Prediction method for damage time of soft package battery, control equipment and storage medium

Abstract

The invention discloses a method for predicting the damage time of a soft package battery. The prediction method comprises the following steps: acquiring image features of the surface of a damaged soft package battery, determining the shape of a crevasse formed on the surface of the damaged soft package battery according to the image features, and detecting the thickness S0 of the crevasse; a sampling port is formed in the sampling battery, the model of the sampling battery is the same as that of the damaged soft package battery, and the shape and the forming position of the sampling port are the same as those of the crevasse; acquiring a change rate parameter of the thickness Sn of the battery at the sampling port along with time, and establishing a damage time prediction model of the model battery through a linear regression algorithm; and substituting the thickness S0 into the damage time prediction model, and calculating to obtain the damage time of the damaged soft package battery. The invention further discloses a control device and a storage medium. Prediction of the damage time of the soft package battery is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium batteries, and in particular to a method for predicting the damage time of a soft-pack battery, a control device, and a storage medium. Background Art

[0002] Soft-pack batteries use a softer surface as packaging material, so soft-pack batteries are not as prone to violent explosions as hard-pack lithium batteries. However, precisely because the packaging material of soft-pack batteries is relatively soft, they are prone to damage during the manufacturing, transportation and secondary processing of soft-pack batteries. For example, the aluminum-plastic film may be accidentally punctured or scratched by sharp objects during the punching process due to improper punching force or hard foreign matter in the punching mold, or after the battery cell is packaged. When the aluminum-plastic film of the soft-pack battery is damaged, it is easy to cause leakage and corrosion. In addition, impurities such as moisture in the outside air will also enter the battery cell through the damaged port, causing side reactions in the battery cell pole piece and electrolyte, deteriorating the performance of the battery, and causing the battery cell to swell.

[0003] For lithium battery companies, estimating the damage time of soft-pack batteries helps to locate the link and cause of the damage, which in turn helps battery manufacturers to determine responsibility and improve quality. Therefore, estimating the damage time of soft-pack batteries is of great significance.

[0004] However, currently, the calculation of the damage time of soft-pack batteries is mostly based on manual estimation, which often leads to inaccurate estimated damage time. Summary of the invention

[0005] The main purpose of the present invention is to propose a method for predicting the damage time of soft-pack batteries, aiming to solve the problem that the current estimated damage time of soft-pack batteries is not accurate enough.

[0006] To achieve the above object, one aspect of the present invention provides a method for predicting the damage time of a soft-pack battery, which comprises:

[0007] Obtain the surface image features of the damaged soft-pack battery, determine the rupture shape of the damaged soft-pack battery according to the image features, and measure the thickness S0 of the battery at the rupture;

[0008] Use an intact battery of the same model as the damaged soft-pack battery as the sample battery, and measure the thickness S1 of the sample battery corresponding to the location of the rupture;

[0009] A sampling port is formed on the sampled battery, the sampling port being the same size and corresponding in position to the broken port of the damaged soft-pack battery;

[0010] The sampled battery is placed in the atmosphere, and the battery thickness Sn at the sampling port is measured at regular intervals. The hardness expansion rate at the battery sampling port is calculated by (Sn-S1) / S1×100%. A damage time prediction model is established based on the damage time and hardness expansion rate of the sampling port by linear regression method.

[0011] The hardness expansion ratio (S0-S1) / S1×100% at the broken opening of the broken soft-pack battery is substituted into the breakage time prediction model to calculate the breakage time of the broken soft-pack battery.

[0012] In some embodiments, the damage time prediction model is y=165.27583x+11.23685;

[0013] Among them, y represents the damage time, in days; x represents the hardness and swelling rate at the rupture of the battery.

[0014] In some embodiments, measuring the thickness S0 includes: measuring the thickness of the battery at different positions of the breach and taking an average value, and the obtained average value is the thickness S0.

[0015] In some embodiments, measuring the thickness S1 includes: measuring the thickness of the sampled batteries at different positions corresponding to the position of the breach and taking an average value, where the average value is the thickness S1;

[0016] In some embodiments, measuring the thickness Sn includes: measuring the thickness of the battery at different positions of the sampling port and taking an average value, and the obtained average value is the thickness Sn.

