Method and device for predicting battery capacity retention ratio, electronic equipment and storage medium

Abstract

The invention provides a battery capacity retention rate prediction method and device, electronic equipment and a storage medium, and belongs to the technical field of lithium batteries, and the method comprises the steps: obtaining the target storage temperature and target storage time of a battery; calling a preset rate model to determine a corresponding capacity recovery attenuation rate of the battery at the target storage temperature; and determining the corresponding capacity retention rate of the battery after the target storage time based on the capacity recovery decay rate. According to the scheme, the prediction accuracy of the battery capacity retention rate can be effectively improved.

Description

Technical Field

[0001] This invention relates to the field of lithium battery technology, and more specifically to a method, apparatus, electronic device, and storage medium for predicting battery capacity retention. Background Technology

[0002] Battery storage life, as a key indicator for evaluating its overall performance and reliability, directly affects the battery's lifespan and safety. In practical applications, lithium batteries are often exposed to complex and variable environmental conditions, such as different temperatures, humidity levels, and charge-discharge cycles. These variables significantly accelerate or slow down the aging process. However, traditional evaluation methods rely on long-term actual testing, typically requiring several years to observe capacity degradation to the critical point of health. This lengthy testing cycle severely restricts the development progress of new products and the speed of market iteration, especially in the context of the rapid development of the new energy industry, making it difficult for companies to respond to market demands in a timely manner, resulting in idle R&D resources and product launch delays. At the same time, directly conducting long-term storage tests is not only time-consuming but also involves high costs, including testing equipment occupation, energy consumption, and human resource investment, resulting in significant resource waste. To address this challenge, existing technologies attempt to use mathematical models for data normalization, such as combining reaction kinetic equations and the Arrhenius equation, using short-term storage data (such as test results within six months) to fit long-term storage behavior, thereby predicting capacity degradation trends. However, existing models have limitations in generalization ability, computational accuracy, and environmental adaptability, making it difficult to accurately reflect the dynamics of capacity recovery and degradation under different combinations of storage temperature and time. This results in insufficient reliability of prediction results and an inability to effectively support the lifespan prediction function of battery management systems. Therefore, there is an urgent need to develop an efficient and robust prediction mechanism to shorten the testing cycle, reduce R&D costs, and improve the practicality of storage lifespan prediction. Summary of the Invention

[0003] To address the aforementioned problems, this application provides a method for predicting battery capacity retention rate, which significantly shortens the testing cycle, reduces R&D costs, and improves prediction accuracy. The technical solution is as follows: In a first aspect, the present invention provides a method for predicting battery capacity retention rate, comprising: Obtain the target storage temperature and target storage time for the battery; The preset rate model is invoked to determine the capacity recovery degradation rate of the battery at the target storage temperature; The capacity retention rate of the battery after the target storage time is determined based on the capacity recovery decay rate.

[0004] Combining the first aspect and the above implementation methods, in some possible implementation methods, determining the capacity retention rate of the battery after the target storage time based on the capacity recovery decay rate includes: Obtain the initial capacity retention rate of the battery; The initial capacity retention rate, target storage time, and capacity recovery decay rate are loaded into the preset capacity decay calculation model to obtain the capacity retention rate.

[0005] Combining the first aspect and the above implementation methods, in some possible implementation methods, before obtaining the target storage temperature and target storage time of the battery, the following steps are included: Obtain historical test data for the battery; A rate model was built based on historical test data.

[0006] Combining the first aspect and the above implementation methods, some possible implementation methods involve constructing a rate model based on historical test data, including: Obtain the battery's first historical storage temperature and the first historical storage time corresponding to the first historical storage temperature from historical test data; The first historical reaction rate of the battery is determined based on the first historical storage temperature and the first historical storage time. Obtain the battery's second historical storage temperature and the second historical storage time corresponding to the second historical storage temperature from historical test data; The second historical reaction rate is determined based on the second historical storage temperature and the second historical storage time, wherein the first historical storage temperature is different from the second historical storage temperature, and the first historical storage time is different from the second storage time. A rate model is constructed based on the first and second historical reaction rates.

[0007] Combining the first aspect and the above implementation methods, in some possible implementation methods, a rate model is constructed based on the first historical reaction rate and the second historical reaction rate, including: Obtain the first natural logarithm of the first historical reaction rate and the second natural logarithm of the second historical reaction rate; Obtain the first temperature reciprocal corresponding to the first historical storage temperature and the second temperature reciprocal corresponding to the second historical storage temperature; A recovery rate model is constructed based on the first natural logarithm, the second natural logarithm, the reciprocal of the first temperature, and the reciprocal of the second temperature.

[0008] Combining the first aspect and the above implementation methods, in some possible implementation methods, before constructing the rate model based on historical test data, the following steps are taken: The rate model is tested, and it is applied when the test results meet the preset test conditions.

[0009] Combining the first aspect and the above implementation methods, in some possible implementation methods, the rate model is tested, and the rate model is applied when the test results of the rate model meet preset test conditions, including: Input the test storage temperature into the rate model to obtain the predicted capacity recovery rate for the test storage temperature; Obtain the actual capacity recovery rate at the test storage temperature; If the error between the predicted capacity recovery rate and the actual capacity recovery rate is less than the preset difference, then the rate model is applied.

[0010] Secondly, the present invention also provides a device for predicting battery capacity retention rate, comprising: The data acquisition unit is used to acquire the target storage temperature and target storage time of the battery. The rate calculation unit is used to call a preset rate model to determine the capacity recovery degradation rate of the battery at the target storage temperature. The capacity retention calculation unit is used to determine the capacity retention rate of the battery after the target storage time based on the capacity recovery decay rate.

