Battery piece sorting method and device

Abstract

The invention provides a battery piece sorting method and device. The sorting method comprises the steps of obtaining a target color image of a to-be-detected battery piece, wherein target color image data comprises a target B value and a target R value; according to the target B value and the target R value, whether the to-be-detected battery piece is a heterochromatic battery piece or not is judged based on a predefined sorting function; wherein the sorting function is obtained in advance in the following mode: collecting a color image of each battery piece in a sample set of marked normal battery pieces and different-color battery pieces, extracting RGB three-channel values of the color images, importing the extracted R value, G value and B value into an R-G-B three-dimensional coordinate system as three-dimensional coordinates, and then projecting the three-dimensional coordinates into a B-R plane, and according to the distribution of the normal battery pieces and the heterochromatic battery pieces in the B-R plane, constructing a sorting function for distinguishing the normal battery pieces and the heterochromatic battery pieces. According to the method, the real sorting rate is improved, and meanwhile, the misjudgment rate is reduced.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of detection technology, and in particular, to a method, device, computer equipment, computer-readable storage medium, and computer program product for sorting battery cells. Background Art

[0002] With the gradual development of photovoltaic power generation technology, distributed photovoltaic power generation and household photovoltaic power generation are gradually promoted, and the demand for aesthetics is gradually increasing, which requires photovoltaic modules to have better color consistency. In the current process, the production process from cell to cell undergoes multiple automated optical inspections (AOI inspections) and is graded by color. The color difference of cells of the same level cannot be distinguished by the naked eye. After the cells are laminated and assembled into photovoltaic modules, there are still about 0.1‰ heterochromatic cells. Even if the color performance is basically the same as that of normal cells before packaging, after lamination, there will be cells that show a large color difference with most of the cells in the module, thereby destroying the overall color consistency of the photovoltaic module. The photovoltaic module itself is composed of about 100 cells. Any heterochromatic cell mixed into the module will cause a huge difference in the color of the photovoltaic module, which is easy to reduce the qualified rate of aesthetic photovoltaic modules. For the detection of heterochromatic cells in the cells used in aesthetic photovoltaic modules, due to the pyramid velvet structure of the cells, their optical properties are extremely complex and disordered. In the process of sorting technology development, no obvious rules and boundaries between heterochromatic cells and normal cells were found by AOI monitoring with industrial cameras. According to public data, the improvement methods of AOI detection for the sorting of heterochromatic cells are mostly focused on accuracy, sampling points, etc. The real sorting rate obtained by the improved AOI detection is about 30%, and the misjudgment rate is about 7%. Among them, the real sorting rate is the number of heterochromatic cells sorted out / the number of cells sorted out × 100%. The misjudgment rate is the normal cells sorted out / the sample size of cells × 100%. For example, the sample size of cells is 100 sheets, 10 are heterochromatic cells, and 90 are normal cells. 10 sheets are sorted out through AOI detection, and only 3 of the 10 sheets are heterochromatic cells. At this time, the real sorting rate is about 30%, and the misjudgment rate is about 7%.

[0003] It should be noted that the above content is not necessarily prior art, nor is it intended to limit the scope of patent protection of this application. Summary of the invention

[0004] The embodiments of the present application provide a battery cell sorting method, apparatus, computer equipment, computer-readable storage medium, and computer program product to solve or alleviate one or more of the technical problems raised above.

[0005] One aspect of an embodiment of the present application provides a method for sorting battery cells, the method comprising:

[0006] Acquire a target color image of the battery cell to be inspected, wherein the target color image data includes a target B value and a target R value;

[0007] According to the target B value and the target R value, determining whether the battery cell to be inspected is a heterochromatic battery cell based on a predefined sorting function;

[0008] Wherein, the sorting function is obtained in advance in the following manner:

[0009] The color image of each cell in the sample set of marked normal cells and heterochromatic cells is collected, and the RGB three-channel values ​​of the color image are extracted. The extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane. According to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed.

