Battery cell shell detection method, battery cell disassembly method and battery cell disassembly system

Abstract

The embodiments of the present application disclose a shell detection method for a battery cell, a disassembly method for a battery cell, and a battery cell disassembly system. The shell detection method for the battery cell includes: obtaining the current shell contour of the battery cell according to the disassembly path of the battery cell; obtaining the shell thickness change data of the battery cell on the disassembly path according to the shell thickness distribution data corresponding to the target curve sample matching the current shell contour in each shell contour sample; wherein the shell contour sample is determined according to the historical disassembly path of the battery cell sample, and the shell thickness distribution data corresponding to the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample. The shell detection method for the battery cell provided in the embodiments of the present application can determine the shell thickness change of the battery cell on the disassembly path, and reduce the probability of causing thermal runaway of the battery cell when the battery cell is disassembled using the shell thickness.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery cell shell detection method, a battery cell disassembly method, and a battery cell disassembly system. Background Art

[0002] In the structure of the battery, the battery cell is an important component. The battery cell includes a shell and a bare battery cell disposed in the shell. In order to facilitate the recycling or testing of the battery cell, the shell of the battery cell is usually disassembled to obtain the bare battery cell for recycling or testing.

[0003] In the related art, the disassembly of the battery cell is to determine the disassembly path of the battery cell and then disassemble the battery cell according to the thickness of the battery cell shell. However, the battery cell will swell to varying degrees during use, causing the thickness of the battery cell shell to change. If the change in the thickness of the battery cell shell along the disassembly path cannot be determined at this time, the bare battery cell inside the shell may be damaged during disassembly, causing thermal runaway of the battery cell. Summary of the invention

[0004] In view of the above problems, the present application provides a battery cell shell detection method, a battery cell disassembly method and a battery cell disassembly system, which can determine the change in shell thickness of the battery cell along the disassembly path, and reduce the probability of thermal runaway of the battery cell when the battery cell is disassembled using the shell thickness.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting a shell of a battery cell, the method comprising: obtaining a current shell contour of the battery cell according to a disassembly path of the battery cell; obtaining shell thickness change data of the battery cell on the disassembly path according to shell thickness distribution data corresponding to a target curve sample matching the current shell contour in each shell contour sample; wherein the shell contour sample is determined according to a historical disassembly path of the battery cell sample, and the shell thickness distribution data corresponding to the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample.

[0006] In the technical solution of the embodiment of the present application, the current shell profile of the battery cell is obtained through the disassembly path of the battery cell, so as to obtain the shell thickness change data of the battery cell on the disassembly path according to the shell thickness distribution data corresponding to the target curve sample matching the current shell profile in each shell profile sample. Therefore, the shell thickness distribution data corresponding to the shell profile sample matching the shell profile can be used to predict the shell thickness change of the battery cell on the disassembly path, thereby reducing the probability of thermal runaway of the battery cell when the battery cell is disassembled by using the shell thickness.

[0007] In some embodiments, the method further includes: sampling the sub-regions in the shell contour sample whose deformation amount is less than the preset deformation amount according to the first sampling frequency, and sampling the sub-regions in the shell contour sample whose deformation amount reaches the preset deformation amount according to the second sampling frequency greater than the first sampling frequency, to obtain each of the sample points; and obtaining the shell thickness distribution data corresponding to the shell contour sample according to the shell thickness corresponding to each sample point. In this way, based on the deformation amount of the region, the region with a large shell thickness change can be encrypted and sampled, so that the obtained shell thickness distribution data can more accurately reflect the shell thickness distribution of the shell contour sample, and then the shell thickness distribution data corresponding to the shell contour sample that matches the shell contour is used to predict the shell thickness change data of the battery cell on the disassembly path, so that the shell thickness change data of the battery cell on the disassembly path can more accurately reflect the shell thickness change of the battery cell on the disassembly path.

[0008] In some embodiments, according to the disassembly path of the battery cell, the current shell contour of the battery cell is obtained, including: determining the sampling area of ​​the battery cell according to the disassembly path; sampling the first area in the sampling area of ​​the battery cell where the deformation probability is less than the preset probability according to the first sampling frequency, and sampling the second area in the sampling area of ​​the battery cell where the deformation probability reaches the preset probability according to the second sampling frequency greater than the first sampling frequency, to obtain each sampling point of the battery cell on the disassembly path; according to each sampling point, the current shell contour is obtained. In this way, the area with a higher probability of shell thickness change can be encrypted and sampled, so that the current shell contour obtained is more accurate, so as to improve the accuracy of the target curve sample matched by the current shell contour, and then improve the accuracy of the shell thickness change of the battery cell obtained by using the shell thickness change data corresponding to the target curve sample.

[0009] In some embodiments, the shell thickness change data of the battery cell on the disassembly path is obtained according to the shell thickness distribution data corresponding to the target curve samples matching the current shell contour in each shell contour sample, including: determining the shell thickness value corresponding to each point on the current shell contour according to the shell thickness distribution data corresponding to each target curve sample one by one; obtaining the shell thickness change data of the battery cell on the disassembly path according to the shell thickness value corresponding to each point on the current shell contour. Since there are usually different sampling points in the shell thickness distribution data corresponding to each target curve sample, the shell thickness values ​​of more points on the current shell contour can be determined by using the shell thickness distribution data corresponding to multiple target curve samples matching the current shell contour, thereby making the acquired shell thickness change data of the battery cell on the disassembly path more accurate.

[0010] In some embodiments, the shell thickness value corresponding to each point on the current shell contour is determined according to each shell thickness distribution data corresponding to each target curve sample, including: determining the shell thickness value corresponding to the target point on the current shell contour that matches the sample point according to the minimum shell thickness corresponding to any sample point of any target curve sample in each shell thickness distribution data; determining the shell thickness value corresponding to each point on the current shell contour according to the shell thickness value corresponding to each target point. Therefore, when the shell thickness corresponding to the same point on the current shell contour is different, the shell thickness with a smaller thickness value can be taken as the shell thickness corresponding to the point, reducing the disassembly depth when disassembling using the shell thickness, thereby reducing the possibility of damaging the internal bare cell of the battery cell during disassembly, and further reducing the probability of causing thermal runaway of the battery cell when disassembling the battery cell using the shell thickness.

[0011] In some embodiments, according to the shell thickness values ​​corresponding to the target points, the shell thickness values ​​corresponding to the points on the current shell profile are determined, including: according to the shell thickness values ​​corresponding to the target points and the shell bulging heights corresponding to the target points, a fitting model representing the corresponding relationship between the bulging height and the shell thickness is obtained; the shell bulging heights corresponding to the points on the current shell profile are input into the fitting model to obtain the shell thickness values ​​corresponding to the points on the current shell profile; wherein the shell bulging heights corresponding to the target points are determined according to the coordinate position of the target points in the target coordinate system and the initial size information of the battery cell, and the target coordinate system is constructed according to any reference point of the battery cell. Thus, the missing shell thickness value of a certain point on the current shell profile can be predicted and supplemented, avoiding the situation where the shell thickness value corresponding to a certain point on the current shell profile is missing, thereby making the shell thickness change data of the battery cell on the disassembly path obtained more comprehensive.

[0012] In some embodiments, the method further includes: determining that there is no target curve sample matching the current shell profile, obtaining the shell bulging height and shell thickness corresponding to each preset sampling point on the shell of the battery sample; obtaining a preset model representing the corresponding relationship between the bulging height and the shell thickness according to the shell bulging height and the shell thickness corresponding to the preset sampling point; inputting the shell bulging height corresponding to each point on the current shell profile into the preset model to obtain the shell thickness change data of the battery on the disassembly path; wherein the shell bulging height corresponding to the preset sampling point is determined according to the coordinate position of the preset sampling point in a preset coordinate system and the initial size information of the battery sample, and the preset coordinate system is constructed according to any reference point of the battery sample. Thus, even if there is no target curve sample matching the current shell profile, the shell thickness value of each point on the current shell profile can be predicted by the preset model representing the corresponding relationship between the bulging height and the shell thickness, so as to determine the shell thickness change data of the battery on the disassembly path, thereby improving the reliability of shell thickness change detection.

[0013] In some embodiments, the cell sample is identical to the product information of the cell, so that the shell swelling degree corresponding to the target curve sample obtained by using the cell sample can be approximately regarded as the shell swelling degree corresponding to the current shell profile, thereby improving the credibility of the shell thickness change data obtained by using the shell thickness change data corresponding to the target curve sample, and further improving the accuracy of the shell thickness detection of the cell.