[0011] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein, Memory, used to store programs; The processor, coupled to the memory, executes a program stored in the memory to implement the steps in the battery capacity retention prediction method in any of the above implementations.

[0012] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the battery capacity retention rate prediction method in any of the above implementations.

[0013] The beneficial effects of this invention are as follows: By obtaining the target storage temperature and target storage time of the battery, and using a preset rate model to determine the capacity recovery decay rate corresponding to the battery at the target storage temperature, the initial capacity retention rate of the battery is further obtained. Subsequently, the initial capacity retention rate, the previously determined target storage time, and the capacity recovery decay rate are used as input parameters and input into a preset capacity decay calculation model to output the accurate capacity retention rate after the target storage time, thereby making the prediction results more accurate and reliable. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A schematic flowchart of the battery capacity retention rate prediction method provided by the present invention; Figure 2 A schematic flowchart of the battery capacity retention rate prediction method provided by the present invention; Figure 3 A schematic diagram illustrating a scenario for the battery capacity retention rate prediction method provided by this invention; Figure 4 A schematic flowchart of the battery capacity retention rate prediction method provided by the present invention; Figure 5 A schematic flowchart of the battery capacity retention rate prediction method provided by the present invention; Figure 6 A schematic diagram of the structure of the battery capacity retention rate prediction device provided by the present invention; Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0017] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0018] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] In traditional lithium-ion battery storage lifetime assessment technologies, the actual storage testing requires a long time to observe the battery's State of Health (SOH) as its capacity decays to the target value, leading to extended new product development cycles. This problem stems from the inherent characteristics of chemical reaction kinetics, meaning that directly obtaining long-term storage data through actual measurements is inefficient, thus hindering R&D progress and negatively impacting product iteration speed. Furthermore, the excessively long testing cycle not only idles R&D resources but also limits the ability to rapidly optimize battery materials and structures.

[0021] This application provides a method for predicting battery capacity retention rate. The method is executed by a battery capacity retention rate prediction device or an electronic device with a battery capacity retention rate prediction program. The details are described below.

[0022] Before demonstrating specific embodiments, the following terms will be explained.

[0023] Battery capacity retention rate refers to the percentage of a battery's usable capacity relative to its initial capacity after a certain period of storage or use. This metric is an important parameter for measuring battery storage life and the degree of performance degradation.

[0024] The target storage temperature refers to the temperature of the battery storage environment set when predicting battery capacity retention. This temperature can be the average temperature of the actual storage environment or a specific temperature point.

[0025] Target storage time refers to the duration of battery storage set when predicting battery capacity retention. This time can be several months or several years, used to evaluate battery performance after long-term storage.

[0026] A rate model is a mathematical model used to describe the relationship between the rate of battery capacity decay or recovery and environmental factors (such as temperature). This model can be built based on empirical data, reaction kinetics theory, or machine learning methods.

[0027] The capacity recovery decay rate refers to the rate at which a battery's capacity changes over time under specific storage conditions. This rate can be the rate of capacity decay or the rate of capacity recovery caused by certain mechanisms, but decay is usually the dominant factor in long-term storage.

[0028] In the development of power batteries for new energy vehicles, continuous monitoring is necessary to obtain capacity degradation data when batteries are stored in different temperature environments for testing. In this scenario, the inability to obtain long-term storage results in the short term forces an extension of the product design verification phase, leading to disruptions in the R&D process. Furthermore, when it is necessary to evaluate storage life under multiple temperature conditions, the lag in test data makes design adjustments lack timely basis, hindering the R&D team from efficiently advancing subsequent verification work.

[0029] If the aforementioned problems are not addressed, the R&D cycle will continue to lengthen, increasing operating costs and potentially impacting market competitiveness. Furthermore, inefficient testing methods hinder accurate predictions of battery performance, making it difficult to execute product launch plans on schedule, thus restricting technological progress in the new energy industry. Therefore, there is an urgent need for a technology that can quickly obtain storage lifetime prediction results to improve R&D efficiency.

[0030] Based on the above, this invention provides a method for predicting battery capacity retention rate. Please refer to [link to relevant documentation]. Figure 1 , Figure 1 This is a flowchart illustrating a method for predicting battery capacity retention rate provided in an embodiment of this application. Figure 1 As shown, the method in this application embodiment may include the following steps S101-S103: S101, obtain the target storage temperature and target storage time of the battery.

[0031] Specifically, the target storage temperature can be manually input by the user via an input device. For example, the user can input a specific temperature value, such as 25 degrees Celsius, on the human-machine interface based on the battery's expected storage environment. Alternatively, the target storage temperature can be obtained by reading from a preset database, which may store recommended storage temperatures for different application scenarios. The target storage time can also be obtained manually; for example, the user can input the expected predicted storage duration, such as one year. Furthermore, the target storage time can also be obtained by interacting with an external system to receive preset storage cycle information.

[0032] S102, call the preset rate model to determine the capacity recovery degradation rate of the battery at the target storage temperature.

[0033] Specifically, a pre-defined rate model is invoked to determine the capacity recovery degradation rate of the battery at the target storage temperature. This rate model can be pre-established and stored in the system's storage medium. In one implementation, the rate model can be a simple lookup table storing the capacity recovery degradation rate values ​​at different temperatures. Once the target storage temperature is obtained, the rate value closest to or directly matching the target storage temperature can be retrieved from the lookup table. In another implementation, the rate model can be a mathematical expression based on an empirical formula, which takes temperature as an input variable and outputs the corresponding capacity recovery degradation rate. For example, this empirical formula can be a polynomial or exponential function whose coefficients are fitted based on a large amount of experimental data. By substituting the target storage temperature into this empirical formula, the corresponding capacity recovery degradation rate can be calculated.

