Battery capacity prediction method and device

Abstract

The battery capacity prediction method and device provided in this application can improve the accuracy of battery capacity prediction. The method includes: obtaining a target capacity prediction model, the target capacity prediction model is obtained based on a first capacity prediction model and a second capacity prediction model, the first capacity prediction model is obtained based on first target battery information and a first fitting function, the first target battery information is used to indicate the battery capacity actually tested in each of M cycles of the battery, the second capacity prediction model is obtained based on second target battery information and a second fitting function, the second target battery information is used to indicate the battery capacity deviation value in each of P cycles of the battery, the minimum cycle period of the P cycles being greater than the maximum cycle period of the M cycles; and predicting the battery capacity of the battery based on the target capacity prediction model.

Description

Technical Field

[0001] The present application relates to the field of battery management, and more particularly, to a battery capacity prediction method and apparatus. Background Art

[0002] With the continuous development of battery technology, batteries have become the main driving power source for many vehicles, such as electric vehicles and electric bicycles, as well as the main energy storage component for electronic devices such as mobile phones, laptops, and electric toys. Batteries will gradually age during use, that is, the battery capacity will gradually decrease.

[0003] The attenuation of battery capacity will greatly affect the normal use of the battery. Accurately predicting battery capacity plays a guiding role in the management and maintenance of the battery during its later use.

[0004] Therefore, how to improve the accuracy of battery capacity prediction and thus extend the battery life has become an urgent problem to be solved in the industry. Summary of the Invention

[0005] The present application provides a battery capacity prediction method and device, which are beneficial to improving the accuracy of battery capacity prediction, thereby extending the service life of the battery.

[0006] In a first aspect, an embodiment of the present application provides a method for generating a battery capacity prediction model, which may include: generating a first capacity prediction model based on first target battery information and a first fitting function of a first battery, wherein the first target battery information is used to indicate the battery capacity of the first battery actually tested in each cycle of M cycles, wherein the fitting degree of the curve corresponding to the first fitting function and the first target battery information satisfies a preset first fitting condition, and M is an integer greater than 1; generating a second capacity prediction model based on second target battery information and a second fitting function of the first battery, wherein the second target battery information is used to indicate the battery capacity of the first battery actually tested in each cycle of M cycles, wherein the fitting degree of the curve corresponding to the first fitting function and the first target battery information satisfies a preset first fitting condition, and M is an integer greater than 1; a battery capacity deviation value in each of P cycle periods of the battery, the battery capacity deviation value being the difference between the battery capacity obtained by actual testing and the battery capacity predicted by the first capacity prediction model, wherein the degree of fit between the second fitting function and the second target battery information satisfies a preset second fitting condition, P is an integer greater than 1, and the minimum cycle period in the P cycle periods is greater than the maximum cycle period in the M cycle periods; and generating a target capacity prediction model based on the first capacity prediction model and the second capacity prediction model, the target capacity prediction model being used to indicate a corresponding relationship between the cycle period and the battery capacity of the first battery.

[0007] It can be seen that the method for generating the capacity prediction model provided in the embodiment of the present application adopts a two-stage generation method. In the first stage, a basic model (i.e., a first capacity prediction model) is generated based on the actual test data within M cycles. In the second stage, a correction model (i.e., a second capacity prediction model) is generated through the actual test data and prediction data (obtained by the first capacity prediction model) within Q cycles, and a target capacity prediction model is generated based on the basic model and the correction model. Among them, the prediction results of the basic model can be corrected by the correction model, which is conducive to improving the accuracy of the battery capacity prediction, thereby extending the service life of the battery.

[0008] It should be noted that, in the embodiment of the present application, the process of a complete charge and / or discharge of the battery can be referred to as a cycle.

[0009] It should also be noted that the battery capacity of the battery in a certain cycle described in the embodiments of the present application refers to the maximum battery capacity of the battery in the cycle.

[0010] Optionally, the battery capacity described in the embodiment of the present application may also be replaced by other parameters that can characterize the battery capacity, such as battery health status, etc., which is not limited in the embodiment of the present application.

[0011] It should also be noted that the cycle periods in the multiple cycle periods (such as N cycle periods) described in the embodiments of the present application are increased sequentially.

[0012] Optionally, the multiple cycles may be continuous or discontinuous, which is not limited in the embodiment of the present application.

[0013] In a possible implementation, the first battery information may include a correspondence between the N cycle periods and a battery capacity of the first battery actually tested and obtained in each of the N cycle periods.

[0014] Optionally, the battery capacity of the first battery in each cycle can be obtained by testing in a variety of ways, which is not limited in this embodiment of the present application.

[0015] In a possible implementation, the battery capacity of the first battery in each cycle may be tested by a battery capacity testing device.

[0016] Optionally, before generating the first capacity prediction model based on the first target battery information and the first fitting function of the first battery, the method may include: obtaining the first battery information of the first battery, where the first battery information is used to indicate the battery capacity actually measured for each cycle of the first battery in N cycle periods, and the N cycle periods include the M cycle periods; determining the first target battery information based on the first battery information and the first fitting function.

[0017] In a possible implementation, determining the first target battery information based on the first battery information and the first fitting function may include: fitting the curve corresponding to the battery capacity actually measured in the first j cycle periods among the N cycle periods through the first fitting function to determine the fitting degree corresponding to the first j cycle periods, where j is an integer greater than 1 and less than or equal to N; determining the first target battery information based on the fitting degree corresponding to the first j cycle periods.

[0018] Exemplarily, if the fitting degrees corresponding to the first M cycle periods among the N cycle periods satisfy the first fitting condition, the first M cycle periods and the battery capacity actually measured for each cycle of the first battery in the first M cycle periods are determined as the first target battery information.

[0019] Optionally, the embodiment of the present application does not limit the form of the first fitting function.

[0020] In a possible implementation, the first fitting function may be an exponential function, a polynomial function or a logarithmic function.

[0021] For example: the exponential function may be m·e n·cyc , where m and n are parameters to be fitted, and cycle is the cycle period of the battery.

[0022] For another example: the polynomial function may be a·cycle x +b·cycle + c, x ∈ (0,1], where a, b, and c are parameters to be fitted, and cycle is the cycle period of the battery.

[0023] For another example: the logarithmic function may be log a cycle, 0 < a < 1, and cycle is the cycle period of the battery.

[0024] In another possible implementation, the first fitting function may include a combination of any two functions among an exponential function, a combination of a polynomial function, and a combination of a logarithmic function.

[0025] In a possible implementation, the first fitting condition may be that the degree of fitting is maximized, or that the degree of fitting reaches a preset first degree of fitting threshold.

