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

Abstract

Embodiments of the present application disclose a kind of electric core detection method, device, electronic equipment and storage medium, the method comprises: obtaining multiple electric core projection images, the multiple electric core projection images correspond to multiple projection angles, and the electric core projection image includes the region of interest of electric core;According to the multiple electric core projection images and the projection angle corresponding to each electric core projection image, the region of interest is three-dimensionally reconstructed, and the three-dimensional image corresponding to the region of interest is obtained;According to the preset direction, the three-dimensional image is sliced, and the slice image corresponding to the preset direction is obtained;According to the slice image, the detection result of the electric core is determined. Implement the embodiment, the accuracy and efficiency of electric core detection can be improved.

Description

Technical Field

[0001] This application relates to the field of battery cell testing technology, and in particular to a battery cell testing method, apparatus, electronic device and storage medium. Background Technology

[0002] In the manufacturing of lithium-ion battery cells, defect detection after hot pressing is a crucial step in cell process quality control. Common detection methods involve photographing the cell without damaging it to detect defects. Conventional imaging methods use projection, but this is susceptible to interference from the tabs of stacked cells, leading to unclear images and inaccurate results. Furthermore, conventional industrial CT (Computed Tomography) systems typically require a 360-degree full scan of the cell, followed by 3D reconstruction. This method demands a large amount of data and is time-consuming, resulting in low efficiency in cell inspection. Summary of the Invention

[0003] This application discloses a battery cell testing method, apparatus, electronic device, and storage medium, which can improve the accuracy and efficiency of battery cell testing.

[0004] This application discloses a method for testing battery cells, the method comprising:

[0005] Multiple cell projection images are acquired, the multiple cell projection images correspond to multiple projection angles of the cell, and the cell projection images include the region of interest of the cell;

[0006] Based on the multiple cell projection images and the projection angles corresponding to each cell projection image, the region of interest of the cell is reconstructed in three dimensions to obtain a three-dimensional image corresponding to the region of interest of the cell.

[0007] The three-dimensional image is sliced ​​according to a preset direction to obtain a sliced ​​image corresponding to the preset direction;

[0008] The detection result of the battery cell is determined based on the sliced ​​image.

[0009] In one embodiment, the step of performing three-dimensional reconstruction of the region of interest (ROI) of the battery cell based on the plurality of battery cell projection images to obtain a three-dimensional image corresponding to the ROI of the battery cell includes:

[0010] The multiple battery cell projection images are filtered to obtain filtered images corresponding to the multiple battery cell projection images respectively;

[0011] Based on the filtered images corresponding to the multiple cell projection images, the region of interest of the cell is reconstructed in three dimensions to obtain a three-dimensional image corresponding to the region of interest of the cell.

[0012] In one embodiment, the battery cell is placed on a rotating platform, and an imaging device is arranged around the rotating platform. The imaging device is used to acquire projected images of the plurality of battery cells. The step of reconstructing the region of interest (ROI) of the battery cell in three dimensions based on the plurality of projected images and the projection angle corresponding to each projected image, to obtain a three-dimensional image corresponding to the ROI of the battery cell, includes:

[0013] Obtain the preset position information corresponding to the imaging device, and the relative position information between the imaging device and the rotating platform;

[0014] Based on the multiple cell projection images, the projection angles corresponding to each cell projection image, the preset position information, and the relative position information, the region of interest of the cell is reconstructed in three dimensions to obtain a three-dimensional image corresponding to the region of interest of the cell.

[0015] In one embodiment, the step of performing three-dimensional reconstruction of the region of interest (ROI) of the battery cell based on the plurality of battery cell projection images, the projection angle corresponding to each of the battery cell projection images, the preset position information, and the relative position information to obtain a three-dimensional image corresponding to the ROI of the battery cell includes:

[0016] Extract image features from the projection images of each of the battery cells;

[0017] Based on the image features and projection angles corresponding to the projected images of each battery cell, the preset position information, and the relative position information, the region of interest of the battery cell is reconstructed in three dimensions to obtain a three-dimensional image corresponding to the region of interest of the battery cell.

[0018] In one embodiment, the rotating platform drives the battery cell to rotate; before performing three-dimensional reconstruction of the region of interest of the battery cell based on the plurality of battery cell projection images, the projection angle corresponding to each battery cell projection image, the preset position information, and the relative position information to obtain a three-dimensional image corresponding to the region of interest of the battery cell, the method further includes:

[0019] Obtain the target rotation angle corresponding to each of the battery cell projection images, wherein the target rotation angle is the angle of rotation of the rotating platform when the imaging device acquires the battery cell projection image; wherein the target rotation angle is within a preset rotation range;

[0020] The projection angle corresponding to each of the battery cell projection images is determined based on the target rotation angle corresponding to each of the battery cell projection images.

[0021] In one embodiment, the step of performing three-dimensional reconstruction of the region of interest (ROI) of the battery cell based on the plurality of battery cell projection images, the projection angle corresponding to each of the battery cell projection images, the preset position information, and the relative position information to obtain a three-dimensional image corresponding to the ROI of the battery cell includes:

[0022] Based on the projection angle corresponding to each of the battery cell projection images, the target position information of the region of interest of each battery cell in the three-dimensional space is determined.

[0023] Based on the multiple cell projection images and the target position information corresponding to each cell projection image, the region of interest of the cell is determined to be a portion of the three-dimensional pixels in the three-dimensional space.

[0024] The tilt angle of the battery cell is determined based on the target cell projection image and the target rotation angle corresponding to the target cell projection image; wherein, the tilt angle is the angle at which the battery cell is tilted relative to the vertical direction, and the target cell projection image is any cell projection image whose corresponding target rotation angle is not a preset angle;

[0025] Based on the partial 3D pixels, the tilt angle of the battery cell, the preset position information, and the relative position information, a local 3D reconstruction of the region of interest of the battery cell is performed to obtain a 3D image corresponding to the region of interest of the battery cell.

[0026] In one embodiment, determining the tilt angle of the battery cell based on the target cell projection image and the target rotation angle corresponding to the target cell projection image includes:

[0027] Identify the projection area corresponding to the battery cell in the target battery cell projection image, and determine the projection tilt angle of the battery cell based on the projection area. The projection tilt angle of the battery cell is the angle formed by the projection of the tilt angle of the battery cell onto the target battery cell projection image.

[0028] The tilt angle of the battery cell is determined based on the projection tilt angle and the target rotation angle corresponding to the projected image of the target battery cell.

[0029] In one embodiment, determining the detection result of the battery cell based on the sliced ​​image includes:

[0030] The sliced ​​image is input into a trained artificial intelligence model, which identifies the electrode region of the sliced ​​image to obtain the positive electrode region and the negative electrode region of the battery cell in the sliced ​​image. The artificial intelligence model is trained based on a set of sample images, which includes multiple sample images divided into positive electrode regions and negative electrode regions.

[0031] The electrode alignment of the battery cell is determined based on the positive electrode region and the negative electrode region of the battery cell.

[0032] The test result of the battery cell is determined based on the electrode alignment.