[0034] It should be noted that a rate model is a mathematical model used to describe the relationship between battery capacity decay or recovery rate and environmental factors (such as temperature). This rate model can be constructed based on empirical data, reaction kinetics theory, or machine learning methods, and no specific limitations are imposed here.

[0035] S103, determine the capacity retention rate of the battery after the target storage time based on the capacity recovery decay rate.

[0036] Specifically, the initial capacity retention rate, target storage time, and capacity recovery decay rate are used as input parameters and fed into a preset capacity decay calculation model. This model is a mathematical model that describes the change in battery capacity with factors such as time, temperature, and decay rate. Through mathematical calculations, the capacity decay calculation model comprehensively considers the battery's initial state and decay trend, thereby outputting the capacity retention rate after the target storage time.

[0037] For example, suppose a battery manufacturer needs to predict the capacity retention of a batch of new lithium-ion batteries after storage in a warehouse environment with an average temperature of 25 degrees Celsius over the next three years. The manufacturer wants to obtain these predictions quickly without conducting long-term real-world testing to guide product launches and inventory management.

[0038] Suppose a user, A, inputs a target storage temperature of 25 degrees Celsius and a target storage time of 3 years into the preset operation interface of the battery management system. This input data is received and stored by the system.

[0039] Subsequently, a pre-defined rate model is invoked to determine the capacity recovery degradation rate of the battery at 25 degrees Celsius. This rate model can be pre-established by fitting short-term test data of similar batteries at different temperatures. For example, the rate model might be a simplified form of the Arrhenius equation or a temperature-based empirical lookup table. Upon receiving the target storage temperature of 25 degrees Celsius, it queries or calculates the capacity recovery degradation rate of this type of battery at that temperature from the rate model. Assuming the model calculation determines the capacity recovery degradation rate of the battery at 25 degrees Celsius to be 1.5% per year.

[0040] Finally, the capacity retention rate of the battery after 3 years of storage is determined based on this capacity recovery degradation rate. Specifically, a simplified capacity degradation calculation logic is used. For example, if we assume the initial capacity retention rate of the battery is 100%, and the capacity decays at a rate of 1.5% per year, then the predicted capacity retention rate after 3 years will be calculated as 100% - (1.5%). 3) = 95.5%. Therefore, the manufacturer can predict that the capacity retention rate of this batch of batteries after three years of storage will be 95.5%.

[0041] In the example above, manufacturers can obtain a predicted capacity retention rate of the battery after three years of storage in a short period of time, without having to wait three years. This method abstracts the complex physicochemical degradation process into a computable rate model, thereby transforming long-term testing into predictions based on model calculations. Therefore, this embodiment significantly shortens the battery storage life assessment cycle and reduces testing costs.

[0042] As shown above, this application obtains the target storage temperature and target storage time of the battery, and determines the capacity recovery decay rate corresponding to the battery at the target storage temperature by calling a preset rate model, and further obtains the initial capacity retention rate of the battery. Subsequently, the initial capacity retention rate, the determined target storage time, and the capacity recovery decay rate are used as input parameters to input the preset capacity decay calculation model to output the accurate capacity retention rate after the target storage time, thereby making the prediction results more accurate and reliable.

[0043] In some embodiments described above in this application, a method for determining the capacity retention rate of a battery after a target storage time based on the capacity recovery decay rate is proposed. However, in its implementation, how to accurately apply the capacity recovery decay rate to the calculation of the capacity retention rate to obtain more accurate prediction results is a technical problem that needs further clarification. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating a method for predicting battery capacity retention rate provided in an embodiment of this application. Figure 2As shown, the method in this application embodiment may include the following steps S201-S203: S201, Obtain the initial capacity retention rate of the battery.

[0044] In this embodiment, the initial capacity retention rate refers to the percentage of the battery's capacity relative to its rated capacity at the start of storage or prediction; it serves as a benchmark for capacity degradation prediction. This initial capacity retention rate can be calculated by performing a full charge-discharge cycle test on the battery, measuring its current capacity, and comparing it to the battery's rated capacity. Alternatively, it can be obtained by consulting the battery's historical data records to obtain its capacity retention rate at a specific point in time (e.g., at the time of manufacture or the last maintenance) as the initial value. In some cases, if the battery is new, its initial capacity retention rate can be set to 100%.

[0045] S202, the initial capacity retention rate, target storage time, and capacity recovery decay rate are loaded into the preset capacity decay calculation model to obtain the capacity retention rate.

[0046] In this embodiment, the capacity decay calculation model is a mathematical model used to describe the change in battery capacity with factors such as time, temperature, and decay rate. This capacity decay calculation model can be a nonlinear decay model, such as an exponential decay model built based on the Arrhenius equation or empirical formulas, where the capacity recovery decay rate is a parameter or coefficient in the model. This capacity decay calculation model can comprehensively consider the battery's initial state, storage conditions, and decay characteristics, thereby accurately predicting the battery's capacity retention rate after a target storage time. Alternatively, this capacity decay calculation model can be a linear decay model, for example: Final capacity retention rate = Initial capacity retention rate - (Capacity recovery decay rate × Target storage time).

