CN118096765B

CN118096765B - Battery cell detection method and device, electronic equipment and storage medium

Info

Publication number: CN118096765B
Application number: CN202410518413.2A
Authority: CN
Inventors: 李海波; 牛茂龙; 才鑫源; 宋谦
Original assignee: Jiangsu Contemporary Amperex Technology Ltd
Current assignee: Jiangsu Contemporary Amperex Technology Ltd
Priority date: 2024-04-28
Filing date: 2024-04-28
Publication date: 2024-10-01
Anticipated expiration: 2044-04-28
Also published as: CN118096765A

Abstract

The embodiment of the application relates to the technical field of batteries and discloses a battery cell detection method, a device, electronic equipment and a storage medium. The cell detection method comprises the following steps: extracting a cell region from a cell image obtained by radiographic imaging; and obtaining a charging level detection result of the battery cell according to the gray value distribution of the pixels in the battery cell region. The battery cell detection method provided by the embodiment of the application can improve the accuracy and the reliability of the battery cell detection result.

Description

Battery cell detection method and device, electronic equipment and storage medium

Technical Field

The application relates to the technical field of batteries, in particular to a method and a device for detecting a battery cell, electronic equipment and a storage medium.

Background

In the construction of the battery, the cells are an important component. To improve the safety of the battery, it is generally necessary to detect the internal structure of the battery cell.

In the related art, the detection mode of the internal structure of the battery cell is to detect the battery cell in the winding process of the battery cell so as to judge whether the feeding position of the battery cell after finished products has defects. However, this method needs to detect during the winding process of the battery cell, and if the battery cell is not disassembled for verification, it cannot be determined whether the detection result is suitable for the battery cell after the finished product is manufactured, which affects the accuracy and reliability of the detection result of the battery cell.

Disclosure of Invention

In view of the above problems, the present application provides a method, an apparatus, an electronic device, and a storage medium for detecting a battery cell, which can improve the accuracy and reliability of the battery cell detection result.

In a first aspect, an embodiment of the present application provides a method for detecting a battery cell, where the method includes: extracting a cell region from a cell image obtained by radiographic imaging; and obtaining a charging level detection result of the battery cell according to the gray value distribution of the pixels in the battery cell region.

According to the technical scheme provided by the embodiment of the application, the cell area is extracted from the cell image obtained by utilizing the radiographic imaging, so that the charge level detection result of the cell is determined according to the gray distribution of the pixels in the cell area. When the cathode material inlet level and the anode material inlet level are overlapped, the number of the cell layers at the overlapped part is increased, so that the number of the layers required to be penetrated in the radiographic imaging is large, and the gray value of the pixels at the overlapped part in the cell region is low; if the cathode charge level and the anode charge level do not overlap, the number of cell layers between the cathode charge level and the anode charge level is small, so that the number of layers required to be penetrated during radiographic imaging is small, and the pixel gray value between the cathode charge level and the anode charge level is high. Therefore, by detecting the gray value distribution of the pixels in the cell area, whether the cathode feeding level and the anode feeding level of the finished cell overlap or not can be judged, so that the accuracy and the reliability of the cell detection result are improved.

In some embodiments, extracting the cell region from the cell image obtained by radiography comprises: according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain a binarized battery cell image of the battery cell image; and obtaining a cell region in the cell image according to the communication region corresponding to the cell in the binarized cell image. Therefore, the noise of the battery cell image can be effectively removed in a binarization mode, and meanwhile, the battery cell region can be accurately extracted from the battery cell image by utilizing the communication region in the binarization image, so that the accuracy of identifying the battery cell region is improved.

In some embodiments, according to gray values of pixels in the battery cell image, performing binarization processing on the battery cell image to obtain a binarized battery cell image of the battery cell image, including: according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain an initial binarized image of the battery cell image; and sequentially carrying out image corrosion and image expansion on the initial binarization image to obtain a binarization cell image of the cell image. Therefore, the method can effectively denoise the binarized image of the battery cell image, improves the definition and the readability of the obtained binarized image, and further improves the accuracy of the battery cell area extracted by the subsequent binarized image.

In some embodiments, according to the connected region corresponding to the battery cell in the binarized battery cell image, obtaining the battery cell region in the battery cell image includes: obtaining a target area in the battery cell image according to the communication area; performing image enhancement processing on the target area to obtain the battery cell area; the image enhancement processing comprises filtering processing on each column of pixels in the vertical direction of the feeding level in the target area so as to highlight or enhance the characteristics in the vertical direction, so that the characteristics of the cathode feeding level and the anode feeding level in the obtained cell area are more outstanding, the cathode feeding position and the anode feeding position can be observed more clearly, and the subsequent cell detection is facilitated.

In some embodiments, according to the gray value distribution of the pixels in the cell area, obtaining the detection result of the charge level of the cell includes: and according to the gray values of the pixels in each column in the vertical direction of the charge level in the battery cell area, obtaining a charge level detection result of the battery cell. When the electric core is detected, the charging level characteristics of the electric core can be effectively utilized for detection, and the accuracy of the charging level detection result of the electric core is improved.

In some embodiments, according to the gray values of the pixels in the columns of the cells in the vertical direction of the charge level, a charge level detection result of the cells is obtained, including: comparing the gray value of each row of pixels with a preset gray value to obtain a charging level detection result of the battery cell; the preset gray value is the minimum gray value detected from the cell area of the abnormal cell overlapped by the feeding level. Therefore, whether the charging positions of the electric cores overlap or not can be rapidly judged by comparing the gray values of the pixels in each row with the preset gray value, and the detection efficiency of the electric cores is improved.

In some embodiments, according to the gray values of the pixels in the columns of the cells in the vertical direction of the charge level, a charge level detection result of the cells is obtained, including: acquiring gray values of pixels in each column in the vertical direction of the feeding level in the cell region; according to the gray values of the pixels in each adjacent column, gray change data of the cell area are obtained; and according to the gray level change data, obtaining a charging level detection result of the battery cell. Therefore, when the charge level detection result of the battery cell is judged, the overall distribution condition of each row of pixels in the vertical direction of the charge level is considered, and the accuracy of the charge level detection result is improved.

In some embodiments, according to the gray level change data, obtaining a detection result of the charge level of the battery cell includes: determining the anode charge level and the cathode charge level of the battery cell according to the gray level difference of adjacent gray values in the gray level change data; and obtaining the overlapping distance between the anode feeding level and the cathode feeding level of the battery cell according to the anode feeding level and the cathode feeding level. Therefore, the obtained material inlet level detection result is more accurate, and subsequent adjustment of the battery cell is facilitated.

