Battery life prediction method, device, vehicle, and program product

Abstract

This application relates to the field of vehicle technology, and in particular to a battery life prediction method, device, vehicle, and program product. The method includes: obtaining the final cumulative charging capacity based on the final capacity retention rate according to a first fitting relationship between the capacity retention rate and the cumulative charging capacity; obtaining the final cumulative mileage based on the final cumulative charging capacity according to a second fitting relationship between the cumulative charging capacity and the cumulative mileage; obtaining the final cumulative time based on a third fitting relationship between the cumulative charging capacity and the cumulative time; obtaining the remaining mileage based on the final cumulative mileage and the current cumulative mileage; and obtaining the remaining usage time based on the final cumulative time and the current cumulative usage time. This solves the problems in related technologies, such as the inability to apply battery life prediction methods to commercial vehicles with special operating conditions and poor generalization ability, improving the accuracy of battery life prediction, ensuring the safety and efficiency of battery use, and providing strong support for the range of electric vehicles.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, vehicle, and program product for predicting battery life. Background Technology

[0002] With the rapid development of the new energy industry, electric vehicles are widely used. As the core of electric vehicles, monitoring the health status of batteries has always been a technical challenge for the industry, and accurately predicting the remaining battery life is also a crucial issue. Methods and systems for predicting the lifespan of power batteries can improve the safety and efficiency of battery use, while also providing strong support for the driving range of electric vehicles.

[0003] In related technologies, the prediction of battery life for new energy commercial vehicles mainly employs physical mechanism modeling and data-driven methods. Physical modeling methods primarily utilize equivalent circuit models, electrochemical models, and aging mechanism models; data-driven methods mainly utilize machine learning methods, cluster analysis, and principal component analysis. Physical modeling methods offer deeper insights and better reflect actual operating conditions, but require complex modeling and calculations. Data-driven methods rely on large amounts of data and may lack an intuitive understanding of the internal processes of the battery.

[0004] In related technologies, the double exponential capacity decay model is used as the battery capacity degradation model. Through regression analysis, trend analysis is performed using data such as capacity retention rate, charge-discharge cycles, and time. When performing mechanism analysis, capacity loss caused by concentration polarization and bipolar polarization is considered. The EKPF (Extended Kalman Particle Filter) algorithm is used to track the battery capacity decay state and obtain the predicted value of the remaining life of the lithium battery.

[0005] However, the above solutions are mainly for passenger cars with low mileage requirements and are not suitable for commercial vehicles with special operating conditions. They have limited application types and poor generalization ability, which urgently need to be addressed. Summary of the Invention

[0006] This application provides a battery life prediction method, device, vehicle, and program product to solve the problems in related technologies, such as the inability of battery life prediction methods to be applied to commercial vehicles with special operating conditions and poor generalization ability. It improves the accuracy of battery life prediction, ensures the safety and efficiency of battery use, and provides strong support for the range of electric vehicles.

[0007] The first aspect of this application provides a method for predicting battery life, comprising the following steps:

[0008] Obtain the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the battery's lifespan;

[0009] Based on the final capacity retention rate, the final cumulative charging capacity is obtained according to the first fitting relationship between the capacity retention rate and the cumulative charging capacity. Based on the final cumulative charging capacity, the final cumulative mileage is obtained according to the second fitting relationship between the cumulative charging capacity and the cumulative mileage. The final cumulative time is obtained according to the third fitting relationship between the cumulative charging capacity and the cumulative time.

[0010] The remaining mileage is obtained based on the final cumulative mileage and the current cumulative mileage, and the remaining usage time is obtained based on the final cumulative time and the current cumulative usage time. The lifespan prediction result of the battery to be predicted is generated based on the remaining mileage and / or the remaining usage time.

[0011] Optionally, in some embodiments, before obtaining the final cumulative charging capacity based on the final capacity retention rate and a first fitting relationship between the capacity retention rate and the cumulative charging capacity, the following steps are included:

[0012] Obtain charging data for each charge of the battery to be predicted;

[0013] The charging data is preprocessed, and the first fitting relationship, the second fitting relationship, and the third fitting relationship are obtained by fitting the preprocessed charging data.

[0014] Optionally, in some embodiments, the step of fitting the first fitting relationship, the second fitting relationship, and the third fitting relationship based on the preprocessed charging data further includes:

[0015] The capacity retention rate, cumulative charging capacity, cumulative mileage, and cumulative usage time for each charge are calculated from the preprocessed charging data.

[0016] The first fitting relationship is obtained by fitting the capacity retention rate corresponding to each charge and the cumulative charging capacity corresponding to each charge.

[0017] The second fitting relationship is obtained by fitting the cumulative charging capacity corresponding to each charging and the cumulative mileage corresponding to each charging;

[0018] The third fitting relationship is obtained by fitting the cumulative charging capacity corresponding to each charging and the cumulative usage time corresponding to each charging.

