Lithium ion battery polarity size difference detection method, system and equipment and storage medium

Abstract

The invention discloses a lithium ion battery polarity dimension difference detection method, system and device, and a storage medium. The method comprises the following steps: acquiring an internal X-ray image of a lithium battery; obtaining a battery internal positive pole point abscissa set according to the lithium battery internal X-ray image; obtaining a positive pole point coordinate curve Kz and a negative pole point coordinate curve KF by using the trained P2PNet deep learning network according to an internal X-ray image of the lithium battery; drawing a vertical line Lk at each abscissa k in an abscissa set of positive points in the battery, solving an intersection point # imgabs0 # of the Lk and the Kz and an intersection point # imgabs1 # of the Lk and the KF, and taking the Euclidean distance between the # imgabs2 # and the # imgabs3 # as the distance between the current positive and negative points; and if the distances between all the positive and negative poles are greater than the standard threshold value of the battery, the battery polarity dimension difference is detected to be qualified, otherwise, the battery polarity dimension difference is detected to be unqualified. Positions of the anode and the cathode in the lithium battery can be identified more accurately, so that whether the distance between the anode and the cathode meets the standard or not is judged accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium battery polarity detection, and in particular to a lithium ion battery polarity size difference detection method, system, terminal equipment and computer readable storage medium. Background Art

[0002] In the production of lithium-ion batteries, winding is a key process. Generally, the positive and negative electrode sheets, separators, positive and negative electrode ears, protective tapes, termination tapes and other materials are fixed on their respective unwinding shafts. The equipment automatically unwinds and automatically corrects and positions to complete the welding of the positive and negative electrode ears, the application of protective tapes, the winding of the battery cells, the application of termination glue, and the unloading to the conveyor belt, and enters the hot pressing process. When the battery cell is wound, in order to prevent the lithium ions diffused from the positive electrode from being embedded in the lattice in the corresponding place of the negative electrode, the negative electrode must completely wrap the positive electrode and have a certain size margin, otherwise there will be certain safety hazards. However, the human eye cannot observe the situation of the negative electrode wrapping the positive electrode from the outside, and X-rays are required to capture the internal situation for analysis.

[0003] After obtaining a radiographic image of the inside of the battery using X-rays, the prior art generally uses traditional image algorithms to detect the positions of the positive and negative electrodes and then calculates the size difference between the positive and negative electrodes, but the experimental effect of position detection is not good. Summary of the invention

[0004] In order to solve the above-mentioned deficiencies of the prior art, the present invention provides a method, system, terminal device and computer-readable storage medium for detecting polarity size differences of lithium-ion batteries, which can achieve more accurate polarity size difference detection of lithium batteries.

[0005] The first object of the present invention is to provide a method for detecting polarity size differences of lithium-ion batteries.

[0006] A second object of the present invention is to provide a lithium-ion battery polarity size difference detection system.

[0007] The third object of the present invention is to provide a terminal device.

[0008] A fourth object of the present invention is to provide a computer-readable storage medium.

[0009] The first object of the present invention can be achieved by adopting the following technical solutions:

[0010] A method for detecting polarity and size differences of lithium-ion batteries, the method comprising:

[0011] Get X-ray images of the inside of lithium batteries;

[0012] According to the X-ray image inside the lithium battery, the horizontal coordinate set of the positive pole inside the battery is obtained;

[0013] According to the X-ray image inside the lithium battery, the positive pole coordinate curve K is obtained using the trained P2PNet deep learning network. z and negative pole coordinate curve K F ;

[0014] Draw a vertical line L at each abscissa k in the abscissa set of the positive pole inside the battery. k , and find L k With K z The intersection of and L k With K F The intersection of

[0015] Will and The Euclidean distance of is taken as the distance between the current positive and negative poles; if the distances between all positive and negative poles are greater than the battery standard threshold, the battery polarity size difference detection is passed, otherwise the battery polarity size difference detection is failed.

