Battery cell detection method, device, apparatus, and computer storage medium

Abstract

The application discloses a kind of battery detection method, device, equipment and computer storage medium.Therein, battery detection method includes: in the case where the battery is photographed based on X-ray and obtains battery image, obtains the N first pixel values of N pixel points in target image region in battery image, N is the integer greater than 1;N first pixel values are respectively subjected to logarithmic transformation, and N second pixel values are obtained;N second pixel values are subjected to ratio processing, and N third pixel values are obtained;based on N third pixel values, obtain battery detection result.The embodiment of the application is helpful to reliably obtain the thickness distribution of battery according to N third pixel values, and improve battery detection effect.

Description

Technical Field

[0001] This application belongs to the field of nondestructive testing technology, and in particular relates to a method, apparatus, equipment and computer storage medium for testing battery cells. Background Technology

[0002] As is well known, X-ray images can be obtained by irradiating a formed battery cell with X-ray equipment, and defects in the battery cell can be detected by processing the X-ray images.

[0003] However, X-ray image imaging is affected by many interference factors, resulting in poor cell detection performance based on X-ray images. Summary of the Invention

[0004] This application provides a battery cell detection method, apparatus, device, and computer storage medium to solve the problem in related technologies where X-ray image imaging is affected by many interference factors, resulting in poor battery cell detection performance based on X-ray images.

[0005] In a first aspect, embodiments of this application provide a cell testing method, the method comprising:

[0006] In the case of obtaining a battery cell image based on X-ray imaging of the battery cell, the N first pixel values ​​of N pixels in the target image region of the battery cell image are obtained, where N is an integer greater than 1;

[0007] Perform a logarithmic transformation on each of the N first pixel values ​​to obtain N second pixel values;

[0008] By comparing the N second pixel values, we obtain N third pixel values;

[0009] The cell detection results are obtained based on N third pixel values.

[0010] In the technical solution of this application embodiment, when a battery cell image is obtained based on X-ray imaging of the battery cell, N first pixel values ​​of N pixels in the target image region of the battery cell image are acquired. Logarithmic transformation is performed on each of the N first pixel values ​​to obtain N second pixel values. A ratio processing is performed on the N second pixel values ​​to obtain N third pixel values. Based on the N third pixel values, the battery cell detection result is obtained. This application embodiment performs logarithmic transformation and ratio processing on the pixel values ​​of each pixel in the target image region of the battery cell image according to the law of X-ray intensity variation. This eliminates the need to obtain the battery cell density and amplifies the influence of battery cell thickness on the pixel values ​​of each pixel, thereby helping to reliably obtain the thickness distribution of the battery cell based on the N third pixel values ​​and improving the battery cell detection effect.

[0011] In some embodiments, the N second pixel values ​​are compared to obtain N third pixel values, including:

[0012] Linear normalization is performed on the N second pixel values ​​to obtain N third pixel values.

[0013] The third pixel value, obtained by linearly normalizing the second pixel value, is decoupled from parameters such as cell density, carbon plate density, and carbon plate thickness. This allows the third pixel value to effectively reflect the cell thickness, thereby improving the detection effect of the cell.

[0014] In some embodiments, linear normalization is performed on N second pixel values ​​to obtain N third pixel values, including:

[0015] Get the maximum and minimum pixel values ​​among N second pixel values;

[0016] Based on the maximum and minimum pixel values, each second pixel value is linearly normalized to obtain the corresponding third pixel value.

[0017] The third pixel value, obtained by linearly normalizing the second pixel value, actually amplifies the influence of the cell thickness. Based on the third pixel value, the relative thickness of various parts of the cell can be better obtained, which helps to effectively detect potential defects in the cell.

[0018] In some embodiments, each second pixel value is linearly normalized based on the maximum and minimum pixel values ​​to obtain a third pixel value corresponding to each second pixel value, including:

[0019] The third pixel value corresponding to each second pixel value is calculated by using the difference between each second pixel value and the minimum pixel value as the numerator, and the sum of the target difference and the preset value as the denominator.

[0020] The preset value is greater than 0, and the target difference is the difference between the maximum pixel value and the minimum pixel value.

[0021] When performing linear normalization, the denominator can include a preset value to avoid the denominator being equal to 0. For various target image regions, the numerical stability of the linear normalization process of the second pixel value can be guaranteed.