[0014] In a second aspect, the present application provides a method for disassembling a battery cell, comprising: determining an output power curve corresponding to the disassembly path based on shell thickness change data of the battery cell along the disassembly path; and controlling a disassembly device to disassemble the battery cell along the disassembly path based on the output power curve; wherein the shell thickness change data is obtained by the battery cell shell detection method in any of the above embodiments.

[0015] By determining an output power curve corresponding to the disassembly path according to shell thickness variation data of the battery cell on the disassembly path, and controlling a disassembly device to disassemble the battery cell along the disassembly path according to the output power curve, the cutting depth of the disassembly device at different positions can be adjusted according to the shell thickness variation data of the battery cell on the disassembly path, thereby reducing the probability of thermal runaway of the battery cell when the battery cell is disassembled.

[0016] In a third aspect, the present application provides a shell detection device for a battery cell, comprising: a curve generation module, used to obtain the current shell contour of the battery cell according to the disassembly path of the battery cell; a shell detection module, used to obtain the shell thickness change data of the battery cell on the disassembly path according to the shell thickness distribution data corresponding to the target curve sample matching the current shell contour in each shell contour sample; wherein the shell contour sample is determined according to the historical disassembly path of the battery cell sample, and the shell thickness distribution data corresponding to the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample.

[0017] In the technical solution of the embodiment of the present application, the current shell profile of the battery cell is obtained through the disassembly path of the battery cell, so as to obtain the shell thickness change data of the battery cell on the disassembly path according to the shell thickness distribution data corresponding to the target curve sample matching the current shell profile in each shell profile sample. Therefore, the shell thickness distribution data corresponding to the shell profile sample matching the shell profile can be used to predict the shell thickness change of the battery cell on the disassembly path, thereby reducing the probability of thermal runaway of the battery cell when the battery cell is disassembled by using the shell thickness.

[0018] In some embodiments, the curve generation module is also used to: sample the sub-area in the shell contour sample where the deformation amount is less than the preset deformation amount according to a first sampling frequency, and sample the sub-area in the shell contour sample where the deformation amount reaches the preset deformation amount according to a second sampling frequency greater than the first sampling frequency, to obtain each of the sample points; and obtain the shell thickness distribution data corresponding to the shell contour sample according to the shell thickness corresponding to each sample point.

[0019] In some embodiments, the curve generation module is specifically used to: determine the sampling area of ​​the battery cell according to the disassembly path; sample the first area in the sampling area of ​​the battery cell where the deformation probability is less than a preset probability according to a first sampling frequency, and sample the second area in the sampling area of ​​the battery cell where the deformation probability reaches a preset probability according to a second sampling frequency greater than the first sampling frequency, to obtain the sampling points of the battery cell on the disassembly path; and obtain the current shell contour based on each of the sampling points.

[0020] In some embodiments, the shell detection module is specifically used to: determine the shell thickness value corresponding to each point on the current shell contour according to the shell thickness distribution data corresponding to each target curve sample; and obtain the shell thickness change data of the battery cell on the disassembly path according to the shell thickness value corresponding to each point on the current shell contour.

[0021] In some embodiments, the shell detection module is specifically used to: determine the shell thickness value corresponding to the target point on the current shell contour that matches the sample point based on any sample point of any of the target curve samples and the minimum shell thickness corresponding to each of the shell thickness distribution data; determine the shell thickness value corresponding to each point on the current shell contour based on the shell thickness value corresponding to each of the target points.

[0022] In some embodiments, the shell detection module is specifically used to: obtain a fitting model representing the correspondence between the bulging height and the shell thickness according to the shell thickness value corresponding to each of the target points and the shell bulging height corresponding to each of the target points; input the shell bulging height corresponding to each point on the current shell contour into the fitting model to obtain the shell thickness value corresponding to each point on the current shell contour; wherein the shell bulging height corresponding to the target point is determined according to the coordinate position of the target point in the target coordinate system and the initial size information of the battery cell, and the target coordinate system is constructed according to any reference point of the battery cell.

[0023] In some embodiments, the shell detection module is also used to: determine that there is no target curve sample that matches the current shell contour, obtain the shell bulging height and shell thickness corresponding to each preset sampling point on the shell of the battery cell sample; obtain a preset model representing the correspondence between the bulging height and the shell thickness based on the shell bulging height and shell thickness corresponding to the preset sampling points; input the shell bulging height corresponding to each point on the current shell contour into the preset model to obtain the shell thickness change data of the battery cell on the disassembly path.

[0024] In some embodiments, the battery cell sample is identical to the product information of the battery cell.

[0025] In a fourth aspect, the present application provides a battery cell disassembly device, the device comprising: a power determination module, used to determine an output power curve corresponding to the disassembly path according to shell thickness change data of the battery cell on the disassembly path; a battery cell disassembly module, used to control a disassembly device to disassemble the battery cell along the disassembly path according to the output power curve; wherein the shell thickness change data is obtained by the battery cell shell detection method described in any of the above embodiments.

[0026] In a fifth aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the method in the implementation of the first aspect or the second aspect when executing the computer program.

[0027] In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the method in the implementation of the first aspect or the second aspect.

[0028] In a seventh aspect, the present application provides a computer program product, which, when running on a computer, enables the computer to execute the method in any optional implementation of the first aspect or the second aspect.

[0029] In an eighth aspect, the present application provides a battery cell disassembly system, comprising the electronic device in the fifth aspect above, and a disassembly device for disassembling the battery cell; the electronic device is connected to the disassembly device. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0031] Figure 1 A first flow chart of a method for detecting a battery cell shell in some embodiments of the present application;

[0032] Figure 2 A schematic diagram of the disassembly path of some embodiments of the present application;

[0033] Figure 3 A schematic diagram of the current shell outline of some embodiments of the present application;

[0034] Figure 4 A schematic diagram of shell thickness distribution in some embodiments of the present application;

[0035] Figure 5 A schematic diagram of sample points of curve samples of some embodiments of the present application;

[0036] Figure 6 A second flow chart of a method for detecting a shell of a battery cell according to some embodiments of the present application;

[0037] Figure 7 A schematic diagram of a target coordinate system for some embodiments of the present application;

[0038] Figure 8 A schematic diagram of another target coordinate system in some embodiments of the present application;

[0039] Fig. 9 A third flow chart of a battery cell shell detection method according to some embodiments of the present application;

[0040] Fig.10 A flowchart of a method for disassembling a battery cell according to some embodiments of the present application;

[0041] Fig.11 A schematic diagram of output power curves of some embodiments of the present application;

[0042] Fig.12 This is a schematic structural diagram of a shell detection device for a battery cell in some embodiments of the present application;

[0043] Fig.13 A schematic diagram of the structure of a battery cell disassembly device according to some embodiments of the present application;

[0044] Fig.14 A schematic diagram of the structure of an electronic device according to some embodiments of the present application;

[0045] Fig.15 This is a schematic diagram of the structure of a battery cell disassembly system according to some embodiments of the present application.

[0046] The reference numerals in the specific implementation manner are as follows:

[0047] Non-dense sampling area-10; dense sampling area-20; 501-curve generation module; 502-shell detection module; 601-power determination module; 602-battery cell disassembly module; 70-electronic device; 701-processor; 702-memory; 703-communication bus; 80-disassembly equipment. DETAILED DESCRIPTION

[0048] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0050] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0051] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0053] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0054] In the structure of the battery, the battery cell is an important component. The battery cell includes a shell and a bare battery cell disposed in the shell. In order to facilitate the recycling or testing of the battery cell, the shell of the battery cell is usually disassembled to obtain the bare battery cell for recycling or testing.

[0055] In the related art, the disassembly of the battery cell is to determine the disassembly path for the battery cell and then disassemble the battery cell according to the thickness of the battery cell shell. However, during the use of the battery cell, the internal bare battery cell will swell to varying degrees, causing the bare battery cell to squeeze the shell, causing the thickness of the battery cell shell to change. At this time, if the change in the shell thickness of the battery cell on the disassembly path cannot be determined, the bare battery cell inside the shell may be damaged during disassembly, causing thermal runaway of the battery cell.

[0056] In view of the above technical problems, the embodiment of the present application obtains the current shell contour of the battery cell through the disassembly path of the battery cell, and obtains the shell thickness change data of the battery cell on the disassembly path according to the shell thickness distribution data corresponding to the target curve sample matching the current shell contour in each shell contour sample. Therefore, the shell thickness distribution data corresponding to the shell contour sample matching the shell contour can be used to predict the shell thickness change of the battery cell on the disassembly path, thereby reducing the probability of thermal runaway of the battery cell when the battery cell is disassembled by using the shell thickness.