[0010] Another aspect of an embodiment of the present application provides a battery cell sorting device, the device comprising:

[0011] An acquisition module, used to acquire a target color image of the battery cell to be inspected, wherein the target color image data includes a target B value and a target R value;

[0012] A determination module, configured to determine whether the battery cell to be inspected is a heterochromatic battery cell based on the target B value and the target R value and based on a predefined sorting function;

[0013] Wherein, the sorting function is obtained in advance in the following manner:

[0014] The color image of each cell in the sample set of marked normal cells and heterochromatic cells is collected, and the RGB three-channel values ​​of the color image are extracted. The extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane. According to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed.

[0015] Another aspect of an embodiment of the present application provides a computer device, including:

[0016] at least one processor; and

[0017] a memory communicatively coupled to the at least one processor;

[0018] Wherein: the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0019] Another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method described above is implemented.

[0020] Another aspect of an embodiment of the present application provides a computer program product, including a computer program, which implements the method described above when executed by a processor.

[0021] The above technical solution adopted in the embodiment of the present application may have the following advantages:

[0022] The cell sorting method provided in the embodiment of the present application uses a sample set of marked normal cells and heterochromatic cells to construct a sorting function, imports the RGB three-dimensional coordinate system based on the R value, G value, and B value of the color image, uses the best projection separation trend of normal cells and heterochromatic cells in the BR plane, and constructs a sorting function on the BR plane to sort normal cells and heterochromatic cells. This embodiment improves the true sorting rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0024] Figure 1 A flow chart schematically shows a method for sorting battery cells according to the first embodiment of the present application;

[0025] Figure 2 The shooting angle during the acquisition of color images is shown;

[0026] Figure 3 A lighting schematic diagram of some embodiments;

[0027] Figure 4 A scatter distribution diagram of a sample set in a three-dimensional coordinate system in some embodiments;

[0028] Figure 5 BR plane projection and sorting lines for some embodiments;

[0029] Figure 6 BG plane projection and sorting lines for some embodiments;

[0030] Figure 7 GR plane projection and sorting lines for some embodiments;

[0031] Figure 8 It is a box diagram of RGB values ​​for comparison;

[0032] Fig. 9 A block diagram of a battery cell sorting device according to the second embodiment of the present application is schematically shown;

[0033] Fig.10 The hardware architecture diagram of the computer device according to the third embodiment of the present application is schematically shown.

[0034] Among them, 1-light source; 2-battery cell; 3-tray; 4-dark box. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0036] It should be noted that the descriptions involving "first", "second", etc. in the embodiments of the present application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0037] Explanation of terms in this application:

[0038] RGB value: It is a color standard. Various colors are obtained by changing and superimposing the three color channels of red (R), green (G), and blue (B). In the RGB model, each color channel can be assigned an intensity value in the range of 0 to 255.

[0039] AOI (Automated Optical Inspection): A method that uses optical technology to automatically detect product defects and anomalies.

[0040] The currently available literature has proposed a variety of improvements to the AOI inspection of battery cells, as follows: Traditional methods mostly use one or more channel colors for multiple judgments, for example, the R channel in RGB is a certain value as the threshold, and cells that are greater than or less than this value are judged as heterochromatic cells. The difference is that a single threshold and multiple sampling points are used for judgment. At present, the following problems have been found in the verification process of this method: First, due to the pyramid velvet, the distance between the camera and each point of the battery cell will cause different angles, and the color of the collected battery cell will be more significantly different, and the thresholds at different points will be different; second, if the camera is perpendicular to the battery cell, due to the diffuse reflection of the velvet and the film layer, its color should be basically close to black, and the difference in its single-channel color difference value is small; third, the detection rate of single threshold sorting is about 30% and the misjudgment rate is about 10%.

[0041] Laminated glass is added to the front end of the industrial camera to simulate the effect after lamination in order to predict the final color of the battery cells of the sorted components. This solution is still in the theoretical stage. In addition, in the process of battery cells to components, not only glass but also sealant is added to the surface. The separation effect of this solution is not improved compared with the traditional method.