[0022] In some embodiments, the cell detection result is obtained based on N third pixel values, including:

[0023] Multiply each of the N third pixel values ​​by a preset weight to obtain N fourth pixel values, where the preset weight is greater than 1;

[0024] The cell detection results are obtained based on N fourth pixel values.

[0025] By multiplying each of the N third pixel values ​​by a preset weight, the differences between the different fourth pixel values ​​can be amplified, which helps to detect cell defects more effectively.

[0026] In some embodiments, after multiplying N third pixel values ​​by a preset weight to obtain N fourth pixel values, the method further includes:

[0027] The pixel values ​​of N pixels are updated to N fourth pixel values ​​to obtain the updated cell image;

[0028] Displays the updated image of the battery cell.

[0029] The updated cell images better showcase the thickness of different parts of the cell, helping users to better observe potential defects. Alternatively, displaying updated cell images can also demonstrate the processing progress and results, enhancing the user experience.

[0030] In some embodiments, the target image region is all or part of the image region in the cell image.

[0031] When the target pixel region is the entire image region of the battery cell, it helps to efficiently identify possible defects in the battery cell and saves the computational resources consumed by overall defect detection of the battery cell; when the target pixel region is a part of the image region of the battery cell, it helps to better detect defects that exist locally in the battery cell and improve the accuracy of battery cell detection.

[0032] Secondly, embodiments of this application provide a battery cell testing device, the device comprising:

[0033] The first acquisition module is used to acquire N first pixel values ​​of N pixels in the target image region of the battery cell image when the battery cell image is obtained by X-ray imaging of the battery cell, where N is an integer greater than 1;

[0034] The logarithmic transformation module is used to perform logarithmic transformations on N first pixel values ​​to obtain N second pixel values;

[0035] The ratio processing module is used to perform ratio processing on N second pixel values ​​to obtain N third pixel values;

[0036] The second acquisition module is used to acquire the cell detection results based on N third pixel values.

[0037] Thirdly, embodiments of this application provide an electronic device, the device including: a processor and a memory storing computer program instructions;

[0038] When the processor executes computer program instructions, it implements the cell detection method as described in the first aspect.

[0039] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the cell detection method as described in the first aspect. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic flowchart of the battery cell testing method provided in the embodiments of this application;

[0042] Figure 2 This is a schematic diagram of the battery cell testing device provided in the embodiments of this application;

[0043] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0044] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0045] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0046] To address the problems of the prior art, embodiments of this application provide a method, apparatus, device, and computer storage medium for testing battery cells. The battery cell testing method provided in this application embodiment will be described first below.

[0047] In certain application scenarios, the formed battery cell can be placed in an X-ray device for imaging to obtain an image of the cell. The easy-to-connect aspect is that the X-ray device emits uniformly distributed X-rays through an X-ray tube. When the X-rays penetrate a specific part of the battery cell, they are affected by factors such as the thickness and density of that part, resulting in a corresponding degree of attenuation. The pixel value of each pixel in the battery cell image can be related to the unattenuated dose of the X-rays after penetrating the corresponding part of the battery cell.

[0048] For example, under the same conditions such as material density, the smaller the thickness of the cell portion penetrated by X-rays, the lower the dose attenuated by X-rays, the higher the dose reaching the imaging device, and the higher the brightness of the corresponding pixel in the cell image. If the pixel value is defined as the brightness value, it can be summarized as the smaller the thickness of the cell portion, the higher the pixel value of the corresponding pixel in the cell image.

[0049] Generally speaking, defects that may exist in battery cells after winding and hot pressing include: wrinkling, overlapping, or metal leakage of the anode and cathode plates. These defects may occur individually or simultaneously.

[0050] The aforementioned defects manifest as uneven thickness at the cell level, while at the cell image level, they manifest as a difference in contrast between the image area corresponding to the defect location and the surrounding background.

[0051] The basic principle of X-ray imaging is that as X-rays pass through an irradiated object, the intensity of the rays continuously decreases due to factors such as scattering and absorption. Ideally, this process of ray intensity change can be described as follows:

[0052] I (x,y) =I 0,(x,y) exp(-h (x,y) (1)

[0053] Among them, I (x,y) The dose attenuated by X-rays at the pixel with coordinates (x, y) in the cell image, as explained above, can be positively correlated with the pixel value at coordinates (x, y). To some extent, it is also used to describe the pixel value at coordinates (x, y). Therefore, to simplify the description, the following can be expressed using I... (x,y) To represent pixel values. 0,(x,y) The dose of the input radiation corresponds to the dose emitted by the X-ray tube mentioned above.