[0033] In one embodiment, the preset direction includes a first preset direction and a second preset direction, the first preset direction corresponding to the length direction of the battery cell, and the second preset direction corresponding to the width direction of the battery cell; slicing the three-dimensional image according to the preset direction to obtain a sliced ​​image corresponding to the preset direction includes:

[0034] The three-dimensional image is sliced ​​according to the first preset direction to obtain a first sliced ​​image corresponding to the first preset direction;

[0035] The three-dimensional image is sliced ​​according to the second preset direction to obtain a second sliced ​​image corresponding to the second preset direction;

[0036] Determining the electrode alignment of the battery cell based on the positive electrode region and the negative electrode region of the battery cell includes:

[0037] Based on the positive electrode region and the negative electrode region of the battery cell in the first slice image, the first electrode alignment degree of the battery cell is determined, and the first electrode alignment degree includes the portion of the negative electrode that extends beyond the positive electrode in the length direction.

[0038] Based on the positive electrode region and the negative electrode region of the battery cell in the second slice image, the second electrode alignment of the battery cell is determined. The second electrode alignment includes the portion of the negative electrode that extends beyond the positive electrode in the width direction.

[0039] This application discloses a battery cell testing device, the device comprising:

[0040] An image acquisition module is used to acquire multiple cell projection images, the multiple cell projection images corresponding to multiple projection angles of the cell, and the cell projection images including the region of interest of the cell;

[0041] The image reconstruction module is used to perform three-dimensional reconstruction of the region of interest of the battery cell based on the plurality of battery cell projection images and the projection angle corresponding to each battery cell projection image, so as to obtain a three-dimensional image corresponding to the region of interest of the battery cell.

[0042] An image slicing module is used to slice the three-dimensional image according to a preset direction to obtain a sliced ​​image corresponding to the preset direction.

[0043] An image detection module is used to determine the detection result of the battery cell based on the sliced ​​image.

[0044] This application discloses an electronic device, including:

[0045] Memory containing executable program code;

[0046] A processor coupled to the memory;

[0047] The processor calls the executable program code stored in the memory to execute the method described in any of the above embodiments.

[0048] This application discloses a computer-readable storage medium storing a computer program, wherein when executed by a processor, the computer program causes the processor to perform the methods described in any of the above embodiments.

[0049] The battery cell detection method, apparatus, electronic device, and storage medium disclosed in this application can acquire multiple battery cell projection images. These multiple battery cell projection images correspond to multiple acquisition angles of the battery cell, and each battery cell projection image includes a region of interest (ROI) of the battery cell. Based on the multiple battery cell projection images, the electronic device can perform three-dimensional reconstruction of the battery cell projection region to obtain a three-dimensional image corresponding to the ROI of the battery cell. It can also slice the three-dimensional image according to a preset direction to obtain sliced ​​images corresponding to the preset direction. Based on the sliced ​​images, the detection result of the battery cell is determined. After using multiple battery cell projection images to perform three-dimensional reconstruction of the ROI of the battery cell, the obtained three-dimensional image has more accurate and comprehensive battery cell information compared to the two-dimensional image obtained by projection. Obtaining sliced ​​images according to the preset direction can also make the sliced ​​images more accurate than the two-dimensional image obtained by projection, thereby improving the accuracy of battery cell detection. It is not necessary to reconstruct the entire battery cell, but only the ROI of the battery cell is reconstructed, which also reduces the time required for three-dimensional reconstruction and improves the efficiency of battery cell detection. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1-A This is a schematic diagram of the electrode sheet of a battery cell disclosed in an embodiment of this application;

[0052] Figure 1-B This is a schematic diagram illustrating an application scenario of a battery cell testing method disclosed in an embodiment of this application;

[0053] Figure 2 This is a schematic flowchart of a battery cell testing method disclosed in an embodiment of this application;

[0054] Figure 3 This is a schematic diagram illustrating an application scenario for detecting the electrode alignment of a battery cell, as disclosed in an embodiment of this application.

[0055] Figure 4 This is a schematic flowchart of another cell testing method disclosed in an embodiment of this application;

[0056] Figure 5 This is a schematic diagram of the tilt angle of a battery cell disclosed in an embodiment of this application;

[0057] Figure 6-A This is a schematic diagram of a first slice image disclosed in an embodiment of this application;

[0058] Figure 6-B This is a schematic diagram of a second slice image disclosed in an embodiment of this application;

[0059] Figure 7 This is a modular schematic diagram of a battery cell testing device disclosed in an embodiment of this application;

[0060] Figure 8 This is a structural block diagram of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0061] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0062] It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0063] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another.

[0064] In related technologies, the detection of electrode alignment in a battery cell typically involves selecting a suitable projection angle and projecting the corner region of the cell to obtain a projected image corresponding to that corner region. Electronic equipment can then determine the distance from the corner of the negative electrode to the corner of the positive electrode within this projected image. This distance is considered a characterization of the electrode alignment. However, electrode alignment can also refer to the portion of the negative electrode that extends beyond the positive electrode in both length and width directions. Figure 1-A As shown, Figure 1-A This is a schematic diagram of the electrode sheet of a battery cell disclosed in an embodiment of this application. The negative electrode sheet 101 and the positive electrode sheet 102 are superimposed. The distance from the corner point of the negative electrode sheet to the corner point of the positive electrode sheet is d. The portion of the width of the negative electrode sheet that exceeds the width of the positive electrode sheet is x. The portion of the length of the negative electrode sheet that exceeds the length of the positive electrode sheet is y. According to the Pythagorean theorem, the square of the distance from the corner point of the negative electrode sheet to the corner point of the positive electrode sheet is equal to the square of the portion of the length of the negative electrode sheet that exceeds the length of the positive electrode sheet plus the square of the portion of the width of the negative electrode sheet that exceeds the width of the positive electrode sheet, that is, x² + y² = d².

[0065] However, if the length of the negative electrode exceeds the length of the positive electrode and the width of the negative electrode exceeds the width of the positive electrode simultaneously, the distance between the corners of the negative electrode and the positive electrode can remain unchanged. If the length of the negative electrode exceeds the length of the positive electrode by increasing and the width of the negative electrode exceeds the width of the positive electrode by decreasing, the distance between the corners of the negative electrode and the positive electrode can remain unchanged. Therefore, it is not accurate to use the distance between the corners of the negative electrode and the positive electrode to detect the electrode alignment of the battery cell.

[0066] This application discloses a battery cell testing method, apparatus, electronic device, and storage medium, which can improve the accuracy and efficiency of battery cell testing.

[0067] The following will be described in detail with reference to the accompanying drawings.

[0068] like Figure 1-B As shown, Figure 1-B This is a schematic diagram of an application scenario for a battery cell testing method disclosed in an embodiment of this application. The application scenario may include an electronic device 110, which may include, but is not limited to, mobile phones, tablets, wearable devices, laptops, PCs (Personal Computers), etc.

[0069] The electronic device 110 can acquire multiple battery cell projection images, which correspond to multiple projection angles of the battery cell. The battery cell projection images include the region of interest of the battery cell. Based on the multiple battery cell projection images, the electronic device 110 can also perform three-dimensional reconstruction of the region of interest of the battery cell to obtain a three-dimensional image corresponding to the region of interest of the battery cell. The three-dimensional image is then sliced ​​according to a preset direction to obtain a sliced ​​image corresponding to the preset direction. Based on the sliced ​​image, the detection result of the battery cell is determined.