[0042] The essence of the scheme of using visual instruments to create a scatter cloud map and eliminate discrete points is similar to the traditional method of separation using a single color channel. The difference is that its threshold can change dynamically according to the increase in sample size.

[0043] Based on the above-mentioned related technologies, the actual sorting rate of AOI inspection of battery cells needs to be further improved. Accordingly, the embodiments of the present application provide a battery cell sorting method, device, computer equipment, computer-readable storage medium, and computer program product.

[0044] In the description of the present application, it should be understood that the numerical labels before the steps do not indicate the order in which the steps are executed, but are only used to facilitate the description of the present application and to distinguish each step, and therefore should not be understood as a limitation on the present application.

[0045] The following uses a computer as the execution subject to introduce the technical solution of the present application through multiple embodiments. It should be noted that these embodiments can be implemented in a variety of different forms and should not be interpreted as being limited to the embodiments described here.

[0046] Embodiment 1

[0047] In some embodiments, a battery sorting method is provided, such as Figure 1 As shown, the battery sorting method may include S100 and S200, which are specifically as follows:

[0048] S100, obtaining a target color image of the battery cell to be inspected, wherein the target color image data includes a target B value and a target R value;

[0049] S200, determining whether the battery cell to be inspected is a heterochromatic battery cell based on the target B value and the target R value and based on a predefined sorting function;

[0050] Wherein, the sorting function is obtained in advance in the following manner:

[0051] The color image of each cell in the sample set of marked normal cells and heterochromatic cells is collected, and the RGB three-channel values ​​of the color image are extracted. The extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane. According to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed.

[0052] The cell sorting method provided in this embodiment uses a sample set of marked normal cells and heterochromatic cells to construct a sorting function, and imports the RGB three-dimensional coordinate system based on the R value, G value, and B value of the color image. The inventor found that the separation trend of normal cells and heterochromatic cells in the BR plane is the best. Based on this, a sorting function is constructed on the BR plane to sort normal cells and heterochromatic cells. Therefore, compared with a single channel as a threshold, the actual sorting rate of this embodiment is higher.

[0053] It is worth noting that, in order to make the score sorting function more suitable for the battery cell to be inspected, in this embodiment, the image acquisition operation of the battery cell to be inspected and the battery cells in the sample set can be kept consistent.

[0054] Since the battery cell itself generates electricity by absorbing light, if the battery cell is photographed perpendicular to the existing shooting plane, the image of the battery cell will be dark blue-black, and its R value and G value will be suppressed, which seriously affects the subsequent sorting of normal battery cells and heterochromatic battery cells. In some embodiments, in the battery cell sorting method, the R value and G value in the color image are enhanced R value and G value. That is, the color image collected in the process of constructing the sorting function is an enhanced color image obtained by R value and G value, so as to improve the information of R value and G value in the color image, specifically in the three-dimensional space coordinate system, it is easier to separate normal battery cells and heterochromatic battery cells. Preferably, the target color image of the battery cell to be inspected is also the enhanced R value and G value. Therefore, the image acquisition operation of the battery cell to be inspected and the battery cell in the sample set can be consistent, so that the sorting function is also applicable to the sorting of the battery cell to be inspected.

[0055] In some embodiments, in the cell sorting method, factors in the process of collecting color images can be adjusted to enhance the R value and G value of the color image. For example, the angle of the shooting surface during image collection is set, and the color image meets the following conditions during the collection process: Figure 2As shown in FIG. 1 , a three-dimensional coordinate system is established with the main grid direction of the cell as the x-axis, the fine grid direction as the y-axis, and the normal of the cell as the z-axis. When collecting color images, the following conditions are met: the angle between the shooting plane and the horizontal plane (xy plane) is 40° to 55°, for example, 40°, 45°, 50°, 55°, etc.; the angle between the shooting plane and the vertical plane (xz plane) is 40° to 50°, for example, 40°, 45°, 50°, etc. As a result, the collected image is closer to the original color of the cell, and the R value and G value of the collected color image are enhanced to varying degrees. The basis for selecting the shooting angle is as follows: in order to improve the light utilization rate, the surface of the battery cell is prepared with a pyramid-shaped velvet surface. The angles between the pyramid oblique surface and the horizontal and vertical directions (two sides) of the battery cell are both 45°, and the theoretical value of the angle between the pyramid oblique surface and the horizontal plane is 54°. In theory, the color of the battery cell should be best expressed when the shooting surface is perpendicular to the pyramid oblique surface. However, after actual testing, when the shooting surface is at an angle of 36° to the horizontal, the color representation is not ideal due to the small depth of field and angle of the camera.

