Battery cycle life prediction method and device, computer equipment, medium and product

Abstract

The invention relates to the technical field of electronics, and discloses a battery cycle life prediction method and device, computer equipment, a medium and a product. According to the method, a battery cycle life prediction model is constructed through historical cycle data of a battery, a buffer operator and a grey prediction model; and inputting the target cycle index of the battery into the battery cycle life prediction model for calculation to obtain battery capacity information of the battery under the target cycle index. The buffer operator can weaken the influence of the rapid change of the historical cycle data on the subsequent prediction, and only a small amount of historical data is needed when the gray prediction model is utilized to construct the battery cycle life prediction model, so that the prediction precision of the constructed battery cycle life prediction model is higher. The battery cycle life prediction model constructed based on the historical cycle data of the battery, the buffer operator and the gray prediction model can achieve more accurate cycle life prediction, and the accuracy and efficiency of battery cycle life prediction are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of electronic technology, and in particular to a battery cycle life prediction method, device, computer equipment, medium and product. Background Art

[0002] Secondary batteries are widely used in daily life, such as portable electronic devices, electric vehicles, energy storage systems, etc. With the development of technology, the performance and life of secondary batteries are constantly improving, but their cycle life is still limited by various factors, such as battery materials, usage conditions, and the number of charge and discharge cycles. Accurately predicting the battery cycle life is of great significance for optimizing battery use, extending battery life, and avoiding safety issues caused by battery failure.

[0003] In the related art, the secondary battery cycle life prediction methods mainly include experimental testing, battery simulation models, etc. These methods can achieve certain prediction effects in some cases, but they have certain limitations. The experimental test method has high accuracy, but it is time-consuming, labor-intensive and costly; the battery simulation model requires a large amount of battery history data and detailed battery parameters to correct the prediction accuracy of the model, otherwise the prediction accuracy of the model is low. Therefore, it is urgent to propose an efficient and highly accurate battery cycle life prediction method. Summary of the invention

[0004] In view of this, the present invention provides a battery cycle life prediction method, device, computer equipment, medium and product to solve the problems of low prediction efficiency and low prediction accuracy in the secondary battery cycle life prediction method in the related art.

[0005] In a first aspect, the present invention provides a battery cycle life prediction method, the method comprising: obtaining a target number of cycles of a battery, historical cycle data of the battery, a buffer operator and a grey prediction model, the historical cycle data being used to characterize historical capacity information corresponding to different historical cycle numbers; constructing a battery cycle life prediction model based on the historical cycle data of the battery, the buffer operator and the grey prediction model, the battery cycle life prediction model being used to characterize the relationship between the number of cycles and capacity information of the battery; inputting the target number of cycles of the battery into the battery cycle life prediction model for calculation, and obtaining the battery capacity information of the battery at the target number of cycles.

[0006] The battery cycle life prediction method provided by the present invention constructs a battery cycle life prediction model through the historical cycle data of the battery, a buffer operator and a gray prediction model, inputs the target number of cycles of the battery into the battery cycle life prediction model for calculation, and obtains the battery capacity information of the battery under the target number of cycles. The method provided by the present invention constructs a battery cycle life prediction model through the historical cycle data of the battery, a buffer operator and a gray prediction model. The buffer operator can realize the smoothing of the historical cycle data, weaken the influence of the rapid change of the historical cycle data on the subsequent prediction, and make the constructed battery cycle life prediction model have higher prediction accuracy. Since the gray system theory has unique advantages in processing uncertainty and small sample data, only a small amount of historical data is required when the gray prediction model in the gray system theory is used to construct the battery cycle life prediction model. The battery cycle life prediction model constructed based on the historical cycle data of the battery, the buffer operator and the gray prediction model can achieve more accurate cycle life prediction, effectively improve the accuracy and efficiency of the battery cycle life prediction, and provide strong support for the optimized use of secondary batteries, extending the battery pack life and avoiding battery pack failure.

[0007] In an optional embodiment, the historical cycle data is the original cycle life sequence of the battery, the grey prediction model includes a grey differential model of the grey system, and the step of constructing the battery cycle life prediction model according to the historical cycle data of the battery, the buffer operator and the grey prediction model includes: using the buffer operator to process the original cycle life sequence to obtain a buffered cycle life sequence; sequentially accumulating the first k data in the buffered cycle life sequence and using them as the kth data of the target sequence, wherein k ranges from 1 to n, n is the number of data in the buffered cycle life sequence, and the target sequence includes n data; converting the target sequence into a sequence generated by the nearest mean; solving the grey differential model using the target sequence and the sequence generated by the nearest mean to obtain model parameter values ​​of the grey differential model; determining the cumulative prediction value function of the grey system based on the model parameter values ​​and the grey differential model; and cumulatively restoring the cumulative prediction value function to obtain the battery cycle life prediction model.

[0008] The method provided in this optional implementation utilizes a buffer operator to smooth historical cycle data, thereby weakening the impact of rapid changes in historical cycle data on subsequent predictions. By using less data to establish a prediction model, it is suitable for scenarios where the amount of data is small or the data is incomplete. The prediction model can handle uncertainty problems and is suitable for dynamically changing systems such as batteries. The prediction results are relatively accurate and can provide useful information for battery management and maintenance.

[0009] In an optional embodiment, after the cumulative prediction value function is cumulatively restored to obtain a battery cycle life prediction model step, the method also includes: obtaining multiple cycle number data and first battery capacity information corresponding to each cycle number data; inputting each cycle number data into the battery cycle life prediction model for calculation to obtain second battery capacity information corresponding to the cycle number; calculating the absolute residual of the corresponding cycle number data based on the first battery capacity information and the second battery capacity information of each cycle number data; calculating the relative residual of the corresponding cycle number data based on the absolute residual of each cycle number data and the first battery capacity data; judging whether the prediction accuracy of the battery cycle life prediction model meets the preset requirements based on the absolute residual and relative residual of each cycle number data to obtain a judgment result; performing optimization operations on the battery cycle life prediction model based on the judgment result, the optimization operations include adjusting model parameters and improving model structure.