[0016] Furthermore, the positive pole coordinate curve K is obtained by using the trained P2PNet deep learning network based on the internal X-ray image of the lithium battery. z and negative pole coordinate curve K F ,include:

[0017] Train the P2PNet deep learning network to obtain a trained P2PNet deep learning network;

[0018] Enhance the X-ray image inside the lithium battery and input the enhanced image into the trained P2PNet deep learning network to obtain the coordinate information of the positive and negative poles;

[0019] Perform curve fitting on all positive poles to obtain the positive pole coordinate curve K z ;

[0020] Perform curve fitting on all negative poles to obtain the negative pole coordinate curve K F .

[0021] Furthermore, the training of the P2PNet deep learning network includes:

[0022] Obtain several X-ray images of the interior of lithium batteries;

[0023] All acquired X-ray images of the inside of lithium batteries are enhanced, and the enhanced images constitute a training data set;

[0024] Label the positive and negative poles of each image in the training data set and record their coordinate information; when labeling, the positive and negative poles are labeled as two category targets;

[0025] The annotated images are used to train the P2PNet deep learning network.

[0026] Furthermore, the X-ray image inside the lithium battery is enhanced, including:

[0027] X-ray image of the inside of a lithium battery Perform median filtering to obtain the filtered image

[0028] Based on the X-ray image and filtered image inside the lithium battery, a preliminary enhanced image is obtained

[0029] Using CLAHE algorithm to Enhance to obtain the enhanced image.

[0030] Furthermore, the step of obtaining a set of horizontal coordinates of the positive pole inside the battery according to the X-ray image inside the lithium battery includes:

[0031] Performing regional cutting on the X-ray image inside the lithium battery to obtain a regional image;

[0032] Perform mean filtering on the regional image; and obtain a set of positive pole horizontal coordinates based on the filtered image.

[0033] Furthermore, the step of performing regional cutting on the X-ray image inside the lithium battery to obtain the regional image includes:

[0034] The grayscale average value of each row of pixels in the X-ray image of the lithium battery is calculated to obtain the grayscale change curve A(i); where i corresponds to the ordinate of the image;

[0035] Calculate the grayscale difference curve G(i) of adjacent set points in A(i), that is, G(i) = A(i-1)-A(i);

[0036] Search from the maximum ordinate to the minimum ordinate, and record the first ordinate i with G(i)>7 as h 1 ;

[0037] From h 1 Search towards the minimum ordinate, and record the first ordinate i where G(i)<3 as h 2 ;

[0038] Cut out the X-ray image of the inside of the lithium battery from the vertical coordinate h 1 With h 2 The area between is taken as the region image.

[0039] Furthermore, obtaining a set of positive pole horizontal coordinates according to the filtered image includes:

[0040] Using adaptive binarization on the filtered image to obtain a binary image;

[0041] Perform connected domain analysis on the binary image to obtain a set of positive connected domains;

[0042] The central abscissa of each connected domain in the positive connected domain set is taken to form the positive pole point abscissa set.

[0043] The second object of the present invention can be achieved by adopting the following technical solutions:

[0044] A lithium-ion battery polarity size difference detection system, the system comprising:

[0045] An image acquisition module, used to acquire an X-ray image of the interior of a lithium battery;

[0046] A set acquisition module is used to obtain a set of horizontal coordinates of the positive pole inside the battery according to an X-ray image inside the lithium battery;

[0047] The curve acquisition module is used to obtain the positive pole coordinate curve K based on the internal X-ray image of the lithium battery using the trained P2PNet deep learning network z and negative pole coordinate curve K F ;

[0048] The intersection acquisition module is used to draw a vertical line L at each horizontal coordinate k in the horizontal coordinate set of the positive pole inside the battery. k , and find L k With K z The intersection of and L k With K F The intersection of

[0049] Detection module, used to and The Euclidean distance of is taken as the distance between the current positive and negative poles; if the distances between all positive and negative poles are greater than the battery standard threshold, the battery polarity size difference detection is passed, otherwise the battery polarity size difference detection is failed.

[0050] The third object of the present invention can be achieved by adopting the following technical solutions:

[0051] A terminal device comprises a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the above-mentioned method for detecting polarity and size differences of lithium-ion batteries is implemented.