[0019] Optionally, in some embodiments, after obtaining the charging data for each charge of the battery to be predicted, the method further includes:

[0020] Determine whether the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time for each charge all meet the preset fitting requirements.

[0021] If any of the capacity retention rate, cumulative charging capacity, cumulative mileage, and cumulative usage time corresponding to each charging session do not meet the preset fitting requirements, then the first fitting relationship is stopped and the third fitting relationship is established.

[0022] Optionally, in some embodiments, the first fitting relationship is:

[0023] f(x)=k0*exp(k1*x)+k2*exp(k3*x);

[0024] Where f(x) is the capacity retention rate, x is the charging capacity, k0 is the initial value of the first exponential term exp(k1*x), k1 is the growth rate or decay rate of the first exponential term exp(k1*x), k2 is the initial amplitude or baseline value of the second exponential term exp(k3*x), and k3 is the growth rate or decay rate of the second exponential term exp(k3*x).

[0025] A second aspect of this application provides a battery life prediction device, comprising:

[0026] The acquisition module is used to acquire the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the battery's lifespan.

[0027] The calculation module is used to obtain the final cumulative charging capacity based on the final capacity retention rate and a first fitting relationship between the capacity retention rate and the cumulative charging capacity, and to obtain the final cumulative mileage based on the final cumulative charging capacity and a second fitting relationship between the cumulative charging capacity and the cumulative mileage, and to obtain the final cumulative time based on a third fitting relationship between the cumulative charging capacity and the cumulative time.

[0028] The generation module is used to obtain the remaining mileage based on the final accumulated mileage and the current accumulated mileage, and to obtain the remaining usage time based on the final accumulated time and the current accumulated usage time, and to generate the life prediction result of the battery to be predicted based on the remaining mileage and / or the remaining usage time.

[0029] Optionally, in some embodiments, before obtaining the final cumulative charging capacity based on the final capacity retention rate and according to a first fitting relationship between the capacity retention rate and the cumulative charging capacity, the calculation module is specifically used for:

[0030] Obtain charging data for each charge of the battery to be predicted;

[0031] The charging data is preprocessed, and the first fitting relationship, the second fitting relationship, and the third fitting relationship are obtained by fitting the preprocessed charging data.

[0032] Optionally, in some embodiments, the computing module is further configured to:

[0033] The capacity retention rate, cumulative charging capacity, cumulative mileage, and cumulative usage time for each charge are calculated from the preprocessed charging data.

[0034] The first fitting relationship is obtained by fitting the capacity retention rate corresponding to each charge and the cumulative charging capacity corresponding to each charge.

[0035] The second fitting relationship is obtained by fitting the cumulative charging capacity corresponding to each charging and the cumulative mileage corresponding to each charging;

[0036] The third fitting relationship is obtained by fitting the cumulative charging capacity corresponding to each charging and the cumulative usage time corresponding to each charging.

[0037] Optionally, in some embodiments, after acquiring the charging data for each charge of the battery to be predicted, the calculation module is further configured to:

[0038] Determine whether the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time for each charge all meet the preset fitting requirements.

[0039] If any of the capacity retention rate, cumulative charging capacity, cumulative mileage, and cumulative usage time at each charging time fail to meet the preset fitting requirements, the first fitting relationship is stopped and the third fitting relationship is established.

[0040] Optionally, in some embodiments, the first fitting relationship is:

[0041] f(x)=k0*exp(k1*x)+k2*exp(k3*x);

[0042] Where f(x) is the capacity retention rate, x is the charging capacity, k0 is the initial value of the first exponential term exp(k1*x), k1 is the growth rate or decay rate of the first exponential term exp(k1*x), k2 is the initial amplitude or baseline value of the second exponential term exp(k3*x), and k3 is the growth rate or decay rate of the second exponential term exp(k3*x).

[0043] A third aspect of this application provides a vehicle including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the battery life prediction method as described in the above embodiments.

[0044] A fourth aspect of this application provides a computer program product having a computer program stored thereon that is executed to implement the battery life prediction method as described in the above embodiments.

[0045] Therefore, this application obtains the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the battery's lifespan. Based on the final capacity retention rate, it obtains the final cumulative charging capacity according to a first fitting relationship between the capacity retention rate and the cumulative charging capacity. Based on the final cumulative charging capacity, it obtains the final cumulative mileage according to a second fitting relationship between the cumulative charging capacity and the cumulative mileage. Based on the third fitting relationship between the cumulative charging capacity and the cumulative time, it obtains the final cumulative mileage and the current cumulative mileage. It then obtains the remaining usage time according to the final cumulative time and the current cumulative usage time, and finally generates the battery's lifespan prediction result based on the remaining mileage and / or the remaining usage time. This solves the problems in related technologies, such as the inability of battery lifespan prediction methods to be applied to commercial vehicles with special operating conditions and poor generalization ability. It improves the accuracy of battery lifespan prediction, ensures the safety and efficiency of battery use, and provides strong support for the range of electric vehicles.