[0010] The method provided by this optional implementation manner determines whether the prediction accuracy of the battery cycle life prediction model meets the preset requirements by calculating the absolute residual and relative residual of each cycle number data, thereby effectively realizing the evaluation of the prediction accuracy of the battery cycle life prediction model, and optimizing the battery cycle life prediction model through the judgment results, thereby ensuring the prediction accuracy of the battery cycle life prediction model.

[0011] In an optional implementation, the buffer operator is shown as follows:

[0012]

[0013] Among them, c d (k) represents the buffer operator, α represents the weakening coefficient, c(k) represents the kth cycle data of the original cycle life sequence, and c(i) represents the ith cycle data of the original cycle life sequence.

[0014] In an optional embodiment, the model parameter value includes a development coefficient value, and after the cumulative prediction value function is cumulatively restored to obtain a battery cycle life prediction model step, the method also includes: determining a target cycle number interval for the battery corresponding to the target cycle number; determining a corresponding target development coefficient value interval based on the target cycle number interval; if the development coefficient value is not in the target development coefficient value interval, determining that the battery cycle life prediction model is a battery cycle life prediction model to be optimized; and optimizing and updating the battery cycle life prediction model to be optimized.

[0015] In an optional embodiment, the historical capacity information includes a capacity retention rate, and the historical cycle data is obtained by the following steps: obtaining the initial battery capacity of the battery and the battery capacities corresponding to different numbers of cycles; calculating the capacity retention rate of the battery at the corresponding number of cycles based on the battery capacity at each number of cycles and the initial battery capacity; and using each number of cycles of the battery and the capacity retention rate corresponding to each number of cycles as historical cycle data.

[0016] In a second aspect, the present invention provides a battery cycle life prediction device, which includes: an acquisition module for acquiring a target number of cycles of a battery, historical cycle data of the battery, and a gray prediction model; a construction module for constructing a battery cycle life prediction model based on the historical cycle data of the battery and the gray prediction model; and a calculation module for inputting the target number of cycles of the battery into the battery cycle life prediction model for calculation to obtain the battery capacity information of the battery at the target number of cycles.

[0017] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the battery cycle life prediction method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0018] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the battery cycle life prediction method of the first aspect or any corresponding embodiment thereof.

[0019] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the battery cycle life prediction method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 is a schematic flow chart of a battery cycle life prediction method according to an embodiment of the present invention;

[0022] Figure 2 is a flow chart of another battery cycle life prediction method according to an embodiment of the present invention;

[0023] Figure 3 Schematic diagram of the correlation between the number of cycles and the measured secondary battery capacity retention rate in an embodiment of the present invention;

[0024] Figure 4 is a schematic diagram of a comparison result between the actually measured capacity retention rate of a secondary battery of the present invention and a predicted value in an embodiment of the present invention;

[0025] Figure 5 It is a schematic diagram of the system architecture of the secondary battery cycle life prediction system;

[0026] Figure 6 is a structural block diagram of a battery cycle life prediction device according to an embodiment of the present invention;

[0027] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0029] In the related art, the methods for predicting the cycle life of secondary batteries mainly include experimental testing, black box models, etc. These methods can achieve certain prediction results in some cases, but they have certain limitations. The experimental testing method has high accuracy, but it is time-consuming, labor-intensive and costly; the black box model is mainly targeted at specific types of batteries and has poor universality.

[0030] In view of this, a battery cycle life prediction method provided in an embodiment of the present application can be applied to a server to realize the prediction of battery cycle life. The method provided in an embodiment of the present application constructs a battery cycle life prediction model through the historical cycle data of the battery, a buffer operator and a gray prediction model. The buffer operator can realize the smoothing of the historical cycle data, weaken the influence of the rapid change of the historical cycle data on the subsequent prediction, and make the constructed battery cycle life prediction model have higher prediction accuracy. Since the gray system theory has unique advantages in dealing with uncertainty and small sample data, only a small amount of historical data is required when using the gray prediction model in the gray system theory to construct the battery cycle life prediction model. The battery cycle life prediction model constructed based on the historical cycle data of the battery, the buffer operator and the gray prediction model can achieve a more accurate cycle life prediction, effectively improve the accuracy and efficiency of the battery cycle life prediction, and provide strong support for the optimized use of secondary batteries, extending the battery pack life and avoiding battery pack failure. At the same time, by predicting the battery cycle life, it is also of great significance in the fields of environmental protection, energy management and green energy, which helps to promote sustainable development and reduce energy waste.

[0031] According to an embodiment of the present invention, an embodiment of a battery cycle life prediction method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] In this embodiment, a battery cycle life prediction method is provided, which can be used for the above-mentioned server. Figure 1 is a flow chart of a battery cycle life prediction method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0033] Step S101, obtaining the target cycle number of the battery, the historical cycle data of the battery, the buffer operator and the grey prediction model.

[0034] Exemplarily, the battery may be a secondary battery for which cycle life prediction is required. The historical cycle data is used to characterize the battery capacity information corresponding to different numbers of cycles of the battery during the historical cycle process. The battery capacity information can be used to characterize the cycle life of the battery. For example, the battery capacity information may include but is not limited to the battery capacity, the battery capacity retention rate, etc., wherein the battery capacity refers to the capacity of the battery when the battery is fully charged during the charging cycle. In the embodiment of the present application, the gray prediction model may include but is not limited to GM(n,h), and GM(n,h) is a differential equation model that can be used to make long-term, continuous and dynamic reflections on the described object. Wherein "n" represents the order of the differential equation, and "h" represents the number of variables in the differential equation. The buffer operator is used to smooth a sequence of data, remove the noise values ​​and outliers therein, thereby reducing the interference level and extracting effective signals. The present application is an embodiment and does not limit the specific content of the buffer operator, and those skilled in the art can determine it according to needs.