[0054] h (x,y) The line integral of the linear attenuation coefficient of a ray passing through an object can be specifically expressed as:

[0055] h (x,y) =∫μdl (2)

[0056] Where μ is the attenuation coefficient of the object being pierced, which is related to the elemental mass of the object (microscopic angle) or the density of the object (macroscopic angle), and l is the thickness of the object being pierced.

[0057] Specifically, in the embodiments of this application, the object being penetrated can be a battery cell. Generally, a battery cell can include wound or stacked cathode sheets, anode sheets, and a separator. In the stacking direction of the cathode sheets, anode sheets, and separator, the battery cell can be considered to be made of a material with a constant attenuation coefficient.

[0058] As shown above, the attenuation coefficient of an object being pierced can be related to the density of the object being pierced. To a certain extent, the attenuation coefficient can be expressed by the material density.

[0059] In practical applications, when X-ray equipment images a battery cell, a support bracket is typically used to hold the cell. In one example, the bracket could be a carbon fiber plate. The X-ray emitted from the lamp would then penetrate the carbon fiber plate and the battery cell before reaching the imaging device. Accordingly, the objects penetrated could include both the carbon fiber plate and the battery cell.

[0060] Based on the above assumptions, the above formula (1) can be approximately expressed as:

[0061] I (x,y) =I 0,(x,y) exp(-μ b l (x,y) -μ c l c (3)

[0062] Where, μ b For the density of the battery cell, l (x,y) The penetration thickness of the battery cell (hereinafter referred to as cell thickness), μ c For the density of the carbon plate, l c The penetration thickness of the carbon plate.

[0063] Generally, the shape and size of carbon plates can be flexibly designed according to needs, and the structure is relatively simple. c With l c It can be measured relatively accurately. However, for μ... b Due to the relatively complex structure of the battery cell, it is difficult to accurately obtain the density values ​​of each part.

[0064] As shown above, it can be done through I (x,y) To represent pixel values, then for I (x,y) The process of performing a logarithmic transformation can be described by the following formula:

[0065] logI (x,y) =-logI 0,(x,y) +μ b l (x,y) +μ c l c (4)

[0066] Wherein, log I (x,y) It can consist of three parts, where log I 0,(x,y) With μ c l c Relatively speaking, it can be reliably obtained, log I (x,y) Mainly affected by μ b l (x,y) The impact.

[0067] It is easy to understand that when the pixel values ​​of the target image area can be decoupled from parameters other than the cell thickness, the distribution of cell thickness can be accurately reflected through the pixel values, thereby achieving reliable detection of cell defects.

[0068] Through logarithmic transformation, μ can be... b l (x,y) The transformation from an exponential to a monomial facilitates the use of ratios, thus eliminating the need for log I. (x,y) The parameter μ in b This allows for a reliable reflection of the cell thickness.

[0069] As shown above, the battery cell can be considered to be made of a material with a constant attenuation coefficient, meaning that the cell density can be considered to be relatively uniformly distributed on a plane perpendicular to the cell thickness direction, μ. b It is a constant value. However, the specific value of the cell density is difficult to obtain accurately.

[0070] Figure 1 A schematic flowchart of a cell testing method according to an embodiment of this application is shown. Figure 1 As shown, the method includes:

[0071] Step 101: In the case of obtaining a cell image based on X-ray imaging of the cell, acquire the N first pixel values ​​of N pixels in the target image region of the cell image, where N is an integer greater than 1;

[0072] Step 102: Perform logarithmic transformation on each of the N first pixel values ​​to obtain N second pixel values;

[0073] Step 103: Perform ratio processing on the N second pixel values ​​to obtain N third pixel values;

[0074] Step 104: Obtain the cell detection result based on N third pixel values.

[0075] In step 101, the cell image can be obtained by taking pictures of the cell with X-rays. In practical applications, it may be necessary to obtain a portion of the cell image from the entire image area to detect defects in the cell. Accordingly, the target image area in the cell image can be processed according to actual needs in order to detect cell defects.