[0046] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0047] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0048] Figure 1 A flowchart of a battery life prediction method provided according to an embodiment of this application;

[0049] Figure 2 A flowchart of a battery life prediction method according to a specific embodiment of this application;

[0050] Figure 3 This is a block diagram of a battery life prediction device provided according to an embodiment of this application;

[0051] Figure 4 This is a block diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0052] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0053] The following description, with reference to the accompanying drawings, describes a battery life prediction method, apparatus, vehicle, and program product according to embodiments of this application. Addressing the problem mentioned in the background art that battery life prediction methods cannot be applied to commercial vehicles with special operating conditions and have poor generalization ability, this application provides a battery life prediction method. In this method, the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the battery's lifespan are obtained. Based on the final capacity retention rate, the final cumulative charging capacity is obtained according to a first fitting relationship between the capacity retention rate and the cumulative charging capacity. Based on the final cumulative charging capacity, the final cumulative mileage is obtained according to a second fitting relationship between the cumulative charging capacity and the cumulative mileage. The final cumulative time is obtained according to a third fitting relationship between the cumulative charging capacity and the cumulative time. The remaining mileage is obtained based on the final cumulative mileage and the current cumulative mileage. The remaining usage time is obtained based on the final cumulative time and the current cumulative usage time. Finally, the battery life prediction result is generated based on the remaining mileage and / or the remaining usage time. This solves the problems in the related art where battery life prediction methods cannot be applied to commercial vehicles with special operating conditions and have poor generalization ability, improving the accuracy of battery life prediction, ensuring the safety and efficiency of battery use, and providing strong support for the range of electric vehicles.

[0054] Specifically, Figure 1 This is a schematic flowchart illustrating the battery life prediction method provided in an embodiment of this application.

[0055] like Figure 1 As shown, the battery life prediction method includes the following steps:

[0056] In step S101, the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the lifespan of the battery to be predicted are obtained.

[0057] In this application embodiment, the battery to be predicted is a battery whose performance and lifespan are not yet fully determined, and whose remaining mileage and remaining usage time need to be estimated through analysis and prediction models, especially the prediction of the battery life of commercial vehicles.

[0058] In this application embodiment, the current cumulative mileage refers to the total driving mileage accumulated by the battery since it was put into use. The current cumulative usage time refers to the total time accumulated by the battery since it was first used, which includes usage time and standby time. The final capacity retention rate refers to the percentage of capacity that the battery is expected to retain at the end of its expected life.

[0059] Understandably, for electric vehicles, cumulative mileage helps assess the degree of battery aging. Battery lifespan is affected not only by usage frequency but also by time. Therefore, this application's embodiments consider current cumulative mileage and current cumulative usage time to accurately predict the battery's remaining mileage and remaining usage time. Furthermore, the final capacity retention rate at the end of the battery's lifespan reflects a direct indicator of battery performance degradation, providing an important basis for battery lifespan prediction.

[0060] Therefore, in step S101, this application evaluates the battery performance and accurately predicts the remaining battery life by detecting the current cumulative mileage, current cumulative usage time and final capacity retention rate, thereby reducing unnecessary battery replacements and lowering operating costs.

[0061] In step S102, based on the final capacity retention rate, the final cumulative charging capacity is obtained according to the first fitting relationship between the capacity retention rate and the cumulative charging capacity. Based on the final cumulative charging capacity, the final cumulative mileage is obtained according to the second fitting relationship between the cumulative charging capacity and the cumulative mileage. The final cumulative time is obtained according to the third fitting relationship between the cumulative charging capacity and the cumulative time.

[0062] In this application embodiment, the final cumulative charging capacity refers to the total amount of charging that the battery can accumulate throughout its entire lifespan; the final cumulative mileage refers to the total mileage that the electric vehicle supported by the battery to be predicted will travel throughout its entire lifespan; and the final cumulative time refers to the total time that the battery will experience from the start of use to the predicted end of its lifespan.

[0063] Based on the background information, among the technologies related to predicting the battery life of new energy commercial vehicles, the physical model method requires complex modeling and calculation, while the data-driven method relies on a large amount of data and lacks an intuitive understanding of the internal processes of the battery. Therefore, this application combines physical models with data-driven models, utilizing the theoretical foundation provided by physical models and the generalization ability of data-driven models to improve the accuracy of model predictions.

[0064] Specifically, this application establishes a first fitting relationship between capacity retention rate and cumulative charging capacity, a second fitting relationship between cumulative charging capacity and cumulative mileage, and a third fitting relationship between cumulative charging capacity and cumulative time. Based on the special characteristics of commercial vehicle operating conditions, historical battery data is obtained, and a fusion model combining physical model and data-driven model is constructed to predict the remaining service life of the battery.