[0057] The shell detection method of the battery cell and the disassembly method of the battery cell disclosed in the embodiment of the present application can be applied to the terminal device to detect the change of the shell thickness of the battery cell on the disassembly path, and control the disassembly equipment to disassemble the battery cell. Among them, the terminal device can be any terminal device such as a mobile terminal, a desktop terminal, a vehicle terminal or a server. The server can be an independent server or a server cluster composed of multiple servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence sampling point equipment.

[0058] According to some embodiments of the present application, a battery cell shell detection method is provided, and the battery cell shell detection method can be applied to the aforementioned terminal device. Figure 1 As shown, the shell detection method of the battery cell includes:

[0059] S101, obtaining a current shell profile of the battery cell according to a disassembly path of the battery cell;

[0060] S102, obtaining shell thickness variation data of the battery cell along the disassembly path according to shell thickness distribution data corresponding to a target curve sample matching the current shell profile in each shell profile sample;

[0061] The shell contour sample is determined according to the historical disassembly path of the battery cell sample, and the shell thickness distribution data corresponding to the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample.

[0062] In some embodiments, the battery cell may be a square battery cell, a cylindrical battery cell, or a battery cell of any other shape. The battery cell disassembly path L refers to the path for disassembling the battery cell shell, such as cutting the battery cell. Figure 2 As shown. The disassembly path of the battery cell can be set according to the actual situation. If it can be set by the user, it can be uploaded to the terminal device. After the terminal device obtains the disassembly path of the battery cell, it can sample the battery cell along the disassembly path to obtain multiple sampling points of the battery cell on the disassembly path. Exemplarily, the path formed by the disassembly path on the shell of the battery cell can be determined as the sampling area of ​​the battery cell, so that the sampling area can be sampled at a certain sampling frequency through a sensor, such as an infrared sensor, to obtain multiple sampling points of the battery cell on the disassembly path.

[0063] After obtaining multiple sampling points of the battery cell on the disassembly path, multiple sampling points can be fitted. For example, by connecting two adjacent sampling points, the current shell contour of the battery cell can be obtained. Figure 3 The current shell contour can represent the shell contour of the battery cell on the disassembly path.

[0064] After obtaining the current shell contour of the battery cell, a shell contour sample matching the current shell contour can be obtained from a database storing different shell contour samples and shell thickness distribution data corresponding to different shell contour samples, and determined as a target curve sample. For example, the current shell contour can be matched with each shell contour sample in the database for similarity, so as to obtain a shell contour sample whose similarity with the current shell contour reaches a preset similarity, such as a shell contour sample whose similarity reaches more than 95% or reaches 100%, and is determined as a target curve sample matching the current shell contour.

[0065] Among them, the shell contour sample can be determined according to the historical disassembly path of the battery cell sample, and the battery cell sample can be a battery cell that has undergone shell thickness detection. Exemplarily, for any battery cell sample, its historical disassembly path and the contour formed by the shell of the battery cell sample on the historical disassembly path can be recorded, that is, the shell contour sample. After obtaining the shell contour sample, each point on the shell contour sample can be sampled at a certain sampling frequency to obtain multiple sample points, and the shell of the battery cell sample can be measured, and the shell thickness corresponding to each sample point can be composed of the shell thickness distribution data corresponding to the shell contour sample.

[0066] The shell thickness corresponding to any sample point can be determined based on the distance between the sample point and the bare cell of the cell sample. For example, the minimum distance between the sample point and the bare cell of the cell sample can be determined as the shell thickness corresponding to the sample point. For example, assuming that the shell thickness distribution of the cell sample along the historical disassembly path is measured by radiographic imaging, such as X-ray imaging or CT scanning, or other detection methods, as shown in FIG. Figure 4 As shown, for the shell contour sample A formed on the historical disassembly path of the battery sample, the minimum distance between any sample point A' and the bare battery B is taken as the shell thickness corresponding to the sample point A'.

[0067] After obtaining the target curve sample matching the current shell profile from each shell profile sample, since the target curve sample matches the current shell profile, the shell expansion degree corresponding to the target curve sample can reflect the shell expansion degree corresponding to the current shell profile. At this time, the shell thickness distribution data of the current shell profile can be obtained according to the shell thickness distribution data corresponding to the target curve sample, so as to obtain the shell thickness change data of the battery cell on the disassembly path according to the shell thickness distribution data of the current shell profile.

[0068] Exemplarily, after obtaining the shell thickness distribution data corresponding to the target curve sample, that is, the shell thickness corresponding to any sample point on the target curve sample, the shell thickness corresponding to the sample point can be determined as the shell thickness corresponding to the point on the current shell contour that matches each sample point, so as to obtain the shell thickness corresponding to each point on the current shell contour that matches each sample point, the shell thickness corresponding to each point, that is, the shell thickness distribution data constituting the current shell contour, so as to use the shell thickness distribution data of the current shell contour as the shell thickness change data of the battery cell on the disassembly path. Alternatively, the shell thickness distribution data of the current shell contour can be formed with a certain point of the current shell contour as the starting point and in a certain path direction of the disassembly path to form a shell thickness change curve that changes with the disassembly path as the shell thickness change data of the battery cell on the disassembly path.

[0069] Considering that the specifications and materials of the battery cell will affect the swelling of the battery cell, in order to make the shell swelling degree corresponding to the shell contour sample obtained through the battery cell sample more accurately reflect the shell swelling degree corresponding to the current shell contour, in some embodiments, the battery cell sample and the battery cell have the same product information. Among them, the product information includes the battery cell model, battery cell size, and the shell material of the battery cell. Since the battery cell sample and the battery cell have the same product information, the swelling effect on the battery cell sample is basically the same as the swelling effect on the battery cell, so that the shell swelling degree corresponding to the target curve sample obtained by using the battery cell sample can be approximately regarded as the shell swelling degree corresponding to the current shell contour, thereby improving the credibility of the shell thickness change data obtained by using the shell thickness change data corresponding to the target curve sample, and then improving the accuracy of the shell thickness detection of the battery cell.

[0070] The current shell profile of the battery cell is obtained through the disassembly path of the battery cell, and the shell thickness change data of the battery cell on the disassembly path is obtained according to the shell thickness distribution data corresponding to the target curve sample matching the current shell profile in each shell profile sample. Therefore, the shell thickness distribution data corresponding to the shell profile sample matching the shell profile can be used to predict the shell thickness change of the battery cell on the disassembly path, thereby reducing the probability of thermal runaway of the battery cell when the shell thickness is used to disassemble the battery cell.

[0071] In order to more accurately determine the change in shell thickness of the battery cell on the disassembly path, in some embodiments, the method further includes: sampling a sub-area in the shell contour sample where the deformation amount is less than a preset deformation amount according to a first sampling frequency, and sampling a sub-area in the shell contour sample where the deformation amount reaches a preset deformation amount according to a second sampling frequency greater than the first sampling frequency, to obtain each of the sample points; and obtaining shell thickness distribution data corresponding to the shell contour sample according to the shell thickness corresponding to each sample point.

[0072] In some embodiments, after obtaining the shell contour of the battery sample on a certain historical disassembly path, i.e., the shell contour sample, the shell contour sample can be segmented to divide the shell contour sample into multiple curve segments, i.e., multiple sub-regions. The segmentation of the shell contour sample can be set according to actual conditions.

[0073] As a possible implementation, it is assumed that the battery cell sample is a square battery cell. When the shell of the square battery cell bulges, it usually presents a morphology of thin ends and thick middle, that is, the rounded area at the junction of the long and short sides will be more severely deformed. Therefore, if the shell contour sample is a curve passing through the rounded area, such as a shell contour formed around a square battery cell, the shell contour sample can be segmented according to the size of the rounded area, such as first dividing the curve segments of each rounded area into sub-areas, and then dividing the curve segments outside the rounded area according to the length of the curve segments of the rounded area, thereby obtaining multiple sub-areas of the shell contour sample; or, the curve segments of each rounded area can be divided into sub-areas first, and then the curve segments between any two rounded areas can be divided into sub-areas, thereby obtaining multiple sub-areas of the shell contour sample. The rounded area can be an area formed by a curve segment within 15mm-25mm of the rounded corner and its periphery, such as an area formed by a curve segment within 20mm of the rounded corner and its periphery.