[0017] In some embodiments, before forming the sampling port on the sampling battery, the method further includes:

[0018] Determine the cause of the breach based on image features;

[0019] If the rupture is caused by scratching, measure the scratch length of the rupture;

[0020] If the rupture is caused by puncture, measure the diameter of the rupture.

[0021] In some embodiments, determining the cause of the breach includes:

[0022] Identify the shape of the breach based on image features;

[0023] comparing the shape of the identified breach with a plurality of comparison figures;

[0024] Determine the cause of the breach based on the comparison results.

[0025] In some embodiments, after determining the cause of the breach, the process further includes:

[0026] Obtain the coordinate position of the breach on the surface of the damaged soft-pack battery;

[0027] The coordinate position of the breach is output to an external device, so that the external device forms a sampling breach at the same position on the surface of the sampling battery.

[0028] In some embodiments, after outputting the coordinate position of the breach to an external device, the method further includes:

[0029] The comparison result is output to an external device so that the external device can form a sampling port at a position on the surface of the sampling battery that is the same as the coordinate position of the breach.

[0030] Another aspect of the present invention provides a control device, the control device comprising:

[0031] a memory for storing computer-executable instructions; and

[0032] A processor is used to execute computer executable instructions to implement the method for predicting the damage time of the soft-pack battery as described above.

[0033] Another aspect of the present invention provides a storage medium storing a computer program. When the computer program is executed by a processor, the method for predicting the damage time of a soft-pack battery as described above is implemented.

[0034] The beneficial effect of the technical solution of the present invention is that a prediction model capable of predicting the damage time of a soft-pack battery is generated based on the linear change characteristic of the change rate of the hard swelling thickness at the rupture of the soft-pack battery. The prediction model can accurately predict the damage moment of the soft-pack battery, and the measurement is convenient and the operation is very simple and easy. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of a method for predicting the damage time of a soft-pack battery according to an embodiment of the present invention;

[0036] Figure 2 A sub-flow chart of a method for predicting the damage time of a soft-pack battery according to an embodiment of the present invention;

[0037] Figure 3 A flowchart of a method for predicting the damage time of a soft-pack battery according to another embodiment of the present invention;

[0038] Figure 4 A curve diagram showing the change of the hard swelling size of a sampled battery over time in one embodiment of the present invention;

[0039] Figure 5 Schematic diagram of the structure of a control device according to an embodiment of the present invention.

[0040] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0041] The scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] It should be noted that the descriptions involving "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features.

[0043] After a soft-pack battery is damaged, the morphology and thickness of the damaged opening may change over time. Based on the change in thickness of the damaged opening, the embodiment of the present application proposes a method and device for calculating the time of occurrence of the damaged opening, thereby improving the accuracy of determining the time of the damaged opening. The technical solution of the embodiment of the present application will be further elaborated in detail below in combination with the embodiment.

[0044] The present invention proposes a method for predicting the damage time of a soft-pack battery, see Figure 1 , Figure 1 Schematic diagram of a flow chart of a method for predicting the damage time of a soft-pack battery in one embodiment of the present invention.

[0045] In this embodiment, the method for predicting the damage time of a soft-pack battery includes:

[0046] Step S100, obtain the image features of the surface of the damaged soft-pack battery, determine the shape of the breach formed on the surface of the damaged soft-pack battery according to the image features, and measure the thickness S0 at the breach. In an embodiment of the present application, the image features of the surface of the damaged soft-pack battery can be obtained by a visual inspection device or equipment. The visual inspection device or equipment may include an industrial camera and a control unit electrically connected thereto. The industrial camera can obtain image features (such as holes, scratches, etc.) on the surface of the damaged soft-pack battery. The control unit is used to control the industrial camera and analyze the image features obtained to obtain the shape of the breach. Furthermore, the periphery of the breach on the surface of the damaged soft-pack battery can also be detected by a visual inspection device to obtain the hard swelling thickness size around the breach. The visual inspection device, for example: uses image processing software or equipment to scan or take pictures of the damaged soft-pack battery to obtain image data of the surface of the damaged soft-pack battery. Then, the shape of the breach formed on the surface of the damaged soft-pack battery is determined based on the image features and the thickness S0 at the breach is detected. For example, the visual inspection device can obtain image data of the damaged soft-pack battery through an industrial camera, and analyze the image data according to the measurement module through the control unit to identify the location, size, shape and other information of the breach, and measure the hard swelling thickness at the breach.