[0056] In some embodiments, in the cell sorting method, during the acquisition of the color image, RGB modulated light is used for lighting, and the intensity ratio of R value, G value, and B value in the RGB modulated light is (6.5-9): (7.5-10): 6. Therefore, changing the light intensity ratio of each RGB channel in the light source to weaken the proportion of blue light in the light source can further improve the separation trend of heterochromatic cell sheets and normal cell sheets. Preferably, the intensity ratio of R value, G value, and B value in the RGB modulated light is 7:8:6, at this time, the separation effect of normal cell sheets and heterochromatic cell sheets is optimal. Furthermore, RGB modulated light is used to illuminate the cell after diffuse reflection, thereby obtaining uniform lighting. For example, see Figure 3 , the cell 2 is placed on the tray 3 of the dark box 4, the light source 1 is located at the bottom of the dark box 4, and the light of the light source is diffusely reflected by the inner wall of the dark box 4 to illuminate the cell 2; it can also be illuminated by forming uniform ambient light after multiple diffuse reflections from any angle of the dark box 4. In addition, when collecting images, a light source coaxial with the camera can also be used for illumination, which can not only obtain uniform illumination, but also improve the separation effect.

[0057] It is worth noting that when acquiring the target color image of the battery cell to be inspected, the intensity and shooting angle of the RGB modulated light can be adjusted so that its acquisition operation is consistent with the image acquisition conditions of the battery cells in the sample set.

[0058] In some embodiments, in the cell sorting method, the extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane, including: constructing a three-dimensional space coordinate system based on the dimensions of the R value, the G value, and the B value; importing the sample set into the three-dimensional space coordinate system according to each R value, G value, and B value to obtain a three-dimensional distribution map; projecting the sample set in the three-dimensional distribution map into the BR plane in the three-dimensional space coordinate system to obtain a two-dimensional distribution map. In this way, the degree of separation between normal cells and heterochromatic cells is maximized. Figure 4 As shown, the sample set is imported into the three-dimensional space coordinate system according to each R value, G value and B value, and different shapes are used to mark the battery cells. Normal battery cells are black spheres, and heterochromatic battery cells are red triangles. The battery cell distribution in the three-dimensional space coordinate system is projected on the BR plane, BG plane, and RG plane respectively, and the obtained two-dimensional distribution diagrams are shown in FIG. Figure 5 , Figure 6 and Figure 7 ,From the figure, it can be seen that the normal cells and the ,different color cells show a good separation trend in the BR plane, but the separation effect is not obvious ,in the other two planes.

[0059] Furthermore, in the cell sorting method, a sorting function for distinguishing normal cells from heterochromatic cells is constructed according to the distribution of normal cells and heterochromatic cells in the BR plane, including: determining the distribution of normal cells and heterochromatic cells in the two-dimensional distribution diagram; constructing the sorting function according to the distribution in the two-dimensional distribution diagram with the goal of maximizing the true sorting rate and minimizing the false positive rate. Thus, the maximum separation effect is achieved while reducing the false positive rate.

[0060] In some embodiments, the constructed sorting function can reduce misjudgment while maintaining the separation rate, and the sorting function includes a straight line, a polyline, or an irregular continuous curve. In some specific embodiments, in the battery cell sorting method, the constructed sorting function includes:

[0061] R(B)=a / (1+e (-0.097B+18) )+b (1)

[0062] Where: R(B) is the sorting value; B is the B value of the battery cell to be inspected; a and b are independent constants. Specifically, when the R value of the battery cell in the sample set is 25-65, the G value is 35-110, and the B value is 140-220, a is 20 and b is 32. Therefore, formula (1) can be used to sort the battery cells to be inspected, so that the sorting effect is better.