[0047] For example, after obtaining the target storage temperature and target storage time of the battery, the capacity recovery decay rate of the battery at the target storage temperature is determined to be 0.01% per day using a rate model. To ensure accurate prediction, the battery's current initial capacity retention rate is first obtained as 95%. Then, this 95% initial capacity retention rate, the target storage time of 100 days, and the 0.01% daily capacity recovery decay rate are input into a preset capacity decay calculation model. This model can be expressed as: Final capacity retention rate = Initial capacity retention rate - (Capacity recovery decay rate × Target storage time). Through calculation, the capacity retention rate of the battery after 100 days is 95% - (0.01% × 100) = 94%.

[0048] As shown above, this application, by obtaining the target storage temperature and target storage time of the battery and calling a preset rate model to determine the capacity recovery decay rate corresponding to the battery at the target storage temperature, further obtains the initial capacity retention rate of the battery. Subsequently, the initial capacity retention rate, the previously determined target storage time, and the capacity recovery decay rate are used as input parameters and fed into a preset capacity decay calculation model. This capacity decay calculation model, through mathematical calculations, comprehensively considers the battery's initial state and decay trend, thereby outputting the accurate capacity retention rate after the target storage time. This approach ensures that the prediction results not only reflect the decay rate but also consider the actual initial state of the battery, making the prediction results more accurate and reliable.

[0049] In some embodiments described above in this application, a preset rate model is used to determine the battery's capacity recovery degradation rate. However, in practical applications, obtaining an accurate and reliable rate model to ensure the precision of the prediction results is a problem that needs to be solved. Therefore, in one feasible embodiment, before performing the above steps to obtain the target storage temperature and target storage time of the battery, the following is further performed: Obtain historical test data for the battery.

[0050] In this embodiment, historical test data refers to the collection of battery performance change information under different storage conditions. This data forms the basis for building an accurate rate model. For example, accelerated aging tests can be conducted on the battery in a controlled laboratory environment to record the capacity decay or recovery of the battery under different temperatures, humidity levels, and storage times. Alternatively, long-term operating data of the battery, including its operating temperature, storage duration, and corresponding capacity status information, can be obtained from a battery management system (BMS) in actual operation or a cloud data platform.

[0051] A rate model was built based on historical test data.

[0052] Specifically, a mathematical model is needed to describe the relationship between battery capacity decay or recovery rate and storage conditions. For example, a physicochemical model, such as the Arrhenius equation, can be used. By fitting historical test data, key parameters such as activation energy and pre-exponential factor can be determined, thereby establishing a quantitative relationship between temperature and reaction rate. Alternatively, data-driven methods can be employed, such as machine learning algorithms like support vector machines, neural networks, or regression trees, to learn from large amounts of historical test data and construct more complex nonlinear rate prediction models.

[0053] For example, a series of storage tests can be conducted on a batch of lithium-ion batteries. For instance, these batteries can be placed at different ambient temperatures (25°C, 45°C, and 60°C) and stored for different durations (1 month, 3 months, and 6 months). At the end of each storage cycle, the actual capacity retention rate of the batteries is measured and recorded. This data on temperature, storage duration, and corresponding capacity retention rate constitutes the historical test data of the batteries. Subsequently, this historical test data is input into a data analysis module. This module can use statistical methods such as least squares to fit the Arrhenius equation. Specifically, it performs a linear regression analysis between the natural logarithm of the capacity decay rate and the reciprocal of the storage temperature to calculate the activation energy and pre-exponential factor of the battery model. Based on these parameters, a rate model that accurately reflects the relationship between the capacity decay rate and storage temperature of the battery model can be constructed.

[0054] As can be seen from the above, by acquiring historical test data of the battery and constructing a rate model based on this data, this application can ensure that the rate model used is customized and optimized for a specific battery type or batch. This significantly improves the accuracy and reliability of the rate model, thereby making the subsequent determination of the capacity recovery degradation rate and the prediction of the capacity retention rate based on this rate model more accurate. It effectively solves the prediction bias problem that may be caused by directly using a general preset model, and improves the overall reliability of battery capacity prediction.

[0055] In some embodiments described above in this application, a rate model based on historical test data is proposed. However, if the rate model construction process lacks sufficient consideration of key influencing factors, the constructed model may fail to accurately reflect the true law of battery capacity degradation, thereby affecting the reliability of battery capacity retention rate prediction. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating a method for predicting battery capacity retention rate provided in an embodiment of this application. Figure 3 As shown, the method in this application embodiment may include the following steps S301-S305: S301, obtain the first historical storage temperature of the battery and the first historical storage time corresponding to the first historical storage temperature from historical test data.

[0056] In this embodiment, the aim is to extract key experimental condition parameters from existing historical battery test data. Historical test data typically includes records of battery performance under different storage conditions. Obtaining the first historical storage temperature and the corresponding first historical storage time is fundamental to building a reaction rate model. This can be achieved by reading pre-recorded storage temperature and storage time data from a structured database or log file using a data parsing module, or by acquiring this historical data in real-time or in batches from a battery management system or laboratory testing equipment via a data interface.

[0057] S302, determine the first historical reaction rate of the battery based on the first historical storage temperature and the first historical storage time.

[0058] It should be noted that battery capacity decay is caused by internal chemical reactions, the rates of which are affected by temperature and time. The average first historical reaction rate can be calculated by combining the battery capacity change before and after the first historical storage time with the first historical storage time using a preset decay formula (e.g., linear decay, exponential decay, etc.). Alternatively, the first historical reaction rate at a specific temperature and time can be derived by analyzing the changing trends of parameters such as battery internal resistance and open-circuit voltage in historical test data, combined with electrochemical theoretical models.