[0076] In other words, the target image region can be determined as needed, and can be all or part of the battery cell image region. The target image region can include N pixels, and each pixel can have a corresponding pixel value. The aforementioned first pixel value can be considered as the pixel value of each pixel in the original battery cell image. And the first pixel value can correspond to the aforementioned I. (x,y) .

[0077] In step 102, logarithmic transformations can be performed on the N first pixel values ​​to obtain N second pixel values. The second pixel values ​​can correspond to the aforementioned log I... (x,y) .

[0078] It's easy to understand that there can be a one-to-one correspondence between the N second pixel values ​​and the N first pixel values. From the perspective of the target image region, it can be considered that the pixel values ​​of each pixel in the target image region have been calculated and updated.

[0079] In step 103, the ratio of the N second pixel values ​​is processed to obtain N third pixel values.

[0080] In this step, by comparing the N second pixel values, the cell density in two second pixel values ​​can be canceled out. Each of the resulting N third pixel values ​​can be decoupled from the cell density, amplifying the influence of cell thickness on the pixel values ​​in the chip image. In other words, the third pixel value can more reliably reflect the cell thickness.

[0081] In step 104, the cell detection result can be obtained based on N third pixel values.

[0082] It's easy to understand that the N third pixel values ​​can be the updated pixel values ​​of the N pixels in the target image region. Accordingly, it can be considered that the pixel values ​​in the target image region have been updated, and the updated pixel values ​​in the target image region can better reflect the thickness distribution of the battery cell.

[0083] Therefore, the process of obtaining the cell detection result based on N third pixel values ​​can be considered as the process of cell detection based on the updated target image region.

[0084] The battery cell detection method provided in this application, when the battery cell image is obtained by X-ray imaging, acquires N first pixel values ​​of N pixels in the target image region of the battery cell image, performs logarithmic transformation on each of the N first pixel values ​​to obtain N second pixel values, performs ratio processing on the N second pixel values ​​to obtain N third pixel values, and obtains the battery cell detection result based on the N third pixel values. This application embodiment performs logarithmic transformation and ratio processing on the pixel values ​​of each pixel in the target image region of the battery cell image based on the X-ray intensity variation law, eliminating the need to obtain the battery cell density and amplifying the influence of battery cell thickness on the pixel values ​​of each pixel. This helps to reliably obtain the battery cell thickness distribution based on the N third pixel values, thereby improving the battery cell detection effect.

[0085] In some examples, the pixel value of a pixel can be a brightness value or a grayscale value, or it can be a radiation dose obtained by converting the brightness value with a preset conversion rule, etc. There are no specific limitations here.

[0086] The following examples illustrate how ratios are handled.

[0087] In one example, as shown above, log I 0,(x,y) With μ c l c It can be reliably obtained, therefore, each second pixel value can be subtracted by log I. 0,(x,y) With μ c l c These two values ​​yield a new pixel value, which is denoted as the fifth pixel value.

[0088] The value of the fifth pixel can actually be denoted as μ. b l (x,y) From the N fifth pixel values, a reference pixel value is selected. Then, each of the N fifth pixel values ​​is divided by the reference pixel value to obtain the N third pixel values. Based on the above explanation, μ b It can be a constant value; therefore, after dividing the fifth pixel value by the base pixel value, μ can be canceled out. b This allows the third pixel value to more reliably reflect the thickness of the battery cell.

[0089] In another example, step 103, which involves comparing the N second pixel values ​​to obtain N third pixel values, may include:

[0090] Linear normalization is performed on the N second pixel values ​​to obtain N third pixel values.

[0091] For example, the conventional linear normalization method can be written as:

[0092]

[0093] in, That is, the third pixel value is obtained by normalizing the second pixel value of the pixel with coordinates (x,y).

[0094] The minimum pixel value among N second pixel values. It is the largest pixel value among N second pixel values.

[0095] log I 0,(x,y) With μ c l c It can be considered a fixed value, with subtraction operations in both the numerator and denominator, thus allowing the cancellation of logI from the second pixel value. 0,(x,y) With μ c l c Therefore, according to formula (5), we can obtain the following values:

[0096]

[0097] Due to μ b It can be a constant value; therefore, μ in the numerator and denominator of formula (6) can be... b Subtracting the subtraction, we can obtain the following formula:

[0098]

[0099] That is, the third pixel value is obtained by normalizing the second pixel value of the pixel point with coordinates (x,y). It can be seen that in formula (7), the third pixel value achieves decoupling from parameters such as cell density, carbon plate density and carbon plate thickness, so that the third pixel value can effectively reflect the cell thickness, thereby helping to improve the detection effect of the cell.