[0063] In some embodiments, in the battery cell sorting method, according to the target B value and the target R value, based on a predefined sorting function, it is determined whether the battery cell to be inspected is a heterochromatic battery cell, including: substituting the target B value of the battery cell to be inspected into the sorting function to obtain R(B); comparing R(B) with the target R value of the battery cell to be inspected; when R(B) is greater than the target R value of the battery cell to be inspected, it is determined that the battery cell to be inspected is a heterochromatic battery cell; when R(B) is not greater than the target R value of the battery cell to be inspected, it is determined that the battery cell to be inspected is a normal battery cell. In this way, the battery cell is sorted to see if it is a heterochromatic battery cell.

[0064] In order to make the present application easier to understand, an exemplary application is provided below in combination with a test example.

[0065] Test Case

[0066] The sorting function is obtained in advance in the following way:

[0067] 1. Sample selection: In aesthetic components, the color performance of the same cell is consistent. A group of cells is divided into two, and the half of the cells are laminated into components in sequence. The heterochromatic cells in the components are manually screened out, and the other half of the cells are found and marked as heterochromatic cells. The remaining cells are normal cells. The heterochromatic cells and normal cells screened out of the same component are classified and marked to form a sample set of 26 normal cells and 16 heterochromatic cells.

[0068] 2. Collect color images of each cell in the sample set of marked normal cells and heterochromatic cells, specifically:

[0069] use Figure 3 In the dark box 4 shown, the cell 2 is placed on the tray 3 of the dark box 4, and the light source 1 is located at the bottom of the dark box 4. The light of the light source is diffusely reflected by the inner wall of the dark box 4 and illuminates the cell 2. The intensity ratio of the three channels of the light source, R value, G value, and B value is 7:8:6. When collecting color images, the angle between the shooting plane and the horizontal plane (xy plane) is 40°, and the angle between the shooting plane and the vertical plane is 45°. Under this condition, the color image of each cell in the sample set is completed. The R value range of the color image of the cell is 25-65, the G value range is 35-110, and the B value range is 140-220.

[0070] 3. Collect images at the same point of the cell according to the above conditions, extract the RGB three-channel values ​​of the color image, and import each color image into PS (Photoshop) software to obtain the RGB value;

[0071] 4. The extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane. According to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed:

[0072] R(B)=a / (1+e (-0.097B+18) )+b (1)

[0073] Where: R(B) is the sorting value; B is the B value of the battery cell to be tested, a is 20, and b is 32.

[0074] The sorting method of the battery cells to be inspected is:

[0075] S100, obtain the target color image of the battery cell to be inspected, the target color image data includes a target B value and a target R value; S200, determine whether the battery cell to be inspected is a heterochromatic battery cell based on the target B value and the target R value and based on a predefined sorting function. The target color image is consistent with the target image acquisition of the sample set. All the battery cells to be inspected constitute a test set. Run S100 and S200 in the computer to complete the sorting of the battery cells to be inspected. According to relevant verification, the true sorting rate of the separation curve of Example 1 is 54%, and the misjudgment rate is 7%.

[0076] Cells of different specifications are sorted according to the conditions of Example 1. According to statistics, the true sorting rate of the cells is 50% to 55%, and the misjudgment rate is within 10%. Compared with the traditional single-channel threshold sorting scheme, the separation rate of this embodiment is increased by about 70%, and its overall accuracy rate is increased by about 15% to 20%. This embodiment can approach the detection limit of the visible light band (400nm to 760nm) of AOI heterochromatic cell cell sorting spectrum analysis.