[0074] As another possible implementation, assuming that the battery cell sample is a cylindrical battery cell, when the shell of the cylindrical battery cell bulges, the deformation of the fillet area at the junction of the bottom and the side surface will be more serious. Therefore, if the shell contour sample is a shell contour passing through the fillet area at the junction of the bottom and the side surface, such as the shell contour formed around the upper and lower bottom surfaces and the side surfaces of the cylindrical battery cell, the shell contour sample can also be segmented according to the size of the fillet area.

[0075] Similarly, other shell contour samples formed by the rounded corners of the battery cell samples can also be segmented in the same way to form multiple sub-areas.

[0076] As another possible implementation, assuming that the battery cell sample is a cylindrical battery cell, and the shell contour sample is a shell contour that does not pass through the rounded corner area, such as a shell contour formed around the side of the cylindrical battery cell, then the shell contour formed at this time is approximately an arc or a circle. Therefore, the shell contour sample can be segmented according to a preset central angle size, such as using a curve segment corresponding to a central angle of N° as a sub-area of ​​the shell contour sample, thereby obtaining multiple sub-areas of the shell contour sample.

[0077] For any sub-region of the shell contour sample, the deformation amount of the sub-region can be measured, such as the change in shell thickness of the sub-region, so as to compare the deformation amount of the sub-region with the preset deformation amount, such as comparing the change in shell thickness of the sub-region with the preset thickness change. Among them, the change in shell thickness of the sub-region of the shell contour sample can refer to the percentage change in shell thickness of the sub-region, which is determined by the shell thickness measured in the sub-region when the battery cell sample does not bulge, such as when it is just out of the factory, and the current shell thickness of the sub-region. If the deformation amount of the sub-region is less than the preset deformation amount, such as the change in shell thickness of the sub-region is less than the preset change, the sub-region is determined as a non-dense sampling region 10, so as to sample the sub-region starting from any boundary of the sub-region at a first sampling frequency. If the deformation amount of the sub-region reaches the preset deformation amount, such as the change in shell thickness of the sub-region reaches the preset change, the sub-region is determined as a dense sampling region 20, so as to sample the sub-region starting from any boundary of the sub-region at a second sampling frequency having a frequency greater than the first sampling frequency, thereby obtaining each sample point of the shell contour sample, such as Figure 5 shown.

[0078] By sampling the sub-region in the shell contour sample whose deformation amount is less than the preset deformation amount according to the first sampling frequency, and sampling the sub-region in the shell contour sample whose deformation amount reaches the preset deformation amount according to the second sampling frequency which is greater than the first sampling frequency, each sample point is obtained, and the shell thickness distribution data corresponding to the shell contour sample is obtained according to the shell thickness corresponding to each sample point, so that based on the deformation amount of the region, the region with a large shell thickness change can be encrypted sampled, so that the acquired shell thickness distribution data can more accurately reflect the shell thickness distribution of the shell contour sample, and then the shell thickness distribution data corresponding to the shell contour sample matching the shell contour can be used to predict the shell thickness change data of the battery cell on the disassembly path, so as to more accurately reflect the shell thickness change of the battery cell on the disassembly path.

[0079] To further improve the accuracy of the detected change in shell thickness of the battery cell on the disassembly path, in some embodiments, the current shell contour of the battery cell is obtained according to the disassembly path of the battery cell, including: determining a sampling area of ​​the battery cell according to the disassembly path; sampling a first area in the sampling area of ​​the battery cell where a deformation amount is less than a preset deformation amount according to a first sampling frequency, and sampling a second area in the sampling area of ​​the battery cell where a deformation amount reaches a preset deformation amount according to a second sampling frequency greater than the first sampling frequency, to obtain sampling points of the battery cell on the disassembly path; and obtaining the current shell contour according to each sampling point.

[0080] In some embodiments, after determining the disassembly path of the battery cell, the path formed by the disassembly path on the shell of the battery cell can be determined as the sampling area of ​​the battery cell. For the sampling area, the sampling area can be segmented to divide the sampling area into multiple sub-areas. The segmentation of the sampling area can be set according to actual conditions.

[0081] As a possible implementation, assuming that the battery cell is a square battery cell, and the sampling area includes the rounded corner area of ​​the battery cell, if the sampling area is formed around the square battery cell, the sampling area can be segmented according to the size of the rounded corner area, such as first dividing the curve segments of each rounded corner area into sub-areas, and then dividing the curve segments outside the rounded corner area according to the length of the curve segments of the rounded corner area, thereby obtaining multiple sub-areas of the sampling area; or, the curve segments of each rounded corner area can be divided into sub-areas first, and then the curve segments between any two rounded corner areas can be divided into sub-areas, thereby obtaining multiple sub-areas of the sampling area.

[0082] As another possible implementation, assuming that the battery cell sample is a cylindrical battery cell, and the sampling area is the shell contour of the rounded area passing through the junction of the bottom and the side, such as the sampling area formed around the upper and lower bottom surfaces and sides of the cylindrical battery cell, the sampling area can also be divided according to the size of the rounded area to obtain multiple sub-areas of the sampling area.

[0083] As another possible implementation, assuming that the battery cell sample is a cylindrical battery cell, and the sampling area sample is a sampling area that does not pass through the rounded area, such as a sampling area formed around the side of the cylindrical battery cell, then the sampling area formed at this time is approximately an arc or a circle. Therefore, the shell contour sample can be segmented according to the preset central angle size, such as using the curve segment corresponding to the central angle of N° as a sub-area of ​​the sampling area, thereby obtaining multiple sub-areas of the sampling area.

[0084] After obtaining multiple sub-areas of the sampling area, the probability of deformation in the sub-area can be counted through big data, such as the deformation of each battery sample in the corresponding sub-area. Exemplarily, the probability that the shell thickness change of a certain sub-area reaches a preset change can be counted. If the deformation probability of the sub-area is less than the preset probability, the sub-area can be determined to be the first area, otherwise, the sub-area can be determined to be the second area. The preset probability can be set according to the actual situation. After determining the first area and the second area, the first area can be sampled at a first sampling frequency, and the second area can be sampled at a second sampling frequency greater than the first sampling frequency to obtain each sampling point of the battery on the disassembly path to form the current shell contour. Thus, the area with a larger probability of shell thickness change can be encrypted and sampled, so that the current shell contour obtained is more accurate, so as to improve the accuracy of the target curve sample matched with the current shell contour, and then improve the accuracy of the shell thickness change of the battery obtained by using the shell thickness change data corresponding to the target curve sample.

[0085] Taking into account that there may be more than one target curve sample matching the current shell contour, in some embodiments, the shell thickness change data of the battery cell on the disassembly path is obtained according to the shell thickness distribution data corresponding to the target curve sample matching the current shell contour in each shell contour sample, including: determining the shell thickness value corresponding to each point on the current shell contour according to the shell thickness distribution data corresponding to each target curve sample; obtaining the shell thickness change data of the battery cell on the disassembly path according to the shell thickness value corresponding to each point on the current shell contour.

[0086] In some embodiments, if multiple target curve samples that match the current shell contour, such as the same as the current shell contour, are obtained from each shell contour sample, then after determining the shell thickness distribution data corresponding to each target curve sample one by one, all sample points in each shell thickness distribution data can be combined into a sample point set, and the shell thickness corresponding to any sample point in the sample point set in each shell thickness distribution data can be obtained.

[0087] If the shell thickness corresponding to the sample point is one, the shell thickness can be determined as the shell thickness corresponding to the sample point; if there are multiple shell thicknesses corresponding to the sample point, one of the multiple shell thicknesses corresponding to the sample point can be selected and determined as the shell thickness value corresponding to the sample point; or, the average shell thickness calculated through multiple shell thicknesses can be determined as the shell thickness value corresponding to the sample point.

[0088] After obtaining the shell thickness value corresponding to each sample point in the sample point set, the shell thickness value corresponding to any sample point can be determined as the shell thickness value corresponding to the target point matching the sample point on the current shell contour, and the shell thickness value corresponding to each target point matching the sample point set on the current shell contour is obtained, so as to determine the shell thickness value corresponding to each point on the current shell contour according to the shell thickness value corresponding to each target point. For example, each target point is taken as each point on the current shell contour, so as to determine the shell thickness value corresponding to each target point as the shell thickness value corresponding to each point on the current shell contour, thereby forming the shell thickness distribution data of the current shell contour. Alternatively, a certain target point can be taken as the starting point, and the shell thickness value corresponding to each target point can be fitted according to a certain path direction of the disassembly path to obtain a shell thickness change curve that changes with the disassembly path, so as to obtain the shell thickness value corresponding to each point through the shell thickness change curve, and the shell thickness value corresponding to each point can be used to form the shell thickness distribution data of the current shell contour. That is, the shell thickness change curve can be determined as the shell thickness distribution data of the current shell contour.