[0100] In practical applications, after the carbon plate is irradiated by the X-ray tube, X-ray residue may remain in it, which can cause noise interference to the cell image. When the carbon plate is irradiated by the X-ray tube for a long time, the noise interference can be considered to be uniformly distributed. Accordingly, the difference operation in the numerator and denominator of formula (5) can also cancel out the noise interference caused by the carbon plate.

[0101] After dividing the numerator by the denominator, μ can be canceled. b This allows the third pixel value to more reliably reflect the thickness of the battery cell, and based on N third pixel values, the detection effect of the battery cell can also be improved.

[0102] The above are some examples of ratio processing in step 103. In practical applications, the ratio processing method can be adjusted as needed. For example, the above linear normalization process can be changed, and the denominator can be determined as the difference between any two unequal second pixel values, etc. Examples will not be given here.

[0103] As mentioned above, formula (5) can be a conventional linear normalization method. In practical applications, the linear normalization of N second pixel values ​​is not limited to the method shown in formula (5). The following will illustrate some feasible implementation methods of linear normalization.

[0104] In one implementation, N second pixel values ​​are linearly normalized to obtain N third pixel values, including:

[0105] Get the maximum and minimum pixel values ​​among N second pixel values;

[0106] Based on the maximum and minimum pixel values, each second pixel value is linearly normalized to obtain the corresponding third pixel value.

[0107] The minimum pixel value can correspond to the above. The maximum pixel value can correspond to the above.

[0108] The third pixel value, obtained by linearly normalizing the second pixel value, actually amplifies the influence of the cell thickness. Based on the third pixel value, the relative thickness of various parts of the cell can be better obtained, which helps to effectively detect potential defects in the cell.

[0109] In another embodiment, each second pixel value is linearly normalized based on the maximum and minimum pixel values ​​to obtain the third pixel value corresponding to each second pixel value, including:

[0110] The third pixel value corresponding to each second pixel value is calculated by using the difference between each second pixel value and the minimum pixel value as the numerator, and the sum of the target difference and the preset value as the denominator.

[0111] The preset value is greater than 0, and the target difference is the difference between the maximum pixel value and the minimum pixel value.

[0112] This preset value can be a positive value close to 0, and its value can be much smaller than the maximum pixel value.

[0113] In this embodiment, when performing linear normalization, the denominator can include a preset value to avoid the denominator being equal to 0. For various target image regions, the numerical stability of the linear normalization process of the second pixel value can be guaranteed.

[0114] This embodiment can be considered a variation of the previous embodiment. For ease of understanding, the implementation process of this embodiment can be illustrated by the following formula:

[0115]

[0116] Here, ∈ corresponds to the preset value mentioned above. It's easy to understand that, strictly speaking, the preset value is not equal to ∈, but rather equal to μ. b ∈. Since ∈ is a small value, ∈ can be approximately equal to μ. b ∈.

[0117] The difference between formula (8) and formula (7) is that a preset value is added to the denominator.

[0118] In practical applications, the first pixel value of each pixel in the target image region may be equal, and correspondingly, the N second pixel values ​​obtained after logarithmic transformation are also equal. In this case, the maximum pixel value among the above N second pixel values ​​is equal to the minimum pixel value, and the denominator calculated based on formula (7) is equal to 0. This may lead to the failure of linear normalization.

[0119] Based on the example above, the preset value can be a positive number close to 0. In this way, while ensuring that the denominator is not 0, the addition of the preset value will not have too much impact on the calculation value of the third pixel, thereby avoiding excessive interference with the relative thickness relationship of various parts of the battery cell.

[0120] In practical applications, to further improve the numerical stability of the calculation, the above formula (9) can be rewritten as:

[0121]

[0122] Optionally, step 104 above, based on N third pixel values, obtains the cell detection result, including:

[0123] Multiply each of the N third pixel values ​​by a preset weight to obtain N fourth pixel values, where the preset weight is greater than 1;

[0124] The cell detection results are obtained based on N fourth pixel values.