[0070] like Figure 2 As shown, Figure 2 This is a schematic flowchart of a battery cell testing method disclosed in an embodiment of this application. This battery cell testing method can be applied to the electronic devices described in the above embodiments, and the method may include the following steps:

[0071] Step 210: Obtain multiple cell projection images.

[0072] The electronic device can acquire multiple battery cell projection images. Optionally, the electronic device can be an imaging device that can directly capture multiple battery cell projection images. The electronic device can also communicate with the imaging device to receive multiple battery cell projection images sent by the imaging device. The imaging device may include a beam output device and a beam detection device. The battery cell projection image can be the image formed by the beam passing through the battery cell, detected by the beam detection device when the beam output device outputs the beam at a projection angle. Optionally, the imaging device can be a CT scanner, which can perform X-ray scanning on the battery cell at different projection angles to obtain multiple battery cell projection images. The beam output device can be an X-ray tube, and the beam detection device can be an X-ray detector.

[0073] The multiple battery cell projection images can correspond to multiple projection angles. This application does not limit the projection angle; multiple battery cell projection images refer to images obtained by capturing the battery cell from different projection angles. Optionally, the multiple battery cell projection images can be obtained by different imaging devices, or they can be images obtained by the same imaging device at different shooting angles. For example, one battery cell projection image can be obtained by projecting the front of the battery cell, i.e., the beam output device outputs a beam towards the front of the battery cell; another image can be obtained by projecting the side of the battery cell, i.e., the beam output device outputs a beam towards the side of the battery cell. By acquiring multiple battery cell projection images, electronic devices can obtain more comprehensive and accurate battery cell information, avoiding the information loss and errors caused by a single projection image.

[0074] The cell projection image includes a region of interest (ROI) for the cell. This ROI can be used to acquire data required for cell detection. Optionally, the electronic device can determine the location of the ROI based on the type of cell detection. For example, if the detection type is electrode alignment detection, where electrode alignment refers to the portion of the negative electrode extending beyond the positive electrode in both length and width, the ROI can be determined to be the corner region of the cell. Similarly, if the detection type is electrode tab detection, the ROI can be determined to be the electrode tab region. Optionally, the ROI may also include, but is not limited to, the electrode region or the entire region of the cell; this embodiment does not impose such limitations.

[0075] like Figure 3 As shown, Figure 3 This is a schematic diagram of an application scenario for detecting the electrode alignment of a battery cell, as disclosed in an embodiment of this application. The application scenario may include an imaging device 310, a battery cell 320, and a rotating platform 330. The imaging device 310 may include a beam output device 311 and a beam detection device 312. The battery cell 320 is placed on the rotating platform 330, and may be placed at the center of the rotating platform 330, so that the rotating platform 330 drives the battery cell 320 to rotate. The imaging device 310 may remain stationary. The rotation angle of the rotating platform 330 may correspond to the projection angle of the battery cell projection image acquired by the imaging device 310. The shape of the battery cell 320 may be a cuboid. The beam output device 311 outputs a beam that may pass through the corner area of ​​the battery cell 320. The beam detection device 312 detects the beam after passing through the corner area of ​​the battery cell 320, thereby generating a battery cell projection image.

[0076] It should be noted that, since the electrode alignment of cell 320 includes the portion of the negative electrode extending beyond the positive electrode in both length and width directions, compared to other areas of cell 320, the electronic device can determine not only the portion of the negative electrode extending beyond the positive electrode in both length and width directions based on the corner area of ​​cell 320. In contrast, the electronic device can only determine one of these dimensions based on other areas. Furthermore, compared to other areas of cell 320, the corner area has a more defined geometry and allows for the acquisition of projected images from various angles. Therefore, the electronic device performs 3D reconstruction on the corner area of ​​cell 320, resulting in a more accurate and efficient 3D image.

[0077] Step 220: Based on multiple cell projection images and the projection angles corresponding to each cell projection image, perform three-dimensional reconstruction of the region of interest of the cell to obtain a three-dimensional image corresponding to the region of interest of the cell.

[0078] Electronic devices can reconstruct the region of interest of a battery cell in three dimensions based on multiple projected images of the battery cells and the projection angles corresponding to each projected image, thereby obtaining a three-dimensional image of the region of interest of the battery cell.

[0079] Optionally, the electronic device can perform 3D reconstruction of the region of interest (ROI) of the battery cell using a 3D reconstruction algorithm, thereby improving the efficiency of the 3D reconstruction. Optionally, the 3D reconstruction algorithm may include a back-projection reconstruction algorithm. The electronic device can back-project each battery cell projection image back into 3D space based on multiple battery cell projection images and their corresponding projection angles, generating back-projection data corresponding to each battery cell projection image. Then, the back-projection data corresponding to each battery cell projection image are superimposed to generate a voxel dataset corresponding to the ROI of the battery cell. The voxel dataset includes multiple voxels, each representing a small cube in 3D space. Finally, the electronic device can obtain a 3D image corresponding to the ROI of the battery cell by performing volume rendering or cross-sectional rendering operations on the voxel dataset. Optionally, the electronic device can also perform 3D reconstruction of the ROI of the battery cell using other 3D reconstruction algorithms, such as filtered reconstruction algorithms. This application embodiment does not limit the 3D reconstruction algorithm; any type of 3D reconstruction algorithm can be selected to perform 3D reconstruction of the ROI of the battery cell.

[0080] Taking the back projection of the first battery cell projection image as an example, the first battery cell projection image is any one of multiple battery cell projection images. The electronic device can interpolate and weight each projected pixel in the first battery cell projection image to obtain the three-dimensional coordinates corresponding to each projected pixel. That is, the electronic device can obtain the back projection data corresponding to each battery cell projection image. The projected pixel refers to the pixel corresponding to the battery cell in the battery cell projection image. In other words, the electronic device can extend each projected pixel back into three-dimensional space along the corresponding projection angle, and then calculate the three-dimensional coordinates corresponding to each pixel.

[0081] In one embodiment, before reconstructing the 3D image corresponding to the region of interest (ROI) of the battery cell, the electronic device can also acquire preset position information corresponding to the imaging device and the relative position information between the imaging device and the rotating platform. Then, based on multiple battery cell projection images, the projection angles corresponding to each battery cell projection image, the preset position information, and the relative position information, the ROI of the battery cell is reconstructed in 3D to obtain the 3D image corresponding to the ROI of the battery cell. Optionally, the electronic device can determine the position information of the 3D image in 3D space based on the projection angles corresponding to each battery cell projection image, the preset position information corresponding to the imaging device, and the relative position information between the imaging device and the rotating platform. Then, based on the multiple battery cell projection images and the position information of the 3D image in 3D space, the 3D image corresponding to the ROI of the battery cell is generated.

[0082] The imaging device and the rotating platform can be pre-set. The preset position information corresponding to the imaging device can include the position information of the beam output device and the beam detection device. Optionally, the preset position information of the imaging device can also include the position information of the beam output device or the position information of the beam detection device, as well as the relative position information between the beam output device and the beam detection device. The relative position information between the imaging device and the rotating platform can include the relative position information between the beam output device and the rotating platform and / or the relative position information between the beam detection device and the rotating platform. Optionally, the battery cell can be placed at the center of the rotating platform, then the relative position information between the imaging device and the rotating platform can be the relative position information between the center of the imaging device and the rotating platform.