[0089] Since there are usually different sampling points in the shell thickness distribution data corresponding to each target curve sample, the shell thickness distribution data corresponding to multiple target curve samples matching the current shell contour can be used to determine the shell thickness values ​​of more points on the current shell contour, thereby making the shell thickness change data of the battery cell on the disassembly path more accurate.

[0090] In order to further reduce the possibility of damaging the bare battery cell when the battery cell is subsequently disassembled using the detected shell thickness, in some embodiments, Figure 6 As shown, according to the shell thickness distribution data corresponding to each target curve sample, the shell thickness value corresponding to each point on the current shell contour is determined, including:

[0091] S201, according to any sample point of any target curve sample, and the minimum shell thickness corresponding to each shell thickness distribution data, determining a shell thickness value corresponding to a target point on the current shell contour that matches the sample point;

[0092] S202: Determine the shell thickness value corresponding to each point on the current shell contour according to the shell thickness value corresponding to each target point.

[0093] In some embodiments, after determining each shell thickness distribution data corresponding one-to-one to each target curve sample, all sample points in each shell thickness distribution data are combined into a sample point set, and the shell thickness corresponding to any sample point in the sample point set in each shell thickness distribution data is obtained.

[0094] If the shell thickness corresponding to the sample point is one, the shell thickness can be determined as the minimum shell thickness corresponding to the sample point; if there are multiple shell thicknesses corresponding to the sample point, the minimum shell thickness corresponding to the sample point can be determined from the multiple shell thicknesses corresponding to the sample point.

[0095] After obtaining the minimum shell thickness corresponding to each sample point in the sample point set, the minimum shell thickness corresponding to any sample point can be determined as the shell thickness value corresponding to the target point matching the sample point on the current shell contour, so as to obtain the shell thickness value corresponding to each target point matching the sample point set on the current shell contour. Thus, the shell thickness value corresponding to each point on the current shell contour is determined according to the shell thickness value corresponding to each target point. In this way, when the shell thickness corresponding to the same point on the current shell contour is different, the shell thickness with a smaller thickness value can be taken as the shell thickness corresponding to the point, thereby reducing the disassembly depth when disassembling using the shell thickness, thereby reducing the possibility of damaging the internal bare cell of the battery cell during disassembly, and further reducing the probability of causing thermal runaway of the battery cell when disassembling the battery cell using the shell thickness.

[0096] Considering the shell thickness values ​​corresponding to the target points on the current shell contour that match the sample points of each target curve sample, when determining the shell thickness values ​​corresponding to each point on the current shell contour, since the sample points in the shell thickness distribution data may be limited, the number of target points is also limited, resulting in the shell thickness values ​​corresponding to each point on the current shell contour may be missing. To this end, in some embodiments, according to the shell thickness values ​​corresponding to each target point, the shell thickness values ​​corresponding to each point on the current shell contour are determined, including: according to the shell thickness values ​​corresponding to each target point and the shell bulging height corresponding to each target point, a fitting model representing the corresponding relationship between the bulging height and the shell thickness is obtained; the shell bulging height corresponding to each point on the current shell contour is input into the fitting model to obtain the shell thickness values ​​corresponding to each point on the current shell contour.

[0097] Among them, the shell bulging height corresponding to the target point can be determined according to the coordinate position of the target point in the target coordinate system and the initial size information of the battery cell. The target coordinate system can be constructed according to any reference point of the battery cell.

[0098] The initial size information of the battery cell refers to the pre-set size of the battery cell when it is not swollen. If the battery cell is a square battery cell, the initial size includes the length, width and height of the battery cell; if the battery cell is a cylindrical battery cell, the initial size includes the bottom radius and height of the battery cell.

[0099] In some embodiments, a target coordinate system can be constructed with any reference point of the battery cell as the origin, and then an initial model of the battery cell can be constructed in the target coordinate system based on the initial size information of the battery cell, and the target point can be mapped to the target coordinate system to determine the minimum distance between the target point and the initial model as the shell bulge height corresponding to the target point.

[0100] As a possible implementation, taking the battery cell as a square battery cell as an example, a certain side corner of the square battery cell can be used as a reference point, or the center of the square battery cell can be used as a reference point, and the length, width and height of the square battery cell can be used to determine the X-axis, Y-axis and Z-axis respectively, and a three-dimensional coordinate system can be constructed as the target coordinate system. Alternatively, taking the battery cell as a cylindrical battery cell as an example, the dot on the bottom surface of the cylindrical battery cell can be used as a reference point, or the center of the cylindrical battery cell can be used as a reference point, and the radius and height of the cylindrical battery cell can be used to construct a three-dimensional coordinate system as the target coordinate system. After obtaining the target coordinate system, a three-dimensional initial model of the battery cell can be constructed in the target coordinate system based on the initial size information of the battery cell, and the target point can be mapped to the target coordinate system to determine the minimum distance between the target point and the three-dimensional initial model as the shell bulge height corresponding to the target point.

[0101] As another possible implementation, taking the battery cell as a square battery cell as an example, if the disassembly path is a path for unilateral disassembly along the length of the battery cell, or a path for unilateral disassembly along the width of the battery cell, or a path for disassembly along the length and width, the midpoint of the rectangle formed by the length and width can be used as the reference point to construct an X-axis and a Y-axis parallel to the length and width, respectively, so as to use the formed two-dimensional coordinate system as the target coordinate system. Alternatively, the corner at the intersection of the length and width can be used as the reference point, and the two corners on the same side of the reference point can be used to form an X-axis or Y-axis, and a perpendicular line to the X-axis or Y-axis can be made through the reference point to construct a two-dimensional coordinate system as the target coordinate system. Alternatively, the midpoint of the width can be taken as the reference point, and a straight line can be established through the two corners on one side of the reference point, which is the X-axis or Y-axis, and a perpendicular line to the X-axis or Y-axis can be made through the reference point, so as to construct a two-dimensional coordinate system as the target coordinate system.

[0102] After the target coordinate system is constructed, the initial model of the battery cell can be constructed in the target coordinate system according to the length and width of the initial size information of the battery cell. Then, any target point is mapped to the target coordinate system, and the minimum distance between the target point and the initial model is used as the shell bulge height corresponding to the target point. Figure 7 As shown in the figure, assuming that the disassembly path is a unilateral disassembly path along the length of the battery cell, the target coordinate system constructed at this time takes the midpoint of the width of the battery cell as the reference point, the width of the battery cell as the Y axis, and the length of the initial model Q is a and the width is b. If the coordinates of the target point D in the target coordinate system are (x, y), the shell bulging height corresponding to the target point can be obtained as |yb / 2|.

[0103] Similarly, if the disassembly path is a unilateral disassembly path along the height of the battery cell, or a unilateral disassembly path along the width of the battery cell, or a disassembly path around the height and width, the shell bulging height corresponding to the target point can also be determined in the above manner.

[0104] As another possible implementation, taking the battery cell as a cylindrical battery cell as an example, if the disassembly path is a path for unilateral disassembly along the height of the battery cell, or a path for disassembly along the side and bottom, the midpoint of the rectangle formed by the bottom diameter and the side height is used as the reference point, and the X-axis and Y-axis parallel to the bottom diameter and the side height are constructed, so as to use the formed two-dimensional coordinate system as the target coordinate system. Alternatively, the corner at the intersection of the bottom diameter and the side height can be used as the reference point, the bottom diameter can be used as the X-axis or Y-axis, and a vertical line of the X-axis or Y-axis can be made through the reference point to construct a two-dimensional coordinate system as the target coordinate system. Alternatively, the midpoint of the bottom diameter can be taken as the reference point, and a straight line can be established through the two corners on one side of the reference point, which is the X-axis or Y-axis, and a vertical line of the X-axis or Y-axis can be made through the reference point, so as to construct a two-dimensional coordinate system as the target coordinate system. After completing the construction of the target coordinate system, the initial model of the battery cell can be constructed in the target coordinate system according to the diameter and height in the initial size information of the battery cell. Then, any target point is mapped to the target coordinate system, so that the minimum distance between the target point and the initial model is used as the shell bulging height corresponding to the target point.