In some embodiments, according to the gray level change data, obtaining a detection result of the charge level of the battery cell includes: detecting the gray level change data by using a pre-trained preset model to obtain the overlapping distance between the anode charge level and the cathode charge level of the battery cell; the preset model is obtained by training gray level change data corresponding to each cell region sample, and each cell region sample comprises a cell region of a normal cell and a cell region of an abnormal cell.

In a second aspect, the present application provides a cell detection device, including:

The region extraction module is used for extracting a cell region from a cell image obtained through radiographic imaging; and the battery cell detection module is used for obtaining the charge level detection result of the battery cell according to the gray value distribution of the pixels in the battery cell region.

According to the technical scheme provided by the embodiment of the application, the cell area is extracted from the cell image obtained by utilizing the radiographic imaging, so that the charge level detection result of the cell is determined according to the gray distribution of the pixels in the cell area, and the accuracy and the reliability of the cell detection result are improved.

In some embodiments, the region extraction module is specifically configured to: according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain a binarized battery cell image of the battery cell image; and obtaining a cell region in the cell image according to the communication region corresponding to the cell in the binarized cell image.

In some embodiments, the region extraction module is specifically configured to: according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain an initial binarized image of the battery cell image; and sequentially carrying out image corrosion and image expansion on the initial binarization image to obtain a binarization cell image of the cell image.

In some embodiments, the region extraction module is specifically configured to: obtaining a target area in the battery cell image according to the communication area; performing image enhancement processing on the target area to obtain the battery cell area; the image enhancement processing includes filtering each column of pixels located in the vertical direction of the incoming bit in the target area.

In some embodiments, the cell detection module is specifically configured to: and according to the gray values of the pixels in each column in the vertical direction of the charge level in the battery cell area, obtaining a charge level detection result of the battery cell.

In some embodiments, the cell detection module is specifically configured to: comparing the gray value of each row of pixels with a preset gray value to obtain a charging level detection result of the battery cell; the preset gray value is the minimum gray value detected from the cell area of the abnormal cell overlapped by the feeding level.

In some embodiments, the cell detection module is specifically configured to: acquiring gray values of pixels in each column in the vertical direction of the feeding level in the cell region; according to the gray values of the pixels in each adjacent column, gray change data of the cell area are obtained; and according to the gray level change data, obtaining a charging level detection result of the battery cell.

In some embodiments, the cell detection module is specifically configured to: determining the anode charge level and the cathode charge level of the battery cell according to the gray level difference of adjacent gray values in the gray level change data; and obtaining the overlapping distance between the anode feeding level and the cathode feeding level of the battery cell according to the anode feeding level and the cathode feeding level.

In some embodiments, the cell detection module is specifically configured to: detecting the gray level change data by using a pre-trained preset model to obtain the overlapping distance between the anode charge level and the cathode charge level of the battery cell; the preset model is obtained by training gray level change data corresponding to each cell region sample, and each cell region sample comprises a cell region of a normal cell and a cell region of an abnormal cell.

In a third aspect, the application provides an electronic device comprising a memory storing a computer program and a processor executing the method in an implementation of the first aspect when the processor executes the computer program.

In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the method in an implementation of the first aspect.

In a fifth aspect, the present application provides a computer program product which, when run on a computer, causes the computer to perform the method of any of the alternative implementations of the first aspect.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the accompanying drawings. In the drawings:

FIG. 1 is a first flowchart of a method for detecting a battery cell according to some embodiments of the present application;

FIG. 2 is a schematic diagram of a cell image according to some embodiments of the application;

FIG. 3 is a schematic diagram of a cell region according to some embodiments of the present application;

Fig. 4a is a schematic diagram of a cell structure with a normal feeding level according to some embodiments of the present application;

FIG. 4b is a schematic diagram of a cell structure with abnormal charge level according to some embodiments of the present application;

FIG. 5a is a schematic diagram illustrating a cell area pixel distribution of a normal cell according to some embodiments of the present application;

FIG. 5b is a schematic diagram illustrating a cell area pixel distribution of an abnormal cell according to some embodiments of the present application;

FIG. 6 is a second flowchart of a method for detecting a battery cell according to some embodiments of the present application;

FIG. 7 is a schematic diagram of gray scale variation data of a normal cell according to some embodiments of the present application;

FIG. 8 is a schematic diagram of gray scale variation data of an abnormal cell according to some embodiments of the present application;

FIG. 9 is a third flowchart of a method for detecting a battery cell according to some embodiments of the present application;

Fig. 10 is a schematic structural diagram of a cell detection device according to some embodiments of the present application;

Fig. 11 is a schematic structural diagram of an electronic device according to some embodiments of the present application.

Reference numerals in the specific embodiments are as follows:

401-region extraction module; 402-a cell detection module; 5-an electronic device; 501-a processor; 502-memory; 503-communication bus.

Detailed Description

Embodiments of the technical scheme of the present application will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present application, and thus are merely examples, and are not intended to limit the scope of the present application.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion.

In the description of embodiments of the present application, the technical terms "first," "second," and the like are used merely to distinguish between different objects and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated, a particular order or a primary or secondary relationship. In the description of the embodiments of the present application, the meaning of "plurality" is two or more unless explicitly defined otherwise.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In the description of the embodiments of the present application, the term "and/or" is merely an association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

In the description of the embodiments of the present application, the term "plurality" means two or more (including two), and similarly, "plural sets" means two or more (including two), and "plural sheets" means two or more (including two).

In the construction of the battery, the cells are an important component. In the production process of the battery cell, the internal structure of the produced battery cell may have the defect of overlapping of the charging positions of the cathode and the anode under the influence of environment, process or other accidental factors. Therefore, to increase the yield of the battery cells, the internal structure of the battery cells needs to be detected.

At present, the internal structure of the battery cell is detected by disassembling the battery cell to detect whether the cathode and anode material inlet positions of the battery cell have defects. However, this method may damage the battery cell, and the safety is poor. Therefore, in the related art, the battery cell can be detected by acquiring the winding image of the battery cell during the winding process of the battery cell, so as to determine whether the feeding position of the battery cell after the finished product has defects. However, this method needs to detect during the winding process of the battery cell, which affects the production efficiency of the battery cell, and after the battery cell is manufactured, if the battery cell is not disassembled and verified, it cannot be determined whether the detection result is suitable for the battery cell after the battery cell is manufactured. Meanwhile, due to the influence of environment, process or other accidental factors, the structure of the final finished battery cell may be different from that of a theoretical finished battery cell manufactured by the winding process, so that the accuracy and the reliability of the battery cell detection result are affected.