[0065] Optionally, in some embodiments, before obtaining the final cumulative charging capacity based on the final capacity retention rate and the first fitting relationship between the capacity retention rate and the cumulative charging capacity, the method includes: acquiring charging data for each charge of the battery to be predicted; preprocessing the charging data; and fitting a first fitting relationship, a second fitting relationship, and a third fitting relationship based on the preprocessed charging data.

[0066] It is understandable that the charging and discharging data, temperature data, current data, and mileage of commercial vehicles differ from those of passenger vehicles. The battery life prediction method in this application analyzes historical data from actual vehicles, taking into account the impact of special operating conditions (cargo transportation, engineering operations, fire fighting, etc.) and driving regularity (mainly reflected in daily operational regularity, fixed routes, and long driving distances) on the data. Therefore, the charging data of the battery to be predicted for each charge in this application embodiment includes: capacity retention rate, cumulative charging capacity, cumulative throughput, mileage, and time.

[0067] Furthermore, after acquiring the charging data for each charge of the battery to be predicted, in order to reduce random fluctuations in the data, this application embodiment uses appropriate filtering and denoising techniques to clean and process the data, avoiding data fluctuations, abnormal changes, loss, etc. caused by special operating conditions.

[0068] Optionally, in this embodiment of the application, real-time data of new energy vehicles can be collected through a preset data acquisition module, with one frame every 10 seconds. The collected data includes fields such as data acquisition time, total current, mileage, SOC (State of Charge), charging status, and maximum voltage of individual battery cells. The original dataset is cleaned, including but not limited to deleting empty fields, erroneous fields, and abnormal fields.

[0069] Next, data standardization is performed, that is, data acquisition time, insulation alarm, vehicle speed and other data are standardized. The acquisition time is converted into a standard time format (datetime, unit: ms), and the mileage, SOC, total current and the highest value of battery cell voltage are converted into floating-point data type, thereby obtaining standard data and forming a matrix according to the time series.

[0070] Optionally, in some embodiments, fitting a first fitting relationship, a second fitting relationship, and a third fitting relationship based on the preprocessed charging data further includes: calculating the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time corresponding to each charge from the preprocessed charging data; fitting the first fitting relationship based on the capacity retention rate and the cumulative charging capacity corresponding to each charge; fitting the second fitting relationship based on the cumulative charging capacity and the cumulative mileage corresponding to each charge; and fitting the third fitting relationship based on the cumulative charging capacity and the cumulative usage time corresponding to each charge.

[0071] Specifically, embodiments of this application can calculate the capacity retention rate, cumulative charging capacity (for pure electric vehicles), cumulative throughput (for hybrid vehicles), and cumulative mileage array based on the above data for each charging time. Optionally, the capacity retention rate can employ a dual Kalman filter algorithm to ensure that the output data is under standard operating conditions. For pure electric vehicles, the charging amount for each charge is counted and accumulated to obtain the cumulative charging capacity. For hybrid vehicles, the capacity for each charge and discharge is counted and accumulated to obtain the cumulative throughput.

[0072] Optionally, in some embodiments, the first fitting relationship is:

[0073] f(x)=k0*exp(k1*x)+k2*exp(k3*x);

[0074] Where f(x) is the capacity retention rate, x is the charging capacity, k0 is the initial value of the first exponential term exp(k1*x), k1 is the growth rate or decay rate of the first exponential term exp(k1*x), k2 is the initial amplitude or baseline value of the second exponential term exp(k3*x), and k3 is the growth rate or decay rate of the second exponential term exp(k3*x).

[0075] It should be noted that in the first fitting relationship, k0 is the initial value of the first exponential term exp(k1*x), representing the value of the first exponential term exp(k1*x) when x = 0; k1 is the growth rate or decay rate of the exponential term exp(k1*x), which determines the speed at which the first exponential term exp(k1*x) increases or decreases with x. If k1 is positive, it means that the term grows exponentially with the increase of x; if k1 is negative, it means that the term decays exponentially with the increase of x; k2 is the initial amplitude or baseline value of the second exponential term exp(k3*x), which represents the value of the second exponential term exp(k3*x) when x = 0; k3 is the growth rate or decay rate of the second exponential term exp(k3*x), which determines the speed at which the second exponential term exp(k3*x) increases or decreases with x. Similar to k1, the sign of k3 determines the growth or decay trend of the second exponential term exp(k3*x).

[0076] Specifically, this application embodiment modifies the dual-exponential model, establishing a relationship expression between the capacity retention rate and the cumulative charging capacity based on the capacity retention rate and the cumulative charging capacity corresponding to each charge, which is the first fitting relationship of this application embodiment. Therefore, this application embodiment can obtain the final cumulative charging capacity based on the final capacity retention rate and the first fitting relationship.

[0077] It should be noted that, for hybrid vehicles, the embodiments of this application can also be based on a dual-exponential model, establishing a relationship expression between the capacity retention rate and the cumulative throughput based on the capacity retention rate corresponding to each charge and the cumulative throughput corresponding to each charge.

