C i,2 .

[0093] If the calculation of the row coordinates of the foil center point in the second column belongs to other cases, the processing method is the same as that of the first column.

[0094] Similarly, for the third column, its preceding columns include the first and second columns (less than one calculation cycle), and the reference center row coordinate C of the third column is 3,ref =sum(C1,C2) / (3-1)=(C1+C2) / 2. Based on the reference center row coordinates and the foil center row coordinates of the third column, the actual foil center row coordinates C3 of the third column are determined as the row coordinates of the foil center line of the third column for subsequent extraction of the foil center line.

[0095] In this embodiment, every 8 columns are set as a calculation cycle.

[0096] Similarly, for the 9th column, its previous columns include the first to eighth columns, and the reference center row coordinate C of the 9th column is 9,ref =sum(C1,...,C8) / 8. Based on the reference center row coordinates of the 9th column and the foil center point row coordinates, the actual foil center point row coordinates C9 of the 9th column are determined as the row coordinates of the foil center line of the 9th column for subsequent extraction of the foil center line.

[0097] In summary, based on the row coordinates C of the actual foil center point in any column i , the reference center coordinates C of the i-th column image data i,ref The calculation formula is:

[0098]

[0099] Since in this embodiment, every 8 columns are set as a calculation cycle, the reference center coordinate C of the i-th column image data is i,ref The calculation formula is as follows:

[0100]

[0101] Based on the grayscale values ​​of each area in the ROI, the pixel points of the coating area are determined column by column, including:

[0102] If the grayscale mean of a consecutive pixel points in the current column is greater than the first threshold, and the maximum grayscale value corresponding to the a consecutive pixel points is less than the second threshold, then the a consecutive pixel points are in the coating area of ​​the current column; traverse the pixel points of the current column to obtain all pixel points in the coating area of ​​the current column; wherein the first threshold is the mean of the grayscale value of the background area and the grayscale value of the coating area; the second threshold is the mean of the grayscale value of the coating area and the grayscale value of the foil area; a is a positive integer, a≥3.

[0103] The maximum grayscale value corresponding to the pixel points in any column of the coating area is taken as the lower boundary of the coating, and the minimum grayscale value is taken as the upper boundary of the coating.

[0104] The grayscale value GP of the coating area, the grayscale value GB of the background area, and the grayscale value GT of the foil area are obtained respectively by using the grayscale histogram or the calculation method of the empirical rule.

[0105] In this embodiment, the relationship between the grayscale values ​​of five consecutive pixels in any column and the first threshold and the second threshold is set as the determination condition for the pixels in the coating area.

[0106] The grayscale values ​​of 5 consecutive pixels in any column (i-th column) are: G(j-2), G(j-1), G(j), G(j+1), G(j+2).

[0107] In this embodiment, if the above five pixels are all pixels in the coating area, their grayscale values ​​simultaneously satisfy:

[0108] sum(G(j-2),G(j-1),G(j),G(j+1),G(j+2)) / 5>GP1;

[0109] max(G(j-2),G(j-1),G(j),G(j+1),G(j+2)) <GP2。

[0110] Among them, the first threshold GP1=(GB+GP) / 2; the second threshold GP2=(GT+GP) / 2.

[0111] Traverse the pixels of the current column to obtain all the pixels of the coating area of ​​the current column.

[0112] Filter the maximum value of the row coordinates of all pixels in the coating area of ​​the current column (column i) , and the minimum value ; Take the maximum value of the row coordinates of all pixels in the coating area of ​​the current column As the lower boundary of the coating area of ​​the current column, the minimum value of the row coordinates of all pixels in the coating area of ​​the current column The upper boundary of the coating area for the current column.

[0113] The pixel points of the coating area are determined column by column to complete the determination of the coating upper boundary and the coating lower boundary of each column.

[0114] Calculate the row coordinate C of the center line of any column of foil i The burr type of the current column is determined by the difference between the upper boundary of the coating of the current column and the lower boundary of the coating of the current column.