Aiming at the technical problems, the embodiment of the application extracts the cell area from the cell image obtained by utilizing the radiographic imaging, so as to determine the charge level detection result of the cell according to the gray distribution of the pixels in the cell area. When the cathode material inlet level and the anode material inlet level are overlapped, the number of the cell layers at the overlapped part is increased, so that the number of the layers required to be penetrated in the radiographic imaging is large, and the gray value of the pixels at the overlapped part in the cell region is low; if the cathode charge level and the anode charge level do not overlap, the number of cell layers between the cathode charge level and the anode charge level is small, so that the number of layers required to be penetrated during radiographic imaging is small, and the pixel gray value between the cathode charge level and the anode charge level is high. Therefore, by detecting the gray value distribution of the pixels in the cell area, whether the cathode feeding level and the anode feeding level of the finished cell overlap or not can be judged, so that the accuracy and the reliability of the cell detection result are improved.

The cell detection method, the device, the electronic equipment and the storage medium disclosed by the embodiment of the application can be applied to a server and are used for detecting whether the cathode and anode material inlet positions of the finished product cell overlap. The server may be an independent server or a server cluster formed by a plurality of servers, and may also be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligent sampling point devices, and the like.

According to some embodiments of the present application, a method for detecting a battery cell is provided, which can be applied to the foregoing server. As shown in fig. 1, the method for detecting the battery cell includes:

S101, extracting a cell region from a cell image obtained by radiographic imaging;

S102, obtaining a charging level detection result of the battery cell according to the gray value distribution of the pixels in the battery cell region.

Radiographic imaging, among others, refers to imaging techniques that use a beam of radiation to pass through a subject to obtain its projection, such as X-Ray imaging. The internal structure of the battery core has a plurality of battery core layers, and when the traditional plane imaging is adopted, such as adopting CCD (charge coupled device ) and other imaging equipment to acquire the battery core images, the battery core has no penetrability, so that only the surface layer images of the battery core can be acquired, and the battery core can not be used for judging the number of the battery core layers. The rays, such as X-rays, can penetrate through the battery cells, so that the acquired image can form pixel points with corresponding gray values according to the number of battery cell layers penetrated by the rays, and if the number of battery cell layers penetrated by the rays is smaller, the gray values of the formed pixel points are lower; on the contrary, the gray value of the formed pixel point is higher. Therefore, the gray level image of the battery cell, namely the battery cell image representing the battery cell layer structure, can be obtained through radiographic imaging, so that the battery cell can be detected by using the gray level value of the pixel in the battery cell image later.

When the battery cell is required to be detected, the battery cell can be subjected to radiographic imaging to obtain a gray level image of the battery cell, wherein the gray level image is the battery cell image. A 16-bit gray scale image of the cell is acquired as a cell image by an X-Ray device, as shown in fig. 2.

After the cell image of the cell is obtained, the cell image may be preprocessed, such as ROI (Region of Interest ) extraction, to extract the cell region from the cell image, as shown in fig. 3.

As a possible implementation manner, for the extraction of the cell area, edge extraction may be performed on the cell image to obtain an edge image of the cell image, so as to extract the cell area from the cell image according to the edge image.

Wherein, the edge extraction refers to one of the image processing for the image contour. The place where the gray level change rate of the image is maximum is defined as an edge, namely an inflection point, wherein the inflection point is a point where the function changes in a concave-convex manner, and the second derivative is zero. And extracting edges of the battery cell images, wherein edge detection operators can be adopted to detect the edges of the battery cell images so as to extract the outlines of all objects from the battery cell images to form edge images. The edge detection operator can be any one of edge operators such as gradient edge operators, roberts edge operators, laplacian edge operators and Sobel edge operators.

After the edge image is acquired, cell boundary detection may be performed on the edge image to extract a cell region from the cell image based on the detected cell boundary. For example, edge lines corresponding to the contours of the cells may be identified from the cell image as cell boundaries to extract the cell regions of the cells from the cell image using the identified cell boundaries. Or the boundary of the battery cell can be identified from the edge image according to a preset gray value. The preset gray value may be a gray value of a boundary pixel of the battery cell. If the preset gray value is utilized, traversing each edge line in the edge image to find the edge line with the gray value identical to the preset gray value or with the difference value smaller than the preset gray value from the edge image, so as to extract the cell region from the cell image by utilizing all the found edge lines.

In addition, the cell regions may also be extracted from the cell images by other conventional ROI extraction methods, such as based on opencv or pre-trained image segmentation models.

Because the battery cell is formed by winding the cathode pole piece, the anode pole piece and the diaphragm, when the starting position of winding the cathode pole piece and the starting position of winding the anode pole piece of the battery cell, namely the cathode material inlet level and the anode material inlet level are not overlapped, the number of battery cell layers on the area between the cathode material inlet level and the anode material inlet level is less than that on the two sides of the area, as shown in fig. 4 a. If the cathode charge level and the anode charge level overlap, the number of cell layers in the region between the two is greater than the number of cell layers on both sides of the region, as shown in fig. 4 b.

If the cathode charge level and the anode charge level do not overlap, the number of cell layers in the region between the cathode charge level and the anode charge level is smaller than that on both sides of the region, so that after the radiography, the gray value of the region between the cathode charge level and the anode charge level is larger than that on both sides of the region, as shown in fig. 5 a. Similarly, if the cathode charge level and the anode charge level overlap, the gray level of the region between the cathode charge level and the anode charge level after the radiography is smaller than the gray level of the regions on both sides thereof, as shown in fig. 5 b. Based on the above, after the cell region is extracted from the cell image, the gray value distribution of the pixels in the cell region can be detected, so as to determine whether the cathode and anode material inlets of the cell overlap based on the gray value distribution.

For example, after the cell region is extracted, adjacent pixels may be clustered according to the gray value of each pixel in the cell region, for example, clustering is performed by a KNN algorithm, so as to obtain a plurality of sub-regions, and then gray value distribution between the sub-regions is detected. If the average gray value of a certain subarea is detected to be larger than the average gray value of subareas at two sides of the subarea, the charge level detection result of the battery cell can be determined to be that the charge levels of the cathode and anode of the battery cell are not overlapped, so that the battery cell is determined to be a normal battery cell; if the average gray value of a certain subarea is detected to be smaller than the average gray value of subareas at two sides of the subarea, the charge level detection result of the battery cell can be determined to be the overlapping of the cathode charge level and the anode charge level of the battery cell, so that the battery cell is determined to be an abnormal battery cell. Or the area of a subarea with an average gray value smaller than that of subareas at two sides of the subarea can be detected; if the area of the subarea is larger than 0, the existence of cathode and anode material inlet level overlapping is indicated, and the cell can be determined to be an abnormal cell at the moment; otherwise, the cell may be determined to be a normal cell.