[0047] Step S200: Use an intact battery of the same model as the damaged soft-pack battery as a sample battery, and measure the thickness S1 of the sample battery corresponding to the position of the rupture.

[0048] Step S300: forming a sampling port on the sampled battery, wherein the sampling port has the same size and corresponding position as the broken port of the damaged soft-pack battery.

[0049] Step S400, placing the sampled battery in an atmospheric environment, measuring the battery thickness Sn at the sampling port at regular intervals, calculating the hardness expansion rate of the battery at the sampling port by (Sn-S1) / S1×100%, and establishing a damage time prediction model based on the damage time of the sampling port and the battery hardness expansion rate by a linear regression method.

[0050] It is understandable that, since the hard swelling change rate at the rupture of the soft-pack battery usually has the characteristic of linear change, the hard swelling change rate at the sampling port can be obtained by measuring the battery thickness Sn at the sampling port of the sampled battery at preset time intervals. When executing this step, the control unit can control the industrial camera to record the moment of measuring the battery thickness Sn at the sampling port each time. For example: use the aforementioned industrial camera to scan, take pictures or record videos of the sampled battery at preset time intervals, and record the changes of the battery thickness Sn at the sampling port over time to obtain the battery hard swelling rate at the sampling port. Exemplarily, when recording the changes of the battery thickness Sn at the sampling port, the sampled battery can be photographed in real time by an industrial camera to obtain the battery thickness Sn at the sampling port over time.

[0051] In the process of establishing the damage time prediction model of this type of battery through linear regression algorithm, the change of the swelling rate of the sampled battery with the number of observation days is measured through a single factor test. The swelling rate of the sampled battery changes as follows (swelling rate = (thickness of the battery after damage - thickness of the intact battery) / thickness of the intact battery × 100%):

[0052]

[0053] Based on the change of the swelling rate of the sampled batteries with the number of observation days, a damage time prediction model for batteries of the same model as the sampled batteries was established using a linear regression algorithm.

[0054] Among them, the univariate linear model y=bx+a, a represents the model constant, b represents the influencing factor of the independent variable, x represents the hardening rate of the battery rupture, and y represents the damage time (days). Figure 4 As shown in the figure, a linear regression analysis is performed on the test data, and the results of the damage time prediction model are as follows:

[0055] y=165.27583x+11.23685.

[0056] Based on the fitting curve, the fit and variance of the damage time prediction model are analyzed as follows:

[0057]

[0058]

[0059] The data show that the goodness of fit of the damage time prediction model, that is, the correlation coefficient, reaches 0.99414, with a statistical significance of P < 0.01, indicating that the regression correlation of the damage time prediction model is significant.

[0060] Furthermore, the regression statistical results of the damage time prediction model verified by test conditions are as follows:

[0061]

[0062] According to the regression statistical results of the above-mentioned damage time prediction model, the residual between the damage time of the soft-pack battery predicted by the damage time prediction model of this embodiment and the actual damage time is no more than 1 day, that is, the error of the damage time of the soft-pack battery predicted by the damage time prediction model of this embodiment is less than or equal to 1 day, and the difference between the predicted damage time and the actual damage time is small.

[0063] It should be noted that the damage time prediction model of the present invention is suitable for evaluating the time when the number of days for soft-pack batteries to be damaged is greater than 7 days. This is because the electrode inside the damaged soft-pack battery within 7 days has not been fully contacted with the outside air, etc., and the reaction has not been fully carried out, so that the hard swelling thickness of the soft-pack battery has not changed significantly. In actual application, when the hard swelling rate swelling of the soft-pack battery is ≤0.05%, it can be known that the number of days for the battery to be damaged does not exceed 7 days. Therefore, the damage time prediction model of the present invention only discusses the case of x>7. The data in the above table show that the predicted value of the damage time prediction model is highly consistent with the actual value, and the accuracy is good. The damage time prediction model has practical guiding significance.