[0125] The implementation method of this embodiment can be represented by the following formula:

[0126]

[0127] Where α is the preset weight mentioned above.

[0128] It is easy to understand that the differences between the N third pixel values ​​obtained by ratio processing may be small. Combined with the method of obtaining N third pixel values ​​by linear normalization as mentioned above, the difference between these third pixel values ​​is usually less than 1.

[0129] In practical applications, in order to better reflect the differences between the N third pixel values, the N third pixel values ​​can be multiplied by a preset weight, which is greater than 1. The differences between the different fourth pixel values ​​can be amplified, which helps to detect cell defects more effectively.

[0130] In some examples, when N third pixel values ​​are obtained through linear normalization, the preset weight can be 2. 8 -1 to 2 16 Values ​​between -1 are used to make the N fourth pixel values ​​differ significantly.

[0131] As shown above, the pixel values ​​of each pixel in the target image region can reflect the thickness or relative thickness of the battery cell at the corresponding location. By multiplying the N fourth pixel values ​​by a preset weight, the difference in battery cell thickness is amplified, which in turn helps to more effectively detect battery cell defects.

[0132] In other examples, by multiplying each of the N third pixel values ​​by a preset weight, the values ​​of the N fourth pixel values ​​can be made to fall within the range of 0 to 255. This data range can overlap with the range of brightness or grayscale values ​​of pixels in a typical scene. Accordingly, each pixel in the target image area can be displayed according to its corresponding fourth pixel value. This helps improve the visualization of differences in battery cell thickness and, consequently, aids users in manually analyzing defects within the battery cell.

[0133] Of course, the above is an example of how to obtain N fourth pixel values ​​by multiplying N third pixel values ​​by preset weights. In actual applications, the preset weights can also be selected according to actual needs.

[0134] In one implementation, after multiplying each of the N third pixel values ​​by a preset weight to obtain N fourth pixel values, the method further includes:

[0135] The pixel values ​​of N pixels are updated to N fourth pixel values ​​to obtain the updated cell image;

[0136] Displays the updated image of the battery cell.

[0137] Referring to the example above, by multiplying each of the N third pixel values ​​by a preset weight, the values ​​of the N fourth pixel values ​​can be made to fall within the range of 0 to 255. When the pixel values ​​of the N pixels are updated to N fourth pixel values, each pixel in the target image area can be displayed according to its corresponding fourth pixel value, which can be reflected in the pixel's brightness or grayscale value.

[0138] In effect, the cell image has been updated, and the updated cell image can better show the thickness of different parts of the cell.

[0139] In this embodiment, displaying the updated cell image helps users better observe potential defects within the cell. Alternatively, displaying the updated cell image can also demonstrate the processing progress and results to the user, enhancing the user experience.

[0140] Optionally, the target pixel region can be all or part of the image region in the cell image.

[0141] In conjunction with the above embodiments, in step 103, the ratio of the N second pixel values ​​was processed. Therefore, the obtained third pixel value can be considered as a relative value. Since there is a corresponding relationship between the third pixel value and the cell thickness, the ratio operation between the second pixel values ​​can be considered as calculating the relative thickness (or relative height) between various parts of the cell.

[0142] When the target pixel region is the entire image region in the battery cell image, the battery cell detection method can be defined as the Globally Relative Height Algorithm (GRHA). In this case, defects in the entire battery cell can be detected, which helps to efficiently determine the possible defects in the battery cell and saves the consumption of computing resources brought about by the overall defect detection of the battery cell.

[0143] When the target pixel region is a part of the image region in the battery cell image, the battery cell detection method can be defined as the Locally Relative Height Algorithm (LRHA). Based on the LRHA, it is helpful to better detect defects that exist locally in the battery cell and improve the accuracy of battery cell detection.

[0144] Combined with the linear normalization process used in step 103 above for the N second pixel values, since the difference between the maximum and minimum pixel values ​​in a local image region is smaller than the difference between the maximum and minimum pixel values ​​in the overall image region, the difference between the N third pixel values ​​obtained by linear normalization can be enhanced, thereby helping to better detect defects in the battery cell.

[0145] The specific implementation method of cell testing can be achieved using existing technologies.