In addition, the feeding level detection result may further include a feeding level overlapping distance. If the average gray value in the cell area is smaller than the distance between the two side boundaries of the sub-areas of the average gray value of the sub-areas at the two sides of the cell area, the distance is used as the cathode and anode material inlet overlapping distance of the cell so as to obtain the specific abnormal condition of the cell, and the abnormal cell can be conveniently classified and intercepted later. The boundary of a sub-region refers to the boundary between the sub-region and its adjacent sub-region.

The cell region is extracted from a cell image obtained by utilizing radiographic imaging, so that the charge level detection result of the cell is determined according to the gray level distribution of pixels in the cell region. When the cathode material inlet level and the anode material inlet level are overlapped, the number of the cell layers at the overlapped part is increased, so that the number of the layers required to be penetrated in the radiographic imaging is large, and the gray value of the pixels at the overlapped part in the cell region is low; if the cathode charge level and the anode charge level do not overlap, the number of cell layers between the cathode charge level and the anode charge level is small, so that the number of layers required to be penetrated during radiographic imaging is small, and the pixel gray value between the cathode charge level and the anode charge level is high. Therefore, by detecting the gray value distribution of the pixels in the cell area, whether the cathode feeding level and the anode feeding level of the finished cell overlap or not can be judged, so that the accuracy and the reliability of the cell detection result are improved.

While in extracting the cell region, to reduce the amount of data for image processing, noise interference in cell region identification is reduced, in some embodiments, extracting the cell region from a cell image obtained by radiographic imaging includes: according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain a binarized battery cell image of the battery cell image; and obtaining a cell region in the cell image according to the communication region corresponding to the cell in the binarized cell image.

As a possible implementation manner, when the cell area needs to be extracted from the cell image, a binarization algorithm may be first used to determine a corresponding threshold value for the gray value of each pixel in the cell image, so as to binarize the cell image by using the threshold value, for example, adaptively binarize the cell image, so as to obtain a binarized cell image of the cell image. The binarized cell image obtained at this time includes a cell region as a foreground and other regions as a background. The binarization algorithm can be any binarization algorithm such as a bimodal method, a P parameter method, an iterative method, an OTSU method and the like.

Taking OTSU binarization algorithm as an example, when the threshold is set as t, P (t) is the probability that a pixel in the cell image is divided into foreground pixels, and the average gray level of the pixels allocated to the foreground is，The probability of dividing pixels in the cell image into the background is that the average gray level isThe accumulated average value of the gray level t isThe gray value of the whole cell image isThe following steps are:

（1）

according to the variance concept, the expression can be expressed as:

（2）

substituting formula (1) into formula (2), there are:

（3）

ultimately, can be written as the following formula, wherein ，，：

（4）

After the optimal threshold is solved by using an OTSU algorithm, binarization processing can be carried out on the battery cell image according to the optimal threshold:

（5）

wherein, Representing the coordinates of the pixel in the cell image.

In order to further improve the definition of the binarized cell image, the image may be subjected to secondary denoising after the adaptive binarization, for example, the image subjected to the adaptive binarization may be subjected to secondary denoising through an open operation, so as to obtain the binarized cell image of the cell image.

After the binarized cell image is obtained, a communication region corresponding to the cell can be extracted from the binarized cell image, so that a region corresponding to the communication region is extracted from the cell image and used as a cell region.

For example, the connected region analysis may be performed on the binarized cell image, that is, each pixel in the binarized cell image may be assigned a new label according to the label of its adjacent pixel, specifically:

wherein, Is a pixelIs used for the new label of the (c),Is a pixelIs included in the label set of adjacent pixels of the display. The labels include foreground or background, and the initial label of the pixel is determined by the binarization described above.

Then, the information such as the area, the circumscribed rectangle and the like of each connected area is counted, and the method specifically comprises the following steps:

wherein, The label is represented as the area of the label area.

After each communication region is obtained, the region having the largest area among the communication regions is determined as the communication region corresponding to the cell, and the region corresponding to the communication region is extracted from the cell image as the cell region.

The binarization is carried out on the battery cell image to obtain a binarized battery cell image of the battery cell image, and the battery cell area in the battery cell image is obtained based on the communication area corresponding to the battery cell in the binarized battery cell image, so that the noise of the battery cell image can be effectively removed in a binarization mode, and meanwhile, the battery cell area can be accurately extracted from the battery cell image by utilizing the communication area in the binarization image, and the accuracy of identifying the battery cell area is further improved.

In order to further improve accuracy of cell region identification, in some embodiments, performing binarization processing on the cell image according to gray values of pixels in the cell image to obtain a binarized cell image of the cell image, including: according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain an initial binarized image of the battery cell image; and sequentially carrying out image corrosion and image expansion on the initial binarization image to obtain a binarization cell image of the cell image.

In some embodiments, after binarizing the cell image according to the gray value of each pixel in the cell image, an initial binarized image of the cell image may be obtained first. After the initial binary image is obtained, the initial binary image can be corroded and re-expanded, so that small objects, isolated areas and small edges can be effectively removed, and meanwhile, the shape of a larger connected area in the image is maintained.

Illustratively, after the initial binarized cell image is obtained by the binarization process, a small kernel called a structural element may be used to slide over the initial binarized cell image and convolve. For each pixel in the initial binarized cell image, the pixels in the area covered by the structural element are updated according to a certain rule, for example, the minimum pixel value is taken as the new value of the central pixel, the input image is set, namely the initial binarized cell image is A, the structural element is B, and the corrosion operation is performedThe expression is as follows:

wherein, Representing the coordinates of the pixels in the image a,The element coordinates in the structural element B are expressed, and the above expression indicates that the minimum value of all covered pixels is taken as a new pixel value within the range of the structural element.

Then, the initial binarized image after the image erosion operation is subjected to image expansion, the image expansion can expand or expand the object in the image by sliding the structural element, and the expansion operation is usedThe expression is as follows:

The open operation calculation formula is as follows:

Thus, through image corrosion and image expansion, a binarized cell image of the cell image can be obtained Therefore, the binary image of the battery cell image can be effectively denoised, the definition and the readability of the obtained binary image are improved, and the accuracy of a battery cell area extracted by the subsequent binary image is further improved.

After the binarized cell image is obtained, the cell region corresponding to the cell can be extracted from the cell image according to the communication region corresponding to the cell in the binarized cell image.