[0083] When the preset position information includes the position information of the beam output device, the relative position information between the imaging device and the rotating platform can be the relative position information between the beam output device and the rotating platform. The electronic equipment can determine the position information of the beam detection device based on the relative position information between the beam output device and the beam detection device, and the position information of the beam output device, and also determine the position information of the rotating platform based on the relative position information between the beam output device and the rotating platform, and the position information of the beam output device.

[0084] Step 230: Slice the three-dimensional image according to a preset direction to obtain a sliced ​​image corresponding to the preset direction.

[0085] While 3D images can display the shape of an object in three spatial directions, applications such as battery cell inspection require observing the internal structure of the cell from different directions. Therefore, it is necessary to slice the 3D image to obtain sliced ​​images along different directions.

[0086] The electronic device can slice a three-dimensional image according to a preset direction to obtain a sliced ​​image corresponding to the preset direction. This sliced ​​image can refer to a two-dimensional image obtained by selecting a plane in three-dimensional space and projecting the three-dimensional image onto that plane. The preset direction can include multiple directions, and the electronic device can slice the three-dimensional image according to each preset direction to obtain a sliced ​​image corresponding to each preset direction, thus obtaining multiple sliced ​​images corresponding to different preset directions. Optionally, the electronic device can slice the three-dimensional image at a target location within the region of interest of the battery cell according to a preset direction. This target location can be preset or determined based on the type of detection performed on the battery cell. For example, if the detection type is electrode alignment detection, the target location can be the position where the positive and negative electrodes in the battery cell overlap.

[0087] In one embodiment, the electronic device can further filter multiple cell projection images to obtain filtered images corresponding to each cell projection image. Then, based on the filtered images corresponding to the multiple cell projection images, a 3D reconstruction of the region of interest (ROI) of the cell is performed to obtain a 3D image corresponding to the ROI of the cell. Implementing this embodiment can remove noise from the cell projection images, thereby improving the accuracy of the 3D reconstruction.

[0088] Step 240: Determine the detection results of the battery cell based on the sliced ​​image.

[0089] Electronic devices can perform image processing on sliced ​​images to obtain cell detection results. Optionally, the electronic device can use image processing algorithms to extract features from the sliced ​​images, obtain feature data of the sliced ​​images, and then determine whether the cell meets preset detection conditions based on the feature data of the sliced ​​images to determine the cell detection result. Optionally, the detection type of cell detection can be electrode alignment detection. Based on the feature data of the sliced ​​images, the electronic device can obtain the length and width of the negative electrode and the length and width of the positive electrode of the cell. The electronic device can determine the first electrode alignment of the cell based on the length of the negative electrode and the length of the positive electrode, and can also determine the second electrode alignment of the cell based on the width of the negative electrode and the width of the positive electrode, thereby determining whether the first electrode alignment and the second electrode alignment meet the corresponding preset detection conditions to determine the cell detection result. The detection types of cell detection may also include, but are not limited to, battery electrode defect detection, battery structure damage detection, battery electrode impurity detection, etc. This application does not limit this, and the electronic device can obtain corresponding detection results according to the detection type.

[0090] Optionally, before performing image processing on the sliced ​​image, the electronic device may also preprocess the sliced ​​image. Preprocessing may include, but is not limited to, filtering, enhancement, and binarization. Filtering can remove noise from the sliced ​​image to smooth it, enhancement can improve the contrast and clarity of the sliced ​​image, and binarization can convert the sliced ​​image into a black and white binary image for image processing.

[0091] Optionally, the electronic device can use image processing algorithms to extract features from the sliced ​​image to obtain feature data of the sliced ​​image. This feature data may include, but is not limited to, the shape, size, and density of the battery cell. For example, the electronic device can use morphological algorithms to extract the outline of the battery cell in the sliced ​​image and calculate the shape features of the battery cell, such as area, perimeter, and aspect ratio. The electronic device can also use edge detection algorithms to extract the edge features of the battery cell in the sliced ​​image, thereby calculating the length and curvature of the battery cell. The electronic device can also use grayscale change analysis algorithms to calculate density features such as density changes inside the battery cell. The embodiments of this application do not limit the image processing algorithms for the sliced ​​image.

[0092] In this embodiment, the electronic device can acquire multiple battery cell projection images, which correspond to multiple acquisition angles of the battery cell. Each projection image includes a region of interest (ROI) of the battery cell. Based on these multiple projection images, the electronic device can perform three-dimensional reconstruction of the projection area to obtain a three-dimensional image corresponding to the ROI. Furthermore, it can slice the three-dimensional image according to a preset direction to obtain sliced ​​images corresponding to the preset direction. Based on these sliced ​​images, the detection result of the battery cell is determined. The three-dimensional image obtained after three-dimensional reconstruction of the ROI using multiple projection images has more accurate and comprehensive battery cell information compared to the projected two-dimensional image. Obtaining sliced ​​images according to the preset direction also makes the sliced ​​images more accurate than the projected two-dimensional image, thereby improving the accuracy of battery cell detection. Since it is not necessary to reconstruct the entire battery cell, only the ROI is reconstructed, which also reduces the time required for three-dimensional reconstruction and improves the efficiency of battery cell detection.

[0093] like Figure 4 As shown, Figure 4 This is a schematic flowchart of another battery cell testing method disclosed in an embodiment of this application. This battery cell testing method can be applied to the electronic devices in the above embodiments, and the battery cell testing method may include the following steps:

[0094] Step 402: Obtain multiple battery cell projection images.

[0095] Step 404: Obtain the preset position information corresponding to the imaging device, as well as the relative position information between the imaging device and the rotating platform.

[0096] The methods for steps 402 to 404 can refer to the methods in the above embodiments, and will not be repeated here.

[0097] Step 406: Obtain the target rotation angle corresponding to the projected image of each battery cell.

[0098] While the rotating platform drives the battery cell to rotate, the position of the imaging device can remain unchanged. Because the rotation of the platform causes the battery cell to rotate, the projection angle of the imaging device relative to the battery cell changes. Therefore, the electronic device can acquire the target rotation angle corresponding to each battery cell's projected image. The target rotation angle is the angle at which the rotating platform rotates when the imaging device acquires the battery cell's projected image, and this target rotation angle is within a preset rotation range. In one example, the preset rotation range is [-θ, θ]. The rotating platform can rotate from an angle of -θ to an angle of θ, where θ can be less than 180 degrees, meaning the battery cell does not need to rotate one full revolution. The rotation speed of the rotating platform is fixed, and the imaging device can acquire battery cell projected images at a fixed frequency. That is, the imaging device can acquire a battery cell projected image once every fixed angle the rotating platform rotates, and acquire multiple battery cell projected images during the rotation of the platform. Optionally, the electronic device can determine the target rotation angle corresponding to each battery cell's projected image based on the rotation speed of the rotating platform and the fixed frequency at which the imaging device acquires the battery cell's projected images.