[0078] Furthermore, in this embodiment, a second fitting relationship is obtained by fitting the cumulative charging capacity and the cumulative mileage corresponding to each charge. Specifically, this embodiment fits the cumulative charging capacity and cumulative mileage using the support vector regression (SVR) model in machine learning algorithms to obtain the relationship expression, i.e., the second fitting relationship in this embodiment is:

[0079] g(x) = kx + b;

[0080] Where g(x) is the cumulative charging capacity, x is the cumulative mileage, k is the slope, which represents the rate of change of charging capacity required for each unit of mileage traveled, and b is the intercept, which represents the initial value of the cumulative charging capacity g(x) when the cumulative mileage x is zero.

[0081] It should be noted that, for hybrid vehicles, the embodiments of this application can also fit the cumulative throughput and cumulative mileage to obtain a second fitting relationship.

[0082] Furthermore, in this embodiment, a third fitting relationship is obtained by fitting the cumulative charging capacity and the cumulative usage time corresponding to each charging session. Specifically, this embodiment establishes a relationship expression between cumulative charging capacity and time. This embodiment uses a support vector regression (SVR) model in machine learning algorithms. The nonlinear SVR expression, i.e., the third fitting relationship, is as follows:

[0083] g(x) = w, φ(T) + b;

[0084] Where g(x) is the cumulative charging capacity, T is the time, w, φ(T) represents the dot product of the weight vector w and the mapped time φ(T) in the high-dimensional space, and b is the bias term.

[0085] It should be noted that in the third fitting relationship, the bias term b allows the model to translate along the y-axis (in this case, the cumulative charging capacity) in the feature space, thereby improving the model's fit.

[0086] Therefore, the embodiments of this application can obtain the relationship between capacity retention rate and mileage based on the first fitting relationship and the second fitting relationship, and obtain the relationship between capacity retention rate and time based on the first fitting relationship and the third fitting relationship.

[0087] Based on the above fitting process, the embodiments of this application can obtain the relationship between cumulative charging capacity / cumulative throughput and time, as well as the relationship between cumulative charging capacity / cumulative throughput and mileage, thereby obtaining the corresponding expected mileage and time based on the predicted demand for capacity retention rate.

[0088] Specifically, this application embodiment statistically analyzes capacity retention rate, cumulative charging capacity / cumulative throughput, mileage, time, etc., constructs a relationship between capacity retention rate and cumulative charging capacity / cumulative throughput, performs formula fitting, and calculates the final cumulative charging capacity reaching the end of the lifespan based on the fitted curve. Based on this final cumulative charging capacity, the final cumulative mileage is obtained according to a second fitting relationship, and the final cumulative time is obtained according to a third fitting relationship.

[0089] In other words, the embodiments of this application first describe the relationship between capacity retention rate and cumulative charging capacity / cumulative throughput by constructing a fitting curve of capacity retention rate and cumulative charging capacity / cumulative throughput. By constructing the relationship between the two, the performance degradation of commercial vehicle batteries over time can be more accurately reflected. Furthermore, cumulative charging capacity is introduced as an intermediate variable to obtain the relationship between capacity retention rate and mileage, as well as the relationship between capacity retention rate and time, thereby accurately predicting the battery life of new energy commercial vehicles.

[0090] Optionally, in some embodiments, after obtaining the charging data of the battery to be predicted for each charge, the method further includes: determining whether the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time corresponding to each charge all meet preset fitting requirements; if any of the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time corresponding to each charge do not meet the preset fitting requirements, then the first fitting relationship is stopped and the third fitting relationship is initiated.

[0091] It is understandable that the number of points for capacity retention directly affects the accuracy and reliability of the fitted model. Generally speaking, the more points, the stronger the predictive ability of the model. Therefore, the fitting requirements preset in the embodiments of this application include a threshold for the number of points for capacity retention.

[0092] The cumulative usage time should be evenly distributed throughout the entire battery life cycle to ensure that the long-term trend of battery performance changes can be captured. Therefore, the fitting requirements preset in the embodiments of this application include a limitation on the cumulative usage time.

[0093] The cumulative mileage should include the vehicle's driving conditions under different conditions, such as urban roads and highways, to reflect the battery's performance under different usage modes. Therefore, the fitting requirements preset in this application embodiment include the limitation of cumulative mileage and driving conditions.

[0094] In addition, the embodiments of this application also need to ensure that there are enough cumulative charging capacity data points in order to perform effective statistical analysis and establish a reliable fitting model. Therefore, the fitting requirements preset in the embodiments of this application include a threshold for cumulative charging capacity.

[0095] When predicting battery life, determining whether the number of capacity retention points, cumulative charging capacity, cumulative mileage, and cumulative usage time meet the fitting requirements is a key step to ensure the accuracy of data analysis.

[0096] Specifically, if any of the following parameters—capacity retention rate, cumulative charging capacity, cumulative mileage, and cumulative usage time—does not meet the aforementioned preset fitting requirements, then no fitting will be performed.