[0059] S303, obtain the second historical storage temperature of the battery and the second historical storage time corresponding to the second historical storage temperature from the test data.

[0060] In this embodiment, the first historical storage temperature and the second historical storage temperature are different, and the first historical storage time and the second historical storage time are different. By obtaining the reaction rate under different temperature and time conditions, the pattern of reaction rate variation with temperature and time can be captured, thereby constructing a more universal and accurate rate model. If the temperature and time are the same, the influence of temperature and time on the reaction rate cannot be effectively reflected. During the data acquisition or screening stage, the selected historical data points can be automatically checked to ensure that at least one of their storage temperature and storage time is different, preferably both are different, to provide sufficient data diversity.

[0061] S304, determine the second historical reaction rate based on the second historical storage temperature and the second historical storage time.

[0062] Specifically, the execution steps of step S304 are the same as those of step S302 above, and will not be repeated here.

[0063] S305, a rate model is constructed based on the first historical reaction rate and the second historical reaction rate.

[0064] In this embodiment, the rate model will serve as the basis for subsequent prediction of battery capacity degradation rate. The rate model can be constructed using the Arrhenius equation or its variants, which describes the exponential relationship between the chemical reaction rate constant and temperature. Parameters such as activation energy in the equation can be solved using two data points. Alternatively, multinomial regression, machine learning algorithms (such as support vector machines and neural networks), etc., can be used to construct a model predicting the reaction rate, using historical reaction rates, storage temperatures, and storage times as inputs.

[0065] Specifically, based on the first and second historical reaction rates under two different conditions defined in steps S302 and S304 above, a mathematical model that can describe the relationship between reaction rate and temperature and time is established, namely, the rate model.

[0066] For example, a series of accelerated aging tests are conducted during the battery research and development or production stage to obtain historical test data. For instance, a batch of batteries is stored at 40 degrees Celsius for 200 hours, and their capacity decay is recorded to calculate the first historical reaction rate. Simultaneously, another batch of the same model of batteries is stored at 60 degrees Celsius for 150 hours, and their capacity decay is recorded to calculate the second historical reaction rate. Here, 40 degrees Celsius and 60 degrees Celsius represent different first and second historical storage temperatures, and 200 hours and 150 hours represent different first and second historical storage times. After obtaining these two sets of historical reaction rates, the linearized form of the Arrhenius equation, ln(k) = -Ea / (R), can be used. The equation is: k = (T) + ln(A), where k is the reaction rate, Ea is the activation energy, R is the ideal gas constant, T is the absolute temperature, and A is the pre-exponential factor. By substituting two sets of data points (ln(k), 1 / T) into the equation, the activation energy Ea and the pre-exponential factor A can be solved, thus constructing a complete rate model. This model can predict the reaction rate at any given temperature.

[0067] As described above, this application determines the first historical reaction rate of the battery by obtaining the first historical storage temperature and the first historical storage time from historical test data. Subsequently, it determines the second historical reaction rate by obtaining the second historical storage temperature and the corresponding second historical storage time from the test data. During this process, it is ensured that the first historical storage temperature and the second historical storage temperature are different, and that the first historical storage time and the second historical storage time are different, so that the two sets of historical data points can fully reflect the sensitivity of the battery capacity decay reaction to temperature and time. Based on the two sets of differentiated historical reaction rate data, a rate model describing the relationship between the reaction rate and temperature and time can be constructed using mathematical methods. Once this rate model is constructed, it can be used as a preset model to determine the capacity recovery decay rate at the target storage temperature, thereby accurately predicting the battery's capacity retention rate after the target storage time. This significantly improves the accuracy and reliability of the rate model, providing support for subsequent capacity retention rate prediction.

[0068] In some embodiments described above in this application, a rate model based on historical test data is proposed. This model is established by acquiring historical reaction rates under different historical storage temperatures and times. However, in the actual construction of the rate model, how to effectively correlate these discrete historical reaction rates with their corresponding historical storage temperatures to form a rate model with scientific basis and predictive ability is a technical problem that needs to be solved. Based on this, please refer to... Figure 4 , Figure 4 This is a flowchart illustrating a method for predicting battery capacity retention rate provided in an embodiment of this application. Figure 4 As shown, the method in this application embodiment may include the following steps S401-S403: S401, obtain the first natural logarithm of the first historical reaction rate and the second natural logarithm of the second historical reaction rate.

[0069] In the embodiments of this application, obtaining the first natural logarithm of the first historical reaction rate and the second natural logarithm of the second historical reaction rate refers to performing a natural logarithmic calculation on the reaction rates measured by the battery at different historical storage temperatures.

[0070] The natural logarithm is a mathematical operation often used to deal with physical quantities that grow or decay exponentially. For example, in chemical kinetics, the relationship between the reaction rate constant and temperature (such as the Arrhenius equation) often involves taking the natural logarithm of the rate constant to linearize it, making it easier to fit data and build models.

[0071] The purpose of obtaining the natural logarithm is to transform nonlinear rate data into a linear form, facilitating subsequent mathematical processing and model building. This operation can be performed directly using mathematical library functions or the built-in logarithmic operation functions of programming languages; for example, the `math.log()` function can be used in Python, and the `log()` function can be used in MATLAB.

[0072] S402, obtain the first temperature reciprocal corresponding to the first historical storage temperature and the second temperature reciprocal corresponding to the second historical storage temperature.