[0099] Step 408: Determine the projection angle corresponding to each cell projection image based on the target rotation angle corresponding to each cell projection image.

[0100] The electronic device can determine the projection angle corresponding to each battery cell's projected image based on the target rotation angle corresponding to each projected image. Optionally, the electronic device can determine a reference rotation angle among multiple target rotation angles, and determine the projection angle corresponding to the battery cell's projected image at the reference rotation angle as the reference projection angle. Then, based on the angle difference between the target rotation angle corresponding to each battery cell's projected image and the reference rotation angle, the angle difference between the projection angle corresponding to each battery cell's projected image and the reference projection angle is determined, thereby obtaining the projection angle corresponding to each battery cell's projected image. In one example, the reference projection angle can be that the front of the battery cell is parallel to the light emitted by the light output device, such as... Figure 3 As shown, the reference rotation angle corresponding to the reference projection angle can be 0 degrees.

[0101] After step 408, the electronic device can execute step 410 or step 414, which correspond to different three-dimensional reconstruction methods.

[0102] Step 410: Extract the image features of each cell projection image.

[0103] Electronic devices can extract image features from the projected images of each battery cell. These image features may include, but are not limited to, edge features, corner features, texture features, and feature points. This application embodiment does not impose any limitations on these features. These image features are used to reconstruct a 3D image. Generally speaking, the more image features extracted, the more accurate the reconstructed 3D image, but the more time the electronic device needs to perform 3D reconstruction.

[0104] Step 412: Based on the image features, projection angle, preset position information, and relative position information corresponding to the projected images of each battery cell, perform three-dimensional reconstruction of the region of interest of the battery cell to obtain the three-dimensional image corresponding to the region of interest of the battery cell.

[0105] Optionally, the electronic device can reconstruct the shape, size, and other information of the three-dimensional image based on the image features and projection angle corresponding to the projected images of each battery cell, and then determine the position information of the three-dimensional image in three-dimensional space based on preset position information and relative position information, thereby determining the three-dimensional image corresponding to the region of interest of the battery cell.

[0106] In this embodiment, the electronic device can also acquire the target rotation angle corresponding to each cell projection image. The target rotation angle is within a preset rotation range. Based on the target rotation angle corresponding to each cell projection image, the projection angle corresponding to each cell projection image is determined. That is, the projection angle can also be within a certain range. The electronic device then extracts the image features of each cell projection image. Based on the image features, projection angle, preset position information, and relative position information corresponding to each cell projection image, the device performs three-dimensional reconstruction of the region of interest of the cell to obtain a three-dimensional image corresponding to the region of interest of the cell. The electronic device does not need to scan the cell projection image around the cell, which reduces the scanning time of the imaging device on the cell, speeds up the construction process of the three-dimensional image, and improves the efficiency of cell detection.

[0107] Step 414: Based on the projection angle corresponding to each cell projection image, determine the target position information of the region of interest of each cell in the three-dimensional space in each cell projection image.

[0108] The electronic device can determine the target position information of the region of interest of the battery cell in three-dimensional space in each battery cell projection image based on the projection angle corresponding to each battery cell projection image. Optionally, the first battery cell projection image can be any one of multiple battery cell projection images. The electronic device can determine the image position information of the region of interest of the battery cell in the first battery cell projection image, and then determine the target position information of the region of interest of the battery cell in three-dimensional space in the first battery cell projection image based on the projection angle and image position information corresponding to the first battery cell projection image.

[0109] Step 416: Based on multiple cell projection images and the target position information corresponding to each cell projection image, determine the partial three-dimensional pixels corresponding to the region of interest of the cell in three-dimensional space.

[0110] Electronic devices can determine the corresponding 3D pixels of the region of interest (ROI) of a battery cell in 3D space based on multiple battery cell projection images and the target position information corresponding to each projection image. Optionally, the electronic device can use matching and registration algorithms to match the overlapping positions in the ROI of the battery cell under different projection angles, and fuse the image information of the overlapping positions in multiple battery cell projection images to determine the corresponding 3D pixels of the ROI in 3D space.

[0111] Step 418: Determine the tilt angle of the battery cell based on the projected image of the target battery cell and the target rotation angle corresponding to the projected image of the target battery cell.

[0112] The target cell projection image is any cell projection image whose corresponding rotation angle is not a preset angle. When the rotating platform rotates to the preset angle, the front of the cell is parallel to the light output from the light output device, allowing the light to pass through the cell parallel to the target angle. The cell's tilt angle cannot be projected into the cell projection image, and the electronic device cannot determine the cell's tilt angle based on the cell projection image corresponding to the preset angle. The tilt angle is the angle at which the cell is tilted relative to the vertical direction. Figure 5 As shown, Figure 5 This is a schematic diagram of the tilt angle of a battery cell disclosed in an embodiment of this application. The battery cell 510 is a vertically placed battery cell, and the tilt angle of the battery cell 510 relative to the vertical direction is 0 degrees. The battery cell 520 is not a vertically placed battery cell, and the tilt angle of the battery cell 520 relative to the vertical direction is φ.

[0113] In one embodiment, the electronic device can identify the projection area corresponding to the battery cell in the target battery cell projection image, determine the projection tilt angle of the battery cell based on the projection area, and then determine the tilt angle of the battery cell based on the projection tilt angle and the target rotation angle corresponding to the target battery cell projection image.

[0114] In this context, the projection area corresponding to the battery cell in the target battery cell projection image can refer to the projection image corresponding to the region of interest of the battery cell. The projection tilt angle of the battery cell is the angle formed by the projection of the battery cell's tilt angle onto the target battery cell projection image. The target rotation angle can be used to characterize the angle formed by the projection of the battery cell's tilt angle onto a plane perpendicular to the plane to which the target battery cell projection image belongs. Specifically, if the preset angle is 0 degrees, that is, when the rotating platform rotates to 0 degrees, the front of the battery cell is parallel to the light output by the light output device, and the preset rotation range of the rotating platform is [-θ, θ], then the electronic device can calculate the absolute value of the target rotation angle, or calculate the difference between the target rotation angle and the preset angle, as another projection tilt angle corresponding to the battery cell's tilt angle. The electronic device can determine the battery cell's tilt angle based on the projection tilt angle and the other projection tilt angle. Mathematically, the tilt angle of the battery cell can be calculated based on the angle formed by the projection of the battery cell's tilt angle onto two mutually perpendicular planes.

[0115] Step 420: Based on some three-dimensional pixels, the tilt angle of the battery cell, preset position information, and relative position information, perform local three-dimensional reconstruction of the region of interest of the battery cell to obtain a three-dimensional image corresponding to the region of interest of the battery cell.

[0116] Local 3D reconstruction refers to the process of reconstructing and filling the unknown parts surrounding known 3D pixels or regions in 3D space through calculation and inference to obtain a complete 3D image. Optionally, these known 3D pixels can be used as the known 3D pixels. Based on the tilt angle of the battery cell, preset position information, and relative position information, the electronic device can reconstruct and fill the parts of the region of interest of the battery cell excluding these known 3D pixels to obtain a 3D image corresponding to the region of interest of the battery cell.