[0115] The row coordinate C of the center line of the foil in any column (i-th column) i Subtract the top edge of the coating of the current column The first difference d 1,i =C i - ;

[0116] The coating lower boundary of the current column (column i) Subtract the row coordinate C of the center line of the foil in this column i The second difference d 2,i = -C i ;

[0117] If the first difference d 1,i <0 or the second difference d 2,i <0, it is judged as Class A burr, such as Figure 6 As shown;

[0118] If dT>d 1,i >0 or dT>d 2,i >0, it is judged as Class B glitch, such as Figure 7 shown.

[0119] Among them, dT is the burr threshold, which indicates the distance between the extended end of the burr and the coating boundary. According to experience, dT is generally set to 3-5 pixels, but its specific value is related to factors such as electrode production and processing technology.

[0120] The burr starts from the foil area and extends toward the coating boundary (coating upper boundary and / or coating lower boundary), and the end close to the coating boundary is the extension end.

[0121] like Figure 6 As shown in the figure, the extension end of the Class A burr has exceeded the coating boundary. If this type of pole piece is used, a safety accident is very likely to occur.

[0122] like Figure 7 As shown, the extended end of the Class B burr maintains a distance dT from the coating boundary. If it is subjected to extrusion or similar operations, it may become a Class A burr and cause a safety accident.

[0123] The electrode burr detection method disclosed in the present application realizes the extraction of the foil centerline and the determination of the boundary of the coating area at the same time according to the gray value distribution characteristics of the electrode image, so as to utilize the difference between the row coordinates of the foil centerline and the boundary of the coating area as the basis for judging the burr type. The calculation method is simple and fast, and it can effectively resist noise interference, and the detection result has high accuracy.

[0124] Based on the same inventive concept, the present application also proposes a pole piece burr detection system, comprising:

[0125] An acquisition module is used to acquire the electrode image and select ROI, which includes the background area, coating area, and foil area;

[0126] A centerline extraction module is used to calculate the row coordinates of the actual foil center point of each column in the ROI column by column to extract the centerline of the foil in the ROI;

[0127] The coating boundary determination module is used to determine the pixel points of the coating area column by column based on the grayscale value of each area in the ROI, and the maximum grayscale value corresponding to the pixel points of the coating area is used as the lower boundary of the coating, and the minimum grayscale value is used as the upper boundary of the coating;

[0128] The burr determination module is used to calculate the difference between the row coordinates of the center line of any column of foil and the upper boundary of the coating of the current column and the lower boundary of the coating of the current column, and determine the burr type of the current column.

[0129] The present invention further proposes an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned pole piece burr detection method.

[0130] The present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the pole piece burr detection method as described above is implemented.

[0131] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting burrs on a pole piece, comprising: The electrode image is obtained and ROI is selected, wherein the ROI includes a background area, a coating area, and a foil area, and is characterized in that it also includes: Calculate the row coordinates of the actual foil center point of each column in the ROI column by column to extract the foil center line in the ROI; The actual row coordinates of the center point of the foil material include: calculating the row coordinates of the center point of the foil material and the row coordinates of the reference center of each column in the ROI column by column; if there are two or more row coordinates of the center point of the foil material in the current column, then calculating the difference between the row coordinates of the reference center of the current column and the row coordinates of each center point of the foil material, and selecting the row coordinates of the center point of the foil material with the smallest distance as the actual row coordinates of the center point of the foil material in the current column; if there are no row coordinates of the center point of the foil material in the current column, then using the row coordinates of the reference center of the current row as the actual row coordinates of the center point of the foil material; Based on the grayscale value of each area in the ROI, the pixels of the coating area are determined column by column, and the maximum value of the row coordinates corresponding to the pixels of any column of the coating area is used as the lower boundary of the coating, and the minimum value is used as the upper boundary of the coating; The differences between the row coordinates of the center line of any column of foil and the upper boundary of the coating of the current column and the lower boundary of the coating of the current column are calculated to determine the burr type of the current column.