[0073] In this embodiment, the reciprocal of temperature (1 / T, where T is the absolute temperature) is a key parameter in the Arrhenius equation, used to describe the exponential relationship between reaction rate and temperature. Converting temperature to its reciprocal form helps to linearize the Arrhenius equation, thereby enabling the determination of kinetic parameters such as activation energy through methods such as linear regression, and thus constructing a rate model.

[0074] Specifically, the first and second historical storage temperatures are converted from Celsius or Fahrenheit to Kelvin (absolute temperature), and then the corresponding reciprocals of the first and second temperatures are calculated respectively.

[0075] For example, if the temperature is T degrees Celsius, then the absolute temperature is T+273.15 K, the reciprocal of which is 1 / (T+273.15).

[0076] S403, a recovery rate model is constructed based on the first natural logarithm, the second natural logarithm, the reciprocal of the first temperature, and the reciprocal of the second temperature.

[0077] Specifically, a mathematical expression is established that can quantitatively describe the relationship between the battery capacity recovery rate and temperature. By utilizing the linearized natural logarithmic rate and the reciprocal of temperature, statistical methods such as linear regression can be used to fit a straight line whose slope and intercept correspond to the activation energy and pre-exponential factor in the Arrhenius equation, thus forming a recovery rate model that can be used to predict the rate at any temperature.

[0078] It should be noted that the recovery rate model can be constructed using the least squares method with linear regression analysis, taking the natural logarithmic rate as the dependent variable and the reciprocal of temperature as the independent variable. By fitting the data, a straight line equation can be obtained: ln(k) = -Ea / R. (1 / T) + ln(A), where k is the rate, T is the absolute temperature, Ea is the activation energy, R is the ideal gas constant, and A is the pre-factor. Alternatively, numerical optimization algorithms, such as gradient descent, can be used to find the optimal model parameters to minimize the error between the predicted and actual values.

[0079] For example, in the battery's historical test data, the first historical storage temperature is 25 degrees Celsius, and the corresponding first historical reaction rate is k1; the second historical storage temperature is 45 degrees Celsius, and the corresponding second historical reaction rate is k2.

[0080] Take the natural logarithm of k1 and k2 respectively to obtain ln(k1) and ln(k2). Convert 25 degrees Celsius to an absolute temperature of 298.15 K and calculate its reciprocal 1 / 298.15; convert 45 degrees Celsius to an absolute temperature of 318.15 K and calculate its reciprocal 1 / 318.15.

[0081] Using the data points ((1 / 298.15, ln(k1)) and (1 / 318.15, ln(k2)), a linear regression algorithm can be used to construct a function of the form ln(rate) = A. The recovery rate model is (1 / temperature) + B, where A and B are constants obtained from the fitting.

[0082] As shown above, by applying the natural logarithm to the historical reaction rate and converting the historical storage temperature into its reciprocal, the originally complex nonlinear relationship is linearized. This approach provides a solid mathematical foundation for constructing an accurate recovery rate model, enabling the model to more accurately reflect the temperature dependence of battery capacity degradation. Therefore, the constructed rate model has higher prediction accuracy and stronger generalization ability, effectively supporting the accurate prediction of subsequent battery capacity retention, thereby improving the reliability and practicality of the entire prediction method.

[0083] In some embodiments described above, this application proposes acquiring historical test data of the battery, constructing a rate model based on this historical test data, and then using this rate model to predict the battery's capacity retention rate. However, in practical applications, the constructed rate model may have certain errors or limitations. If it is directly applied to prediction, the accuracy of the prediction results may be insufficient, thereby affecting the reliability of battery performance evaluation. Therefore, in a feasible embodiment, before performing the above steps of constructing a rate model based on historical test data, the following additional steps are performed: The rate model is tested, and it is applied when the test results meet the preset test conditions.

[0084] In this embodiment of the application, testing the rate model refers to validating the constructed rate model to evaluate its predictive power and accuracy.

[0085] Specifically, the known input data is substituted into the model, and the model's output is compared with the actual observed results, for example, by calculating the error between the predicted and actual values. Alternatively, statistical methods, such as cross-validation, can be used to divide historical data into training and test sets, using the training set to build the model and the test set to evaluate its performance. "Preset test conditions" refer to the standards or thresholds used to determine whether the model meets the application requirements when testing the rate model.

[0086] For example, the preset test conditions can be set such that the error between the predicted value and the actual value is less than a certain preset percentage or absolute value, or the model's coefficient of determination reaches a certain preset value, or the root mean square error is lower than a certain threshold.

[0087] Applying the rate model refers to putting the rate model into the actual battery capacity retention prediction process after it has passed testing and met the preset conditions.

[0088] As can be seen from the above, this application tests and verifies the rate model after its construction. The model is only used when its prediction results meet preset accuracy conditions. This effectively avoids the problem of distorted capacity retention rate prediction results due to defects or inaccuracies in the model itself, significantly improving the accuracy and reliability of battery capacity retention rate prediction.

[0089] In some embodiments described above in this application, a rate model is constructed and tested to apply the model when preset test conditions are met. However, in practical applications, how to specifically test the rate model and how to definitively determine whether the test results meet the preset conditions to ensure the accuracy and reliability of the model's predictions are issues that require further refinement and resolution. Based on this, please refer to... Figure 5 , Figure 5 This is a flowchart illustrating a method for predicting battery capacity retention rate provided in an embodiment of this application. Figure 5 As shown, the method in this application embodiment may include the following steps S501-S503: S501 inputs the test storage temperature into the rate model to obtain the predicted capacity recovery rate for the test storage temperature.