[0035] Step S102, constructing a battery cycle life prediction model based on the historical cycle data of the battery, the buffer operator and the grey prediction model.

[0036] Exemplarily, a battery cycle life prediction model is constructed by using the battery's historical cycle data, a buffer operator, and a gray prediction model. The constructed battery cycle life prediction model is used to characterize the correlation between the number of cycles and the battery capacity information. The role of the buffer operator is to perform smooth optimization processing on the historical cycle data. Using a weakened buffer operator to perform smooth optimization on the historical data can effectively reduce the impact of rapid changes in historical cycle data on subsequent predictions. The mathematical expression of the buffer operator can be designed and optimized according to the specific battery data characteristics and prediction requirements. The embodiments of the present application do not limit the specific content of the buffer operator, and those skilled in the art can determine it according to needs.

[0037] Step S103, inputting the target cycle number of the battery into the battery cycle life prediction model for calculation to obtain the battery capacity information of the battery under the target cycle number.

[0038] Exemplarily, the target number of cycles is input into a battery cycle life prediction model for solution, and the battery capacity information at the target number of cycles can be obtained.

[0039] The battery cycle life prediction method provided in this embodiment constructs a battery cycle life prediction model through the historical cycle data of the battery, a buffer operator and a gray prediction model. The buffer operator can realize the smoothing of the historical cycle data, weaken the influence of the rapid changes of the historical cycle data on the subsequent prediction, and make the constructed battery cycle life prediction model more accurate. Since the gray system theory has unique advantages in processing uncertainty and small sample data, only a small amount of historical data is required when the gray prediction model in the gray system theory is used to construct the battery cycle life prediction model. The battery cycle life prediction model constructed based on the historical cycle data of the battery, the buffer operator and the gray prediction model can achieve a more accurate cycle life prediction, effectively improving the accuracy and efficiency of the battery cycle life prediction. It can help users replace the battery in time when the battery cycle life is about to expire, thereby extending the overall service life of the battery pack, reducing equipment failures caused by battery performance degradation, and providing strong support for the optimized use of secondary batteries and extending the life of the battery pack.

[0040] In this embodiment, a battery cycle life prediction method is provided, which can be used for the above-mentioned server. Figure 2 is a flow chart of a battery cycle life prediction method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0041] Step S201, obtain the target cycle number of the battery, the historical cycle data of the battery and the grey prediction model. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0042] In some optional implementations, the historical capacity information includes a capacity retention rate, and the historical cycle data is obtained by the following steps:

[0043] Step a1, obtaining the initial battery capacity of the battery and the battery capacities corresponding to different cycle numbers.

[0044] For example, in the embodiment of the present application, the initial battery capacity of the battery and the battery capacity corresponding to different cycle times can be obtained by laboratory measurement. During the measurement process, it is necessary to ensure that the factors affecting the cycle life, such as discharge rate, temperature, and charging method, are the same.

[0045] In the embodiment of the present application, since the battery cycle is long and the amount of cycle data is large, in order to save computing power without affecting the accuracy, the battery capacity corresponding to different cycle times can be obtained by setting the cycle time interval and selecting the points of some cycle times to obtain the battery capacity to obtain the historical cycle data. Exemplarily, obtaining the battery capacity corresponding to different cycle times includes: determining the initial change law between the battery cycle times and the battery capacity, determining the cycle time interval of the battery at different cycle times using the initial change law, determining the number of point-taking cycles using the cycle time interval, and obtaining the battery capacity corresponding to the number of point-taking cycles.

[0046] Specifically, in the early stage of the battery cycle, as the number of cycles increases, the battery capacity decays more dramatically. In the middle and late stages of the battery cycle, as the number of cycles increases, the battery capacity decays gradually. Therefore, in the early stage of the battery cycle, the point-taking interval is the first number, and in the middle and late stages of the battery cycle, the point-taking interval is the second number, wherein the first number is greater than the second number. For example, when the number of cycles is 0 to 200, a point is taken every 50 cycles, and when the number of cycles is greater than two hundred, a point is taken every 100 cycles. The early stage of the battery cycle can be a period corresponding to a cycle number of 0 to 200, and the middle and late stages of the battery cycle can be a period corresponding to a cycle number greater than 200. The embodiment of the present application uses different cycle number intervals to take points at different stages of the battery cycle, and the data obtained can better reflect the law of change of battery capacity with the number of cycles.

[0047] Step a2, calculating the capacity retention rate of the battery at the corresponding number of cycles based on the battery capacity at each number of cycles and the initial battery capacity.

[0048] Exemplarily, the capacity retention rate at each cycle number is equal to the ratio of the battery capacity at the corresponding cycle number to the initial battery capacity. In the embodiment of the present application, a curve showing the change of the battery capacity retention rate with the cycle number can be drawn with the cycle number as the horizontal coordinate and the capacity retention rate as the vertical coordinate. By observing the trend of the curve, the change law of the battery capacity retention rate with the cycle number can be intuitively understood.

[0049] Step a3, taking the number of cycles of the battery and the capacity retention rate corresponding to each cycle number as historical cycle data.

[0050] Step S202: constructing a battery cycle life prediction model based on the historical cycle data of the battery, the buffer operator and the grey prediction model.