[0026] In one possible implementation, generating the first capacity prediction model based on the first target battery information and the first fitting function may include: fitting a curve corresponding to the first target battery information through the first fitting function to determine parameters to be fitted of the first fitting function; and substituting the parameters to be fitted of the first fitting function into the first fitting function to generate the first capacity prediction model.

[0027] Optionally, before determining the second target battery information of the first battery based on the second battery information of the first battery and the second fitting function, the method may further include: obtaining the second battery information of the first battery, the second battery information being used to indicate a battery capacity deviation value of the first battery in each of Q cycle periods, the battery capacity deviation value being the difference between the battery capacity obtained by actual testing and the battery capacity predicted by the first capacity prediction model, the minimum cycle period in the Q cycle periods being greater than the maximum cycle period in the M cycle periods; and determining the second target battery information based on the second battery information and the second fitting function.

[0028] Optionally, the embodiment of the present application does not limit the form of the second fitting function.

[0029] In a possible implementation, the second fitting function may be an exponential function, a polynomial function, or a logarithmic function.

[0030] In another possible implementation, the second fitting function may include a combination of any two of an exponential function, a combination of polynomial functions, and a combination of logarithmic functions.

[0031] In one possible implementation, the above-mentioned determination of the second target battery information based on the second battery information and the second fitting function may include: fitting the curve corresponding to the battery capacity actually tested in the first k cycles among the Q cycles through the second fitting function, and determining the fitting degree corresponding to the first k cycles, where k is an integer greater than 1 and less than or equal to Q; and determining the second target battery information based on the fitting degree corresponding to the first k cycles.

[0032] For example, if the fitting degrees corresponding to the first P cycles among the Q cycles meet the second fitting condition, the battery capacity actually tested in the first P cycles and in each of the first P cycles of the first battery is determined as the second target battery information.

[0033] In a possible implementation, the second fitting condition may be that the degree of fitting is maximized, or that the degree of fitting reaches a preset second degree of fitting threshold.

[0034] Optionally, the first fitting condition and the second fitting condition may be the same or different, which is not limited in the embodiment of the present application.

[0035] In one possible implementation, determining the second capacity prediction model based on the second target battery information and the second fitting function may include: fitting a curve corresponding to the second target battery information through the second fitting function to determine parameters to be fitted of the second fitting function; and substituting the parameters to be fitted of the second fitting function into the second fitting function to determine the second capacity prediction model.

[0036] In one possible implementation, the above-mentioned generation of the target capacity prediction model based on the first capacity prediction model and the second capacity prediction model may include: weighting the first capacity prediction model and the second capacity prediction model by a preset weighting coefficient to generate the target capacity prediction model, wherein the weighting coefficient may include a first weighting coefficient of the first capacity prediction model and a second weighting coefficient of the second capacity prediction model.

[0037] Optionally, the method may further include: predicting the battery capacity of a second battery based on the target capacity prediction model, where the second battery has the same model and / or production batch as the first battery.

[0038] Optionally, the second battery and the first battery may be the same battery.

[0039] It's important to note that during battery aging, capacity decay can be roughly divided into two stages: In the first stage, capacity decay gradually stabilizes over time or over the number of cycles; in the second stage, the rate of capacity decay suddenly accelerates, leading to a rapid decline in battery performance. This process is often referred to as a capacity "dive." The turning point between these two stages is known as the capacity "dive point." A capacity "dive" significantly accelerates battery aging, shortens battery life, impacts normal use, and can even cause financial losses.

[0040] Therefore, if the capacity drop point can be predicted in advance, that is, if the cycle in which the capacity drop occurs can be predicted, it will be helpful to adopt appropriate management and maintenance strategies for the battery in a timely manner, thereby extending the battery life.

[0041] In a second aspect, an embodiment of the present application provides a method for predicting a battery capacity drop, which may include: obtaining third battery information of a first battery, the third battery information being used to indicate the battery capacity of the first battery actually tested in each of L cycles, where L is an integer greater than 2; performing two differential operations on the battery capacity actually tested in the L cycles to obtain L-2 operation results; and determining, based on the L-2 operation results, whether the battery capacity of the first battery has dropped in the L cycles.

[0042] In one possible implementation, if the Kth operation result among the (L-2) operation results is less than or equal to a preset first threshold, it is determined that the battery capacity of the first battery has dropped within the K+2th cycle among the L cycles, where K is an integer greater than or equal to 0 and less than or equal to L-2.

[0043] That is, when the Kth calculation result is less than or equal to the first threshold, it indicates that the capacity of the first battery has dropped during the cycle corresponding to the Kth calculation result. For example, the first threshold can be 0 or 0.5, that is, the difference between the first threshold and 0 can be 0 or approximately 0.

[0044] In another possible implementation, if the (L-2) calculation results are all greater than the first threshold, it is determined that the battery capacity of the first battery has not dropped within the L cycles.

[0045] Optionally, the first battery information may be determined in the following two ways.

[0046] Method 1: If the battery capacity of the first battery drops in the K+2th cycle among the L cycles, then the N cycles include the first K+2 cycles among the L cycles.

[0047] Method 2: If it is determined that the battery capacity of the first battery does not drop within the L cycles, then the N cycles include the first N cycles of the L cycles.

[0048] It can be seen that the method provided in the embodiment of the present application can predict the battery capacity at each stage of the battery aging process. That is to say, the battery capacity in the gradual stabilization trend stage can be predicted, and the battery capacity in the diving stage can also be predicted. The capacity diving point can be predicted, and the battery diving can be predicted, which is conducive to timely adopting appropriate management and maintenance strategies for the battery based on the attenuation of the battery capacity, thereby improving the battery life.

[0049] In a third aspect, an embodiment of the present application further provides a battery capacity prediction method, which may include: obtaining a target capacity prediction model, the target capacity prediction model being used to indicate the correspondence between the battery cycle and the battery capacity, the target capacity prediction model being obtained based on a first capacity prediction model and a second capacity prediction model, the first capacity prediction model being obtained based on the first target battery information of the battery and a first fitting function, the first target battery information being used to indicate the battery capacity actually tested in each cycle of M cycles of the battery, the degree of fit of the first fitting function and the curve corresponding to the first target battery information meeting a preset first fitting condition, the first fitting function meeting a preset first fitting condition, and the second fitting function meeting a preset first fitting condition. The second capacity prediction model is obtained based on the second target battery information and the second fitting function of the battery, the second target battery information is used to indicate the battery capacity deviation value of the battery in each cycle of P cycles, and the battery capacity deviation value is the difference between the battery capacity obtained by actual testing and the battery capacity predicted by the first capacity prediction model. The fit degree of the second fitting function and the second target battery information meets the preset second fitting condition, wherein M and P are both integers greater than 1, and the minimum cycle period in the P cycle periods is greater than the maximum cycle period in the M cycle periods; based on the target capacity prediction model, the battery capacity of the battery is predicted.