[0105] As another possible implementation, taking the battery cell as a cylindrical battery cell as an example, if the disassembly path is a path for disassembly along the edge of the bottom surface of the battery cell, the center of the bottom surface can be used as a reference point to construct a two-dimensional coordinate system as a target coordinate system, and then according to the radius in the initial size information of the battery cell, the initial model Q' of the bottom surface of the battery cell is constructed in the target coordinate system, such as Figure 8 Then, any target point is mapped to the target coordinate system, and the minimum distance between the target point and the initial model Q' is used as the shell bulging height corresponding to the target point.

[0106] After determining the shell bulging height corresponding to each target point, a fitting model representing the corresponding relationship between the bulging height and the shell thickness can be obtained according to the shell thickness value corresponding to each target point and the shell bulging height corresponding to each target point.

[0107] As a possible implementation, the fitting model may be a pre-trained classification model, which may be an SVM classifier or other AI detection model. For the training of the classification model, the shell bulging height corresponding to each target point may be sequentially input into the pre-built classification model, and each time the predicted shell thickness output by the classification model is obtained, the predicted shell thickness is matched with the shell thickness value corresponding to the shell bulging height input this time.

[0108] When the two do not match, the gradient descent method is used to adjust the network parameters of the fitting model through error back propagation, and then the next training is carried out until the predicted shell thickness obtained after each input of the shell bulging height corresponding to the target point matches the shell thickness value corresponding to the shell bulging height input this time. This means that the training of the classification model is completed and a fitting model representing the corresponding relationship between bulging height and shell thickness is obtained.

[0109] As another possible implementation, the fitting model may be a function fitting model, that is, a function fitting is performed on the shell thickness value and the shell bulging height corresponding to each target point to obtain a fitting model. Exemplarily, the shell bulging height corresponding to each target point may be used as an independent variable, and the shell thickness value corresponding to each target point may be used as a dependent variable. A linear fitting is performed on the shell thickness value and the shell bulging height corresponding to each target point to obtain a fitting model representing the corresponding relationship between the bulging height and the shell thickness.

[0110] After obtaining the fitting model representing the corresponding relationship between the bulging height and the shell thickness, the shell bulging height corresponding to each point on the current shell contour can be input into the fitting model to obtain the shell thickness value corresponding to each point on the current shell contour.

[0111] By obtaining a fitting model representing the correspondence between the bulging height and the shell thickness according to the shell thickness value corresponding to each target point and the shell bulging height corresponding to each target point, the shell bulging height corresponding to each point on the current shell contour is input into the fitting model to obtain the shell thickness value corresponding to each point on the current shell contour, so as to predict and supplement the missing shell thickness value of a certain point on the current shell contour, thereby avoiding the situation where the shell thickness value corresponding to a certain point on the current shell contour is missing, thereby making the acquired shell thickness change data of the battery cell on the disassembly path more comprehensive.

[0112] Taking into account that there may not be a target curve sample matching the current shell contour in each shell contour sample, in order to avoid being unable to detect the shell thickness change data of the battery cell on the disassembly path, in some embodiments, the method also includes: determining that there is no target curve sample matching the current shell contour, obtaining the shell bulging height and shell thickness corresponding to each preset sampling point on the shell of the battery cell sample; obtaining a preset model representing the correspondence between the bulging height and the shell thickness according to the shell bulging height and shell thickness corresponding to the preset sampling points; inputting the shell bulging height corresponding to each point on the current shell contour into the preset model to obtain the shell thickness change data of the battery cell on the disassembly path.

[0113] Among them, the preset sampling point can be any point on the shell of the battery cell sample. The shell bulge height corresponding to the preset sampling point can be determined according to the coordinate position of the preset sampling point in the preset coordinate system and the initial size information of the battery cell sample. The preset coordinate system can be constructed according to any reference point of the battery cell sample.

[0114] The initial size information of the battery cell sample refers to the pre-set battery cell size of the battery cell sample when no swelling occurs. If the battery cell sample is a square battery cell, the initial size includes the length, width and height of the battery cell sample; if the battery cell sample is a cylindrical battery cell, the initial size includes the bottom radius and height of the battery cell sample.

[0115] In some embodiments, a preset coordinate system can be constructed with any reference point of the battery cell sample as the origin, and then an initial model of the battery cell sample is constructed in the preset coordinate system based on the initial size information of the battery cell sample, and the preset sampling point is mapped to the target coordinate system to determine the minimum distance between the preset sampling point and the initial model as the shell bulge height corresponding to the preset sampling point.

[0116] For example, taking the battery cell sample as a square battery cell, a certain side corner of the square battery cell can be used as a reference point, or the center of the square battery cell can be used as a reference point, and the length, width and height of the square battery cell can be used to determine the X-axis, Y-axis and Z-axis respectively, to construct a three-dimensional coordinate system as the preset coordinate system. Alternatively, taking the battery cell sample as a cylindrical battery cell, for example, the dot on the bottom surface of the cylindrical battery cell can be used as a reference point, or the center of the cylindrical battery cell can be used as a reference point, and the radius and height of the cylindrical battery cell can be used to construct a three-dimensional coordinate system as the preset coordinate system. After obtaining the preset coordinate system, a three-dimensional initial model of the battery cell sample can be constructed in the preset coordinate system based on the initial size information of the battery cell sample, and the preset sampling point can be mapped to the preset coordinate system, so that the minimum distance between the preset sampling point and the three-dimensional initial model is determined as the shell bulging height corresponding to the preset sampling point.

[0117] After determining the shell bulging height corresponding to each preset sampling point, a preset model representing the corresponding relationship between the bulging height and the shell thickness can be obtained according to the shell thickness value corresponding to each preset sampling point and the shell bulging height corresponding to each preset sampling point.

[0118] As a possible implementation, the preset model may be a pre-trained classification model, which may be an SVM classifier or other AI detection model. For the training of the classification model, the shell bulging height corresponding to each preset sampling point may be sequentially input into the pre-built classification model, and each time the predicted shell thickness output by the classification model is obtained, the predicted shell thickness is matched with the shell thickness value corresponding to the shell bulging height input this time.

[0119] When the two do not match, the gradient descent method is used to adjust the network parameters of the preset model through error back propagation, and then the next training is carried out until the predicted shell thickness obtained after each input of the shell bulging height corresponding to the preset sampling point matches the shell thickness value corresponding to the shell bulging height input this time. This means that the training of the classification model is completed and the preset model representing the correspondence between the bulging height and the shell thickness is obtained.

[0120] As another possible implementation, the preset model may be a function model, that is, a function fitting is performed on the shell thickness value and the shell bulging height corresponding to each preset sampling point to obtain the preset model. Exemplarily, the shell bulging height corresponding to each preset sampling point may be used as an independent variable, and the shell thickness value corresponding to each preset sampling point may be used as a dependent variable. A linear fitting is performed on the shell thickness value and the shell bulging height corresponding to each preset sampling point to obtain a preset model representing the corresponding relationship between the bulging height and the shell thickness.

[0121] After obtaining the preset model representing the correspondence between the bulging height and the shell thickness, the shell bulging height corresponding to each point on the current shell contour can be input into the preset model to obtain the shell thickness value corresponding to each point on the current shell contour.

[0122] In the absence of a target curve sample matching the current shell contour, a preset model representing the correspondence between bulging height and shell thickness is obtained according to the shell thickness values ​​corresponding to each preset sampling point on the shell of the battery cell sample and the shell bulging height corresponding to each preset sampling point, so that the shell bulging height corresponding to each point on the current shell contour is input into the preset model to obtain the shell thickness value corresponding to each point on the current shell contour. Therefore, even if there is no target curve sample matching the current shell contour, the shell thickness value of each point on the current shell contour can be predicted by the preset model representing the correspondence between bulging height and shell thickness, so as to determine the shell thickness change data of the battery cell on the disassembly path, thereby improving the reliability of shell thickness change detection.

[0123] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution in the present application will be described clearly and completely below. In some embodiments, Fig. 9 As shown, the shell detection method of the battery cell includes:

[0124] S301, determining a sampling area of ​​the battery cell according to a disassembly path of the battery cell.

[0125] S302, according to the first sampling frequency, sampling the first area in the sampling area of ​​the battery cell where the deformation probability is less than the preset probability, and according to the second sampling frequency greater than the first sampling frequency, sampling the second area in the sampling area of ​​the battery cell where the deformation probability reaches the preset probability, to obtain the sampling points of the battery cell on the disassembly path.

