Lithium battery life prediction method and device, terminal equipment and medium

Abstract

The invention provides a lithium battery life prediction method and device, terminal equipment and a medium, and the method comprises the steps: building an initial cycle life prediction model based on a degradation mechanism of a lithium battery SEI film in a charging and discharging process; based on the degradation mechanism of the lithium battery SEI film in the storage process, an initial storage life prediction model is constructed; for any one of the initial cycle life model and the initial storage life model, acquiring experimental battery data for performing model verification on the one, and performing fitting training on the one by using the experimental battery data to obtain a cycle life model and a storage life model which are trained to be converged; and obtaining the calibrated battery capacity, temperature data, charge and discharge rate, battery storage charge state and working mode of the lithium battery to be tested, and predicting the service life of the lithium battery to be tested in the working mode by combining the cycle life model and the storage life model. The lithium battery life prediction accuracy can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of lithium electronic batteries, and specifically relates to a lithium battery life prediction method, device, terminal equipment and medium. Background Art

[0002] As lithium batteries age, their performance degrades, which may cause the device to overheat or fail to work. Predicting the remaining service life of lithium batteries can help device owners replace batteries in a timely manner and avoid potential safety risks. By predicting the remaining service life of lithium batteries, device owners can more effectively plan battery replacement and inventory management, avoid efficiency losses caused by replacing batteries too early or too late, and ensure the consistency of the entire battery pack and optimize overall performance. It can also more accurately estimate the recycling and reuse value of lithium batteries, thereby promoting environmental protection and sustainable development.

[0003] Currently, the remaining service life of lithium batteries is predicted mainly through the following methods: the empirical formula method, which summarizes some empirical formulas based on a large amount of data and experimental results to predict the remaining service life of the battery. The advantage of this method is that the amount of calculation is small, but the difficulty lies in the consideration of diverse factors and the difficulty in fitting parameter identification and formula construction accurately; the model method, which uses machine learning or deep learning models to train and learn a large amount of battery data to achieve accurate prediction of the remaining service life of the battery. This method requires a large amount of data and powerful computing power; accelerated aging test, which conducts charge and discharge experiments on the battery in an accelerated environment, and uses the number of cycles to evaluate the remaining service life. The accuracy of this method is limited by the difference between the accelerated environment and the actual usage scenario.

[0004] In addition, since the use of lithium batteries includes many storage stages (when the battery is in storage, if the battery is not charged or discharged, the changes in the SEI film will be relatively slow) and cycle stages (during the battery charging and discharging process, the SEI film will undergo continuous damage and repair), the SEI film aging rates are different in different stages. The traditional lithium battery life prediction method does not consider the impact of different SEI film aging rates in different stages under different working modes on the lithium battery life prediction, which reduces the accuracy of lithium battery life prediction. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a lithium battery life prediction method, device, terminal equipment and medium to improve the accuracy of lithium battery life prediction.

[0006] In a first aspect, the present invention provides a method for predicting the life of a lithium battery, the method comprising the following steps:

[0007] Based on the degradation mechanism of the SEI film of lithium batteries during the charging and discharging process, an initial cycle life prediction model is constructed; the initial cycle life prediction model is used to describe the correlation between battery capacity loss and temperature and charging and discharging rate;

[0008] Based on the degradation mechanism of the SEI film of lithium batteries during storage, an initial storage life prediction model is constructed; the initial storage life prediction model is used to describe the correlation between battery capacity loss and battery storage state of charge;

[0009] For either the initial cycle life model or the initial storage life model, respectively, obtaining experimental battery data for model verification of the one, and performing fitting training on the one using the experimental battery data to obtain a cycle life model and a storage life model trained to convergence;

[0010] The calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge and working mode of the lithium battery to be tested are obtained, and the life of the lithium battery to be tested under the working mode is predicted by combining the cycle life model and the storage life model.