[0050] As can be seen, the battery capacity prediction method provided in the embodiments of this application, which uses the battery capacity prediction model generated by the two-stage model generation method to perform battery capacity prediction, can improve the accuracy of battery capacity prediction. In addition, the ability to predict the battery's drop point facilitates battery management and maintenance, thereby extending the battery's service life.

[0051] Optionally, the embodiment of the present application does not limit the method for obtaining the target capacity prediction model.

[0052] In a possible implementation, the target capacity prediction model may be pre-configured in the prediction device.

[0053] In another possible implementation, the prediction device may receive the target capacity prediction model from other devices. For example, the prediction device may receive the target capacity prediction model from the above-mentioned generation device.

[0054] In another possible implementation, the prediction device may generate the target capacity prediction model. For example, the prediction device may generate the target capacity prediction model using the generation method described in the first and second aspects above.

[0055] In a fourth aspect, embodiments of the present application further provide a device for generating a battery capacity prediction model, configured to execute the method described in the first aspect or any possible implementation thereof and / or the method described in the second aspect or any possible implementation thereof. Specifically, the generating device may include a unit for executing the method described in the first aspect or any possible implementation thereof, and / or a unit for executing the method described in the second aspect or any possible implementation thereof.

[0056] In a fifth aspect, embodiments of the present application further provide a battery capacity prediction device for executing the method described in the third aspect or any possible implementation thereof. Specifically, the prediction device may include a unit for executing the method described in the third aspect or any possible implementation thereof.

[0057] In a sixth aspect, embodiments of the present application further provide a device for generating a battery capacity prediction model, comprising: at least one processor and a transceiver. Furthermore, the at least one processor is coupled to the transceiver. The at least one processor is configured to execute instructions causing the server to implement the method described in the first aspect or any possible implementation thereof and / or the method described in the second aspect or any possible implementation thereof.

[0058] Optionally, the generating device may further include a memory, wherein the memory, the transceiver and the at least one processor are coupled, and the memory is used to store the above instructions.

[0059] In a seventh aspect, embodiments of the present application further provide a battery capacity prediction device, comprising: at least one processor and a transceiver. Furthermore, the at least one processor is coupled to the transceiver. The at least one processor is configured to execute instructions so that the terminal implements the method described in the third aspect or any possible implementation thereof.

[0060] Optionally, the prediction device may further include a memory, wherein the memory, the transceiver and the at least one processor are coupled, and the memory is used to store the above instructions.

[0061] Optionally, the device described in any one of the fourth to seventh aspects can be used in an electronic device.

[0062] In an eighth aspect, the present application further provides a chip comprising: an input interface, an output interface, and at least one processor. Optionally, the chip device further comprises a memory. The at least one processor is configured to execute code in the memory. When the at least one processor executes the code, the chip implements the methods described in the above aspects or any possible implementation thereof.

[0063] In a ninth aspect, the present application also provides a computer-readable storage medium for storing a computer program, which includes methods for implementing the above aspects or any possible implementation thereof.

[0064] In a tenth aspect, the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to implement the methods described in the above aspects or any possible implementation thereof.

[0065] The generation device, prediction device, electronic device, computer storage medium, computer program product and chip provided in the embodiments of the present application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the various methods provided above and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A schematic flowchart of a method 100 for generating a battery capacity prediction model according to an embodiment of the present application is provided;

[0067] Figure 2 A schematic flow chart of a method 200 for predicting battery capacity drop according to an embodiment of the present application is provided;

[0068] Figure 3 A schematic flow chart of a battery capacity prediction method 300 according to an embodiment of the present application is provided;

[0069] Figure 4 A schematic flow chart of an apparatus 400 according to an embodiment of the present application is provided;

[0070] Figure 5 A schematic flow chart of an apparatus 500 according to an embodiment of the present application is provided;

[0071] Figure 6 A schematic flow chart of an apparatus 600 according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0072] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0073] Figure 1 This is a schematic flowchart of a method 100 for generating a battery capacity prediction model provided in an embodiment of the present application. This method 100 can be executed by a device for generating a battery capacity prediction model (which will be described in detail below and referred to as a generating device for short).

[0074] S101: Obtain first battery information of a first battery, where the first battery information is used to indicate a battery capacity of the first battery actually tested in each of N cycles, where N is an integer greater than 1.

[0075] It should be noted that, in the embodiment of the present application, the process of a complete charge and / or discharge of the battery can be referred to as a cycle.

[0076] It should also be noted that the battery capacity of the battery in a certain cycle described in the embodiments of the present application refers to the maximum battery capacity of the battery in the cycle.

[0077] Optionally, the battery capacity described in the embodiment of the present application may also be replaced by other parameters that can characterize the battery capacity, such as the battery state of health (SOH), etc., which is not limited in the embodiment of the present application.

[0078] It should also be noted that the cycle periods in the multiple cycle periods (such as N cycle periods) described in the embodiments of the present application are increased sequentially.

[0079] Optionally, the multiple cycles may be continuous or discontinuous, which is not limited in the embodiment of the present application.

[0080] For example, if the number of the multiple cycles is 5, the 5 cycles may include the first cycle, the second cycle, the third cycle, the fourth cycle and the fifth cycle.

[0081] For another example, taking the number of the multiple cycles as 5, the 5 cycles may include the 1st cycle, the 3rd cycle, the 5th cycle, the 7th cycle and the 9th cycle.

[0082] In a possible implementation, the first battery information may include a correspondence between the N cycle periods and a battery capacity of the first battery actually tested and obtained in each of the N cycle periods.

[0083] For example, as shown in Table 1 below, taking the value of N as 200, the first battery information may include the 1st to 200th cycle periods, and the corresponding relationship between the battery capacities C1, C2, ..., C200 of the first battery in each cycle period from the 1st to the 200th cycle period. The 1st cycle period is the minimum cycle period of the 200 cycles, and the 200th cycle period is the maximum cycle period of the 200 cycles.

[0084] Table 1

[0085] Cycle period (period) 1 2 3 … 200 Battery capacity (mAh) C1 C2 C3 … C200

[0086] Optionally, the battery capacity of the first battery in each cycle can be obtained through various testing methods, and the embodiments of the present application do not limit this.

[0087] In a possible implementation, the battery capacity of the first battery in each cycle can be tested by a battery capacity testing device.

[0088] S102. Based on the first battery information and the first fitting function, determine the first target battery information, which is used to indicate the actually tested battery capacity of the first battery in each cycle of the M cycles. Here, the fitting degree between the first curve corresponding to the first target battery information and the second curve corresponding to the first fitting function meets a preset first fitting condition. M is an integer greater than 1, and the N cycles include the M cycles.