[0126] S303: Obtain the current shell contour according to each sampling point.

[0127] S304, determine whether there is a target curve sample matching the current shell profile in each shell profile sample; if so, execute S305, otherwise, execute S309. The shell profile sample is determined according to the historical disassembly path of the battery cell sample; the battery cell sample has the same product information as the battery cell.

[0128] S305 , according to any sample point of any target curve sample and the minimum shell thickness corresponding to the shell thickness distribution data of each target curve sample, determine the shell thickness value corresponding to the target point on the current shell contour that matches the sample point.

[0129] The shell thickness distribution data of the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample. For determining the shell thickness distribution data of the shell contour sample, the sub-region in the shell contour sample whose deformation amount is less than the preset deformation amount can be sampled according to the first sampling frequency, and the sub-region in the shell contour sample whose deformation amount reaches the preset deformation amount can be sampled according to the second sampling frequency greater than the first sampling frequency to obtain each sample point, so as to obtain the shell thickness distribution data corresponding to the shell contour sample according to the shell thickness corresponding to each sample point.

[0130] S306: Obtain a fitting model representing the corresponding relationship between the bulging height and the shell thickness according to the shell thickness value corresponding to each target point and the shell bulging height corresponding to each target point.

[0131] Among them, the shell bulging height corresponding to the target point can be determined according to the coordinate position of the target point in the target coordinate system and the initial size information of the battery cell. The target coordinate system is constructed according to any reference point of the battery cell.

[0132] S307, inputting the shell bulging height corresponding to each point on the current shell contour into the fitting model to obtain the shell thickness value corresponding to each point on the current shell contour.

[0133] S308, obtaining shell thickness change data of the battery cell along the disassembly path according to the shell thickness value corresponding to each point on the current shell contour.

[0134] S309, obtaining the shell swelling height and shell thickness corresponding to each preset sampling point on the shell of the battery cell sample.

[0135] Among them, the preset sampling point can be any point on the shell of the battery cell sample. The shell bulge height corresponding to the preset sampling point can be determined according to the coordinate position of the preset sampling point in the preset coordinate system and the initial size information of the battery cell sample. The preset coordinate system can be constructed according to any reference point of the battery cell sample.

[0136] S310, obtaining a preset model representing a corresponding relationship between the bulging height and the shell thickness according to the shell bulging height and the shell thickness corresponding to the preset sampling points.

[0137] S311, inputting the shell swelling height corresponding to each point on the current shell contour into a preset model to obtain shell thickness change data of the battery cell on the disassembly path.

[0138] According to some embodiments of the present application, a method for disassembling a battery cell is provided, and the method for disassembling a battery cell can be applied to the aforementioned terminal device. Fig.10 As shown, the disassembly method of the battery cell includes:

[0139] S401, determining an output power curve corresponding to the disassembly path according to the shell thickness change data of the battery cell along the disassembly path;

[0140] S402, controlling a disassembly device to disassemble the battery cell along the disassembly path according to the output power curve;

[0141] The shell thickness variation data is obtained by the shell detection method of the battery cell in any of the above embodiments.

[0142] In some embodiments, after obtaining the shell thickness change data of the battery cell on the disassembly path, since the shell thickness change data includes the shell thickness value corresponding to each point on the disassembly path, the output power W corresponding to each point on the disassembly path can be determined according to the pre-set correspondence between the shell thickness h and the output power W of the disassembly device. The correspondence between the shell thickness h and the output power W of the disassembly device is used to indicate that when the output power of the disassembly device is W, the corresponding disassembled shell thickness is h. The disassembly device can be a cutter device or a laser sensor, etc.

[0143] After determining the output power corresponding to each point on the disassembly path, if there are endpoints in the disassembly path, then one of the endpoints of the disassembly path can be selected as the starting point of the disassembly path; if the disassembly path is a path that goes around the battery cell, then one of the points on the disassembly path can be selected as the starting point of the disassembly path. After determining the starting point of the disassembly path, the output power W corresponding to each point along the path direction of the disassembly path can be calculated to form an output power curve corresponding to the disassembly path. Fig.11 shown.

[0144] After obtaining the output power curve corresponding to the disassembly path, the disassembly equipment can be controlled to adjust the output power according to the output power curve and disassemble the battery cell along the disassembly path starting from the starting point of the disassembly path.

[0145] By determining an output power curve corresponding to the disassembly path according to shell thickness variation data of the battery cell on the disassembly path, and controlling a disassembly device to disassemble the battery cell along the disassembly path according to the output power curve, the cutting depth of the disassembly device at different positions can be adjusted according to the shell thickness variation data of the battery cell on the disassembly path, thereby reducing the probability of thermal runaway of the battery cell when the battery cell is disassembled.

[0146] Fig.12 A schematic structural block diagram of a shell detection device for a battery cell provided in an embodiment of the present application is shown. It should be understood that the device and Figure 1 , Figure 6 as well as Fig. 9 Corresponding to the method embodiment executed in, the steps involved in the aforementioned method can be executed. The specific functions of the device can be found in the description above. To avoid repetition, detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device. Specifically, the device includes: a curve generation module 501, which is used to obtain the current shell contour of the battery cell according to the disassembly path of the battery cell; a shell detection module 502, which is used to obtain the shell thickness change data of the battery cell on the disassembly path according to the shell thickness distribution data corresponding to the target curve sample matching the current shell contour in each shell contour sample; wherein, the shell contour sample is determined according to the historical disassembly path of the battery cell sample, and the shell thickness distribution data corresponding to the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample.

[0147] In the technical solution of the embodiment of the present application, the current shell profile of the battery cell is obtained through the disassembly path of the battery cell, so as to obtain the shell thickness change data of the battery cell on the disassembly path according to the shell thickness distribution data corresponding to the target curve sample matching the current shell profile in each shell profile sample. Therefore, the shell thickness distribution data corresponding to the shell profile sample matching the shell profile can be used to predict the shell thickness change of the battery cell on the disassembly path, thereby reducing the probability of thermal runaway of the battery cell when the battery cell is disassembled by using the shell thickness.

[0148] According to some embodiments of the present application, the curve generation module 501 is also used to: sample the sub-area in the shell contour sample where the deformation variable is less than the preset deformation variable according to a first sampling frequency, and sample the sub-area in the shell contour sample where the deformation variable reaches the preset deformation variable according to a second sampling frequency greater than the first sampling frequency, to obtain each of the sample points; and obtain the shell thickness distribution data corresponding to the shell contour sample according to the shell thickness corresponding to each sample point.

[0149] According to some embodiments of the present application, the curve generation module 501 is specifically used to: determine the sampling area of ​​the battery cell according to the disassembly path; sample the first area in the sampling area of ​​the battery cell where the deformation probability is less than a preset probability according to a first sampling frequency, and sample the second area in the sampling area of ​​the battery cell where the deformation probability reaches a preset probability according to a second sampling frequency greater than the first sampling frequency, to obtain the sampling points of the battery cell on the disassembly path; and obtain the current shell contour according to each of the sampling points.

[0150] According to some embodiments of the present application, the shell detection module 502 is specifically used to: determine the shell thickness value corresponding to each point on the current shell contour according to the shell thickness distribution data corresponding to each target curve sample; and obtain the shell thickness change data of the battery cell on the disassembly path according to the shell thickness value corresponding to each point on the current shell contour.

[0151] According to some embodiments of the present application, the shell detection module 502 is specifically used to: determine the shell thickness value corresponding to the target point on the current shell contour that matches the sample point based on any sample point of any of the target curve samples and the minimum shell thickness corresponding to the sample point in each of the shell thickness distribution data; determine the shell thickness value corresponding to each point on the current shell contour based on the shell thickness value corresponding to each of the target points.

[0152] According to some embodiments of the present application, the shell detection module 502 is specifically used to: obtain a fitting model representing the correspondence between the bulging height and the shell thickness according to the shell thickness value corresponding to each of the target points and the shell bulging height corresponding to each of the target points; input the shell bulging height corresponding to each point on the current shell contour into the fitting model to obtain the shell thickness value corresponding to each point on the current shell contour; wherein the shell bulging height corresponding to the target point is determined according to the coordinate position of the target point in the target coordinate system and the initial size information of the battery cell, and the target coordinate system is constructed according to any reference point of the battery cell.