[0117] In one embodiment, the electronic device can perform local 3D reconstruction of the region of interest (ROI) of each battery cell based on the cell's tilt angle, preset position information, and relative position information, using an image processor to obtain a 3D image of the ROI corresponding to the battery cell. Implementing this embodiment, compared to a central processing unit (CPU), the general computing capabilities of an image processor are more suitable for local 3D reconstruction, which can improve the speed of 3D reconstruction and thus increase the efficiency of battery cell detection.

[0118] In this embodiment of the application, compared with the three-dimensional reconstruction method in steps 410-412, the local three-dimensional reconstruction method in steps 414-420 can further accelerate the speed at which the electronic device calculates the three-dimensional image corresponding to the region of interest of the battery cell, thereby enabling the battery cell detection speed to meet the detection speed requirements of the industrial production line, and thus ensuring the safety of each battery cell produced in the industrial sector.

[0119] Step 422: Slice the 3D image according to a preset direction to obtain a sliced ​​image corresponding to the preset direction.

[0120] In one embodiment, the preset direction includes a first preset direction and a second preset direction. The first preset direction corresponds to the length direction of the battery cell, and the second preset direction corresponds to the width direction of the battery cell. The electronic device can slice the three-dimensional image according to the first preset direction to obtain a first slice image corresponding to the first preset direction, and slice the three-dimensional image according to the second preset direction to obtain a second slice image corresponding to the second preset direction. Figure 6-A As shown, Figure 6-A This is a schematic diagram of a first slice image disclosed in an embodiment of this application. The white area can be the electrode of the battery cell, such as... Figure 6-B As shown, Figure 6-B This is a schematic diagram of a second slice image disclosed in an embodiment of this application.

[0121] Step 424: Input the sliced ​​image into the trained artificial intelligence model, and use the artificial intelligence model to identify the electrode region of the sliced ​​image to obtain the positive electrode region and the negative electrode region of the cell in the sliced ​​image.

[0122] The artificial intelligence model is trained based on a set of sample images, which includes multiple images divided into positive and negative electrode regions. When there are multiple slice images, the electronic device can input each slice image into the trained artificial intelligence model. The model then identifies the electrode regions in each slice image to determine the positive and negative electrode regions of the battery cell within each slice.

[0123] Optionally, the sliced ​​image may include a first sliced ​​image and a second sliced ​​image. The electronic device can input the first sliced ​​image into a trained artificial intelligence model, and the artificial intelligence model can identify the electrode regions in the first sliced ​​image to obtain the positive electrode region and the negative electrode region of the battery cell in the first sliced ​​image, such as... Figure 6-A As shown, the longer white stripe area in the white region can be the negative electrode area 610, and the shorter white stripe area in the white region can be the positive electrode area 620. The electronic device can also input the second slice image into a trained artificial intelligence model, and use the artificial intelligence model to identify the electrode area in the second slice image to obtain the positive electrode area and the negative electrode area of ​​the cell in the second slice image.

[0124] Step 426: Determine the electrode alignment of the battery cell based on the positive electrode area and the negative electrode area of ​​the battery cell.

[0125] Optionally, the electronic device can determine the lengths of the positive and negative electrode regions of the battery cell. Subtracting the length of the positive electrode region from the length of the negative electrode region yields the electrode alignment of the battery cell. For example... Figure 6-A As shown, the first slice image includes multiple positive electrode regions and multiple negative electrode regions. Taking one negative electrode region 610 and one positive electrode region 620 as an example, the electronic device can determine the length of the negative electrode region 610 and the length of the positive electrode region 620. Subtracting the length of the positive electrode region 620 from the length of the negative electrode region 610 yields the first electrode alignment of the battery cell. Optionally, the electronic device can also calculate a first average length of the multiple negative electrode regions and a second average length of the multiple positive electrode regions in the first slice image, and subtract the second average from the first average to obtain the first electrode alignment of the battery cell. Figure 6-B The calculation method for the alignment of the second electrode shown is the same as that for the alignment of the first electrode, and will not be repeated here.

[0126] In one embodiment, the sliced ​​image may include a first sliced ​​image and a second sliced ​​image. Based on the positive electrode region and the negative electrode region of the battery cell in the first sliced ​​image, a first electrode alignment of the battery cell is determined. The first electrode alignment includes the portion of the negative electrode that extends beyond the positive electrode in the length direction. The electronic device further determines a second electrode alignment of the battery cell based on the positive electrode region and the negative electrode region of the battery cell in the second sliced ​​image. The second electrode alignment includes the portion of the negative electrode that extends beyond the positive electrode in the width direction. The first electrode alignment and the second electrode alignment can constitute the electrode alignment of the battery cell.

[0127] Step 428: Determine the cell test results based on the electrode alignment.

[0128] Optionally, the electronic device can determine whether the electrode alignment is within a preset alignment range. If the electrode alignment is within the preset alignment range, the test result of the cell is determined to be qualified. If the electrode alignment is not within the preset alignment range, the test result of the cell is determined to be unqualified.

[0129] When the electrode alignment includes a first electrode alignment and a second alignment, the electronic device can determine whether the first electrode alignment is within a preset first alignment range and whether the electrode alignment is within a preset second alignment range. If the first electrode alignment is within the preset first alignment range and the second electrode alignment is within the preset second alignment range, the test result of the battery cell is determined to be that the battery cell is qualified. If the first electrode alignment is not within the preset first alignment range or the second electrode alignment is not within the preset second alignment range, the test result of the battery cell is determined to be that the battery cell is unqualified.

[0130] In this embodiment of the application, by determining a first slice image in the length direction of the battery cell and determining the first electrode alignment based on the first slice image, and by determining a second slice image in the width direction of the battery cell and determining the second electrode alignment based on the second slice image, it is possible to determine whether the electrode alignment in the length direction and the electrode alignment in the width direction of the battery cell meet the preset requirements, thereby improving the accuracy of battery cell detection.

[0131] like Figure 7 As shown, Figure 7 This is a modular schematic diagram of a battery cell testing device disclosed in an embodiment of this application. The battery cell testing device 700 may include an image acquisition module 710, an image reconstruction module 720, an image slicing module 730, and an image detection module 740, wherein:

[0132] The image acquisition module 710 is used to acquire multiple battery cell projection images, which correspond to multiple projection angles of the battery cell, and the battery cell projection images include the region of interest of the battery cell.

[0133] The image reconstruction module 720 is used to perform three-dimensional reconstruction of the region of interest of the battery cell based on multiple battery cell projection images and the projection angles corresponding to each battery cell projection image, so as to obtain a three-dimensional image corresponding to the region of interest of the battery cell.

[0134] The image slicing module 730 is used to slice a three-dimensional image according to a preset direction to obtain a sliced ​​image corresponding to the preset direction.

[0135] The image detection module 740 is used to determine the detection result of the battery cell based on the sliced ​​image.

[0136] In one embodiment, the image reconstruction module 720 is further configured to perform filtering processing on multiple battery cell projection images to obtain filtered images corresponding to the multiple battery cell projection images respectively; and to perform three-dimensional reconstruction on the region of interest of the battery cell based on the filtered images corresponding to the multiple battery cell projection images respectively to obtain a three-dimensional image corresponding to the region of interest of the battery cell.