[0051] Specifically, the historical cycle data is the original cycle life sequence of the battery, and the grey prediction model includes a grey differential model of the grey system. In the embodiment of the present application, the original cycle life sequence is used to characterize the capacity retention rate of the battery under different cycle times. The above step S202 includes:

[0052] Step S2021, using a buffer operator to process the original cycle life sequence to obtain a buffered cycle life sequence.

[0053] For example, in the embodiment of the present application, the original cycle life sequence can be shown as the following formula (1):

[0054] C=[c(1),c(2),…c(k),…,c(n)] (1)

[0055] Wherein, C represents the original cycle life sequence, and the original cycle life sequence includes n cycle data. Wherein, c(k) represents the kth cycle data, k=1,...,n. The embodiment of the present application takes the cycle number interval of 100 as an example for illustrative explanation. When k=1, it means the first point taking, and the cycle number is 100; k=2, it means the second point taking, and the cycle number is 200..., and so on. The embodiment of the present application does not limit the specific method of taking points, and those skilled in the art can determine it according to needs.

[0056] Furthermore, a suitable buffer operator can be determined by analyzing the historical cycle data of the battery. In the embodiment of the present application, the buffer operator can be shown as the following formula (2):

[0057]

[0058] Among them, c d (k) represents a buffer operator, α represents a weakening coefficient, and 0<α<1.

[0059] Use the buffer operator to process each cycle data of the original cycle life sequence, let c d (k) = x (0) (k), the cycle life sequence after buffering can be shown as follows:

[0060] X (0) =[x (0) (1),x (0) (2),…,x (0) (k),…,x (0) (n)] (3)

[0061] Among them, X (0) represents the cycle life sequence after buffering, where x (0) (k) represents the cycle life data after the kth buffer, k=1, ..., n.

[0062] Step S2022, accumulate the first k data in the buffered cycle life sequence in turn and use them as the kth data of the target sequence, where k ranges from 1 to n, n is the number of data in the buffered cycle life sequence, and the target sequence includes n data.

[0063] For example, in the embodiment of the present application, since the data in the sequence of the above formula (3) are mostly irregular, random, and have obvious fluctuations, if the buffered cycle life sequence is accumulated and regenerated, X is obtained. (0) The (1-AGO) sequence (target sequence) is shown in the following formula (4):

[0064] X (1) =[x (1) (1),x (1) (2),…,x (1) (k),…,x (1) (n)](4)

[0065] Among them, X (1) represents the target sequence,

[0066] The newly generated target sequence is a monotonically growing curve, which increases the regularity of the original data and weakens the volatility.

[0067] Step S2023, converting the target sequence into a sequence generated by the nearest mean.

[0068] Exemplarily, in the embodiment of the present application, the adjacent mean generation sequence is generated by the following formulas (5) and (6):

[0069] Z (1) ={z (1) (k)|k=1,2,…,n}(5)

[0070]

[0071] Among them, Z (1) represents the sequence generated by the nearest mean, z (1) (k) represents the data in the sequence immediately adjacent to the mean.

[0072] Step S2024, solving the grey differential model using the target sequence and the sequence generated by the adjacent mean value to obtain the model parameter values ​​of the grey differential model.

[0073] For example, in the embodiment of the present application, the grey system may be GM(1,1), and the grey differential model of GM(1,1) is shown in the following formula (7):

[0074] x (0) (k)+az(1) (k) = b(7)

[0075] Among them, a represents the development coefficient and b is the grey action. a and b are the model parameters of the GM (1,1) model and can be estimated by the least squares method.

[0076] Construct the first matrix Y based on the buffered cycle life sequence N As shown in the following formula (8), the second matrix B is constructed based on the adjacent mean generation sequence as shown in the following formula (9).

[0077] Y N =[x (0) (2),x (0) (3),…,x (0) (n)] T (8)

[0078]

[0079] set up is the parameter vector to be estimated. Based on the grey differential model shown in equation (7), the parameter vector to be estimated can be determined as As shown in the following formula (10).

[0080]

[0081] According to the least squares method, we can get the following formula (11):

[0082]

[0083] Based on formula (11), the values ​​of model parameters a and b can be calculated.

[0084] Step S2025, determining the cumulative prediction value function of the grey system based on the model parameter values ​​and the grey differential model.

[0085] For example, in the embodiment of the present application, the GM (1, 1) model believes that the accumulated target sequence can be described by a first-order linear differential equation. The whitening equation of the GM (1, 1) model is shown in the following equation (12):

[0086]

[0087] After solving the model parameters a and b, the cumulative prediction value function of the grey system is determined based on the grey differential model as shown in the following formula (13). The following formula (13) can calculate the cumulative data value corresponding to k.

[0088]

[0089] in, Represents the accumulated data value of data point k+1.

[0090] Step S2025, performing cumulative restoration on the cumulative prediction value function to obtain a battery cycle life prediction model.

[0091] For example, in the embodiment of the present application, the cumulative prediction value function obtained according to the above formula (13) is cumulatively restored to obtain the following formula (14):

[0092]

[0093] in, The predicted value of the battery capacity retention rate at data point k+1 is represented. Based on the above formula (14), the battery cycle life can be predicted, and the above formula (14) can be used as a battery cycle life prediction model.

[0094] In some optional implementations, the above step S202 further includes:

[0095] Step b1, obtaining a plurality of cycle number data and first battery capacity information corresponding to each cycle number data.

[0096] Exemplarily, in the embodiment of the present application, the first battery capacity information may be a measured battery capacity retention rate of the battery at a corresponding number of cycles.

[0097] Step b2, inputting each cycle number data into a battery cycle life prediction model for calculation to obtain second battery capacity information corresponding to the cycle number.

[0098] Exemplarily, in the embodiment of the present application, the second battery capacity information is a predicted battery capacity retention rate of the battery at a corresponding number of cycles obtained by prediction using a battery cycle life prediction model.