[0089] Optionally, the embodiments of the present application do not limit the form of the first fitting function.

[0090] In a possible implementation, the first fitting function can be an exponential function, a polynomial function, or a logarithmic function.

[0091] For example: The exponential function can be m·e n·cyc , where m and n are parameters to be fitted, and cycle is the cycle of the battery.

[0092] Another example: The polynomial function can be a·cycle x +b·cycle + c, x ∈ (0,1], where a, b, and c are parameters to be fitted, and cycle is the cycle of the battery.

[0093] Another example: The logarithmic function can be log a cycle, 0 < a < 1, and cycle is the cycle of the battery.

[0094] In another possible implementation, the first fitting function can include any combination of two functions from the combination of an exponential function, a combination of a polynomial function, and a combination of a logarithmic function.

[0095] Specifically, S102 can include: fitting the curve corresponding to the actually tested battery capacity in the first j cycles of the N cycles through the first fitting function to determine the fitting degree corresponding to the first j cycles, where j is an integer greater than 1 and less than or equal to N; determining the first target battery information based on the fitting degree corresponding to the first j cycles.

[0096] In one possible implementation, if the degree of fit corresponding to the first M cycles among the N cycles meets the first fitting condition, the battery capacity actually tested in each of the first M cycles and the first battery in the first M cycles is determined as the first target battery information.

[0097] For example, taking the first battery information shown in Table 1 as an example, the horizontal coordinate in the two-dimensional coordinate system is the cycle period and the vertical coordinate is the battery capacity. When the value of j is 2, the first fitting function is used to fit the curve 2 formed by point 1 (cycle period 1, C1) and point 2 (cycle period 2, C2), and the fitting degree R2 is obtained; when the value of j is 3, the first fitting function is used to fit the curve 3 formed by point 1 (cycle period 1, C1), point 2 (cycle period 2, C2) and point 3 (cycle period 3, C3), and the fitting degree R3 is obtained; when the value of j is M, the first fitting function is used to fit the curve 3 formed by point 1 (cycle period 1, C1), point 2 (cycle period 2, C2) and point 3 (cycle period 3, C3), and the fitting degree R4 is obtained. The curve M formed by point 1 (cycle period 1, C1), point 2 (cycle period 2, C2)…point 200 (cycle period 200, C200) is fitted to obtain the fitting degree RM; by analogy, when the value of j is N, the curve 200 formed by point 1 (cycle period 1, C1), point 2 (cycle period 2, C2)…point 200 (cycle period 200, C200) is fitted through the first fitting function to obtain the fitting degree R200; if the fitting degree RM among the fitting degrees R1, R2, RM…R200 meets the first fitting condition, then the battery capacity actually tested in the first M cycles corresponding to the fitting degree RM and each of the first M cycles is determined as the first target battery information.

[0098] In a possible implementation, the first fitting condition may be that the degree of fitting is maximized, or that the degree of fitting reaches a preset first degree of fitting threshold.

[0099] S103: Generate a first capacity prediction model based on the first target battery information and the first fitting function.

[0100] In one possible implementation, the curve corresponding to the first target battery information can be fitted using the first fitting function to determine the parameters to be fitted of the first fitting function; the parameters to be fitted of the first fitting function are substituted into the first fitting function to generate the first capacity prediction model.

[0101] S104: Obtain second battery information of the first battery, where the second battery information is used to indicate a battery capacity deviation value of the first battery in each of Q cycle periods, where the battery capacity deviation value is the difference between the battery capacity obtained by actual testing and the battery capacity predicted by the first capacity prediction model, and the minimum cycle period of the Q cycle periods is greater than the maximum cycle period of the M cycle periods.

[0102] In a possible implementation, the second battery information may include a correspondence between the Q cycle periods and a battery capacity of the first battery actually tested and obtained in each of the Q cycle periods.

[0103] For example, as shown in Table 2 below, taking the value of N as 200 and the value of M as 150 as an example, the value of Q is 50, that is, the second battery information may include the 151st to 200th cycle periods, and the corresponding relationship between the battery capacity deviation values ΔC151, ΔC152, …, ΔC200 of the first battery in each cycle period from the 151st to the 200th cycle periods, wherein the battery capacity deviation value is the difference between the battery capacity C obtained by actual testing and the battery capacity C' predicted by the first capacity prediction model.

[0104] Table 2

[0105]

[0106] S105: Based on the second battery information and the second fitting function of the first battery, determine the second target battery information of the first battery, where the second target battery information is used to indicate the battery capacity deviation value of the first battery in each of P cycle periods, and the Q cycle periods include the P cycle periods, wherein the degree of fit between the third curve corresponding to the second target battery information and the fourth curve corresponding to the second fitting function meets a preset second fitting condition.

[0107] Optionally, the embodiment of the present application does not limit the form of the second fitting function.

[0108] In a possible implementation, the second fitting function may be an exponential function, a polynomial function, or a logarithmic function.

[0109] In another possible implementation, the second fitting function may include a combination of any two of an exponential function, a combination of polynomial functions, and a combination of logarithmic functions.

[0110] Optionally, the forms of the first fitting function and the second fitting function may be the same or different, which is not limited in the embodiment of the present application.

[0111] Specifically, S105 may include: fitting the curve corresponding to the battery capacity actually tested in the first k cycles of the Q cycles through the second fitting function, and determining the fitting degree corresponding to the first k cycles, where k is an integer greater than 1 and less than or equal to Q; and determining the second target battery information based on the fitting degree corresponding to the first k cycles.

[0112] In one possible implementation, if the degree of fit corresponding to the first P cycles among the Q cycles meets the second fitting condition, the battery capacity actually tested during the first P cycles and the first battery in each of the first P cycles is determined as the second target battery information.

[0113] For example, taking the second battery information shown in Table 2 as an example, the horizontal coordinate in the two-dimensional coordinate system is the cycle period and the vertical coordinate is the battery capacity. When the value of k is 2, the curve 152 formed by the point 151 (cycle period 151, ΔC151) and the point 152 (cycle period 152, ΔC152) is fitted by the second fitting function to obtain the fitting degree R152; when the value of k is 3, the curve 153 formed by the point 151 (cycle period 151, ΔC151), the point 152 (cycle period 152, ΔC152) and the point 153 (cycle period 153, ΔC153) is fitted by the second fitting function to obtain the fitting degree R153; when the value of k is P, the curve 153 formed by the point 151 (cycle period 151, ΔC151), the point 152 (cycle period 152, ΔC152) and the point 153 (cycle period 153, ΔC153) is fitted by the second fitting function to obtain the fitting degree R153. (cycle period 151, C151), point 152 (cycle period 152, C152)…point P (cycle period P, CP) are fitted to obtain the degree of fit RP; similarly, when the value of k is N, the curve N formed by point 1 (cycle period 151, C151), point 152 (cycle period 152, C152)…point N (cycle period N, CN) is fitted through the second fitting function to obtain the degree of fit RN; if the degree of fit R151, R152, RP…RN among the degrees of fit R1-P meets the first fitting condition, then the battery capacity actually tested in the first P cycles corresponding to the degree of fit RP and each of the first P cycles is determined as the second target battery information.