[0137] In one embodiment, the battery cell is placed on a rotating platform, and an imaging device is arranged around the rotating platform to acquire multiple projected images of the battery cell. The image reconstruction module 720 is also used to acquire preset position information corresponding to the imaging device, as well as the relative position information between the imaging device and the rotating platform. Based on the multiple projected images of the battery cell, the projection angle corresponding to each projected image of the battery cell, the preset position information, and the relative position information, the region of interest of the battery cell is reconstructed in three dimensions to obtain a three-dimensional image corresponding to the region of interest of the battery cell.

[0138] In one embodiment, the image reconstruction module 720 is further configured to extract image features of each cell's projected image; and to perform three-dimensional reconstruction of the region of interest of the cell based on the image features, projection angle, preset position information, and relative position information corresponding to each cell's projected image, thereby obtaining a three-dimensional image corresponding to the region of interest of the cell.

[0139] In one embodiment, the rotating platform drives the battery cell to rotate; the battery cell detection device 700 further includes an angle determination module for obtaining the target rotation angle corresponding to each battery cell projection image, the target rotation angle being the angle at which the rotating platform rotates when the imaging device acquires the battery cell projection image; wherein, the target rotation angle is within a preset rotation range; and the projection angle corresponding to each battery cell projection image is determined based on the target rotation angle corresponding to each battery cell projection image.

[0140] In one embodiment, the image reconstruction module 720 is further configured to: determine the target position information of the region of interest of the battery cell in the three-dimensional space according to the projection angle corresponding to each battery cell projection image; determine the partial three-dimensional pixels corresponding to the region of interest of the battery cell in the three-dimensional space according to the multiple battery cell projection images and the target position information corresponding to each battery cell projection image; determine the tilt angle of the battery cell according to the target battery cell projection image and the target rotation angle corresponding to the target battery cell projection image; wherein, the tilt angle is the angle at which the battery cell is tilted relative to the vertical direction, and the target battery cell projection image is any battery cell projection image whose corresponding target rotation angle is not a preset angle; and perform local three-dimensional reconstruction of the region of interest of the battery cell according to the partial three-dimensional pixels, the tilt angle of the battery cell, the preset position information, and the relative position information to obtain the three-dimensional image corresponding to the region of interest of the battery cell.

[0141] In one embodiment, the image reconstruction module 720 is further configured to identify the projection area corresponding to the battery cell in the target battery cell projection image, and determine the projection tilt angle of the battery cell based on the projection area. The projection tilt angle of the battery cell is the angle formed by the projection of the tilt angle of the battery cell onto the target battery cell projection image. The tilt angle of the battery cell is determined based on the projection tilt angle and the target rotation angle corresponding to the target battery cell projection image.

[0142] In one embodiment, the image detection module 740 is further configured to input the sliced ​​image into a trained artificial intelligence model, and to identify the electrode regions of the sliced ​​image through the artificial intelligence model to obtain the positive electrode region and the negative electrode region of the battery cell in the sliced ​​image. The artificial intelligence model is trained based on a set of sample images, which includes multiple sample images divided into positive and negative electrode regions. Based on the positive and negative electrode regions of the battery cell, the electrode alignment of the battery cell is determined. Based on the electrode alignment, the detection result of the battery cell is determined.

[0143] In one embodiment, the preset direction includes a first preset direction and a second preset direction, the first preset direction corresponding to the length direction of the battery cell and the second preset direction corresponding to the width direction of the battery cell; the image slicing module 730 is further configured to slice the three-dimensional image according to the first preset direction to obtain a first slice image corresponding to the first preset direction; slice the three-dimensional image according to the second preset direction to obtain a second slice image corresponding to the second preset direction; the image detection module 740 is further configured to determine the first electrode alignment degree of the battery cell based on the positive electrode area and the negative electrode area of ​​the battery cell in the first slice image, the first electrode alignment degree including the portion of the negative electrode extending beyond the positive electrode in the length direction; and determine the second electrode alignment degree of the battery cell based on the positive electrode area and the negative electrode area of ​​the battery cell in the second slice image, the second electrode alignment degree including the portion of the negative electrode extending beyond the positive electrode in the width direction.

[0144] In this embodiment, the electronic device can acquire multiple battery cell projection images, which correspond to multiple acquisition angles of the battery cell. Each projection image includes a region of interest (ROI) of the battery cell. Based on these multiple projection images, the electronic device can perform three-dimensional reconstruction of the projection area to obtain a three-dimensional image corresponding to the ROI. Furthermore, it can slice the three-dimensional image according to a preset direction to obtain sliced ​​images corresponding to the preset direction. Based on these sliced ​​images, the detection result of the battery cell is determined. The three-dimensional image obtained after three-dimensional reconstruction of the ROI using multiple projection images has more accurate and comprehensive battery cell information compared to the projected two-dimensional image. Obtaining sliced ​​images according to the preset direction also makes the sliced ​​images more accurate than the projected two-dimensional image, thereby improving the accuracy of battery cell detection. Since it is not necessary to reconstruct the entire battery cell, only the ROI is reconstructed, which also reduces the time required for three-dimensional reconstruction and improves the efficiency of battery cell detection.

[0145] like Figure 8 As shown, in one embodiment, an electronic device is provided, which may include:

[0146] Memory 810 storing executable program code;

[0147] Processor 820 coupled to memory 810;

[0148] The processor 820 calls the executable program code stored in the memory 810 to implement the cell detection method provided in the above embodiments.

[0149] The memory 810 may include random access memory (RAM) or read-only memory (ROM). The memory 810 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 810 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described above. The data storage area may also store data created during the use of the electronic device.

[0150] Processor 820 may include one or more processing cores. Processor 820 connects to various parts of the electronic device using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 810, and by calling data stored in memory 810. Optionally, processor 820 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 820 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 820 and may be implemented separately using a communication chip.

[0151] Understandably, electronic devices may include more or fewer structural elements than those shown in the block diagram above, such as power modules, physical buttons, WiFi (Wireless Fidelity) modules, speakers, Bluetooth modules, sensors, etc., and are not limited herein.

[0152] This application discloses a computer-readable storage medium storing a computer program that causes a computer to perform the methods described in the above embodiments.

[0153] Furthermore, this application further discloses a computer program product that, when run on a computer, enables the computer to execute all or part of the steps in any of the cell testing methods described in the above embodiments.

[0154] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0155] The present application provides a detailed description of a battery cell testing method, apparatus, electronic device, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present application. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present application. Therefore, the content of this specification should not be construed as a limitation of the present application.