[0052] The fourth object of the present invention can be achieved by adopting the following technical solutions:

[0053] A computer-readable storage medium stores a program, and when the program is executed by a processor, the above-mentioned lithium-ion battery polarity size difference detection method is implemented.

[0054] The present invention has the following beneficial effects compared with the prior art:

[0055] The present invention combines traditional algorithms with the P2PNet deep learning network to more accurately identify the positions of the positive and negative electrodes inside the lithium battery, thereby accurately determining whether the distance between the positive and negative electrodes meets the standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0057] Figure 1 This is a flow chart of a method for detecting polarity and size differences of lithium-ion batteries according to Embodiment 1 of the present invention;

[0058] Figure 2 The original image of the internal structure of the battery taken by the X-ray camera in this embodiment 1;

[0060] Figure 3 The image is obtained by cutting the original image into regions in the first embodiment;

[0061] Figure 4 The connected domain image obtained by using the traditional algorithm to perform connected domain analysis in this embodiment 1;

[0062] Figure 5 This is a result diagram of the horizontal coordinate of the positive electrode inside the battery obtained by using the traditional algorithm in this embodiment 1;

[0063] Figure 6 This is a schematic diagram of curve fitting of the obtained battery positive and negative electrode result sets after training using the P2PNet network in Example 1;

[0064] Figure 7 is a schematic diagram of the intersection set finally outputted by this embodiment;

[0065] Figure 8 This is a structural block diagram of a lithium-ion battery polarity size difference detection system according to Embodiment 2 of the present invention;

[0066] Fig. 9 This is a structural block diagram of the terminal device of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should be understood that the specific embodiments described are only used to explain the present application and are not used to limit the present application.

[0068] Embodiment 1:

[0069] like Figure 1 As shown, this embodiment provides a method for detecting polarity and size differences of lithium-ion batteries, comprising the following steps:

[0070] S101, obtaining an X-ray image of the interior of a lithium battery.

[0071] X-ray image of the interior of a lithium battery I 1 ,like Figure 2 shown.

[0072] S102. According to the X-ray image inside the lithium battery, a set of horizontal coordinates of the positive poles is obtained using a traditional algorithm.

[0073] Further, step S102 includes:

[0074] (1) For image I 1 Perform region cutting to obtain region image I 2 .

[0075] Further, step (1) comprises:

[0076] (1-1) to I 1 Calculate the grayscale average of each row of pixels to obtain the grayscale change curve A(i), where i corresponds to the ordinate of the image;

[0077] (1-2) Calculate the grayscale difference curve G(i) of adjacent set points in A(i), that is, G(i) = A(i-1)-A(i);

[0078] (1-3) Search from the maximum ordinate to the minimum ordinate, and record the first ordinate i where G(i)>7 as h 1 ;

[0079] (1-4) from h 1 Search towards the minimum ordinate, and record the first ordinate i where G(i)<3 as h 2 ;

[0080] (1-5) From Figure I 1 Cut out the vertical coordinate at h 1 With h 2 The area between the two is obtained by 2 ,like Figure 3 shown.

[0081] (2) For the regional image I 2 Perform mean filtering to obtain image I 3 ; for image I 3 Adaptive binarization is used to obtain the connected domain of the positive pole and the horizontal coordinate set P of the positive pole points.

[0082] Further, step (2) comprises:

[0083] (2-1) Adaptive binarization is used to obtain the binary image B, that is:

[0084]

[0085] In the formula, x and y are the horizontal and vertical coordinates of the image, respectively. 3 It is to use a 3×31 rectangular frame to image I 2 Perform mean filtering to obtain the image, T 1 is the preset binarization threshold;

[0086] In this embodiment, T 1 Take 0.999;

[0087] (2-2) Perform opening and closing operations on the binary image B to remove isolated noise and obtain the denoised binary image B 2 ; The structural element used in the opening operation is a 3×3 rectangular element, and the structural element used in the closing operation is a 13×13 rectangular element;