[0090] In this embodiment, inputting the test storage temperature into the rate model to obtain the predicted capacity recovery rate for the test storage temperature refers to simulating and predicting the battery capacity recovery degradation under specific test conditions using a constructed rate model. The test storage temperature can be one or more preset, representative temperature points. For example, it can be a typical temperature that the battery may encounter during actual use or storage, or a temperature used for accelerated aging testing. The rate model can be an Arrhenius equation; substituting the test storage temperature into this equation calculates the predicted capacity recovery rate.

[0091] S502, obtain the actual capacity recovery rate at the test storage temperature.

[0092] Specifically, the battery capacity recovery rate corresponding to the aforementioned test storage temperature is obtained through actual experimental measurements or from reliable historical data. The actual capacity recovery rate is the true extent of capacity degradation of a battery after a period of storage at a specific test storage temperature. This can be obtained by conducting actual storage tests on the battery at the test storage temperature and measuring the battery capacity before and after storage.

[0093] For example, a batch of batteries can be stored at 45 degrees Celsius for 30 days, and then their capacity decay can be measured to calculate the actual capacity recovery rate at that temperature.

[0094] S503 If the error between the predicted capacity recovery rate and the actual capacity recovery rate is less than the preset difference, then the rate model is applied.

[0095] Specifically, the accuracy of the rate model is evaluated by comparing the difference between the predicted and actual values. The error value can be the absolute difference between the predicted and actual capacity recovery rates, or it can be a relative error. The preset difference is a pre-defined threshold representing an acceptable range of prediction error. This preset difference can be determined based on factors such as the accuracy requirements of the actual application scenario, battery type, and industry standards. If the calculated error value is less than the preset difference, it indicates that the rate model's prediction results are sufficiently accurate and can be trusted and applied to subsequent battery capacity retention prediction tasks. Conversely, if the error value is greater than the preset difference, it indicates that the rate model may have biases and requires further optimization or reconstruction.

[0096] For example, a test storage temperature is selected, such as 50 degrees Celsius. 50 degrees Celsius is input into the rate model, which calculates a predicted capacity recovery rate, for example, 0.0020 / day. Simultaneously, through actual experiments, a batch of batteries is stored at 50 degrees Celsius for a period of time, and their actual capacity recovery rate at that temperature is measured, for example, 0.0021 / day. The error value between the predicted and actual capacity recovery rates is calculated; for example, the absolute error is |0.0020 - 0.0021| = 0.0001. If the preset difference is set to 0.0002, since 0.0001 is less than 0.0002, the rate model is considered to meet the preset test conditions and can be applied.

[0097] As can be seen from the above, this application ensures that the rate model used has sufficient accuracy by rigorously validating it before applying it to predict battery capacity retention. This effectively avoids prediction bias caused by model inaccuracy, thereby improving the reliability and practicality of the battery capacity retention prediction results.

[0098] based on Figure 1 The flowchart below will be combined with... Figure 6 This application provides a detailed description of the battery capacity retention prediction device provided in its embodiments. It should be noted that... Figure 6 The battery capacity retention rate prediction device in the present application is used to perform the following. Figure 1 - Figure 6 The methods shown in the embodiments are for illustrative purposes only, illustrating the parts relevant to the embodiments of this application. For specific technical details not disclosed, please refer to this application. Figure 1 - Figure 6 In the embodiment shown, the battery capacity retention rate prediction device 600 may include a data acquisition unit 601, a rate calculation unit 602, and a retention rate calculation unit 603, as detailed below: Data acquisition unit 601 is used to acquire the target storage temperature and target storage time of the battery; The rate calculation unit 602 is used to call a preset rate model to determine the capacity recovery decay rate of the battery at the target storage temperature. The retention rate calculation unit 603 is used to determine the capacity retention rate of the battery after the target storage time based on the capacity recovery decay rate.

[0099] Optionally, in some embodiments, the retention rate calculation unit 603 can be used for: Obtain the initial capacity retention rate of the battery; The initial capacity retention rate, target storage time, and capacity recovery decay rate are loaded into the preset capacity decay calculation model to obtain the capacity retention rate.

[0100] Optionally, in some embodiments, the data acquisition unit 601 can be used to: Obtain historical test data for the battery; A rate model was built based on historical test data.

[0101] Optionally, in some embodiments, the data acquisition unit 601 can be used to: Obtain the battery's first historical storage temperature and the first historical storage time corresponding to the first historical storage temperature from historical test data; The first historical reaction rate of the battery is determined based on the first historical storage temperature and the first historical storage time. Obtain the battery's second historical storage temperature and the second historical storage time corresponding to the second historical storage temperature from the test data; The second historical reaction rate is determined based on the second historical storage temperature and the second historical storage time, wherein the first historical storage temperature is different from the second historical storage temperature, and the first historical storage time is different from the second historical storage time. A rate model is constructed based on the first and second historical reaction rates.

[0102] Optionally, in some embodiments, the data acquisition unit 601 can be used to: Obtain the first natural logarithm of the first historical reaction rate and the second natural logarithm of the second historical reaction rate; Obtain the first temperature reciprocal corresponding to the first historical storage temperature and the second temperature reciprocal corresponding to the second historical storage temperature; A recovery rate model is constructed based on the first natural logarithm, the second natural logarithm, the reciprocal of the first temperature, and the reciprocal of the second temperature.

[0103] Optionally, in some embodiments, the data acquisition unit 601 can be used to: The rate model is tested, and it is applied when the test results meet the preset test conditions.