[0114] In a possible implementation, the second fitting condition may be that the degree of fitting is maximized, or that the degree of fitting reaches a preset second degree of fitting threshold.

[0115] Optionally, the first fitting condition and the second fitting condition may be the same or different, which is not limited in the embodiment of the present application.

[0116] S106: Determine a second capacity prediction model based on the second target battery information and the second fitting function.

[0117] In one possible implementation, the curve corresponding to the second target battery information can be fitted using the second fitting function to determine the parameters to be fitted of the second fitting function; the parameters to be fitted of the second fitting function are substituted into the second fitting function to determine the second capacity prediction model.

[0118] S107: Generate a target capacity prediction model based on the first capacity prediction model and the second capacity prediction model, where the target capacity prediction model is used to indicate a corresponding relationship between the cycle period of the first battery and the battery capacity.

[0119] In one possible implementation, the first capacity prediction model and the second capacity prediction model may be weighted by a preset weighting coefficient to generate a target capacity prediction model, wherein the weighting coefficient may include a first weighting coefficient of the first capacity prediction model and a second weighting coefficient of the second capacity prediction model.

[0120] Optionally, the method 100 may further include: predicting the battery capacity of a second battery based on the target capacity prediction model, where the second battery has the same model and / or production batch as the first battery.

[0121] Optionally, the second battery and the first battery may be the same battery.

[0122] It should be noted that, among the above S101 to S107, S103, S106, and S107 are necessary steps of method 100, and the remaining steps are optional steps. Among them, S101 to S102 only schematically introduce a possible implementation method for obtaining the first target battery information, and S104 to S105 only schematically introduce a possible implementation method for obtaining the second target battery information. However, the embodiments of the present application are not limited to obtaining the first target battery information only by the method described in the above S101 to S102, and obtaining the second target battery information by the method described in the above S104 to S105. For example, the first target battery information and the second target battery information can be pre-configured in the generating device.

[0123] The method for generating a capacity prediction model provided in an embodiment of the present application adopts a two-stage generation method. In the first stage, a basic model (i.e., a first capacity prediction model) is generated based on actual test data within M cycles. In the second stage, a revised model (i.e., a second capacity prediction model) is generated based on actual test data and predicted data (obtained by the first capacity prediction model) within Q cycles. Based on the basic model and the revised model, a target capacity prediction model is generated. The revised model can correct the prediction results of the basic model, thereby improving the accuracy of battery capacity prediction.

[0124] It's important to note that during battery aging, capacity decay can be roughly divided into two stages: In the first stage, capacity decay gradually stabilizes over time or over the number of cycles; in the second stage, the rate of capacity decay suddenly accelerates, leading to a rapid decline in battery performance. This process is often referred to as a capacity "dive." The turning point between these two stages is known as the capacity "dive point." A capacity "dive" significantly accelerates battery aging, shortens battery life, impacts normal use, and can even cause financial losses.

[0125] Therefore, if the capacity drop point can be predicted in advance, that is, if the cycle in which the capacity drop occurs can be predicted, it will be helpful to adopt appropriate management and maintenance strategies for the battery in a timely manner, thereby extending the battery life.

[0126] Based on this, Figure 2 A schematic flow chart of a battery capacity drop prediction method 200 provided in an embodiment of the present application is shown. The method 200 may include the following steps S201 to S203. Optionally, the method may be executed by the above-mentioned generating device.

[0127] S201 : Obtain third battery information of a first battery, where the third battery information is used to indicate a battery capacity of the first battery actually tested in each of L cycles, where L is an integer greater than 2.

[0128] S202 , performing two differential operations on the battery capacities actually tested during the L cycles to obtain L-2 operation results.

[0129] For example, as shown in Table 3 below, taking the value of L as 300, the third battery information may include the corresponding relationship between the 1st to 300th cycles and the battery capacities C1, C2, ..., C300 of the first battery in each cycle from the 1st to the 300th cycle. A first differential operation is performed on the battery capacities actually tested within the L cycles to obtain L-1 calculation results, namely ΔC1, ΔC2...ΔC299. A second differential operation is performed on the L-1 calculation results obtained from the first differential operation to obtain L-2 calculation results, namely ΔC1', ΔC2'...ΔC299'.

[0130] Table 3

[0131]

[0132] S203 : Based on the L-2 calculation results, determine whether the battery capacity of the first battery drops within the L cycles.

[0133] In one possible implementation, if the Kth operation result among the (L-2) operation results is less than or equal to a preset first threshold, it is determined that the battery capacity of the first battery has dropped within the K+2th cycle among the L cycles, where K is an integer greater than or equal to 0 and less than or equal to L-2.

[0134] That is, when the Kth calculation result is less than or equal to the first threshold, it indicates that the capacity of the first battery has dropped during the cycle corresponding to the Kth calculation result. For example, the first threshold can be 0 or 0.5, that is, the difference between the first threshold and 0 can be 0 or approximately 0.

[0135] For example, taking the (L-2) calculation results as shown in ΔC1', ΔC2'...ΔC298' in Table 3 as an example, if ΔC150'=0, the capacity of the first battery drops in the 152nd cycle corresponding to ΔC150'.

[0136] In another possible implementation, if the (L-2) calculation results are all greater than the first threshold, it is determined that the battery capacity of the first battery has not dropped within the L cycles.

[0137] Optionally, after S203 , the method 200 may further include: obtaining the first battery information described in the method 100 based on the determination result.

[0138] In a possible implementation, if the battery capacity of the first battery drops within the K+2th cycle among the L cycles, the N cycles include the first K+2 cycles among the L cycles.

[0139] For example, taking the (L-2) calculation results as shown in Table 3, ΔC1', ΔC2'...ΔC298', and the first threshold value as 0, if ΔC150'=0, then the capacity of the first battery will drop in the 152nd cycle corresponding to ΔC150'. The N cycles included in the first battery information in method 100 may include at least the 1st to 152nd cycles shown in Table 3. For example, the N cycles may include the 1st to 200th cycles shown in Table 3.

[0140] In another possible implementation, if it is determined that the battery capacity of the first battery has not dropped within the L cycles, the N cycles include the first N cycles of the L cycles.