[0064] Step S500: Substitute the hard swelling rate at the break of the damaged soft-pack battery (S0-S1) / S1×100% into the damage time prediction model to calculate the damage time of the damaged soft-pack battery. For example, the hard swelling rate at the break of the damaged soft-pack battery is input into the damage time prediction model y=165.27583x+11.23685 obtained in step S400 to obtain the damage time of the damaged soft-pack battery.

[0065] In this embodiment, the damage time prediction model for calculating the time of occurrence of the soft-pack battery rupture is formed by the change rate of the hard swelling thickness at the rupture of the soft-pack battery. Since the change rate of the hard swelling thickness at the rupture of the soft-pack battery has the characteristic of linear change, the prediction model established based on the change rate of the hard swelling thickness at the rupture of the soft-pack battery combined with the linear regression method is conducive to determining the accurate rupture time.

[0066] In some embodiments, when executing step S100, the process of detecting the thickness S0 at the breach is: detecting several hard swelling thicknesses at different positions around the breach and taking a first average value, and taking the first average value as the thickness S0. In some cases, the thickness values ​​measured in different measuring directions of the hard swelling area at the breach may be different, so multiple detections are performed at different positions around the breach to obtain several hard swelling thicknesses and take a first average value, and take the first average value as the thickness S0. Correspondingly, the process of detecting the battery thickness Sn at the sampling port is: detecting several hard swelling thicknesses at different positions around the sampling port and taking a second average value, and taking the second average value as the battery thickness Sn at the sampling port. The reason for taking the second average value as the battery thickness Sn at the sampling port is the same as the aforementioned reason for taking the first average value as the thickness S0, and will not be repeated here.

[0067] In some embodiments, Figure 2 As shown, the specific process of executing step S400 includes:

[0068] Step S410, taking the moment when the sampling port is formed as the starting moment, measure the second average value every preset time. When executing this step, the control unit records the moment when the sampling port is formed on the surface of the sampling battery through the timing module. After that, measure the second average value at the sampling port of the sampling battery every preset time. For example, the preset time is set to 1 week, and the second average value at the sampling port of the sampling battery is measured 1 week after the moment when the sampling port is formed on the surface of the sampling battery, and the second average value is measured again after 1 week, and so on and so forth repeatedly until the second average value at the sampling port of the sampling battery no longer changes.

[0069] Step S420, associate the detected multiple second average values ​​with the detection time, and generate a mapping relationship table between the battery thickness Sn at the sampling port and the detection time. When executing this step, the control unit can record the number of measurements of the second average value, the duration of the preset time, and the measured second average value, and finally establish a corresponding relationship between the preset time and the second average value measured after the preset time, so as to generate and save a mapping relationship table between the battery thickness Sn at the sampling port and the detection time. For example, the moment when the sampling port is formed on the surface of the sampled battery is set as the starting moment, and then the hard swelling thickness at the sampling port is measured every week. Of course, it is also possible to record the hard swelling changes of the sampled battery at all times by cooperating with a high-speed camera and a laser measuring instrument.

[0070] In some embodiments, Figure 3 As shown, before executing step S300, the method further includes:

[0071] Step S201, judging the cause of the rupture according to the image features. If the rupture is formed by scratching, the length of the scratch is measured; if the rupture is formed by puncture, the aperture of the rupture is measured. It can be understood that the rupture on the surface is generally formed by scratching or puncturing by a sharp object. After the visual inspection device detects the rupture on the surface of the damaged soft-pack battery, it determines whether the rupture on the surface of the damaged soft-pack battery is formed by scratching or puncturing according to the shape of the rupture. If the visual inspection device determines that the rupture on the surface of the damaged soft-pack battery is formed by scratching, the length of the scratch is measured by the measuring module; if the visual inspection device determines that the rupture on the surface of the damaged soft-pack battery is formed by puncture, the aperture of the rupture is measured. If the cause of the rupture is judged to be scratching, the length of the scratch is measured; if the cause of the rupture is judged to be puncture, the aperture of the rupture is measured. Exemplarily, when it is judged that the rupture is formed by scratching or puncturing, the shape of the rupture can be identified by the visual inspection device. After the shape of the breach is identified, the identified shape of the breach is compared with a plurality of comparison examples, and the cause of the breach is determined based on the comparison result.