[0077] Comparative Example

[0078] Using the separation scheme of single-channel threshold, the sorting threshold point of a single channel of the sample set is obtained in the same way as above. Similarly, the RGB data of the cells to be tested is collected according to the above steps 1, 2 and 3, and pre-sorting is completed according to the sorting threshold of a single channel, and heterochromatic cells are selected. The test set is made into components according to the labels, and the real heterochromatic cells are manually sorted again. Compared with the pre-sorting results of the single-channel threshold, the real sorting rate of the single-channel threshold is 30% to 35%. See Figure 8 , Figure 8The RGB value box plot of normal cells and heterochromatic cells using the single-channel threshold method, where the x-axis represents the measurement range of RGB values; the capital letters on the y-axis represent normal cells, and the lowercase letters represent heterochromatic cells. For example, the R on the ordinate indicates that the R value distribution range of normal cells is 35 to 62, that is, the R value of normal cells in the sample set is distributed between 35 and 62, r is the R value distribution range of heterochromatic cells; G is the G value distribution range of normal cells, g is the G value distribution range of normal cells; B is the B value distribution range of normal cells; and b is the B value distribution range of normal cells. Figure 8 It can be seen that when the separation scheme relies on the single-channel threshold, there is a large overlap between normal cells and heterochromatic cells. This is because when the single-channel threshold is used for sorting, the other two channels of normal cells and heterochromatic cells are likely to overlap. When using this box diagram for sorting, for example, using the R value as the sorting channel and 35 as the sorting point, when the measured R value of the cell to be classified is greater than or equal to 35, it is judged to be normal; otherwise, it is heterochromatic.

[0079] Embodiment 2

[0080] Fig. 9 The block diagram of the cell sorting device according to the embodiment of the present application is schematically shown. The device can be sorted into one or more program modules, one or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiment of the present application. The program module referred to in the embodiment of the present application refers to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. Fig. 9 As shown, the device may include: an acquisition module and a determination module.

[0081] An acquisition module, used to acquire a target color image of the battery cell to be inspected, wherein the target color image data includes a target B value and a target R value;

[0082] A determination module, configured to determine whether the battery cell to be inspected is a heterochromatic battery cell based on the target B value and the target R value and based on a predefined sorting function;

[0083] Wherein, the sorting function is obtained in advance in the following manner:

[0084] The color image of each cell in the sample set of marked normal cells and heterochromatic cells is collected, and the RGB three-channel values ​​of the color image are extracted. The extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane. According to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed.

[0085] In an optional embodiment, the R value and the G value in the color image are enhanced R value and G value.

[0086] In an optional embodiment, the color image meets the following conditions during the acquisition process:

[0087] The plane where the battery cell is located is the first plane, and the plane perpendicular to the plane where the battery cell is located is the second plane. The shooting plane setting angle of image acquisition satisfies:

[0088] The included angle between the shooting surface and the first plane is 40° to 55°, and the included angle between the shooting surface and the second plane is 40° to 50°.

[0089] In an optional embodiment, during the acquisition of the color image, RGB modulated light is used for lighting, and the intensity ratio of R value, G value, and B value in the RGB modulated light is (6.5-9): (7.5-10): 6; and / or

[0090] RGB modulated light is diffusely reflected and reaches the cell for lighting.

[0091] In an optional embodiment, the extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane, including:

[0092] Construct a three-dimensional space coordinate system based on R value dimension, G value dimension and B value dimension;

[0093] Importing the R value, G value and B value corresponding to each battery cell in the sample set into the three-dimensional space coordinate system to obtain a three-dimensional distribution diagram; wherein one battery cell corresponds to a point in the three-dimensional coordinate system;

[0094] The points corresponding to the respective battery cells in the three-dimensional distribution diagram are projected onto the BR plane in the three-dimensional space coordinate system to obtain a two-dimensional distribution diagram.

[0095] In an optional embodiment, according to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed, including:

[0096] Determine the distribution of normal cells and heterochromatic cells in the two-dimensional distribution diagram;

[0097] With the goal of maximizing the true sorting rate and minimizing the false positive rate, the sorting function is constructed according to the distribution in the two-dimensional distribution graph.