[0097] Therefore, in step S102, based on the analysis of the special working conditions and driving regularity of commercial vehicles, this application integrates the physical mechanism model method and the data-driven method to improve the double exponential model, introduces the cumulative charging capacity as an intermediate variable to obtain the relationship between capacity retention rate and mileage, as well as the relationship between capacity retention rate and time, so as to more accurately predict the final state of the battery.

[0098] In step S103, the remaining mileage is obtained based on the final accumulated mileage and the current accumulated mileage, and the remaining usage time is obtained based on the final accumulated time and the current accumulated usage time. The life prediction result of the battery to be predicted is generated based on the remaining mileage and / or the remaining usage time.

[0099] Specifically, in step S101, this embodiment of the application obtains the current cumulative mileage and current cumulative usage time of the battery. In step S102, the cumulative charging capacity is introduced as an intermediate variable to obtain the relationship between capacity retention rate and mileage, as well as the relationship between capacity retention rate and time, to obtain the final cumulative mileage and final cumulative time. Then, this embodiment of the application can use the difference between the final cumulative mileage and the current cumulative mileage as the remaining mileage, and the difference between the final cumulative time and the current cumulative usage time as the remaining usage time, thereby obtaining the life prediction result of the battery to be predicted.

[0100] It should be noted that the predicted lifespan of the battery in this application embodiment can be the remaining mileage, the remaining usage time, or both.

[0101] To enable those skilled in the art to further understand the battery life prediction method of the embodiments of this application, the following examples illustrate the implementation steps of the method.

[0102] Specifically, Figure 2 Here is a flowchart of a battery life prediction method according to a specific embodiment of this application, as shown below. Figure 2 As shown, the battery life prediction method includes the following steps:

[0103] Step S201: Obtain raw data and calculate the charging time, capacity retention rate, cumulative charging capacity, and cumulative mileage for each charge.

[0104] Step S202: Determine whether the number of capacity retention rate points, vehicle running time, and cumulative mileage meet the fitting requirements. If they meet the fitting requirements, proceed to step S204; otherwise, proceed to step S203.

[0105] Step S203: Do not perform fitting, end the process;

[0106] Step S204: Fit the capacity retention rate and cumulative charging capacity curves;

[0107] Step S205: Calculate the remaining cumulative charging capacity at the end of the lifespan based on the fitted curve.

[0108] Step S206: Based on the fitting relationship between mileage, time, and capacity retention rate, obtain the total mileage and total time;

[0109] Step S207: Calculate the remaining mileage and remaining time based on the current accumulated mileage and time, and end the process.

[0110] Therefore, this application analyzes historical data from actual vehicles, considering the impact of special operating conditions and driving patterns of commercial vehicles on the data, and uses appropriate filtering and denoising techniques to reduce random fluctuations in the data. It statistically analyzes capacity retention rate, cumulative charging capacity / cumulative throughput, mileage, time, etc. By constructing the relationship between capacity retention rate and cumulative charging capacity / cumulative throughput, it performs formula fitting, calculates the remaining cumulative charging capacity at the end of the lifespan based on the fitted curve, and calculates the remaining mileage and time at the end of the lifespan based on the ratio of cumulative charging capacity to mileage and time in a recent period.

[0111] The battery life prediction method proposed in this application obtains the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the battery's lifespan. Based on the final capacity retention rate, the final cumulative charging capacity is obtained according to a first fitting relationship between the capacity retention rate and the cumulative charging capacity. Based on the final cumulative charging capacity, the final cumulative mileage is obtained according to a second fitting relationship between the cumulative charging capacity and the cumulative mileage. The final cumulative time is obtained according to a third fitting relationship between the cumulative charging capacity and the cumulative time. The remaining mileage is obtained based on the final cumulative mileage and the current cumulative mileage. The remaining usage time is obtained based on the final cumulative time and the current cumulative usage time. Finally, the battery life prediction result is generated based on the remaining mileage and / or the remaining usage time. This solves the problems in related technologies, such as the inability to apply battery life prediction methods to commercial vehicles with special operating conditions and poor generalization ability. It improves the accuracy of battery life prediction, ensures the safety and efficiency of battery use, and provides strong support for the range of electric vehicles.

[0112] Next, the battery life prediction device according to an embodiment of this application is described with reference to the accompanying drawings.

[0113] Figure 3 This is a block diagram of a battery life prediction device according to an embodiment of this application.

[0114] like Figure 3 As shown, the battery life prediction device 10 includes: an acquisition module 100, a calculation module 200, and a generation module 300.