[0141] For example, taking the (L-2) calculation results as shown in Table 3 (ΔC1', ΔC2'...ΔC298'), and the first threshold value as 0, if ΔC1', ΔC2'...ΔC298' are all > 0, then the first battery has not experienced a capacity drop from the 1st to the 300th cycle. The N cycles included in the first battery information in method 100 can include at least the 1st cycle to any cycle shown in Table 3.

[0142] Optionally, the number of N cycle periods included in the first battery information in method 100 may be greater than the number of cycle periods shown in Table 3, so as to provide more cycle periods for generating the target battery capacity model.

[0143] It can be seen that the method provided in the embodiment of the present application can predict the battery capacity at each stage of the battery aging process. That is to say, the battery capacity in the gradual stabilization trend stage can be predicted, and the battery capacity in the diving stage can also be predicted. The capacity diving point can be predicted, and the battery diving can be predicted, which is conducive to timely adopting appropriate management and maintenance strategies for the battery based on the attenuation of the battery capacity, thereby improving the battery life.

[0144] Combined with the above Figure 1 and Figure 2 The generation method of the battery capacity prediction model provided by the embodiment of the present application is introduced. The battery capacity prediction method provided by the embodiment of the present application will be introduced below.

[0145] Figure 3 A schematic flow chart of a battery capacity prediction method 300 provided in an embodiment of the present application is shown. The method 300 can be executed by a battery capacity prediction device (which will be described in detail below and referred to as a prediction device for short).

[0146] S301, obtaining a target capacity prediction model, where the target capacity prediction model is used to indicate a correspondence between a battery cycle and a battery capacity, the target capacity prediction model being obtained based on a first capacity prediction model and a second capacity prediction model, the first capacity prediction model being obtained based on first target battery information of the battery and a first fitting function, the first target battery information being used to indicate a battery capacity actually tested in each of M cycle cycles of the battery, the first fitting function and a curve corresponding to the first target battery information satisfying a preset first fitting condition, the second capacity prediction model being obtained based on the second target battery information of the battery and a second fitting function, the second target battery information being used to indicate a battery capacity deviation value of the battery in each of P cycle cycles of the battery, the battery capacity deviation value being a difference between a battery capacity actually tested and a battery capacity predicted by the first capacity prediction model, the second fitting function and the second target battery information satisfying a preset second fitting condition, wherein M and P are both integers greater than 1, and the minimum cycle period of the P cycle cycles is greater than the maximum cycle period of the M cycle cycles.

[0147] Optionally, the embodiment of the present application does not limit the method for obtaining the target capacity prediction model.

[0148] In a possible implementation, the target capacity prediction model may be pre-configured in the prediction device.

[0149] In another possible implementation, the prediction device may receive the target capacity prediction model from other devices. For example, the prediction device may receive the target capacity prediction model from the above-mentioned generation device.

[0150] In another possible implementation, the prediction device may generate the target capacity prediction model. For example, the prediction device may use the generation method described in method 100 and method 200 to generate the target capacity prediction model.

[0151] S302: Predicting the battery capacity of the battery based on the target capacity prediction model.

[0152] Optionally, the prediction model may also predict the battery capacity of other batteries of the same model and / or production batch as the battery based on the target capacity prediction model.

[0153] In a possible implementation, the prediction model may input the target cycle period to be predicted into the target capacity prediction to output the battery capacity corresponding to the target cycle period.

[0154] As can be seen, the battery capacity prediction method provided in the embodiments of this application, which uses the battery capacity prediction model generated by the two-stage model generation method to perform battery capacity prediction, can improve the accuracy of battery capacity prediction. In addition, the ability to predict the battery's drop point facilitates battery management and maintenance, thereby extending the battery's service life.

[0155] Combined with the above Figure 1 and Figure 2 The invention provides a method for generating a battery capacity prediction model. Figure 3 The battery capacity prediction method provided by the embodiment of the present application is introduced. Figures 4 to 6 A generation device for executing the above generation method and a prediction device for executing the above prediction method are introduced.

[0156] It is understandable that, in order to realize the above functions, the generating device or the predicting device includes hardware and / or software modules corresponding to the execution of each function. In combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in combination with the embodiments, but such implementation should not be considered to be beyond the scope of this application.

[0157] In this embodiment, the generation device or prediction device can be divided into functional modules based on the above-described method examples. For example, different functional modules can be divided according to different functions, or two or more functions can be integrated into a single processing module. The integrated modules can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used.

[0158] In the case of dividing each functional module into corresponding functional modules, Figure 4 A possible schematic diagram of the composition of the generating device or prediction device involved in the above embodiment is shown. Figure 4 As shown, the device 400 may include: a transceiver unit 410 and a processing unit 420.

[0159] The processing unit 420 may control the transceiver unit 410 to implement the method performed by the generating device or the predicting device in the embodiment of the method 200 described above, and / or other processes used for the technology described herein.

[0160] It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0161] In the case of integrated units, the apparatus 400 may include a processing unit, a storage unit, and a communication unit. The processing unit may be used to control and manage the operations of the apparatus 400, for example, to support the apparatus 400 in executing the steps performed by the aforementioned units. The storage unit may be used to support the apparatus 400 in executing and storing program codes and data. The communication unit may be used to support communication between the apparatus 400 and other devices.

[0162] The processing unit may be a processor or a controller. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, and so on. The storage unit may be a memory. The communication unit may specifically be a device that interacts with other electronic devices, such as a radio frequency circuit, a Bluetooth chip, or a Wi-Fi chip.

[0163] In a possible implementation, the generating device or predicting device involved in the embodiment of the present application may be a device having Figure 5 The device 500 of the structure shown can be a structural diagram of a generating device or a structural diagram of a predicting device. The device 500 includes a processor 510 and a transceiver 520. The processor 510 and the transceiver 520 communicate with each other through an internal connection path. Figure 4 The relevant functions implemented by the processing unit 420 in the embodiment can be implemented by the processor 510, and the relevant functions implemented by the transceiver unit 410 can be implemented by the processor 510 controlling the transceiver 520.

[0164] Optionally, the apparatus 500 may further include a memory 530 , and the processor 510 , the transceiver 520 , and the memory 530 communicate with each other via an internal connection path. Figure 4 The related functions implemented by the storage unit described in the preceding paragraph can be implemented by the memory 530.

[0165] An embodiment of the present application also provides a computer storage medium, which stores computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned related method steps to implement the method for generating a battery capacity prediction model in the above-mentioned method embodiment or implement the battery capacity prediction method in the above-mentioned method embodiment.

[0166] An embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the above-mentioned related steps to implement the method for generating a battery capacity prediction model in the above-mentioned method embodiment or implement the battery capacity prediction method in the above-mentioned method embodiment.