[0099] Step b3, calculating the absolute residual of the corresponding cycle number based on the first battery capacity information and the second battery capacity information of each cycle number data.

[0100] For example, in the embodiment of the present application, the absolute residual can be calculated by the following formula (15):

[0101]

[0102] Among them, ε (0) (k) represents the absolute residual of the number of cycles corresponding to k, x (0) (k) represents the first battery capacity information corresponding to the number of cycles k, The second battery capacity information indicating the number of cycles corresponding to k.

[0103] Step b4, calculating the relative residual of the corresponding cycle number data according to the absolute residual of each cycle number data and the first battery capacity data.

[0104] For example, in the embodiment of the present application, the absolute residual sequence under different cycle numbers can be expressed by the following formula (16):

[0105] ε (0) =(ε (0) (1), ε (0) (2), …, ε (0) (n)) (16)

[0106] The relative residual of each cycle number data can be calculated by the following formula (17):

[0107]

[0108] Among them, Q(k) represents the relative residual of the number of cycles corresponding to k.

[0109] Step b5, judging whether the prediction accuracy of the battery cycle life prediction model meets the preset requirements based on the absolute residual and relative residual of each cycle number data, and obtaining a judgment result.

[0110] For example, in the embodiment of the present application, it is possible to determine whether the predicted value of the gray model meets the accuracy requirements based on the residual sequence and the relative residual. The embodiment of the present application does not limit the specific judgment method, and those skilled in the art can determine it according to needs. Specifically, by comparing the absolute residual with the first preset threshold, and comparing the relative residual with the second preset threshold, if the absolute residual is less than the first preset threshold, and the relative residual is less than the second preset threshold, it can be determined that the prediction accuracy of the battery cycle life prediction model meets the preset requirements.

[0111] In some optional implementations, the above step S202 further includes:

[0112] Step b6, performing optimization operations on the battery cycle life prediction model based on the judgment result, the optimization operations include adjusting model parameters and improving model structure.

[0113] For example, in an embodiment of the present application, if the prediction accuracy of the battery cycle life prediction model meets preset requirements, the model is optimized by adjusting model parameters, improving model structure, or combining other prediction methods.

[0114] In some optional implementations, the model parameter value includes a development coefficient value, and the above step S202 further includes:

[0115] Step b7, determining a target cycle number interval for the battery corresponding to the target cycle number.

[0116] Step b8, determining the corresponding target development coefficient value interval based on the target cycle number interval.

[0117] Exemplarily, the development coefficient reflects the development trend of the system. In the battery cycle life prediction model, the development coefficient is closely related to the change trend of performance indicators such as the battery's capacity decay rate and internal resistance change rate. If the development coefficient is large, it means that the battery performance changes rapidly and may be in a rapid decay stage; conversely, if the development coefficient is small, it means that the battery performance changes slowly and is in a relatively stable stage. Different development coefficient values ​​correspond to different cycle life stages and performance change characteristics of the battery. For example, in the early stage of the battery cycle, the development coefficient may be small. As the number of cycles increases, the development coefficient gradually increases. When the battery approaches the end of its life, the development coefficient may increase sharply. Therefore, when the battery cycle life prediction model is used to predict the battery cycle life, the development coefficient of the battery cycle life prediction model reflects the applicable stage of the battery cycle life prediction. In the embodiment of the present application, in order to achieve accurate prediction of the battery capacity information at the target cycle number, the corresponding target cycle number interval is determined based on the target cycle number, and the corresponding target development coefficient interval is determined based on the target cycle number interval. Specifically, different cycle number intervals represent different stages of the battery cycle life, and different cycle number intervals correspond to different development coefficient value intervals. The corresponding target cycle number interval is determined based on the target cycle number, and then the target development coefficient value interval corresponding to the target cycle number interval is determined.

[0118] In the embodiment of the present application, when -a≤0.3, the battery cycle life prediction model can be used for medium-term and long-term predictions; when 0.3<-a≤0.5, the battery cycle life prediction model can be used for short-term predictions, and medium-term and long-term predictions should be used with caution; when 0.5<-a≤0.8, the battery cycle life prediction model should be very cautious for short-term predictions; when 0.8<-a≤1, the GM(1,1) model should be corrected; when a>1, the GM(1,1) model should not be used. Specifically, the short-term prediction can be a battery cycle life prediction for cycles between 0 and 300 times, the medium-term prediction can be a battery cycle life prediction for cycles between 300 and 1000 times, and the long-term prediction can be a battery cycle life prediction for cycles greater than 1000 times. Assuming that the target number of cycles is 100, the corresponding target cycle number interval is 0 to 300 times, and then it can be determined that if you want to achieve accurate prediction of battery capacity information under the target number of cycles, the interval of the target development coefficient value a is 0.3<-a≤0.5.

[0119] Furthermore, by monitoring the size of the development coefficient, the life stage of the battery can be roughly determined. The applicable range of the pre-set development coefficient value is determined based on a large amount of experimental data and practical application experience. By conducting a large number of cycle life tests on batteries of different types and specifications, analyzing the change law of the development coefficient at different life stages, the development coefficient range suitable for different prediction accuracy requirements and application scenarios can be determined. According to the development coefficient value calculated in the battery cycle life prediction model, and comparing it with the pre-set applicable range, the applicability of the model under the current battery state can be determined. If the calculated development coefficient value falls within the applicable range, it means that the prediction model has good applicability under the current situation and can more accurately predict the cycle life of the battery; if the development coefficient value exceeds the applicable range, it is necessary to adjust or improve the model, or reselect a prediction model that is more suitable for the current battery state.

[0120] Step b9: If the development coefficient value is not within the target development coefficient value interval, determining that the battery cycle life prediction model is the battery cycle life prediction model to be optimized.