[0115] Specifically, the acquisition module 100 is used to acquire the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the lifespan of the battery to be predicted; the calculation module 200 is used to obtain the final cumulative charging capacity based on the final capacity retention rate and a first fitting relationship between the capacity retention rate and the cumulative charging capacity, and to obtain the final cumulative mileage based on the final cumulative charging capacity and a second fitting relationship between the cumulative charging capacity and the cumulative mileage, and to obtain the final cumulative time based on the third fitting relationship between the cumulative charging capacity and the cumulative time; the generation module 300 is used to obtain the remaining mileage based on the final cumulative mileage and the current cumulative mileage, and to obtain the remaining usage time based on the final cumulative time and the current cumulative usage time, and to generate the lifespan prediction result of the battery to be predicted based on the remaining mileage and / or the remaining usage time.

[0116] Optionally, in some embodiments, before obtaining the final cumulative charging capacity based on the final capacity retention rate and the first fitting relationship between the capacity retention rate and the cumulative charging capacity, the calculation module 200 is specifically used to: acquire charging data for each charge of the battery to be predicted; preprocess the charging data, and fit the first fitting relationship, the second fitting relationship, and the third fitting relationship based on the preprocessed charging data.

[0117] Optionally, in some embodiments, the calculation module 200 is further configured to: calculate from the preprocessed charging data the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time corresponding to each charge; fit a first fitting relationship based on the capacity retention rate and the cumulative charging capacity corresponding to each charge; fit a second fitting relationship based on the cumulative charging capacity and the cumulative mileage corresponding to each charge; and fit a third fitting relationship based on the cumulative charging capacity and the cumulative usage time corresponding to each charge.

[0118] Optionally, in some embodiments, after obtaining the charging data of the battery to be predicted for each charge, the calculation module 200 is further configured to: determine whether the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time corresponding to each charge all meet the preset fitting requirements; and if any of the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time corresponding to each charge do not meet the preset fitting requirements, stop the first fitting relationship and proceed to the third fitting relationship.

[0119] Optionally, in some embodiments, the first fitting relationship is:

[0120] f(x)=k0*exp(k1*x)+k2*exp(k3*x);

[0121] Where f(x) is the capacity retention rate, x is the charging capacity, k0 is the initial value of the first exponential term exp(k1*x), k1 is the growth rate or decay rate of the first exponential term exp(k1*x), k2 is the initial amplitude or baseline value of the second exponential term exp(k3*x), and k3 is the growth rate or decay rate of the second exponential term exp(k3*x).

[0122] It should be noted that the foregoing explanation of the battery life prediction method embodiment also applies to the battery life prediction device of this embodiment, and will not be repeated here.

[0123] The battery life prediction device proposed in this application obtains the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the battery's lifespan. Based on the final capacity retention rate, it obtains the final cumulative charging capacity according to a first fitting relationship between the capacity retention rate and the cumulative charging capacity. Based on the final cumulative charging capacity, it obtains the final cumulative mileage according to a second fitting relationship between the cumulative charging capacity and the cumulative mileage. Based on the final cumulative charging capacity, it obtains the final cumulative time according to a third fitting relationship between the cumulative charging capacity and the cumulative time. It obtains the remaining mileage based on the final cumulative mileage and the current cumulative mileage, and obtains the remaining usage time based on the final cumulative time and the current cumulative usage time. Finally, it generates the battery life prediction result based on the remaining mileage and / or the remaining usage time. This solves the problems in related technologies, such as the inability of battery life prediction methods to be applied to commercial vehicles with special operating conditions and poor generalization ability. It improves the accuracy of battery life prediction, ensures the safety and efficiency of battery use, and provides strong support for the range of electric vehicles.

[0124] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0125] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0126] When processor 402 executes the program, it implements the battery life prediction method provided in the above embodiments.

[0127] Furthermore, the vehicle also includes:

[0128] Communication interface 403 is used for communication between memory 401 and processor 402.

[0129] The memory 401 is used to store computer programs that can run on the processor 402.

[0130] The memory 401 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0131] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0132] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0133] Processor 402 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0134] This application also provides a computer program product having a computer program stored thereon, which, when executed, implements the battery life prediction method described above.

[0135] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0136] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0137] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0138] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0139] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0140] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for predicting battery life, characterized in that, Includes the following steps: Obtain the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the battery's lifespan; Based on the final capacity retention rate, the final cumulative charging capacity is obtained according to the first fitting relationship between the capacity retention rate and the cumulative charging capacity. Based on the final cumulative charging capacity, the final cumulative mileage is obtained according to the second fitting relationship between the cumulative charging capacity and the cumulative mileage. The final cumulative time is obtained according to the third fitting relationship between the cumulative charging capacity and the cumulative time. The remaining mileage is obtained based on the final accumulated mileage and the current accumulated mileage, and the remaining usage time is obtained based on the final accumulated time and the current accumulated usage time. The lifespan prediction result of the battery to be predicted is generated based on the remaining mileage and / or the remaining usage time. Before obtaining the final cumulative charging capacity based on the final capacity retention rate and according to a first fitting relationship between the capacity retention rate and the cumulative charging capacity, the process includes: Obtain charging data for each charge of the battery to be predicted; The charging data is preprocessed, and the first fitting relationship, the second fitting relationship, and the third fitting relationship are obtained by fitting the preprocessed charging data. The first fitting relationship is: f(x)=k0*exp(k1*x)+k2*exp(k3*x); Where f(x) is the capacity retention rate, x is the cumulative charging capacity, k0 is the initial amplitude or base value of the first exponential term exp(k1*x), k1 is the growth rate or decay rate of the first exponential term exp(k1*x), k2 is the initial amplitude or base value of the second exponential term exp(k3*x), and k3 is the growth rate or decay rate of the second exponential term exp(k3*x). When k1 is positive, it indicates that the first exponential term exp(k1*x) is increasing; when k1 is negative, it indicates that the first exponential term exp(k1*x) is decreasing. When k3 is positive, it indicates that the second exponential term exp(k3*x) is increasing; when k3 is negative, it indicates that the second exponential term exp(k3*x) is decreasing.