[0167] In addition, an embodiment of the present application also provides a device, which can specifically be a chip, component or module, and the device may include a connected processor and memory; wherein the memory is used to store computer-executable instructions, and when the device is running, the processor can execute the computer-executable instructions stored in the memory to enable the chip to execute the battery capacity prediction model generation method in the above-mentioned method embodiments or execute the battery capacity prediction method in the above-mentioned method embodiments.

[0168] Figure 6 FIG. 6 is a schematic diagram showing the structure of a chip 600. The chip 600 includes one or more processors 610 and an interface circuit 620. Optionally, the chip 600 may further include a bus 630.

[0169] The processor 610 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 610 or instructions in the form of software. The above-mentioned processor 610 can be a general-purpose processor, a digital signal processing (DSP), an integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The various methods and steps disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0170] The interface circuit 620 can be used to send or receive data, instructions or information. The processor 610 can use the data, instructions or other information received by the interface circuit 620 to process, and can send the processing completion information through the interface circuit 620.

[0171] Optionally, the chip also includes a memory, which may include a read-only memory and a random access memory, and provides operating instructions and data to the processor. Part of the memory may also include a non-volatile random access memory (NVRAM).

[0172] Optionally, the memory stores an executable software module or a data structure, and the processor can perform corresponding operations by calling an operation instruction stored in the memory (the operation instruction may be stored in an operating system).

[0173] Optionally, the chip can be used in a version management device or access version management device involved in an embodiment of the present application. Optionally, the interface circuit 620 can be used to output the execution result of the processor 610. Regarding the method for generating a battery capacity prediction model or a battery capacity prediction method provided in one or more embodiments of the present application, reference can be made to the aforementioned embodiments and will not be repeated here.

[0174] It should be noted that the corresponding functions of the processor 610 and the interface circuit 620 can be implemented through hardware design, software design, or a combination of hardware and software, and there is no limitation here.

[0175] The embodiment of the present application also provides an electronic device, which includes the above Figure 4 The device 400 described in Figure 5 The device 500 or Figure 6 The chip 600 described in.

[0176] It should be noted that the generation device, prediction device, computer storage medium, computer program product, chip or terminal provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0177] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0178] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0179] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0180] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0181] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0182] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0183] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as 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.

[0184] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A battery capacity prediction method, characterized in that: include: Obtaining a target capacity prediction model, where the target capacity prediction model is used to indicate a correspondence between a battery cycle and a battery capacity, the target capacity prediction model being obtained based on a first capacity prediction model and a second capacity prediction model, the first capacity prediction model being obtained based on first target battery information and a first fitting function of the battery, the first target battery information being used to indicate a battery capacity actually tested in each of M cycle cycles, the first fitting function and a curve corresponding to the first target battery information satisfying a preset first fitting condition, the second capacity prediction model being obtained based on the second target battery information and a second fitting function of the battery, the second target battery information being used to indicate a battery capacity deviation value in each of P cycle cycles of the battery, the battery capacity deviation value being a difference between a battery capacity actually tested and a battery capacity predicted by the first capacity prediction model, the second fitting function and the second target battery information satisfying a preset second fitting condition, wherein M and P are both integers greater than 1, and a minimum cycle period among the P cycle cycles is greater than a maximum cycle period among the M cycle cycles; The battery capacity of the battery is predicted based on the target capacity prediction model.

2. The method according to claim 1, characterized in that The obtaining of the target capacity prediction model includes: generating a first capacity prediction model based on the first target battery information and the first fitting function; generating a second capacity prediction model based on the second target battery information and the second fitting function; The target capacity prediction model is generated based on the first capacity prediction model and the second capacity prediction model.

3. The method according to claim 2, characterized in that Before generating the first capacity prediction model based on the first target battery information and the first fitting function of the battery, the method further includes: Obtaining first battery information of the battery, where the first battery information is used to indicate a battery capacity actually tested and obtained in each of N cycles of the battery, where the N cycles include the M cycle; Fitting a curve corresponding to the battery capacity actually tested during the first j cycles of the N cycles using the first fitting function to obtain a fitting degree corresponding to the first j cycles, where j is an integer greater than 1 and less than or equal to N; If the fitting degrees corresponding to the first M cycles among the N cycles meet the first fitting condition, the first M cycles and the battery capacity actually tested in each of the first M cycles are determined as the first target battery information.

4. The method according to claim 3, characterized in that The obtaining first battery information of the battery includes: determining, based on third battery information of the battery, whether a battery capacity of the battery drops within L cycles, the third battery information including the L cycles and a battery capacity actually tested in each of the L cycles, where L is an integer greater than 2; Based on the determination result, the first battery information is obtained.

5. The method according to claim 4, characterized in that The determining, based on the third battery information of the battery, whether the battery capacity of the battery drops within L cycles includes: Performing two differential operations on the battery capacity actually tested during the L cycles to obtain L-2 operation results; Based on the L-2 calculation results, it is determined whether the battery capacity of the battery drops within the L cycles.

6. The method according to claim 5, characterized in that The determining, based on the L-2 calculation results, whether the battery capacity of the battery drops within the L cycles includes: If the Kth calculation result among the L-2 calculation results is less than or equal to a preset first threshold, it is determined that the battery capacity of the battery has dropped within the K+2th cycle among the L cycles, where K is an integer greater than or equal to 0 and less than or equal to L-2; or If the L-2 calculation results are all greater than the first threshold, it is determined that the battery capacity of the battery has not dropped within the L cycle periods.

7. The method according to any one of claims 4 to 6, characterized in that If the battery capacity of the battery drops in the K+2th cycle among the L cycles, the N cycles include the first K+2 cycles among the L cycles.

8. The method according to any one of claims 4 to 6, characterized in that If the battery capacity of the battery does not drop within the L cycles, the N cycles include the first N cycles of the L cycles.

9. The method according to claim 2, characterized in that Before generating a second capacity prediction model based on the second target battery information and the second fitting function of the battery, the method further includes: Obtaining second battery information of the battery, where the second battery information is used to indicate a battery capacity deviation value of the battery in each of Q cycle periods, where the Q cycle periods include the P cycle periods, and a minimum cycle period of the Q cycle periods is greater than a maximum cycle period of the M cycle periods; Fitting a curve corresponding to the battery capacity deviation value in the first k cycles of the Q cycles using the second fitting function to obtain a fitting degree corresponding to the first k cycles, where k is an integer greater than 1 and less than or equal to Q; If the fitting degrees corresponding to the first P cycles among the Q cycles meet the second fitting condition, the first P cycles and the battery capacity deviation value of the battery in each cycle among the first P cycles are determined as the second target battery information.