[0121] Exemplarily, if the development coefficient value of the battery cycle life prediction model belongs to the target development coefficient value interval, it is determined that the battery cycle life prediction model can predict the battery capacity information under the target cycle number. If the development coefficient value is not in the target development coefficient value interval, it means that the battery cycle life prediction model cannot predict the battery capacity information under the target cycle number, and the model needs to be updated.

[0122] Step b10, optimizing and updating the battery cycle life prediction model to be optimized.

[0123] Exemplarily, in an embodiment of the present application, the model parameters of the battery cycle life prediction model to be optimized can be updated by acquiring more historical cycle data, thereby achieving optimization update of the battery cycle life prediction model to be optimized.

[0124] Through the above steps, a prediction model based on grey system theory can be effectively established to predict the cycle life of secondary batteries. With the continuous development and application of grey system theory, its application prospects in fields such as battery management will become increasingly broad.

[0125] Step S203, inputting the target cycle number of the battery into the battery cycle life prediction model for calculation to obtain the battery capacity information of the battery under the target cycle number.

[0126] For details, please see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0127] The following is a specific example to illustrate the process of constructing the battery cycle life prediction model in the embodiment of the present invention.

[0128] The specific steps of the embodiment are as follows:

[0129] 1. Design an experiment and collect data

[0130] Experiment on battery cycle number and capacity retention rate

[0131] 1. Purpose of the experiment

[0132] Explore the changing pattern of battery capacity retention rate under different cycle numbers to provide a basis for battery performance evaluation and life prediction.

[0133] 2. Experimental materials and equipment

[0134] Experimental batteries: Select several lithium-ion batteries of the same model and batch to ensure similar initial performance.

[0135] Battery testing system: can accurately measure the battery's charge and discharge capacity, voltage, current and other parameters.

[0136] Constant temperature box: used to control the experimental environment temperature and keep it within a certain range (such as 25℃±2℃) to reduce the impact of temperature on battery performance.

[0137] 3. Experimental steps

[0138] 3.1 Battery pretreatment

[0139] Place the selected battery in a constant temperature box for a period of time to allow it to reach thermal equilibrium and stabilize the temperature at the set value.

[0140] Perform the initial charge and discharge of the battery to activate the battery and record the initial capacity. The charging method uses constant current and constant voltage charging. First, charge with a constant current until the battery voltage reaches the set upper limit voltage (such as 3.2V), and then switch to constant voltage charging until the charging current drops to the set cutoff current (such as 0.05C, C is the rated capacity of the battery). The discharge process uses constant current discharge, and discharges the battery to the set lower limit voltage (such as 2.7V) with a constant current.

[0141] 3.2 Cycle experiment

[0142] Install the battery on the battery test system and set the charge and discharge cycle program. Perform continuous charge and discharge cycle experiments on the battery according to the charge and discharge method during pretreatment. After each cycle, record the actual charge and discharge capacity of the battery (n means taking the battery capacity data corresponding to n different cycle numbers). Set different cycle numbers, such as 100 times, 200 times, 300 times, 400 times, and 500 times.

[0143] 3.3 Data collection and recording

[0144] At each set cycle number node, in addition to recording the battery's charge and discharge capacity, the battery's voltage, current and other parameters are also measured and recorded. These data will be used for subsequent analysis of changes in battery performance. The data for each measurement is collated and numbered to ensure data accuracy and traceability.

[0145] 4. Experimental results analysis

[0146] 4.1 Calculation of capacity retention rate

[0147] According to the battery capacity data recorded after each cycle, calculate the battery capacity retention rate R n , the calculation formula is:

[0148]

[0149] Among them, C n is the battery capacity after the nth cycle, and C0 is the initial capacity of the battery.

[0150] 4.2 Drawing a curve

[0151] With the cycle number as the horizontal axis and the capacity retention rate as the vertical axis, a curve is drawn showing the change of battery capacity retention rate with the cycle number. By observing the trend of the curve, we can intuitively understand the change law of battery capacity retention rate. Figure 3 shown.

[0152] Analyze the characteristics of the curve, such as whether there is an obvious turning point, the speed of the downward trend, etc. For abnormal points in the curve, it is necessary to further check the accuracy of the experimental data. If necessary, repeat the relevant experimental steps for verification.

[0153] 2. Model calculation prediction

[0154] The experimental data are extracted and processed according to the buffer operator model to reduce data fluctuations.

[0155] The data after the buffer operator is applied are shown in Table 1, which provides a basis for model prediction.

[0156] Table 1

[0157] Cycle times 100 200 300 400 500 Capacity retention rate / % 99.4 98.7 96.9 96.3 94.5

[0158] 1. The original cycle life sequence obtained from the experimental data is processed using the buffer operator, and the buffered cycle life sequence obtained is:

[0159] X (0) =[99.4,98.7,96.9,96.3,94.5]

[0160] 2. Generate the sequence according to formula (2) to obtain X (0) 1-AGO sequence (target sequence): The original data is accumulated to eliminate random fluctuations and expose potential patterns.

[0161] X (1) =[99.4,198.1,295.0,391.3,485.8]

[0162] The newly generated series is a monotonically growing curve, which increases the regularity of the original data and weakens the volatility.

[0163] 3. Generate X according to formula (3) and formula (4) (1) The sequence generated by the adjacent mean of is:

[0164] Z (1) =[49.7,148.75,246.55,343.15,438.55]

[0165] Then the cycle life sequence after buffering is X (0) And the adjacent mean generation sequence Z of the 1-AGO sequence (1) The data matrix Y N and B is:

[0166] Y N =[98.7,96.9,96.3,94.5] T

[0167]

[0168] 4. Using formula (11), a can be obtained as:

[0169]

[0170] That is: a=0.0137, b=100.6207.