[0072] Step S202, obtaining the coordinate position of the breach on the surface of the damaged soft-pack battery. In the embodiment of the present application, the visual inspection device can collect the coordinates of each image feature on the surface of the damaged soft-pack battery under the control of the control unit, so as to determine the position of the breach on the surface of the damaged soft-pack battery. After the position of the breach is obtained, it can be used as a reference for the forming sampling port.

[0073] Step S203: Output the coordinate position of the breach to an external device, so that the external device can form the sampling port at the same position on the surface of the sampling battery. When executing this step, the control unit outputs the acquired coordinate position of the breach to an external device, such as a breach device. After receiving the coordinate position of the breach, the external device forms a sampling port at the same position on the surface of the sampling battery of the same model. Please continue to refer to Figure 3 In one embodiment, after step S203, the following steps are further included:

[0074] Step S204, output the comparison result to an external device. In the embodiment of the present application, if the control unit determines that the rupture is caused by scratching after comparison, the control unit outputs the comparison result and the scratch length data of the rupture to the external device. The external device scratches a preset area on the surface of the sampling battery according to the comparison result received to form a sampling port with the same scratch length as the rupture. In the process of forming the sampling port, the external device is equipped with a processing tool such as a cutter to form the sampling port on the surface of the sampling battery.

[0075] For another example, if the comparison result shows that the breach is formed by puncture, the control unit outputs the comparison result and the aperture data of the breach obtained by measurement to the external device. The external device punctures a preset area on the surface of the sampling battery to form a sampling port with the same aperture as the breach according to the comparison result received. In the process of forming the sampling port, the external device is equipped with a processing tool such as a needle to form the sampling port on the surface of the sampling battery.

[0076] The following will take the damage of the top seal of a soft pack battery as an example to explain in detail the damage time calculation scheme of this application:

[0077] Assume that there is a small damaged opening (break) in the middle of the top seal of a soft-pack battery head, the battery is swollen and the head is hard.

[0078] In order to estimate the time when the damage occurs, several soft-pack batteries of the same model as the damaged soft-pack battery are taken as sampling batteries. It should be noted here that since the application measures the thickness of the damaged mouth, its hardness and swelling changes have certain rules. Therefore, there is no limit on the number of sampled batteries. You can take multiple pieces or one piece. If multiple pieces are taken as sampling batteries, the voltage of the sampled batteries will be uniformly adjusted to the battery's shipping power state (such as charging the battery's voltage to 60% SOC with constant current and constant voltage). Use a visual inspection device to detect the initial thickness of the damaged mouth of the damaged soft-pack battery. Then use a rupture device (such as a needle or a knife) to pierce a small hole in the middle of the top seal of the sampling battery. The small hole is required to pierce the upper aluminum-plastic film, but not to damage the bare battery cell inside the battery.

[0079] Cut a piece of pH test paper of appropriate size and stick it on the damaged part of the battery. Leave it overnight and you will find that the position on the pH test paper corresponding to the damaged part has changed color, indicating that the packaging aluminum-plastic film has been punctured and the internal electrolyte vapor can overflow from the damaged part.

[0080] Then control the visual inspection device to start monitoring the thickness changes at the sampling port of the damaged sampled battery every week, and keep good data records. It is important to record the thickness of the punctured battery head and the thickness of the punctured battery middle at the same time. Because of the presence of the damaged port on the battery head, external moisture and other components in the air will diffuse into the battery, causing side reactions on the pole piece at the battery head, which will gradually turn black, harden and deform, causing the thickness of the battery head to continue to increase. The middle part of the battery may swell due to gas production in the battery.

[0081] Reference Figure 5 As shown, the present application embodiment also provides a control device, the control device 10 includes a memory 1005 and a processor 1001. The memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module and computer executable instructions.