[0153] According to some embodiments of the present application, the shell detection module 502 is also used to: determine that there is no target curve sample that matches the current shell contour, and obtain the shell swelling height and shell thickness corresponding to each preset sampling point on the shell of the battery cell sample; obtain a preset model representing the correspondence between the swelling height and the shell thickness based on the shell swelling height and shell thickness corresponding to the preset sampling points; input the shell swelling height corresponding to each point on the current shell contour into the preset model to obtain the shell thickness change data of the battery cell on the disassembly path.

[0154] According to some embodiments of the present application, the battery cell sample is the same as the product information of the battery cell.

[0155] Fig.13 A schematic structural block diagram of a battery cell disassembly device provided in an embodiment of the present application is shown. It should be understood that the device and Fig.10 Corresponding to the method embodiment executed in, the steps involved in the aforementioned method can be executed. The specific functions of the device can be found in the description above. To avoid repetition, detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device. Specifically, the device includes: a power determination module 601, which is used to determine the output power curve corresponding to the disassembly path according to the shell thickness change data of the battery cell on the disassembly path; a battery cell disassembly module 602, which is used to control the disassembly equipment along the disassembly path according to the output power curve to disassemble the battery cell; wherein the shell thickness change data is obtained by the shell detection method of the battery cell described in any of the above embodiments.

[0156] In the technical solution of the embodiment of the present application, an output power curve corresponding to the disassembly path is determined according to the shell thickness change data of the battery cell on the disassembly path, so that the disassembly equipment is controlled to disassemble the battery cell along the disassembly path according to the output power curve, so that the cutting depth of the disassembly equipment at different positions can be adjusted according to the shell thickness change data of the battery cell on the disassembly path, thereby reducing the probability of thermal runaway of the battery cell when the battery cell is disassembled.

[0157] According to some embodiments of the present application, Fig.14As shown, an embodiment of the present application provides an electronic device 70, including: a processor 701 and a memory 702, the processor 701 and the memory 702 are interconnected and communicate with each other through a communication bus 703 and / or other forms of connection mechanisms (not marked), the memory 702 stores a computer program executable by the processor 701, and when the computing device is running, the processor 701 executes the computer program to execute a method executed by a terminal device in any optional implementation method, for example: according to the disassembly path of the battery cell, the current shell contour of the battery cell is obtained; according to the shell thickness distribution data corresponding to the target curve sample matching the current shell contour in each shell contour sample, the shell thickness change data of the battery cell on the disassembly path is obtained; wherein the shell contour sample is determined according to the historical disassembly path of the battery cell sample, and the shell thickness distribution data corresponding to the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample. Alternatively, according to the shell thickness change data of the battery cell on the disassembly path, an output power curve corresponding to the disassembly path is determined; according to the output power curve, a disassembly device is controlled to disassemble the battery cell along the disassembly path; wherein the shell thickness change data is obtained by the shell detection method of the battery cell described in any of the above embodiments.

[0158] The present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method in any of the aforementioned optional implementations is executed.

[0159] Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0160] The present application provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the method in any optional implementation manner.

[0161] The present application provides a battery cell disassembly system, such as Fig.15As shown, it includes an electronic device 70 as in the above embodiment, and a disassembling device 80 for disassembling a battery cell; the electronic device 70 is in communication connection with the disassembling device 80 .

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A method for detecting a battery cell shell, characterized in that: The method comprises: According to the disassembly path of the battery cell, a current shell profile of the battery cell is obtained; Obtaining shell thickness variation data of the battery cell on the disassembly path according to shell thickness distribution data corresponding to a target curve sample matching the current shell profile in each shell profile sample; Among them, the shell contour sample is determined according to the historical disassembly path of the battery cell sample, the shell thickness distribution data corresponding to the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample, and the battery cell sample has the same product information as the battery cell.

2. The method according to claim 1, characterized in that The method further comprises: According to a first sampling frequency, a sub-region of the shell contour sample whose deformation amount is less than a preset deformation amount is sampled, and according to a second sampling frequency greater than the first sampling frequency, a sub-region of the shell contour sample whose deformation amount reaches a preset deformation amount is sampled to obtain each of the sample points; According to the shell thickness corresponding to each sample point, shell thickness distribution data corresponding to the shell contour sample is obtained.

3. The method according to claim 1, characterized in that According to the disassembly path of the battery cell, the current shell profile of the battery cell is obtained, including: Determining a sampling area of ​​the battery cell according to the disassembly path; According to a first sampling frequency, a first area in the sampling area of ​​the battery cell where the deformation probability is less than a preset probability is sampled, and according to a second sampling frequency greater than the first sampling frequency, a second area in the sampling area of ​​the battery cell where the deformation probability reaches a preset probability is sampled to obtain sampling points of the battery cell on the disassembly path; The current shell contour is obtained according to each of the sampling points.

4. The method according to any one of claims 1 to 3, characterized in that: According to the shell thickness distribution data corresponding to the target curve sample matching the current shell profile in each shell profile sample, the shell thickness variation data of the battery cell on the disassembly path is obtained, including: Determine the shell thickness value corresponding to each point on the current shell contour according to the shell thickness distribution data corresponding to each target curve sample; According to the shell thickness values ​​corresponding to each point on the current shell contour, shell thickness change data of the battery cell on the disassembly path is obtained.

5. The method according to claim 4, characterized in that Determining the shell thickness value corresponding to each point on the current shell profile according to the shell thickness distribution data corresponding to each target curve sample one by one, including: According to any sample point of any target curve sample, the shell thickness value corresponding to the target point on the current shell contour matching the sample point is determined according to the minimum shell thickness corresponding to each shell thickness distribution data; The shell thickness value corresponding to each point on the current shell contour is determined according to the shell thickness value corresponding to each target point.

6. The method according to claim 5, characterized in that Determining the shell thickness value corresponding to each point on the current shell contour according to the shell thickness value corresponding to each target point includes: According to the shell thickness value corresponding to each of the target points and the shell bulging height corresponding to each of the target points, a fitting model representing the corresponding relationship between the bulging height and the shell thickness is obtained; Inputting the shell bulging height corresponding to each point on the current shell contour into the fitting model to obtain the shell thickness value corresponding to each point on the current shell contour; The shell bulging height corresponding to the target point is determined according to the coordinate position of the target point in the target coordinate system and the initial size information of the battery cell, and the target coordinate system is constructed according to any reference point of the battery cell.

7. The method according to any one of claims 1-3, 5-6, characterized in that: The method further comprises: Determining that there is no target curve sample matching the current shell profile, and obtaining the shell bulging height and shell thickness corresponding to each preset sampling point on the shell of the battery cell sample; According to the shell bulging height and shell thickness corresponding to the preset sampling points, a preset model representing the corresponding relationship between the bulging height and the shell thickness is obtained; Inputting the shell swelling height corresponding to each point on the current shell contour into the preset model to obtain shell thickness change data of the battery cell on the disassembly path; The shell bulging height corresponding to the preset sampling point is determined according to the coordinate position of the preset sampling point in a preset coordinate system and the initial size information of the battery cell sample, and the preset coordinate system is constructed according to any reference point of the battery cell sample.

8. A method for disassembling a battery cell, characterized in that: include: Determining an output power curve corresponding to the disassembly path according to the shell thickness change data of the battery cell along the disassembly path; According to the output power curve, controlling a disassembly device to disassemble the battery cell along the disassembly path; Wherein, the shell thickness change data is obtained by the shell detection method of the battery cell according to any one of claims 1-7.

9. A shell detection device for a battery cell, characterized in that: The device comprises: A curve generation module, used for obtaining the current shell contour of the battery cell according to the disassembly path of the battery cell; A shell detection module, used to obtain shell thickness variation data of the battery cell on the disassembly path according to shell thickness distribution data corresponding to a target curve sample matching the current shell profile in each shell profile sample; Among them, the shell contour sample is determined according to the historical disassembly path of the battery cell sample, the shell thickness distribution data corresponding to the shell contour sample includes the shell thickness corresponding to each sample point on the shell contour sample, and the battery cell sample has the same product information as the battery cell.

10. A battery cell disassembly device, characterized in that: The device comprises: A power determination module, used to determine an output power curve corresponding to the disassembly path according to the shell thickness change data of the battery cell on the disassembly path; A cell disassembly module, used for controlling a disassembly device to disassemble the cell along the disassembly path according to the output power curve; Wherein, the shell thickness change data is obtained by the shell detection method of the battery cell according to any one of claims 1-7.

11. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

13. A battery cell disassembly system, characterized in that: It comprises the electronic device as claimed in claim 11, and a disassembly device for disassembling a battery cell; the electronic device is connected to the disassembly device.

Images