[0104] Optionally, in some embodiments, the data acquisition unit 601 can be used to: Input the test storage temperature into the rate model to obtain the predicted capacity recovery rate for the test storage temperature; Obtain the actual capacity recovery rate at the test storage temperature; If the error between the predicted capacity recovery rate and the actual capacity recovery rate is less than the preset difference, then the rate model is applied.

[0105] The battery capacity retention rate prediction device 600 provided in the above embodiments can realize the technical solutions described in the above battery capacity retention rate prediction method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above battery capacity retention rate prediction method embodiments, and will not be repeated here.

[0106] like Figure 7 As shown, the present invention also provides an electronic device 700. The electronic device 700 includes a processor 701, a memory 702, and a display 703. Figure 7 Only some components of the electronic device 700 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0107] In some embodiments, processor 701 may be a central processing unit (CPU), microprocessor, or other data processing chip for running program code stored in memory 702 or processing data, such as the battery capacity retention prediction program in this invention.

[0108] In some embodiments, processor 701 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 701 may be local or remote. In some embodiments, processor 701 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0109] In some embodiments, memory 702 may be an internal storage unit of electronic device 700, such as a hard disk or memory of electronic device 700. In other embodiments, memory 702 may also be an external storage device of electronic device 700, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 700.

[0110] Furthermore, the memory 702 may include both internal storage units of the electronic device 700 and external storage devices. The memory 702 is used to store application software and various types of data installed on the electronic device 700.

[0111] In some embodiments, display 703 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 703 is used to display information from electronic device 700 and to display a visual user interface. Components 701-703 of electronic device 700 communicate with each other via a system bus.

[0112] In one embodiment, when processor 701 executes a battery capacity retention rate prediction program in memory 702, the following steps may be performed: Obtain the target storage temperature and target storage time for the battery; The preset rate model is invoked to determine the capacity recovery degradation rate of the battery at the target storage temperature; The capacity retention rate of the battery after the target storage time is determined based on the capacity recovery decay rate.

[0113] It should be understood that when the processor 701 executes the battery capacity retention rate prediction program in the memory 702, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0114] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 700 mentioned. Electronic device 700 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 700 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0115] Accordingly, this application also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, it can implement the steps or functions in the battery capacity retention prediction method provided in the above-described method embodiments.

[0116] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0117] The above provides a detailed description of the battery capacity retention prediction method, apparatus, electronic device, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for predicting battery capacity retention rate, characterized in that, The method includes: Obtain the target storage temperature and target storage time for the battery; The preset rate model is invoked to determine the capacity recovery degradation rate of the battery at the target storage temperature; The capacity retention rate of the battery after the target storage time is determined based on the capacity recovery decay rate.

2. The method according to claim 1, characterized in that, Determining the capacity retention rate of the battery after the target storage time based on the capacity recovery decay rate includes: Obtain the initial capacity retention rate of the battery; The initial capacity retention rate, the target storage time, and the capacity recovery decay rate are loaded into a preset capacity decay calculation model to obtain the capacity retention rate.

3. The method according to claim 1, characterized in that, Before obtaining the target storage temperature and target storage time of the battery, the method includes: Obtain historical test data for the battery; A rate model is constructed based on the historical test data.

4. The method according to claim 3, characterized in that, The process of constructing a rate model based on the historical test data includes: The first historical storage temperature of the battery and the first historical storage time corresponding to the first historical storage temperature are obtained from the historical test data. The first historical reaction rate of the battery is determined based on the first historical storage temperature and the first historical storage time. Obtain the second historical storage temperature of the battery and the second historical storage time corresponding to the second historical storage temperature from the historical test data; The second historical reaction rate is determined based on the second historical storage temperature and the second historical storage time, wherein the first historical storage temperature is different from the second historical storage temperature, and the first historical storage time is different from the second historical storage time. A rate model is constructed based on the first historical reaction rate and the second historical reaction rate.

5. The method according to claim 4, characterized in that, The construction of the rate model based on the first historical reaction rate and the second historical reaction rate includes: Obtain the first natural logarithm of the first historical reaction rate and the second natural logarithm of the second historical reaction rate; Obtain the first temperature reciprocal corresponding to the first historical storage temperature and the second temperature reciprocal corresponding to the second historical storage temperature; A recovery rate model is constructed based on the first natural logarithm, the second natural logarithm, the reciprocal of the first temperature, and the reciprocal of the second temperature.

6. The method according to claim 3, characterized in that, Before constructing the rate model based on the historical test data, the method includes: The rate model is tested, and the rate model is applied when the test results of the rate model meet the preset test conditions.

7. The method according to claim 6, characterized in that, The step of testing the rate model and applying the rate model when the test results of the rate model meet preset test conditions includes: The test storage temperature is input into the rate model to obtain the predicted capacity recovery rate for the test storage temperature; Obtain the actual capacity recovery rate at the tested storage temperature; If the error between the predicted capacity recovery rate and the actual capacity recovery rate is less than a preset difference, then the rate model is applied.

8. A device for predicting battery lifespan, characterized in that, The device includes: The data acquisition unit is used to acquire the target storage temperature and target storage time of the battery. A rate calculation unit is used to call a preset rate model to determine the capacity recovery decay rate of the battery at the target storage temperature. The capacity retention calculation unit is used to determine the capacity retention rate of the battery after the target storage time based on the capacity recovery decay rate.

9. An electronic device, characterized in that, The electronic device includes: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the electronic device to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1 to 7.

Images