[0098] In an optional embodiment, the constructed sorting function includes:

[0099] R(B)=a / (1+e (-0.097B+18))+b (1)

[0100] Wherein: R(B) is the sorting value; B is the B value of the battery cell to be tested; a and b are constants independently of each other.

[0101] In an optional embodiment, when the R value of the battery cells in the sample set ranges from 25 to 65, the G value ranges from 35 to 110, and the B value ranges from 140 to 220, a is 20 and b is 32.

[0102] In an optional embodiment, determining whether the to-be-inspected cell is a heterochromatic cell based on the target B value and the target R value and based on a predefined sorting function includes:

[0103] Inputting the target B value of the battery cell to be inspected into the sorting function to obtain R(B);

[0104] Comparing the R(B) with the target R value of the battery cell to be inspected;

[0105] When the R(B) is greater than the target R value of the battery cell to be inspected, it is determined that the battery cell to be inspected is a heterochromatic battery cell;

[0106] When the R(B) is not greater than the target R value of the battery cell to be inspected, it is determined that the battery cell to be inspected is a normal battery cell.

[0107] Embodiment 3

[0108] Fig.10 The schematic diagram of the hardware architecture of the computer device 10000 suitable for implementing the battery cell sorting method of the first embodiment according to the third embodiment of the present application is schematically shown. In some embodiments, the computer device 10000 may be a terminal device such as a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or a server cluster composed of multiple servers), etc. Fig.10 As shown, the computer device 10000 includes but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other through a system bus. Among them:

[0109] The memory 10010 includes at least one type of computer-readable storage medium, and the readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (such as an SD or DX memory), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000, such as a hard disk or a memory of the computer device 10000. In other embodiments, the memory 10010 may also be an external storage device of the computer device 10000, such as a plug-in hard disk equipped on the computer device 10000, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 10010 may also include both the internal storage module of the computer device 10000 and its external storage device. In this embodiment, the memory 10010 is generally used to store the operating system and various application software installed in the computer device 10000, such as the program code of the battery cell sorting method of the first embodiment, etc. In addition, the memory 10010 can also be used to temporarily store various data that have been output or will be output.

[0110] In some embodiments, the processor 10020 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. The processor 10020 is generally used to control the overall operation of the computer device 10000, such as performing control and processing related to data interaction or communication with the computer device 10000. In this embodiment, the processor 10020 is used to run the program code stored in the memory 10010 or process data.

[0111] The network interface 10030 may include a wireless network interface or a wired network interface, and the network interface 10030 is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 to an external terminal through a network, and to establish a data transmission channel and a communication link between the computer device 10000 and the external terminal. The network may be a wireless or wired network such as an intranet, the Internet, the Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0112] It should be pointed out that Fig.10 Only a computer device having components 10010 - 10030 is shown, but it should be understood that implementation of all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0113] In this embodiment, the battery cell sorting method of embodiment 1 stored in the memory 10010 can also be sorted into one or more program modules and executed by one or more processors (such as processor 10020) to complete the embodiment of the present application.

[0114] Embodiment 4

[0115] The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the battery cell sorting method in the first embodiment are implemented.

[0116] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEP ROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the computer-readable storage medium can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store the operating system and various application software installed on the computer device, such as the program code of the battery cell sorting method of the first embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

[0117] Embodiment 5

[0118] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0119] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented by general-purpose computer devices, they can be concentrated on a single computer device, or distributed on a network composed of multiple computer devices, optionally, they can be implemented by executable program codes of computer devices, so that they can be stored in a storage device and executed by the computer device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0120] It should be noted that the above are only preferred embodiments of the present application, and the patent protection scope of the present application is not limited thereto. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for sorting battery cells. It is characterized in that The method comprises: Acquire a target color image of the battery cell to be inspected, wherein the target color image data includes a target B value and a target R value; According to the target B value and the target R value, determining whether the battery cell to be inspected is a heterochromatic battery cell based on a predefined sorting function; Wherein, the sorting function is obtained in advance in the following manner: The color image of each cell in the sample set of marked normal cells and heterochromatic cells is collected, and the RGB three-channel values ​​of the color image are extracted. The extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane. According to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed.