2. The pole piece burr detection method according to claim 1, characterized in that: The step of calculating the row coordinates of the actual foil center point of each column in the ROI column by column to extract the foil center line in the ROI includes: Calculate the row coordinates of the foil center point in each column of the ROI column by column; if there is only one row coordinate of the foil center point in the current column, use the row coordinate of the foil center point as the actual row coordinate of the foil center point and the row coordinate of the foil center line of the current column to extract the foil center line in the ROI.

3. The pole piece burr detection method according to claim 1, characterized in that: Also includes: If it is the first column, the default row coordinates of the first column are calculated based on the position relationship between the foil area and the ROI row in the first column and the number of rows of ROI; if there are no row coordinates of the foil center point in the first column, the default row coordinates are used as the foil center row coordinates, the reference center row coordinates, and the actual foil center row coordinates; if there are two or more foil center row coordinates in the first column, the default row coordinates are used as the reference center row coordinates.

4. The pole piece burr detection method according to claim 1 or 2, characterized in that: The row coordinates of the center point of the foil include: The image data of ROI is screened column by column. At least three consecutive pixels with grayscale values ​​greater than the grayscale threshold of the foil are selected in any column to form a point set. The mean of the row coordinates in the point set is used as the row coordinate of the center point of the foil in the current column.

5. The pole piece burr detection method according to claim 3, characterized in that: The reference center row coordinates include: The row coordinates of the actual foil center point of the first column of image data are taken as the reference center row coordinates of the first column; each T column is set as a calculation cycle, and the average of the row coordinates of the actual foil center point from the (i-1)th column to the (iT)th column is taken as the reference center row coordinates of the i-th column of image data; if it is less than one calculation cycle, the average of the row coordinates of the actual foil center point from the (i-1)th column to the first column is calculated as the reference center row coordinates of the i-th column; wherein, i>T≥2.

6. The pole piece burr detection method according to claim 1, characterized in that: The pixel points of the coating area include: If the grayscale mean of a consecutive pixel points in the current column is greater than the first threshold, and the maximum grayscale value corresponding to the a consecutive pixel points is less than the second threshold, then the a consecutive pixel points are in the coating area of ​​the current column; traverse the pixel points of the current column to obtain all pixel points in the coating area of ​​the current column; wherein the first threshold is the mean of the grayscale value of the background area and the grayscale value of the coating area; the second threshold is the mean of the grayscale value of the coating area and the grayscale value of the foil area; a is a positive integer, a≥3.

7. The pole piece burr detection method according to claim 1, characterized in that: The glitch types of the current column include: Calculate the first difference between the row coordinates of the center line of any column of foil and the upper boundary of the coating in the current column, and the second difference between the row coordinates of the lower boundary of the coating in the current column and the center line of the foil in the current column; if the first difference or the second difference is less than zero, it is determined to be a Class A burr; if the first difference or the second difference is greater than zero and less than the burr threshold, it is determined to be a Class B burr.

8. A pole piece burr detection system, characterized in that: include: The acquisition module is used to acquire the electrode image and select the ROI, which includes the background area, coating area, and foil area; A centerline extraction module is used to calculate the row coordinates of the actual foil center point of each column in the ROI column by column to extract the centerline of the foil in the ROI; The actual row coordinates of the center point of the foil material include: calculating the row coordinates of the center point of the foil material and the row coordinates of the reference center of each column in the ROI column by column; if there are two or more row coordinates of the center point of the foil material in the current column, then calculating the difference between the row coordinates of the reference center of the current column and the row coordinates of each center point of the foil material, and selecting the row coordinates of the center point of the foil material with the smallest distance as the actual row coordinates of the center point of the foil material in the current column; if there are no row coordinates of the center point of the foil material in the current column, then using the row coordinates of the reference center of the current row as the actual row coordinates of the center point of the foil material; The coating boundary determination module is used to determine the pixel points of the coating area column by column based on the grayscale value of each area in the ROI, and the maximum grayscale value corresponding to the pixel points of the coating area is used as the lower boundary of the coating, and the minimum grayscale value is used as the upper boundary of the coating; The burr determination module is used to calculate the difference between the row coordinates of the center line of any column of foil and the upper boundary of the coating of the current column and the lower boundary of the coating of the current column, and determine the burr type of the current column.

Images