In order to improve the definition and the readability of the cell region extracted from the cell image, so as to improve the accuracy of detecting the cell region, in some embodiments, obtaining the cell region in the cell image according to the connected region corresponding to the cell in the binarized cell image includes: obtaining a target area in the battery cell image according to the communication area; performing image enhancement processing on the target area to obtain the battery cell area; the image enhancement processing includes filtering each column of pixels located in the vertical direction of the incoming bit in the target area.

In some embodiments, after obtaining the connected region corresponding to the cell in the binarized cell image, the region corresponding to the connected region may be extracted from the cell image as the target region according to the connected region.

After the target area is obtained, the charge level characteristics of the battery cells are reflected in the vertical direction of the charge level of the cathode and the anode in the battery cell image obtained through radiographic imaging, so that at least each column of pixels in the vertical direction of the charge level of the cathode and the anode of the battery cells in the target area can be subjected to filtering treatment so as to protrude or enhance the characteristics in the vertical direction, the charge level characteristics of the cathode and the anode in the obtained battery cell area are more outstanding, the charge position of the cathode and the charge position of the anode can be observed more clearly, and the subsequent battery cell detection is facilitated.

In addition to performing filtering processing on each column of pixels located in the vertical direction of the input level in the target area, at least one image enhancement processing mode such as global contrast stretching, laplace filtering and gaussian filtering may be adopted to perform image enhancement on the target area.

As a possible implementation manner, the image enhancement processing is performed on the target area, which may be to adjust the gray level distribution of the target area by using global contrast stretching; filtering processing is carried out on each column of pixels in the vertical direction of the material inlet position in the target area, and pixel characteristics of each column of pixels in the vertical direction of the material inlet position are highlighted or enhanced; the target area is subjected to Laplace filtering, and edges and details in the target area are highlighted to enhance image characteristics; after Laplace filtering, gaussian filtering is carried out on the target area, high-frequency noise introduced in Laplace filtering is reduced, an image is smoothed, the overall contrast of the image is improved, and the phenomenon that image edges are discontinuous after Laplace filtering is reduced, so that a cell area is obtained.

For example, after obtaining the target region, the pixel value range of the target region may be adjusted first to enhance the image contrast of the target region. Such as moving the pixel values of the target area from the original rangeExpansion to a new rangeWhereinFor the pixel value of the target area,For the pixel values after contrast stretching,Is the minimum pixel value of the target region,Is the maximum pixel value of the target region.

After the global contrast stretching of the target area is completed, the target area with the global contrast being pulled up can be longitudinally filtered, namely, each column of pixels in the vertical direction of the input position is filtered. If a one-dimensional vertical filter is defined, a one-dimensional filter (kernel) is set asAnd has a length of L,Representing the position offset of the filter in the vertical direction of the incoming level with respect to the input image, i.e. the target area,For the pixel value of the target area,Is the pixel value of the target area after longitudinal filtering.

After the longitudinal filtering of the target region is completed, the target region after the longitudinal filtering is completed may be subjected to laplace filtering. Such as performing a second differentiation on the target area to detect edges and details in the target area.

The laplace operator calculation formula is as follows:

after the laplace operator is utilized to complete the laplace filtering of the target area, the target area after the laplace filtering is completed can be subjected to Gaussian filtering. For example, the pixel values of the target area are weighted and averaged, the target area is smoothed and noise is removed, and image details and edges are reserved.

Wherein the gaussian function is as follows:

after the image enhancement processing is completed in the target area, the region of interest can be extracted again for the target area after the image enhancement processing is completed, so that the cell area is obtained. And determining the target area after the image enhancement processing is completed as a battery cell area. The final extracted cell area may be as shown in fig. 5a or fig. 5 b. Therefore, the characteristics of the cathode and anode material inlet positions in the obtained battery cell area are more outstanding, the subsequent battery cell detection is facilitated, and the accuracy of the battery cell detection is improved.

After the cell region is extracted, the feeding of the cell can be determined to be a detection result according to the gray value distribution of the pixels in the cell region. Considering that the charge level characteristics of the battery cell are all reflected in the vertical direction of the charge level of the anode and the cathode in the battery cell image obtained through radiographic imaging, in some embodiments, the charge level detection result of the battery cell is obtained according to the gray value distribution of the pixels in the battery cell area, and the method comprises the following steps: and according to the gray values of the pixels in each column in the vertical direction of the charge level in the battery cell area, obtaining a charge level detection result of the battery cell.

The gray value of any column of pixels may be an average gray value of each pixel point in the column of pixels, or a mode value in the gray values of each pixel point in the column of pixels. For any column of pixels, the gray values of the pixels in the column of pixels may be added to average the gray values of the pixels in the column of pixels, to finally obtain the average value of the pixels in the column of pixels, i.e. the gray values of the pixels in the column of pixels. Such as:

wherein, Indicating the area of the electrical cell,Indicating the height of the cell region,The gray value of the pixel point of the cell area in the ith row and the jth column,The pixel mean value of the j-th column pixel, i.e., the gray value of the j-th column pixel.

Since the number of layers penetrated by rays is reduced by two at the cathode and anode charge levels when the cathode and anode charge levels are not overlapped, as shown in fig. 4a, the higher the brightness after imaging, the higher the gray value of the pixel between the cathode and anode charge levels; in contrast, the number of layers penetrated by the radiation increases by two between the anode and cathode positions, as shown in fig. 4b, and the lower the brightness after imaging, the lower the gray value of the pixel between the anode and cathode positions. Therefore, after the gray values of the pixels in each column in the vertical direction of the input level are obtained, each column of pixels can be traversed from left to right or from right to left, so as to obtain the gray value variation trend of the pixels in each column. If the gray value change trend is from small to large to small in the pixels of each row, determining that the cathode charge level and the anode charge level are not overlapped; if there are partial columns of pixels in which the gradation value change trend is from large to small, it is determined that the cathode charge level and the anode charge level overlap.

Or the minimum gray value of each pixel in the cell area can be obtained as a preset gray value for the abnormal cells overlapped in the cathode and anode charge level. The abnormal battery cell is identical to the battery cell to be detected in specification and model. It can be understood that the cell region acquiring manner of the abnormal cell is the same as the cell region acquiring manner of the cell to be detected, and the cell region acquiring manner can be acquired by adopting the above-described manner. When the cathode material inlet level and the anode material inlet level are overlapped, the number of layers required to be penetrated by the rays between the cathode material inlet level and the anode material inlet level is the largest, so that the gray value of the pixel point between the cathode material inlet level and the anode material inlet level is the smallest, and the preset gray value can represent the gray value when the cathode material inlet level and the anode material inlet level are overlapped.