Claims

1. A method for testing battery cells, characterized in that, The battery cell is placed on a rotating platform, and an imaging device is arranged around the rotating platform to acquire projected images of the battery cell; the method includes: Multiple cell projection images are acquired, the multiple cell projection images correspond to multiple projection angles of the cell, and the cell projection images include the region of interest of the cell; Obtain the preset position information corresponding to the imaging device, and the relative position information between the imaging device and the rotating platform; Based on the multiple cell projection images, the projection angle corresponding to each cell projection image, the preset position information, and the relative position information, the region of interest of the cell is reconstructed in three dimensions to obtain a three-dimensional image corresponding to the region of interest of the cell. The three-dimensional image is sliced ​​according to a preset direction to obtain a sliced ​​image corresponding to the preset direction; Based on the sliced ​​image, the detection result of the battery cell is determined; The step of reconstructing the region of interest (ROI) of the battery cell in three dimensions based on the plurality of battery cell projection images, the projection angle corresponding to each battery cell projection image, the preset position information, and the relative position information to obtain a three-dimensional image corresponding to the ROI of the battery cell includes: Based on the projection angle corresponding to each of the battery cell projection images, the target position information of the region of interest of each battery cell in the three-dimensional space is determined. Based on the multiple cell projection images and the target position information corresponding to each cell projection image, the region of interest of the cell is determined to be a portion of the three-dimensional pixels in the three-dimensional space. The tilt angle of the battery cell is determined based on the target cell projection image and the target rotation angle corresponding to the target cell projection image; wherein, the tilt angle is the angle at which the battery cell is tilted relative to the vertical direction, and the target cell projection image is any cell projection image whose corresponding target rotation angle is not a preset angle; Based on the partial 3D pixels, the tilt angle of the battery cell, the preset position information, and the relative position information, a local 3D reconstruction of the region of interest of the battery cell is performed to obtain a 3D image corresponding to the region of interest of the battery cell.

2. The method according to claim 1, characterized in that, The step of performing three-dimensional reconstruction of the region of interest (ROI) of the battery cell to obtain a three-dimensional image corresponding to the ROI of the battery cell includes: The multiple battery cell projection images are filtered to obtain filtered images corresponding to the multiple battery cell projection images respectively; Based on the filtered images corresponding to the multiple cell projection images, the region of interest of the cell is reconstructed in three dimensions to obtain a three-dimensional image corresponding to the region of interest of the cell.

3. The method according to claim 1, characterized in that, The step of reconstructing the region of interest (ROI) of the battery cell in three dimensions based on the plurality of battery cell projection images, the projection angle corresponding to each battery cell projection image, the preset position information, and the relative position information to obtain a three-dimensional image corresponding to the ROI of the battery cell includes: Extract image features from the projection images of each of the battery cells; Based on the image features and projection angles corresponding to the projected images of each battery cell, the preset position information, and the relative position information, the region of interest of the battery cell is reconstructed in three dimensions to obtain a three-dimensional image corresponding to the region of interest of the battery cell.

4. The method according to claim 1, characterized in that, The rotating platform drives the battery cell to rotate; before performing three-dimensional reconstruction of the region of interest of the battery cell based on the multiple battery cell projection images, the projection angle corresponding to each battery cell projection image, the preset position information, and the relative position information to obtain a three-dimensional image corresponding to the region of interest of the battery cell, the method further includes: Obtain the target rotation angle corresponding to each of the battery cell projection images, wherein the target rotation angle is the angle of rotation of the rotating platform when the imaging device acquires the battery cell projection image; wherein the target rotation angle is within a preset rotation range; The projection angle corresponding to each of the battery cell projection images is determined based on the target rotation angle corresponding to each of the battery cell projection images.

5. The method according to claim 1, characterized in that, The step of determining the tilt angle of the battery cell based on the target cell projection image and the target rotation angle corresponding to the target cell projection image includes: Identify the projection area corresponding to the battery cell in the target battery cell projection image, and determine the projection tilt angle of the battery cell based on the projection area. The projection tilt angle of the battery cell is the angle formed by the projection of the tilt angle of the battery cell onto the target battery cell projection image. The tilt angle of the battery cell is determined based on the projection tilt angle and the target rotation angle corresponding to the projected image of the target battery cell.

6. The method according to any one of claims 1 to 5, characterized in that, The step of determining the detection result of the battery cell based on the sliced ​​image includes: The sliced ​​image is input into a trained artificial intelligence model, which identifies the electrode region of the sliced ​​image to obtain the positive electrode region and the negative electrode region of the battery cell in the sliced ​​image. The artificial intelligence model is trained based on a set of sample images, which includes multiple sample images divided into positive electrode regions and negative electrode regions. The electrode alignment of the battery cell is determined based on the positive electrode region and the negative electrode region of the battery cell. The test result of the battery cell is determined based on the electrode alignment.

7. The method according to claim 6, characterized in that, The preset direction includes a first preset direction and a second preset direction, wherein the first preset direction corresponds to the length direction of the battery cell and the second preset direction corresponds to the width direction of the battery cell; The step of slicing the three-dimensional image according to a preset direction to obtain a sliced ​​image corresponding to the preset direction includes: The three-dimensional image is sliced ​​according to the first preset direction to obtain a first sliced ​​image corresponding to the first preset direction; The three-dimensional image is sliced ​​according to the second preset direction to obtain a second sliced ​​image corresponding to the second preset direction; Determining the electrode alignment of the battery cell based on the positive electrode region and the negative electrode region of the battery cell includes: Based on the positive electrode region and the negative electrode region of the battery cell in the first slice image, the first electrode alignment degree of the battery cell is determined, and the first electrode alignment degree includes the portion of the negative electrode that extends beyond the positive electrode in the length direction. Based on the positive electrode region and the negative electrode region of the battery cell in the second slice image, the second electrode alignment of the battery cell is determined. The second electrode alignment includes the portion of the negative electrode that extends beyond the positive electrode in the width direction.

8. A battery cell testing device, characterized in that, The battery cell is placed on a rotating platform, and an imaging device is arranged around the rotating platform to acquire projected images of the battery cell; the device includes: An image acquisition module is used to acquire multiple cell projection images, the multiple cell projection images corresponding to multiple projection angles of the cell, and the cell projection images including the region of interest of the cell; The image reconstruction module is used to acquire preset position information corresponding to the imaging device, and relative position information between the imaging device and the rotating platform; based on the multiple cell projection images, the projection angle corresponding to each cell projection image, the preset position information, and the relative position information, the module performs three-dimensional reconstruction of the region of interest of the cell to obtain a three-dimensional image corresponding to the region of interest of the cell. An image slicing module is used to slice the three-dimensional image according to a preset direction to obtain a sliced ​​image corresponding to the preset direction. An image detection module is used to determine the detection result of the battery cell based on the sliced ​​image; The image reconstruction module is further configured to: determine the target position information of the region of interest of the battery cell in three-dimensional space in each of the battery cell projection images according to the projection angle corresponding to each of the battery cell projection images; determine a portion of the three-dimensional pixels corresponding to the region of interest of the battery cell in the three-dimensional space according to the plurality of battery cell projection images and the target position information corresponding to each battery cell projection image; determine the tilt angle of the battery cell according to the target battery cell projection image and the target rotation angle corresponding to the target battery cell projection image; wherein, the tilt angle is the angle at which the battery cell is tilted relative to the vertical direction, and the target battery cell projection image is any battery cell projection image whose corresponding target rotation angle is not a preset angle; and perform local three-dimensional reconstruction of the region of interest of the battery cell according to the portion of the three-dimensional pixels, the tilt angle of the battery cell, the preset position information, and the relative position information to obtain a three-dimensional image corresponding to the region of interest of the battery cell.

9. An electronic device, characterized in that, include: Memory containing executable program code; A processor coupled to the memory; The processor invokes the executable program code stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein, when executed by a processor, the computer program causes the processor to perform the method according to any one of claims 1 to 7.

Images