[0088] (2-3) Denoised binary image B 2 Perform connected domain analysis and obtain the circumscribed rectangle of each connected domain;

[0089] (2-4) Remove the connected domains that do not meet the conditions and obtain the positive connected domain set Z, such as Figure 4 As shown, the conditions are:

[0090]

[0091] Where w is the short side length of the minimum circumscribed rectangle of the connected domain, h is the long side length of the minimum circumscribed rectangle of the connected domain, and H is the image I 3 Total width; T 2 is the initial width threshold, which is used to remove connected domains with too small width;

[0092] In this embodiment, T 2Take 3px;

[0093] (2-5) Take the central horizontal coordinates of each connected domain in the set Z to form the positive pole horizontal coordinate set P. The set result is shown in the figure below. Figure 5 shown.

[0094] S103. According to the X-ray image inside the lithium battery, the positive pole coordinate curve and the negative pole coordinate curve are obtained using the trained P2PNet deep learning network.

[0095] Use the trained P2PNet deep learning network to obtain image I 1 Positive pole coordinate curve K z and negative pole coordinate curve K F .

[0096] Further, step S103 includes:

[0097] (1) Train the P2PNet deep learning network.

[0098] (1-1) Taking X-ray images of the inside of lithium batteries on several production lines

[0099] (1-2) For all images Perform enhancements and build datasets;

[0100] Further, step (1-2) comprises:

[0101] (1-2-1) Image Perform 21×21 median filtering to obtain the filtered image

[0102] (1-2-2) Obtaining preliminary enhanced image

[0103] (1-2-3) Using improved adaptive histogram equalization (CLAHE) to image Enhanced image All final enhanced images The set formed is the training data set O;

[0104] (1-2-4) Labeling the data set: Use the point labeling method to label each positive and negative pole in each image in the training data set O and record its coordinate information. When labeling, the positive and negative poles will be labeled as two category targets;

[0105] (1-3) Training network: Send the labeled data set to the P2PNet network for training to obtain model N.

[0106] (2) Use the trained P2PNet deep learning network to obtain image I 1 Positive pole coordinate curve K z and negative pole coordinate curve K F .

[0107] Further, step (2) comprises:

[0108] (2-1) For image I 1 Enhance the image The method is the same as step (1-2);

[0109] (2-2) Input into model N to obtain the coordinate information of the positive and negative poles of the image;

[0110] (2-3) Perform curve fitting on all positive poles obtained in step (2-2) to obtain the positive pole coordinate curve K z The results of the positive and negative electrode fitting curves are as follows Figure 6 As shown;

[0111] (2-4) Perform curve fitting on all negative poles obtained in step (2-2) to obtain the negative pole coordinate curve K F .

[0112] S104, obtaining the positive and negative pole coordinates according to the positive pole horizontal coordinate set, the positive pole coordinate curve, and the negative pole coordinate curve.

[0113] Draw a vertical line L at each horizontal coordinate k in the positive pole horizontal coordinate set P k , and find L k With K z The intersection of and L k With K F The intersection of

[0114] The intersection set result is as follows Figure 7 shown.

[0115] S105. Determine whether the distance between the positive and negative electrodes meets the size requirements based on the coordinates of the positive and negative poles.

[0116] Will and The Euclidean distance D k As the distance between the current positive and negative poles; for the distance D between all positive and negative poles k Both are greater than the battery standard threshold T D , that is, the battery polarity size difference detection is considered to be passed, otherwise it is considered that the battery polarity size difference detection is failed.

[0117] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above embodiments may be completed by instructing related hardware through a program, and the corresponding program may be stored in a computer-readable storage medium.