[0171] According to formula (12), the whitening equation is:

[0172]

[0173] At the same time, according to formula (13), the cumulative prediction function is obtained:

[0174]

[0175] 5. Calculated by the response function And then add them up and restore them to get the predicted value of the model The model is tested for accuracy and the absolute and relative residuals between the actual and predicted values ​​are calculated, as shown in Table 2.

[0176] Table 2

[0177] Cycle times Actual capacity retention rate / % Predicted capacity retention rate / % Absolute residual ε(k) / % Relative residual Q(k) / % 100 99.4 99.4 0 0 200 98.7 98.58 0.12 0.12 300 96.9 97.24 0.34 0.35 400 96.3 95.92 0.38 0.39 500 94.5 94.61 0.11 0.12

[0178] As can be seen from Table 2, the maximum relative residual of the residual analysis between the predicted value of the gray prediction model and the battery capacity retention rate obtained in the example is 0.39%. This analysis result shows that the model is in good condition in terms of accuracy. This not only reflects the accuracy and reliability of the model in data processing, but also provides strong support and basis for subsequent related research and practical applications, and further proves that the gray prediction model has certain advantages and feasibility in this field. Comparison of the actual battery capacity retention rate and the predicted value Figure 4 The feasibility analysis of the model is tested, and the grey prediction model -a≤0.3, so the obtained prediction model can be used for medium and long-term prediction.

[0179] Furthermore, the present application also provides a secondary battery cycle life prediction system based on grey system theory, which requires comprehensive consideration of multiple aspects such as system architecture and hardware configuration.

[0180] The system architecture of the secondary battery cycle life prediction system can be as follows: Figure 5 As shown, the system can be divided into the following parts:

[0181] Data preprocessing module: preprocess the collected data, including removing outliers, filling missing values, data normalization, etc.

[0182] Feature selection module: Select features useful for cycle life prediction.

[0183] Grey prediction module: implements grey prediction models, such as GM (1,1) model, GMT model, etc.

[0184] Result output module: outputs the predicted battery cycle life value.

[0185] User interface module: provides a friendly user interface to facilitate user operation.

[0186] The system provided in the embodiment of the present application has a lifelong learning function, which can continuously update and optimize the prediction model, improve the prediction accuracy, and meet the evolving battery technology and market needs. The system has a lifelong learning function, which can continuously update and optimize the prediction model, improve the prediction accuracy, and meet the evolving battery technology and market needs. It realizes intelligent and refined battery management, thereby improving the efficiency of battery use, extending battery life, reducing costs, and protecting the environment, which has huge social and economic benefits.

[0187] In this embodiment, a battery cycle life prediction device is also provided, which is used to implement the above embodiments and preferred implementations, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0188] This embodiment provides a battery cycle life prediction device, such as Figure 6 As shown, including:

[0189] An acquisition module 601 is used to acquire a target cycle number of a battery, historical cycle data of the battery, a buffer operator, and a grey prediction model, wherein the historical cycle data is used to characterize historical capacity information corresponding to different historical cycle numbers;

[0190] A construction module 602 is used to construct a battery cycle life prediction model based on the historical cycle data of the battery, the buffer operator and the grey prediction model. The battery cycle life model is used to characterize the relationship between the number of cycles and the capacity information of the battery.

[0191] The calculation module 603 is used to input the target cycle number of the battery into the battery cycle life prediction model for calculation to obtain the battery capacity information of the battery under the target cycle number.

[0192] In some optional embodiments, the historical cycle data is an original cycle life sequence of the battery, the grey prediction model includes a grey differential model of the grey system, and the construction module 602 includes:

[0193] A first processing submodule processes the original cycle life sequence using a buffer operator to obtain a buffered cycle life sequence;

[0194] The second processing submodule is used to accumulate the first k data in the buffered cycle life sequence in sequence and use them as the kth data of the target sequence, where k ranges from 1 to n, n is the number of data in the buffered cycle life sequence, and the target sequence includes n data;

[0195] The third processing submodule is used to convert the target sequence into a sequence generated by the adjacent mean;

[0196] A solution submodule is used to solve the grey differential model using the target sequence and the sequence generated by the adjacent mean value to obtain the model parameter values ​​of the grey differential model;

[0197] A first determination submodule is used to determine the cumulative prediction value function of the grey system based on the model parameter value and the grey differential model;

[0198] The second determination submodule is used to perform cumulative restoration on the cumulative prediction value function to obtain a battery cycle life prediction model.

[0199] In some optional implementations, the construction module 602 further includes:

[0200] An acquisition submodule, used for acquiring a plurality of cycle number data and first battery capacity information corresponding to each cycle number data;

[0201] A first calculation submodule is used to input each cycle number data into the battery cycle life prediction model for calculation to obtain the second battery capacity information corresponding to the cycle number;

[0202] A second calculation submodule, used for calculating the absolute residual of the corresponding cycle number data based on the first battery capacity information and the second battery capacity information of each cycle number data;

[0203] A third calculation submodule, used for calculating the relative residual of the corresponding cycle number data according to the absolute residual of each cycle number data and the first battery capacity data;

[0204] A judgment submodule is used to judge whether the prediction accuracy of the battery cycle life prediction model meets the preset requirements based on the absolute residual and relative residual of each cycle number data, and obtain a judgment result;

[0205] The first optimization submodule is used to perform optimization operations on the battery cycle life prediction model based on the judgment result, and the optimization operations include adjusting model parameters and improving model structure.

[0206] In some optional implementations, the buffer operator is shown as follows:

[0207]

[0208] Among them, c d (k) represents the buffer operator, α represents the weakening coefficient, c(k) represents the kth cycle data of the original cycle life sequence, and c(i) represents the ith cycle data of the original cycle life sequence.