10. The method according to claim 2, characterized in that The generating a target capacity prediction model based on the first capacity prediction model and the second capacity prediction model includes: The target capacity prediction model is generated based on the first capacity prediction model, the second capacity prediction model and preset weighting coefficients, where the weighting coefficients include a first weighting coefficient of the first capacity prediction model and a second weighting coefficient of the second capacity prediction model.

11. The method according to claim 1, wherein The first fitting function includes one or more of an exponential function, a polynomial function, and a logarithmic function; and / or, The second fitting function includes one or more of an exponential function, a polynomial function, and a logarithmic function.

12. A method for generating a battery capacity prediction model, characterized in that: include: generating a first capacity prediction model based on first target battery information of a first battery and a first fitting function, wherein the first target battery information is used to indicate a battery capacity actually tested and obtained during each of M cycles of the first battery, wherein a degree of fit of a curve corresponding to the first fitting function and the first target battery information satisfies a preset first fitting condition, and M is an integer greater than 1; generating a second capacity prediction model based on second target battery information of the first battery and a second fitting function, wherein the second target battery information is used to indicate a battery capacity deviation value of the first battery in each of P cycles, the battery capacity deviation value being a difference between a battery capacity obtained by actual testing and a battery capacity predicted by the first capacity prediction model, wherein a degree of fit between the second fitting function and the second target battery information satisfies a preset second fitting condition, P is an integer greater than 1, and a minimum cycle period of the P cycles is greater than a maximum cycle period of the M cycles; A target capacity prediction model is generated based on the first capacity prediction model and the second capacity prediction model, where the target capacity prediction model is used to indicate a corresponding relationship between a cycle period of the first battery and a battery capacity.

13. The method according to claim 12, characterized in that Before generating the first capacity prediction model based on the first target battery information of the first battery and the first fitting function, the method further includes: Obtaining first battery information of the first battery, where the first battery information is used to indicate a battery capacity of the first battery actually tested in each of N cycles, where the N cycles include the M cycle; Fitting a curve corresponding to the battery capacity actually tested during the first j cycles of the N cycles using the first fitting function to obtain a fitting result corresponding to the first j cycles, where j is an integer greater than 1 and less than or equal to N; If the fitting degrees corresponding to the first M cycles among the N cycles meet the first fitting condition, the battery capacities actually tested for the first M cycles and the first battery in each of the first M cycles are determined as the first target battery information.

14. The method according to claim 13, characterized in that The obtaining first battery information of the first battery includes: determining, based on third battery information of the first battery, whether a battery capacity of the first battery decreases within L cycles, the third battery information including the L cycles and a battery capacity actually tested in each of the L cycles, where L is an integer greater than 2; Based on the determination result, the first battery information is obtained.

15. The method according to claim 14, characterized in that The determining, based on the third battery information of the first battery, whether the battery capacity of the first battery drops within L cycles includes: Performing two differential operations on the battery capacity actually tested during the L cycles to obtain L-2 operation results; Based on the L-2 calculation results, it is determined whether the battery capacity of the first battery drops within the L cycles.

16. The method according to claim 15, characterized in that The determining, based on the L-2 calculation results, whether the battery capacity of the first battery decreases within the L cycles includes: If the Kth calculation result among the L-2 calculation results is less than or equal to a preset first threshold, it is determined that the battery capacity of the first battery has dropped within the K+2th cycle among the L cycles, where K is an integer greater than or equal to 0 and less than or equal to L-2; or If the L-2 calculation results are all greater than the first threshold, it is determined that the battery capacity of the first battery has not dropped within the L cycle periods.

17. The method according to any one of claims 14 to 16, characterized in that If the battery capacity of the first battery drops within the K+2th cycle among the L cycles, the N cycles include the first K+2 cycles among the L cycles.

18. The method according to any one of claims 14 to 16, characterized in that If the battery capacity of the first battery does not drop within the L cycles, the N cycles are the first N cycles of the L cycles.

19. The method according to claim 12, wherein: Before generating a second capacity prediction model based on the second target battery information of the first battery and the second fitting function, the method further includes: Obtaining second battery information of the first battery, where the second battery information is used to indicate a battery capacity deviation value of the first battery in each of Q cycles, where the Q cycles include the P cycles, and a minimum cycle period of the Q cycles is greater than a maximum cycle period of the M cycles; Fitting a curve corresponding to the battery capacity deviation value in the first k cycles of the Q cycles using the second fitting function to obtain a fitting result corresponding to the first k cycles, where k is an integer greater than 1 and less than or equal to Q; If the fitting degrees corresponding to the first P cycles among the Q cycles meet the second fitting condition, the first P cycles and the battery capacity deviation value of the first battery in each cycle of the first P cycles are determined as the second target battery information.

20. The method according to claim 12, wherein The method further comprises: Based on the target capacity prediction model, a battery capacity of a second battery is predicted, where the second battery has the same model and / or production batch as the first battery.

21. The method according to claim 12, wherein The generating a target capacity prediction model based on the first capacity prediction model and the second capacity prediction model includes: The target capacity prediction model is generated based on the first capacity prediction model, the second capacity prediction model and preset weighting coefficients, where the weighting coefficients include a first weighting coefficient of the first capacity prediction model and a second weighting coefficient of the second capacity prediction model.

22. The method according to claim 12, wherein: The first fitting function includes one or more of an exponential function, a polynomial function, and a logarithmic function; and / or, The second fitting function includes one or more of an exponential function, a polynomial function, and a logarithmic function.

23. A battery capacity prediction device, comprising at least one processor and a memory, wherein the at least one processor and the memory are coupled, characterized in that: The at least one processor executes the program or instruction stored in the memory, so that the apparatus implements the method according to any one of claims 1 to 11.

24. A device for generating a battery capacity prediction model, comprising at least one processor and a memory, wherein the at least one processor and the memory are coupled, characterized in that: The at least one processor executes the program or instruction stored in the memory, so that the apparatus implements the method according to any one of claims 12 to 22.

25. A chip device comprising at least one processor and an interface circuit, wherein the at least one processor is coupled to the interface circuit, and the at least one processor sends or receives information via the interface circuit, wherein: When the at least one processor executes the program code or instruction, the method according to any one of claims 1 to 11 or the method according to any one of claims 12 to 22 is implemented.

26. An electronic device, characterized in that: It includes the battery capacity prediction device as described in claim 23, the battery capacity prediction model generation device as described in claim 24, or the chip device as described in claim 25.

27. A computer-readable storage medium for storing a computer program, characterized in that: The computer program comprises instructions for implementing the method of any one of claims 1 to 11 or any one of claims 12 to 22 above.

28. A computer program product comprising instructions, characterized in that: When the instructions are executed on a computer or a processor, the computer or the processor is caused to implement the method according to any one of claims 1 to 11 or any one of claims 12 to 22.

Images