[0118] It should be noted that although the method operations of the above embodiments are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0119] Embodiment 2:

[0120] like Figure 8 As shown, this embodiment provides a lithium-ion battery polarity size difference detection system, which includes an image acquisition module 801, a set acquisition module 802, a curve acquisition module 803, an intersection acquisition module 804 and a battery polarity size difference detection module 805, wherein:

[0121] An image acquisition module 801 is used to acquire an X-ray image of the interior of a lithium battery;

[0122] A set acquisition module 802 is used to obtain a set of horizontal coordinates of positive poles inside the battery according to an X-ray image inside the lithium battery;

[0123] The curve acquisition module 803 is used to obtain the positive pole coordinate curve K based on the internal X-ray image of the lithium battery using the trained P2PNet deep learning network z and negative pole coordinate curve K F ;

[0124] The intersection acquisition module 804 is used to draw a vertical line L at each horizontal coordinate k in the horizontal coordinate set of the positive pole inside the battery. k , and find L k With K z The intersection of and L k With K F The intersection of

[0125] Battery polarity and size difference detection module 805 is used to detect and The Euclidean distance of is taken as the distance between the current positive and negative poles; if the distances between all positive and negative poles are greater than the battery standard threshold, the battery polarity size difference detection is passed, otherwise the battery polarity size difference detection is failed.

[0126] The specific implementation of each module in this embodiment can refer to the above-mentioned embodiment 1, which will not be described one by one here; it should be noted that the system provided in this embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0127] Embodiment 3:

[0128] This embodiment provides a terminal device, which can be a computer, such as Figure 6 As shown, a processor 902, a memory, an input device 903, a display 904 and a network interface 905 connected via a system bus 901 are provided. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 906 and an internal memory 907. The non-volatile storage medium 906 stores an operating system, a computer program and a database. The internal memory 907 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the processor 902 executes the computer program stored in the memory, the method for detecting polarity and size difference of a lithium-ion battery in the above-mentioned embodiment 1 is implemented as follows:

[0129] Get X-ray images of the inside of lithium batteries;

[0130] According to the X-ray image inside the lithium battery, the horizontal coordinate set of the positive pole inside the battery is obtained;

[0131] According to the X-ray image inside the lithium battery, the positive pole coordinate curve K is obtained using the trained P2PNet deep learning network. z and negative pole coordinate curve K F ;

[0132] Draw a vertical line L at each abscissa k in the abscissa set of the positive pole inside the battery. k , and find L k With K z The intersection of and L k With K F The intersection of

[0133] Will and The Euclidean distance of is taken as the distance between the current positive and negative poles; if the distances between all positive and negative poles are greater than the battery standard threshold, the battery polarity size difference detection is passed, otherwise the battery polarity size difference detection is failed.

[0134] Embodiment 4:

[0135] This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for detecting polarity and size differences of lithium-ion batteries of the above embodiment 1 is implemented as follows:

[0136] Get X-ray images of the inside of lithium batteries;

[0137] According to the X-ray image inside the lithium battery, the horizontal coordinate set of the positive pole inside the battery is obtained;

[0138] According to the X-ray image inside the lithium battery, the positive pole coordinate curve K is obtained using the trained P2PNet deep learning network. z and negative pole coordinate curve K F ;

[0139] Draw a vertical line L at each abscissa k in the abscissa set of the positive pole inside the battery. k , and find L k With K z The intersection of and L k With K F The intersection of

[0140] Will and The Euclidean distance of is taken as the distance between the current positive and negative poles; if the distances between all positive and negative poles are greater than the battery standard threshold, the battery polarity size difference detection is passed, otherwise the battery polarity size difference detection is failed.

[0141] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0142] The above is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solution and inventive concept of the present invention within the scope disclosed by the present invention, which shall fall within the protection scope of the present invention.

Claims

1. A method for detecting polarity and size differences of lithium-ion batteries, characterized in that: The method comprises: Get X-ray images of the inside of lithium batteries; According to the X-ray image inside the lithium battery, the horizontal coordinate set of the positive pole inside the battery is obtained; According to the X-ray image inside the lithium battery, the positive pole coordinate curve K is obtained using the trained P2PNet deep learning network. z and negative pole coordinate curve K F ; Draw a vertical line L at each abscissa k in the abscissa set of the positive pole inside the battery. k , and find L k With K z The intersection of and L k With K F The intersection of Will and The Euclidean distance of is taken as the distance between the current positive and negative poles; if the distances between all positive and negative poles are greater than the battery standard threshold, the battery polarity size difference detection is passed, otherwise the battery polarity size difference detection is failed.