[0082] exist Figure 5 In the control device 10 shown, the network interface 1004 is mainly used to connect to the background server and communicate signals with the background server; the user interface 1003 is mainly used to connect to the client (user end) and communicate signals with the client; and the processor 1001 can be used to call the computer executable instructions stored in the memory 1005. When the computer executable instructions are called and executed by the processor 1001, a method for predicting the damage time of a soft-pack battery is implemented. The control device 10 also includes a control unit (not shown in the figure) for executing the computer executable instructions.

[0083] Based on the computer executable instructions of the aforementioned embodiments, a computer readable storage medium is also proposed in some embodiments, and the storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes. The computer readable storage medium stores computer executable instructions, and when the computer executable instructions are executed by the processor, the method for predicting the damage time of the soft-pack battery recorded in the aforementioned embodiments is implemented.

[0084] The above description is only a partial or preferred embodiment of the present invention. Neither the text nor the drawings can limit the scope of protection of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the overall concept of the present invention, or direct / indirect application in other related technical fields are included in the scope of protection of the present invention.

Claims

1. A method for predicting the damage time of a soft pack battery, characterized in that: include: Acquire the surface image features of the damaged soft-pack battery, determine the rupture shape of the damaged soft-pack battery according to the image features, and measure the thickness S0 of the battery at the rupture; Using an intact battery of the same model as the damaged soft-pack battery as a sample battery, and measuring the thickness S1 of the sample battery corresponding to the position of the rupture; A sampling port is formed on the sampled battery, wherein the sampling port has the same size and a corresponding position as the broken port of the damaged soft-pack battery; The sampled battery is placed in an atmospheric environment, and the battery thickness Sn at the sampling port is measured at regular intervals. The hardening and swelling rate at the battery sampling port is calculated by (Sn-S1) / S1×100%, and a damage time prediction model is established based on the damage time and hardening and swelling rate of the sampling port by a linear regression method; The hard expansion rate at the break of the damaged soft-pack battery (S0-S1) / S1×100% is substituted into the damage time prediction model to calculate the damage time of the damaged soft-pack battery.

2. The prediction method according to claim 1, characterized in that: The damage time prediction model is y=165.27583x+11.23685; Among them, y represents the damage time in days; x represents the hardness and swelling rate at the rupture of the battery.

3. The prediction method according to claim 1, characterized in that: Measuring the thickness S0 includes: measuring the battery thickness at different positions of the breach and taking an average value, and the obtained average value is the thickness S0.

4. The prediction method according to claim 3, characterized in that: Measuring the thickness S1 includes: measuring the thickness of the sampled battery at different positions corresponding to the position of the breach and taking an average value, where the average value is the thickness S1; Measuring the thickness Sn includes: measuring the battery thickness at different positions of the sampling port and taking an average value, and the obtained average value is the thickness Sn.

5. The prediction method according to claim 1, characterized in that: Before forming the sampling port on the sampling battery, the method further includes: Determining the cause of the breach according to the image features; If the rupture is caused by scratching, measuring the scratch length of the rupture; If the rupture is formed by puncture, the aperture of the rupture is measured.

6. The prediction method according to claim 5, characterized in that: The causes of the judgment breach include: Identify the shape of the breach according to the image features; comparing the identified shape of the breach with a plurality of comparison examples; The formation cause of the breach is determined according to the comparison result.

7. The prediction method according to claim 6, characterized in that: The determination of the cause of the breach also includes: Obtaining the coordinate position of the breach on the surface of the damaged soft-pack battery; The coordinate position of the breach is output to an external device, so that the external device forms the sampling port at the same position on the surface of the sampling battery.

8. The prediction method according to claim 7, characterized in that: After outputting the coordinate position of the breach to an external device, the method further includes: The comparison result is output to an external device, so that the external device can form the sampling port at the same position as the coordinate position of the breach on the surface of the sampling battery.

9. A control device, characterized in that: The control device comprises: a memory for storing computer-executable instructions; and A processor, configured to execute the computer executable instructions to implement the method for predicting the damage time of a soft-pack battery as claimed in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting the damage time of a soft-pack battery according to any one of claims 1 to 8 is implemented.

Images