After the gray values of the pixels in each column are obtained, a plurality of boundaries can be determined from the pixels in each column according to the gray value differences of the pixels in each adjacent column. If the gray value difference between two adjacent pixels reaches a preset value, a pixel with smaller or larger gray value can be extracted as a boundary. The preset value can be set according to actual conditions. After the boundaries are extracted, detecting whether the gray values of pixels in each column between any two boundaries are matched with the preset gray values, and if so, judging whether the difference value between the gray values and the preset gray values is within the preset range. If the gray value of each row of pixels between the two boundaries is matched with the preset gray value, if the difference value between the gray value of each row of pixels between the two boundaries and the preset gray value is smaller than the preset threshold value, determining that the charge level detection result of the battery cell is that the charge level overlap exists; otherwise, it can be determined that the charge level detection result of the battery cell is that there is no charge level overlap. The preset threshold value can be set according to actual conditions. For example, a plurality of preset gray values corresponding to a plurality of abnormal cells with the same specification and model as the cell to be detected are obtained, and then the difference between the maximum value and the minimum value in each preset gray value is used as a preset threshold.

The gray values of the pixels in the vertical direction of the charge level in the cell area are used for determining the charge level detection result of the cell, so that the charge level characteristic of the cell can be effectively utilized for detection when the cell is detected, and the accuracy of the charge level detection result of the cell is improved.

In order to more efficiently detect the battery cell, in some embodiments, according to the gray values of the pixels in the battery cell region, the detection result of the charge level of the battery cell is obtained, where the gray values are located in the vertical direction of the charge level, and the detection result includes:

Comparing the gray value of each row of pixels with a preset gray value to obtain a charging level detection result of the battery cell; the preset gray value is the minimum gray value detected from the cell area of the abnormal cell overlapped by the feeding level.

In some embodiments, the minimum gray value of each pixel in the cell area of the abnormal cell overlapped with the cathode and anode charge level can be obtained as the preset gray value. The abnormal battery cell is identical to the battery cell to be detected in specification and model.

After the gray values of the pixels in each column are obtained, the gray values of the pixels in each column can be compared with a preset gray value. If a certain column of pixels with gray values smaller than or equal to the preset gray value exists in each column of pixels, or a certain column of pixels with differences between the gray values and the preset gray values smaller than a preset threshold value exists, determining that the charge level detection result of the battery cell is that the charge level overlap exists; if the gray value of each row of pixels is larger than the preset gray value, or the gray value of each row of pixels is larger than the preset gray value, and the difference value between the gray value of each row of pixels and the preset gray value is larger than the preset threshold value, the charge level detection result of the battery cell can be determined to be that no charge level overlap exists. Therefore, whether the charging positions of the electric cores overlap or not can be rapidly judged by comparing the gray values of the pixels in each row with the preset gray value, and the detection efficiency of the electric cores is improved.

In order to make the charge level detection result of the battery cell more accurate, in addition to obtaining the charge level detection result of the battery cell by comparing the gray values of the pixels in each row with a preset gray value, in some embodiments, as shown in fig. 6, according to the gray values of the pixels in each row located in the vertical direction of the charge level in the battery cell area, the charge level detection result of the battery cell is obtained, including:

S201, acquiring gray values of pixels in each column in the vertical direction of the material inlet level in the battery cell area;

S202, according to the gray values of the pixels in each adjacent column, gray change data of the cell area are obtained;

s203, according to the gray level change data, obtaining a charging level detection result of the battery cell.

In some embodiments, after the cell area is obtained, gray values of pixels in each column may be sequentially extracted from left to right or from right to left in a vertical direction located at the feeding level, and then gray values of pixels in adjacent columns are sequentially arranged, so that gray change data of the cell area may be obtained. Or converting the gray value of each adjacent column of pixels into a gray value change curve representing the corresponding relation between the gray value and the cell position by taking the left side of the cell region as a starting position, wherein the gray value change curve is the gray change data of the cell region.

Since the number of radiation transmission layers is reduced between the cathode charge level and the anode charge level based on the radiation imaging principle, such as the X-ray imaging principle, if the cell is a normal cell in which the cathode charge level and the anode charge level are not overlapped, the gray level change data of the normal cell suddenly rises to generate a peak, and then suddenly falls, as shown in fig. 7. If the cell is an abnormal cell with overlapping cathode and anode charge levels, the number of radiation penetration layers is increased between the cathode and anode charge levels based on the radiation imaging principle, so that the gray level change data of the abnormal cell suddenly drops to generate a trough, and then suddenly rises, as shown in fig. 8.

Therefore, after the gray scale change data of the cell region is obtained, the change trend of the gray scale change data of the cell region can be detected. And if the gray level change data of the cell area is matched with the gray level change data of the normal cell in a similarity manner. If the gray level change data of the cell area is consistent with the change trend of the gray level change data of the normal cell, if the similarity of the gray level change data and the gray level change data is greater than the preset similarity, such as 80%, determining that the charge level detection result of the cell corresponding to the cell area is that the charge level is not overlapped; otherwise, the charging level detection result of the battery cell corresponding to the battery cell region can be determined to be charging level overlapping. Or matching the gray level change data of the cell area with the gray level change data of the abnormal cell in a similarity manner. If the gray level change data of the cell area is consistent with the change trend of the gray level change data of the abnormal cell, if the similarity of the gray level change data and the abnormal cell is greater than the preset similarity, determining that the charge level detection result of the cell corresponding to the cell area is charge level overlapping; otherwise, the detection result of the feeding level of the battery cell corresponding to the battery cell region can be determined to be that the feeding level is not overlapped.

Or the gray level change data can be detected by using a pre-trained preset model to obtain the charge level detection result of the battery cell. The preset model may be an SVM classifier or other lightweight AI detection model.

For training the preset model, the cell area is firstly extracted from a large number of normal cells and abnormal cells to serve as cell area samples, and after the gray level change data of each cell area sample are determined in the mode, the gray level change data of each cell area sample are input into the preset model to be trained so as to obtain the preset model for training.

As a possible implementation manner, the gray level change data of each cell area sample may be sequentially input into the preset model, and after each input is performed, whether the preset model output overlaps or not is obtained, the input level prediction result is matched with the preset input level detection result corresponding to the gray level change data input at this time.

And under the condition that the two are not matched, adopting a gradient descent method, adjusting network parameters of the preset model through error back propagation, and then performing the next training until a predicted material inlet level detection result obtained after gray level change data of a cell area sample are input each time is matched with a preset material inlet level detection result corresponding to the gray level change data input at this time, and indicating that the training of the preset model is completed to obtain the preset model trained in advance.