2. The battery cell sorting method according to claim 1, It is characterized in that The R values ​​and G values ​​in the color image are enhanced R values ​​and G values.

3. The battery cell sorting method according to claim 2, It is characterized in that The color image meets the following conditions during the acquisition process: The plane where the battery cell is located is the first plane, and the plane perpendicular to the plane where the battery cell is located is the second plane. The shooting plane setting angle of image acquisition satisfies: The included angle between the shooting surface and the first plane is 40° to 55°, and the included angle between the shooting surface and the second plane is 40° to 50°.

4. The battery cell sorting method according to claim 1, It is characterized in that During the acquisition of the color image, RGB modulated light is used for lighting, and the intensity ratio of R value, G value, and B value in the RGB modulated light is (6.5-9): (7.5-10): 6; and / or RGB modulated light is diffusely reflected and reaches the cell for lighting.

5. The battery cell sorting method according to claim 1, It is characterized in that The extracted R, G, and B values ​​are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane, including: Construct a three-dimensional space coordinate system based on R value dimension, G value dimension and B value dimension; Importing the R value, G value and B value corresponding to each battery cell in the sample set into the three-dimensional space coordinate system to obtain a three-dimensional distribution diagram; wherein one battery cell corresponds to a point in the three-dimensional coordinate system; The points corresponding to the respective battery cells in the three-dimensional distribution diagram are projected onto the BR plane in the three-dimensional space coordinate system to obtain a two-dimensional distribution diagram.

6. The battery cell sorting method according to claim 5, It is characterized in that According to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed, including: Determine the distribution of normal cells and heterochromatic cells in the two-dimensional distribution diagram; With the goal of maximizing the true sorting rate and minimizing the false positive rate, the sorting function is constructed according to the distribution in the two-dimensional distribution graph.

7. The battery cell sorting method according to claim 1, It is characterized in that The constructed sorting functions include: R(B)=a / (1+e (-0.097B+18) )+b (1) Wherein: R(B) is the sorting value; B is the B value of the battery cell to be tested; a and b are constants independently of each other.

8. The battery cell sorting method according to claim 7, It is characterized in that When the R value of the battery cells in the sample set ranges from 25 to 65, the G value ranges from 35 to 110, and the B value ranges from 140 to 220, a is 20 and b is 32.

9. The battery cell sorting method according to claim 7 or 8, It is characterized in that According to the target B value and the target R value, determining whether the battery cell to be inspected is a heterochromatic battery cell based on a predefined sorting function includes: Inputting the target B value of the battery cell to be inspected into the sorting function to obtain R(B); Comparing the R(B) with the target R value of the battery cell to be inspected; When the R(B) is greater than the target R value of the battery cell to be inspected, it is determined that the battery cell to be inspected is a heterochromatic battery cell; When the R(B) is not greater than the target R value of the battery cell to be inspected, it is determined that the battery cell to be inspected is a normal battery cell.

10. A battery cell sorting device, It is characterized in that The device comprises: An acquisition module, used to acquire a target color image of the battery cell to be inspected, wherein the target color image data includes a target B value and a target R value; A determination module, configured to determine whether the battery cell to be inspected is a heterochromatic battery cell based on the target B value and the target R value and based on a predefined sorting function; Wherein, the sorting function is obtained in advance in the following manner: The color image of each cell in the sample set of marked normal cells and heterochromatic cells is collected, and the RGB three-channel values ​​of the color image are extracted. The extracted R value, G value, and B value are imported into the RGB three-dimensional coordinate system as three-dimensional coordinates, and then projected into the BR plane. According to the distribution of normal cells and heterochromatic cells in the BR plane, a sorting function for distinguishing normal cells from heterochromatic cells is constructed.

11. A computer device, It is characterized in that include: at least one processor; and a memory communicatively connected to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images