2. The control method according to claim 1, characterized in that: According to the X-ray image inside the lithium battery, the positive pole coordinate curve K is obtained by using the trained P2PNet deep learning network. z and negative pole coordinate curve K F ,include: Train the P2PNet deep learning network to obtain a trained P2PNet deep learning network; Enhance the X-ray image inside the lithium battery and input the enhanced image into the trained P2PNet deep learning network to obtain the coordinate information of the positive and negative poles; Perform curve fitting on all positive poles to obtain the positive pole coordinate curve K z ; Perform curve fitting on all negative poles to obtain the negative pole coordinate curve K F .

3. The control method according to claim 2, characterized in that: The training of the P2PNet deep learning network includes: Obtain several X-ray images of the interior of lithium batteries; All acquired X-ray images of the inside of lithium batteries are enhanced, and the enhanced images constitute a training data set; Label the positive and negative poles of each image in the training data set and record their coordinate information; when labeling, the positive and negative poles are labeled as two category targets; The annotated images are used to train the P2PNet deep learning network.

4. The control method according to any one of claims 2 and 3, characterized in that: Enhance the X-ray images inside lithium batteries, including: X-ray image of the inside of a lithium battery Perform median filtering to obtain the filtered image Based on the X-ray image and filtered image inside the lithium battery, a preliminary enhanced image is obtained Using CLAHE algorithm to Enhance to obtain the enhanced image.

5. The control method according to any one of claims 1 to 3, characterized in that: The step of obtaining a set of horizontal coordinates of the positive pole inside the battery according to the X-ray image inside the lithium battery includes: Performing regional cutting on the X-ray image inside the lithium battery to obtain a regional image; Perform mean filtering on the regional image; and obtain a set of positive pole horizontal coordinates based on the filtered image.

6. The control method according to claim 5, characterized in that: The step of performing regional cutting on the X-ray image inside the lithium battery to obtain the regional image includes: The grayscale average value of each row of pixels in the X-ray image of the lithium battery is calculated to obtain the grayscale change curve A(i); where i corresponds to the ordinate of the image; Calculate the grayscale difference curve G(i) of adjacent set points in A(i), that is, G(i) = A(i-1)-A(i); Search from the maximum ordinate to the minimum ordinate, and record the first ordinate i with G(i)>7 as h1; Search from h1 to the minimum ordinate, and record the first ordinate i with G(i)<3 as h2; The region with the ordinate between h1 and h2 is cut out from the X-ray image of the interior of the lithium battery as a regional image.

7. The control method according to claim 5, characterized in that: The step of obtaining a set of positive pole horizontal coordinates according to the filtered image includes: Using adaptive binarization on the filtered image to obtain a binary image; Perform connected domain analysis on the binary image to obtain a set of positive connected domains; The central abscissa of each connected domain in the positive connected domain set is taken to form the positive pole point abscissa set.

8. A lithium-ion battery polarity size difference detection system, characterized in that: The system comprises: An image acquisition module, used to acquire an X-ray image of the interior of a lithium battery; A set acquisition module is used to obtain a set of horizontal coordinates of the positive pole inside the battery according to an X-ray image inside the lithium battery; The curve acquisition module is used to obtain the positive pole coordinate curve K based on the internal X-ray image of the lithium battery using the trained P2PNet deep learning network z and negative pole coordinate curve K F ; The intersection acquisition module is used to draw a vertical line L at each horizontal coordinate k in the horizontal coordinate set of the positive pole inside the battery. k , and find L k With K z The intersection of and L k With K F The intersection of Battery polarity and size difference detection module, used to and The Euclidean distance of is taken as the distance between the current positive and negative poles; if the distances between all positive and negative poles are greater than the battery standard threshold, the battery polarity size difference detection is passed, otherwise the battery polarity size difference detection is failed.

9. A terminal device, comprising a processor and a memory for storing a program executable by the processor, characterized in that: When the processor executes the program stored in the memory, the control method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the control method according to any one of claims 1 to 7 is implemented.

Images