Therefore, when the charge level detection result of the battery cell is judged, the overall distribution condition of each row of pixels in the vertical direction of the charge level is considered, and the accuracy of the charge level detection result is improved.

In some embodiments, in addition to determining whether there is overlap in the cathode charge level and the anode charge level of the cell, the charge level detection result may also include an overlap distance between the anode charge level and the cathode charge level of the cell. And obtaining a charging level detection result of the battery cell according to the gray level change data, wherein the charging level detection result comprises the following steps: determining the anode charge level and the cathode charge level of the battery cell according to the gray level difference of adjacent gray values in the gray level change data; and obtaining the overlapping distance between the anode feeding level and the cathode feeding level of the battery cell according to the anode feeding level and the cathode feeding level.

In some embodiments, after the gray level change data of the cell area is obtained, the gray level difference of the adjacent gray level values in the gray level change data may be obtained first. The gray scale difference is the absolute value of the difference between adjacent gray scale values. Then, one of the two columns of pixels corresponding to the highest gray level difference in each gray level difference and one of the two columns of pixels corresponding to the next highest gray level difference in each gray level difference are respectively determined as an anode charge level and a cathode charge level of the battery cell.

After determining the anode charge level and the cathode charge level of the battery cell, if the gray level change data of the battery cell area is matched with the gray level change data of the normal battery cell or is not matched with the gray level change data of the abnormal battery cell, determining that the overlapping distance between the anode charge level and the cathode charge level of the battery cell is 0; if the gray level change data of the cell area is matched with the gray level change data of the abnormal cell or is not matched with the gray level change data of the normal cell, determining the distance between the anode charge level and the cathode charge level as the overlapping distance between the anode charge level and the cathode charge level of the cell.

Or after determining the gray level change data of the cell area and matching the gray level change data of the abnormal cell or not matching the gray level change data of the normal cell, determining one of two columns of pixels corresponding to the highest gray level difference in each gray level difference and one of two columns of pixels corresponding to the next highest gray level difference in each gray level difference as the anode charge level and the cathode charge level of the cell respectively, so as to determine the distance between the anode charge level and the cathode charge level as the overlapping distance between the anode charge level and the cathode charge level of the cell.

Or after determining the anode charge level and the cathode charge level of the battery core, detecting whether the gray value of each column of pixels positioned between the anode charge level and the cathode charge level in the gray change data is smaller than the gray value of each column of pixels positioned outside the anode charge level and the cathode charge level; if yes, determining the distance between the anode feeding level and the cathode feeding level as the overlapping distance between the anode feeding level and the cathode feeding level of the battery cell; otherwise, the overlapping distance between the anode charge level and the cathode charge level of the cell is determined to be 0.

The anode feeding level and the cathode feeding level of the battery cell are determined through the gray level difference of adjacent gray values in the gray level change data, so that the overlapping distance between the anode feeding level and the cathode feeding level of the battery cell is obtained based on the anode feeding level and the cathode feeding level, the obtained feeding level detection result is more accurate, and the battery cell can be conveniently adjusted subsequently.

In addition, in some embodiments, after the gray level change data of the cell area is obtained, a pre-trained preset model may be used to detect the gray level change data, so as to obtain an overlapping distance between the anode charge level and the cathode charge level of the cell; the preset model is obtained by training gray level change data corresponding to each cell region sample, and each cell region sample comprises a cell region of a normal cell and a cell region of an abnormal cell.

As a possible implementation manner, gray change data corresponding to each cell area sample may be sequentially input into a preset model, and after a predicted overlapping distance between an anode input level and a cathode input level output by the preset model is obtained in each input, the predicted overlapping distance is matched with a preset overlapping distance corresponding to the gray change data input at this time.

And under the condition that the two are not matched, adopting a gradient descent method, adjusting network parameters of the preset model through error back propagation, and then performing the next training until the predicted overlapping distance obtained after each time of input of gray change data is matched with the preset overlapping distance corresponding to the training sample input at this time, and indicating that the training of the preset model is completed to obtain the preset model trained in advance.

After the pre-trained preset model is obtained, gray level change data of the cell area can be input into the pre-trained preset model, so that the overlapping distance between the anode material inlet level and the cathode material inlet level of the cell is identified through the pre-trained preset model.

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below. In some embodiments, as shown in fig. 9, the method for detecting a battery cell includes:

S301, acquiring a battery cell image generated by a battery cell through ray imaging;

s302, performing binarization processing on the battery cell image according to the gray value of each pixel in the battery cell image to obtain an initial binarization image of the battery cell image;

s303, sequentially performing corrosion operation and expansion operation on the initial binarized image to obtain a binarized cell image of the cell image;

s304, carrying out connected region analysis on the binarized cell image, extracting a region with the largest connected region area as an interested region, and determining a target region in the cell image according to the interested region;

S305, using global contrast stretching to adjust gray level distribution of a target area, and performing longitudinal filtering, laplacian filtering and Gaussian filtering on the target area subjected to global contrast stretching to obtain a battery cell area;

S306, according to gray values of pixels of adjacent columns in the vertical direction of the feeding level in the cell area, gray change data of the cell area are obtained;

s307, gray level change data of the cell area are input into a pre-trained SVM classifier to be detected, and the overlapping distance between the anode material inlet level and the cathode material inlet level of the cell is obtained.

Fig. 10 shows a schematic block diagram of a cell detection device according to an embodiment of the present application, and it should be understood that the device corresponds to the method embodiments executed in fig. 1, fig. 6, and fig. 9, and is capable of executing the steps involved in the foregoing method, and specific functions of the device may be referred to the above description, and detailed descriptions thereof are omitted herein for avoiding repetition. The device includes at least one software functional module that can be stored in memory in the form of software or firmware (firmware) or cured in an Operating System (OS) of the device. Specifically, the device comprises: a region extraction module 401, configured to extract a cell region from a cell image obtained by radiographic imaging; and the cell detection module 402 is configured to obtain a detection result of the charge level of the cell according to the gray value distribution of the pixels in the cell region.

According to some embodiments of the present application, the region extraction module 401 is specifically configured to: according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain a binarized battery cell image of the battery cell image; and obtaining a cell region in the cell image according to the communication region corresponding to the cell in the binarized cell image.

According to some embodiments of the present application, the region extraction module 401 is specifically configured to: according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain an initial binarized image of the battery cell image; and sequentially carrying out image corrosion and image expansion on the initial binarization image to obtain a binarization cell image of the cell image.