[0146] For example, contrast enhancement algorithms or edge detection algorithms can be used to extract areas where the cell thickness changes drastically, thus enabling cell detection.

[0147] For example, histogram equalization or low-pass filtering can be used to further process the updated target image region, and neural network models can be used to identify the cell defects and defect types present in the processed target image region.

[0148] For example, the updated target image area can be sent to a display device for display, and users can manually determine the cell defects present in the target image area.

[0149] To simplify the description, the specific implementation methods of cell detection will not be illustrated here.

[0150] In some implementations, the process of processing the pixel values ​​of N pixels can be performed in a graphics processing unit (GPU), which helps to accelerate parallel computing and improve processing efficiency.

[0151] Furthermore, the pixel value processing can be specifically performed on the GPU using the MaxPooling2D function of the TensorFlow framework.

[0152] As can be seen from the description of the embodiments above, the cell detection method provided in this application is unaffected by objective factors such as cell density and external equipment factors (e.g., carbon plate thickness and density). Processing the cell image using a global relative height algorithm or a local relative height algorithm can effectively avoid linear attenuation coefficients related to cell density and is unaffected by different hardware. This makes the cell detection method a general processing algorithm, expanding its application scope. Simultaneously, it also improves the imaging effect of X-ray images to a certain extent.

[0153] like Figure 2 As shown in the figure, this application embodiment also provides a battery cell testing device, including:

[0154] The first acquisition module 201 is used to acquire N first pixel values ​​of N pixels in the target image region of the battery cell image when the battery cell image is obtained by X-ray imaging of the battery cell, where N is an integer greater than 1;

[0155] The logarithmic transformation module 202 is used to perform logarithmic transformation on N first pixel values ​​respectively to obtain N second pixel values;

[0156] The ratio processing module 203 is used to perform ratio processing on N second pixel values ​​to obtain N third pixel values;

[0157] The second acquisition module 204 is used to acquire the cell detection result based on N third pixel values.

[0158] Optionally, the ratio processing module 203 may include:

[0159] The processing unit is used to perform linear normalization on N second pixel values ​​to obtain N third pixel values.

[0160] Optionally, the processing unit may include:

[0161] Get sub-units, used to obtain the maximum and minimum pixel values ​​among N second pixel values;

[0162] The processing subunit is used to perform linear normalization on each second pixel value based on the maximum and minimum pixel values ​​to obtain the third pixel value corresponding to each second pixel value.

[0163] Optionally, the processing subunit can be specifically used for:

[0164] The third pixel value corresponding to each second pixel value is calculated by using the difference between each second pixel value and the minimum pixel value as the numerator, and the sum of the target difference and the preset value as the denominator.

[0165] The preset value is greater than 0, and the target difference is the difference between the maximum pixel value and the minimum pixel value.

[0166] Optionally, the second acquisition module 204 may include:

[0167] The first acquisition unit is used to multiply N third pixel values ​​by a preset weight to obtain N fourth pixel values;

[0168] The second acquisition unit is used to acquire the cell detection result based on N fourth pixel values.

[0169] Optionally, the cell testing device may also include:

[0170] The update module is used to update the pixel values ​​of N pixels to N fourth pixel values ​​to obtain the updated cell image;

[0171] The display module is used to display the updated battery cell image.

[0172] Optionally, the target image region is all or part of the image region in the cell image.

[0173] It should be noted that this cell testing device is the same as the cell testing method described above. All implementation methods in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0174] Figure 3 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0175] An electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0176] Specifically, the processor 301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0177] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.

[0178] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to this disclosure.

[0179] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the cell detection methods in the above embodiments.

[0180] In one example, the electronic device may also include a communication interface 303 and a bus 310. For example, Figure 3 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0181] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0182] Bus 310 may include hardware, software, or both. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0183] In addition, in conjunction with the cell detection methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the cell detection methods in the above embodiments.