[0209] In some optional implementations, the model parameter value includes a development coefficient value, and the construction module 602 further includes:

[0210] A third determination submodule is used to determine a target cycle number interval corresponding to a target cycle number of the battery;

[0211] A fourth determination submodule, configured to determine a corresponding target development coefficient value interval based on the target cycle number interval;

[0212] a fifth determination submodule, configured to determine that the battery cycle life prediction model is a battery cycle life prediction model to be optimized if the development coefficient value is not within the target development coefficient value interval;

[0213] The second optimization submodule is used to optimize and update the battery cycle life prediction model to be optimized.

[0214] In some optional implementations, the historical capacity information includes a capacity retention rate, and the historical cycle data is obtained by the following steps:

[0215] Obtain the initial battery capacity of the battery and the battery capacity corresponding to different cycle times;

[0216] Calculating the capacity retention rate of the battery at the corresponding number of cycles based on the battery capacity at each number of cycles and the initial battery capacity;

[0217] The number of cycles of the battery and the capacity retention rate corresponding to each cycle number are taken as historical cycle data.

[0218] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0219] The battery cycle life prediction device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0220] The embodiment of the present invention also provides a computer device having the above Figure 6 The battery cycle life prediction device shown.

[0221] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0222] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0223] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0224] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0225] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0226] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0227] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0228] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0229] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A battery cycle life prediction method, characterized in that: The method comprises: Obtaining a target cycle number of the battery, historical cycle data of the battery, a buffer operator, and a grey prediction model, wherein the historical cycle data is used to characterize historical capacity information corresponding to different historical cycle numbers; Constructing a battery cycle life prediction model according to the historical cycle data, the buffer operator and the grey prediction model, wherein the battery cycle life model is used to characterize the relationship between the number of cycles and capacity information of the battery; The target cycle number of the battery is input into the battery cycle life prediction model for calculation to obtain the battery capacity information of the battery under the target cycle number.

2. The method according to claim 1, characterized in that The historical cycle data is an original cycle life sequence of the battery, the grey prediction model includes a grey differential model of a grey system, and the step of constructing a battery cycle life prediction model according to the historical cycle data of the battery, the buffer operator and the grey prediction model includes: Processing the original cycle life sequence using the buffer operator to obtain a buffered cycle life sequence; The first k data in the buffered cycle life sequence are accumulated in sequence and used as the kth data of the target sequence, wherein the value of k ranges from 1 to n, and n is the number of data in the buffered cycle life sequence, and the target sequence includes n data; Converting the target sequence into a sequence generated by the adjacent mean; Solving the grey differential model using the target sequence and the adjacent mean generation sequence to obtain model parameter values ​​of the grey differential model; Determining a cumulative prediction value function of a grey system based on the model parameter values ​​and the grey differential model; The cumulative prediction value function is cumulatively restored to obtain the battery cycle life prediction model.

3. The method according to claim 2, characterized in that After the step of cumulatively restoring the cumulative prediction value function to obtain the battery cycle life prediction model, the method further includes: Acquire a plurality of cycle number data and first battery capacity information corresponding to each cycle number data; Inputting each cycle number data into the battery cycle life prediction model for calculation to obtain second battery capacity information corresponding to the cycle number; Calculate the absolute residual of the corresponding cycle number data based on the first battery capacity information and the second battery capacity information of each cycle number data; Calculate the relative residual of the corresponding cycle number data according to the absolute residual of each cycle number data and the first battery capacity data; Based on the absolute residual and relative residual of each cycle number data, judging whether the prediction accuracy of the battery cycle life prediction model meets the preset requirements, and obtaining a judgment result; An optimization operation is performed on the battery cycle life prediction model based on the judgment result, and the optimization operation includes adjusting model parameters and improving model structure.

4. The method according to claim 2, characterized in that: The buffer operator is shown in the following formula: Among them, c d (k) represents the buffer operator, α represents the weakening coefficient, c(k) represents the kth cycle data of the original cycle life sequence, and c(i) represents the ith cycle data of the original cycle life sequence.

5. The method according to claim 2, characterized in that: The model parameter value includes a development coefficient value. After the step of cumulatively restoring the cumulative prediction value function to obtain the battery cycle life prediction model, the method further includes: Determine a target cycle number interval for the battery corresponding to the target cycle number; Determine a corresponding target development coefficient value interval based on the target cycle number interval; If the development coefficient value is not within the target development coefficient value interval, determining that the battery cycle life prediction model is the battery cycle life prediction model to be optimized; The battery cycle life prediction model to be optimized is optimized and updated.

6. The method according to any one of claims 1 to 5, characterized in that: The historical capacity information includes the capacity retention rate, and the historical cycle data is obtained by the following steps: Obtain the initial battery capacity of the battery and the battery capacity corresponding to different cycle times; Calculating the capacity retention rate of the battery at the corresponding number of cycles based on the battery capacity at each number of cycles and the initial battery capacity; The number of cycles of the battery and the capacity retention rate corresponding to each cycle number are used as the historical cycle data.

7. A battery cycle life prediction device, characterized in that: The device comprises: An acquisition module, used to acquire a target cycle number of the battery, historical cycle data of the battery, a buffer operator, and a grey prediction model, wherein the historical cycle data is used to characterize historical capacity information corresponding to different historical cycle numbers; A construction module, which constructs a battery cycle life prediction model according to the historical cycle data of the battery, the buffer operator and the grey prediction model, wherein the battery cycle life model is used to characterize the relationship between the number of cycles and capacity information of the battery; The calculation module is used to input the target cycle number of the battery into the battery cycle life prediction model for calculation to obtain the battery capacity information of the battery under the target cycle number.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the battery cycle life prediction method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the battery cycle life prediction method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the battery cycle life prediction method according to any one of claims 1 to 6.

Images