According to some embodiments of the present application, the region extraction module 401 is specifically configured to: obtaining a target area in the battery cell image according to the communication area; performing image enhancement processing on the target area to obtain the battery cell area; the image enhancement processing includes filtering each column of pixels located in the vertical direction of the incoming bit in the target area.

According to some embodiments of the application, the cell detection module 402 is specifically configured to:

and according to the gray values of the pixels in each column in the vertical direction of the charge level in the battery cell area, obtaining a charge level detection result of the battery cell.

Acquiring gray values of pixels in each column in the vertical direction of the feeding level in the cell region; according to the gray values of the pixels in each adjacent column, gray change data of the cell area are obtained; and according to the gray level change data, obtaining a charging level detection result of the battery cell.

According to some embodiments of the application, the cell detection module 402 is specifically configured to: determining the anode charge level and the cathode charge level of the battery cell according to the gray level difference of adjacent gray values in the gray level change data; and obtaining the overlapping distance between the anode feeding level and the cathode feeding level of the battery cell according to the anode feeding level and the cathode feeding level.

According to some embodiments of the application, the cell detection module 402 is specifically configured to: detecting the gray level change data by using a pre-trained preset model to obtain the overlapping distance between the anode charge level and the cathode charge level of the battery cell; the preset model is obtained by training gray level change data corresponding to each cell region sample, and each cell region sample comprises a cell region of a normal cell and a cell region of an abnormal cell.

According to some embodiments of the present application, as shown in fig. 11, an embodiment of the present application provides an electronic device 5, including: processor 501 and memory 502, the processor 501 and memory 502 being interconnected and in communication with each other by a communication bus 503 and/or other form of connection mechanism (not shown), the memory 502 storing a computer program executable by the processor 501, the processor 501 executing the computer program when the computing device is running to perform the method performed by the external machine in any alternative implementation, such as: extracting a cell region from a cell image obtained by radiographic imaging; and obtaining a charging level detection result of the battery cell according to the gray value distribution of the pixels in the battery cell region.

The present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs a method according to any of the preceding alternative implementations.

The storage medium may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable Programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.

The present application provides a computer program product which, when run on a computer, causes the computer to perform the method in any of the alternative implementations.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application, and are intended to be included within the scope of the appended claims and description. In particular, the technical features mentioned in the respective embodiments may be combined in any manner as long as there is no structural conflict. The present application is not limited to the specific embodiments disclosed herein, but encompasses all technical solutions falling within the scope of the claims.

Claims

1. A method for detecting a cell, the method comprising:

Extracting a cell region from a cell image obtained by radiographic imaging;

According to the gray value distribution of the pixels in the cell area, obtaining a charging level detection result of the cell;

and obtaining a charging level detection result of the battery cell according to the gray value distribution of the pixels in the battery cell region, wherein the charging level detection result comprises the following steps:

clustering adjacent pixels according to the gray value of each pixel in the cell area to obtain a plurality of subareas;

Detecting the average gray value of each subarea, and determining that the charge level detection result of the battery cell is the cathode-anode charge level overlap of the battery cell under the condition that the average gray value of one subarea is smaller than the average gray value of subareas at two sides of the subarea;

The cathode feeding level comprises a cathode feeding level and an anode feeding level, the cathode feeding level comprises a starting position of winding of a cathode pole piece of the battery cell, and the anode feeding level comprises a starting position of winding of an anode pole piece of the battery cell.

2. The method of claim 1, wherein extracting the cell region from the cell image obtained by radiography comprises:

according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain a binarized battery cell image of the battery cell image;

and obtaining a cell region in the cell image according to the communication region corresponding to the cell in the binarized cell image.

3. The method of claim 2, wherein performing binarization processing on the cell image according to the gray value of each pixel in the cell image to obtain a binarized cell image of the cell image comprises:

according to the gray value of each pixel in the battery cell image, binarizing the battery cell image to obtain an initial binarized image of the battery cell image;

and sequentially carrying out image corrosion and image expansion on the initial binarization image to obtain a binarization cell image of the cell image.

4. A method according to claim 2 or 3, wherein obtaining a cell region in the cell image from a connected region in the binarized cell image corresponding to the cell comprises:

Obtaining a target area in the battery cell image according to the communication area;

Performing image enhancement processing on the target area to obtain the battery cell area;

The image enhancement processing includes filtering each column of pixels located in the vertical direction of the incoming bit in the target area.

5. A method according to any one of claims 1-3, wherein obtaining the charge level detection result of the cell according to the gray value distribution of the pixels in the cell region comprises:

6. The method of claim 5, wherein obtaining the charge level detection result of the cell according to the gray values of the pixels in the columns in the vertical direction of the charge level in the cell region comprises:

comparing the gray value of each row of pixels with a preset gray value to obtain a charging level detection result of the battery cell;

The preset gray value is the minimum gray value detected from the cell area of the abnormal cell overlapped by the feeding level.

7. The method of claim 5, wherein obtaining the charge level detection result of the cell according to the gray values of the pixels in the columns in the vertical direction of the charge level in the cell region comprises:

acquiring gray values of pixels in each column in the vertical direction of the feeding level in the cell region;

According to the gray values of the pixels in each adjacent column, gray change data of the cell area are obtained;

and according to the gray level change data, obtaining a charging level detection result of the battery cell.

8. The method of claim 7, wherein obtaining the charge level detection result of the cell according to the gray level change data comprises:

determining the anode charge level and the cathode charge level of the battery cell according to the gray level difference of adjacent gray values in the gray level change data;

And obtaining the overlapping distance between the anode feeding level and the cathode feeding level of the battery cell according to the anode feeding level and the cathode feeding level.

9. The method of claim 8, wherein obtaining the charge level detection result of the cell according to the gray level change data comprises:

Detecting the gray level change data by using a pre-trained preset model to obtain the overlapping distance between the anode charge level and the cathode charge level of the battery cell;

The preset model is obtained by training gray level change data corresponding to each cell region sample, and each cell region sample comprises a cell region of a normal cell and a cell region of an abnormal cell.

10. A cell detection device for implementing the method of any one of claims 1 to 9, the device comprising:

the region extraction module is used for extracting a cell region from a cell image obtained through radiographic imaging;

and the battery cell detection module is used for obtaining the charge level detection result of the battery cell according to the gray value distribution of the pixels in the battery cell region.

11. An electronic device comprising a processor and a memory storing a computer program, characterized in that the processor implements the method of any one of claims 1 to 9 when executing the computer program.

12. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any one of claims 1 to 9.