2. The method according to claim 1, characterized in that, The step of fitting the first fitting relationship, the second fitting relationship, and the third fitting relationship based on the preprocessed charging data further includes: The capacity retention rate, cumulative charging capacity, cumulative mileage, and cumulative usage time for each charge are calculated from the preprocessed charging data. The first fitting relationship is obtained by fitting the capacity retention rate corresponding to each charge and the cumulative charging capacity corresponding to each charge. The second fitting relationship is obtained by fitting the cumulative charging capacity corresponding to each charging and the cumulative mileage corresponding to each charging; The third fitting relationship is obtained by fitting the cumulative charging capacity corresponding to each charging and the cumulative usage time corresponding to each charging.

3. The method according to claim 1, characterized in that, After acquiring the charging data for each charge of the battery to be predicted, the method further includes: Determine whether the capacity retention rate, the cumulative charging capacity, the cumulative mileage, and the cumulative usage time for each charge all meet the preset fitting requirements. If any of the capacity retention rate, cumulative charging capacity, cumulative mileage, and cumulative usage time corresponding to each charging session do not meet the preset fitting requirements, then the first fitting relationship, the second fitting relationship, and the third fitting relationship are stopped.

4. A battery life prediction device, characterized in that, include: The acquisition module is used to acquire the current cumulative mileage, current cumulative usage time, and final capacity retention rate at the end of the battery's lifespan. The calculation module is used to obtain the final cumulative charging capacity based on the final capacity retention rate and a first fitting relationship between the capacity retention rate and the cumulative charging capacity, and to obtain the final cumulative mileage based on the final cumulative charging capacity and a second fitting relationship between the cumulative charging capacity and the cumulative mileage, and to obtain the final cumulative time based on a third fitting relationship between the cumulative charging capacity and the cumulative time. The generation module is used to obtain the remaining mileage based on the final accumulated mileage and the current accumulated mileage, and to obtain the remaining usage time based on the final accumulated time and the current accumulated usage time, and to generate the life prediction result of the battery to be predicted based on the remaining mileage and / or the remaining usage time. Before obtaining the final cumulative charging capacity based on the final capacity retention rate and according to the first fitting relationship between the capacity retention rate and the cumulative charging capacity, the calculation module is specifically used for: Obtain charging data for each charge of the battery to be predicted; The charging data is preprocessed, and the first fitting relationship, the second fitting relationship, and the third fitting relationship are obtained by fitting the preprocessed charging data. The first fitting relationship is: f(x)=k0*exp(k1*x)+k2*exp(k3*x); Where f(x) is the capacity retention rate, x is the cumulative charging capacity, k0 is the initial amplitude or base value of the first exponential term exp(k1*x), k1 is the growth rate or decay rate of the first exponential term exp(k1*x), k2 is the initial amplitude or base value of the second exponential term exp(k3*x), and k3 is the growth rate or decay rate of the second exponential term exp(k3*x). When k1 is positive, it indicates that the first exponential term exp(k1*x) is increasing; when k1 is negative, it indicates that the first exponential term exp(k1*x) is decreasing. When k3 is positive, it indicates that the second exponential term exp(k3*x) is increasing; when k3 is negative, it indicates that the second exponential term exp(k3*x) is decreasing.

5. The apparatus according to claim 4, characterized in that, The computing module is also used for: The capacity retention rate, cumulative charging capacity, cumulative mileage, and cumulative usage time for each charge are calculated from the preprocessed charging data. The first fitting relationship is obtained by fitting the capacity retention rate corresponding to each charge and the cumulative charging capacity corresponding to each charge. The second fitting relationship is obtained by fitting the cumulative charging capacity corresponding to each charging and the cumulative mileage corresponding to each charging; The third fitting relationship is obtained by fitting the cumulative charging capacity corresponding to each charging and the cumulative usage time corresponding to each charging.

6. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the battery life prediction method as described in any one of claims 1-3.

7. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the battery life prediction method as described in any one of claims 1-3.

Images