[0184] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0185] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0186] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0187] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0188] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method of detecting a battery cell, the method comprising: The method comprises the following steps: In the case of obtaining an electric core image by shooting the electric core based on X-rays, N first pixel values of N pixel points in a target image region in the electric core image are acquired, N being an integer greater than 1; The N first pixel values are respectively subjected to logarithmic transformation to obtain N second pixel values; The maximum pixel value and the minimum pixel value in the N second pixel values are acquired; A third pixel value corresponding to each second pixel value is calculated by taking the difference between each second pixel value and the minimum pixel value as the numerator and the sum between a target difference value and a preset value as the denominator, wherein the preset value is greater than 0, the target difference value is the difference between the maximum pixel value and the minimum pixel value, the third pixel value can realize decoupling with the electric core density, the carbon plate density and the carbon plate thickness, and the third pixel value can reflect the electric core thickness; An electric core detection result is acquired based on the N third pixel values; The expression of the first pixel value is: I (x,y) = I 0,(x,y) exp(-μ b l (x,y) -μ c l c ) where I 0,(x,y) is the dose of the incoming radiation, μ b is the density of the cell, l (x,y) is the thickness of the cell, μ c is the density of the carbon plate, l c is the thickness of the carbon plate; The expression of the second pixel value obtained after the logarithmic transformation of the first pixel value is: log I (x,y) = -log I 0,(x,y) + μ b l (x,y) + μ c l c wherein log I 0,(x,y) with μ c l c is a constant value; In the process of calculating the third pixel value corresponding to each of the second pixel values with the difference between each of the second pixel values and the minimum pixel value as the numerator and the sum between the target difference value and the preset value as the denominator, since the difference operation exists in both the numerator and the denominator, logI 0,(x,y) and μ c are removed, in the ratio operation process, μ c is removed, so the third pixel value is only related to l b . (x,y) ​ 2. The method of claim 1, wherein, The acquisition of the electric core detection result based on the N third pixel values comprises the following steps: The N third pixel values are respectively multiplied by a preset weight to obtain N fourth pixel values, the preset weight being greater than 1; An electric core detection result is acquired based on the N fourth pixel values.

3. The method of claim 2, wherein, After the N third pixel values are respectively multiplied by the preset weight to obtain the N fourth pixel values, the method further comprises the following steps: The pixel values of the N pixel points are updated to the N fourth pixel values to obtain an updated electric core image; The updated electric core image is displayed.

4. The method of claim 1, wherein, The target image region is all or part of the image region in the electric core image.

5. An electric cell detection device, characterized by, The device comprises: A first acquisition module is configured to acquire N first pixel values of N pixel points in a target image region in an electric core image in the case of obtaining the electric core image by shooting the electric core based on X-rays, N being an integer greater than 1; A logarithmic transformation module is configured to respectively subject the N first pixel values to logarithmic transformation to obtain N second pixel values; An acquisition subunit is configured to acquire the maximum pixel value and the minimum pixel value in the N second pixel values; A processing subunit is configured to calculate a third pixel value corresponding to each second pixel value by taking the difference between each second pixel value and the minimum pixel value as the numerator and the sum between a target difference value and a preset value as the denominator, wherein the preset value is greater than 0, the target difference value is the difference between the maximum pixel value and the minimum pixel value, the third pixel value can realize decoupling with the electric core density, the carbon plate density and the carbon plate thickness, and the third pixel value can reflect the electric core thickness; A second acquisition module is configured to acquire an electric core detection result based on the N third pixel values; The expression of the first pixel value is: I (x,y) = I 0,(x,y) exp(-μ b l (x,y) -μ c l c ) where I 0,(x,y) is the dose of the incoming radiation, μ b is the density of the cell, l (x,y) is the thickness of the cell, μ c is the density of the carbon plate, l c is the thickness of the carbon plate; The expression of the second pixel value obtained after the logarithmic transformation of the first pixel value is: log I (x,y) = -log I 0,(x,y) + μ b l (x,y) + μ c l c wherein log I 0,(x,y) with μ c l c is a constant value; In the process of calculating the third pixel value corresponding to each of the second pixel values with the difference between each of the second pixel values and the minimum pixel value as the numerator and the sum between the target difference value and the preset value as the denominator, since the difference operation exists in both the numerator and the denominator, logI 0,(x,y) is removed, and in the ratio operation process, μ c is removed, so the third pixel value is only related to l c . b (x,y) ​​ 6. An electronic device, comprising: The device comprises a processor and a memory storing computer program instructions; The processor executes the computer program instructions to implement the electric core detection method according to any one of claims 1-4.

7. A computer storage medium, characterized in that Computer program instructions are stored in the computer storage medium, and the computer program instructions are executed by the processor to realize the battery cell detection method in any one of claims 1-4.

Images