[0011] Optionally, the expression of the initial cycle life prediction model is as follows:

[0012]

[0013] Among them, Q loss1 It represents the battery capacity loss of lithium battery during the charging and discharging process, A represents the pre-exponential factor, E represents the a represents activation energy, T represents temperature, C rate represents the cycle rate, Ah represents the accumulated ampere-hour, which is the product of the current and the charge and discharge time, and R represents the ideal gas constant. represents the additional temperature rise caused by rate stress, a represents the rate change factor under the influence of rate, z represents the cycle basic attenuation rate, m represents the temperature amplitude adjustment factor, n represents the rate amplitude adjustment factor, A, E a ,m,n,a,z are the parameters to be solved for the initial cycle life prediction model.

[0014] Optionally, the expression of the initial storage life prediction model is as follows:

[0015]

[0016] Among them, Q loss2 It represents the battery capacity loss of lithium battery during storage, A0 represents the calendar decay basic amplitude factor, Bs represents the SOC independent impact factor, SOC represents the battery storage state of charge, and the battery storage state of charge is the ratio between the current stored electric energy of the lithium battery and its maximum battery capacity, C srepresents the composite influencing factor of SOC and temperature, k represents the Boltzmann constant, Z represents the empirical constant, t represents the calendar storage time in days, A0, Bs, E a0 ,C s are the parameters to be solved for the initial storage life prediction model.

[0017] Optionally, the working mode includes at least one stage; the stage is a charging and discharging stage or a storage stage.

[0018] Optionally, obtain the calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge and working mode of the lithium battery to be tested, and combine the cycle life model and storage life model to predict the life of the lithium battery to be tested in the working mode, including:

[0019] For each stage in turn, the battery capacity loss of the previous stage is used as the initial battery capacity loss of the current stage; if the current stage is the charge and discharge stage, the temperature data and the charge and discharge rate are input into the cycle life model to obtain the current battery capacity loss of the lithium battery to be tested in the current stage, and the total battery capacity loss of the lithium battery to be tested in the current stage is calculated according to the initial battery capacity loss and the current battery capacity loss, and the predicted life of the lithium battery to be tested in the current stage is calculated through the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested; if the current stage is the storage stage, the battery storage state of charge is input into the storage life model to obtain the current battery capacity loss of the lithium battery to be tested in the current stage, and the total battery capacity loss of the lithium battery to be tested in the current stage is calculated according to the initial battery capacity loss and the current battery capacity loss, and the predicted life of the lithium battery to be tested in the current stage is calculated through the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested;

[0020] The predicted life of the last stage is determined as the predicted life of the lithium battery under test in the working mode.

[0021] Optionally, the predicted life of the lithium battery to be tested at the current stage is calculated based on the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested, including:

[0022] Calculate the capacity loss rate of the lithium battery to be tested based on the calibrated battery capacity and the total battery capacity loss;

[0023] By calculating the formula

[0024]

[0025] Get the predicted life span.

[0026] In a second aspect, the present invention provides a lithium battery life prediction device, comprising:

[0027] The cycle life prediction module builds an initial cycle life prediction model based on the degradation mechanism of the SEI film of lithium batteries during the charge and discharge process. The initial cycle life prediction model is used to describe the correlation between battery capacity loss and temperature and charge and discharge rate.

[0028] The storage life prediction module builds an initial storage life prediction model based on the degradation mechanism of the SEI film of lithium batteries during storage. The initial storage life prediction model is used to describe the correlation between battery capacity loss and battery storage charge state.

[0029] A model training module, for obtaining experimental battery data for model verification of either the initial cycle life model or the initial storage life model, and performing fitting training on the model using the experimental battery data to obtain a cycle life model and a storage life model trained to convergence;

[0030] The life prediction module is used to obtain the calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge and working mode of the lithium battery to be tested, and combine the cycle life model and storage life model to predict the life of the lithium battery to be tested in the working mode.

[0031] In a third aspect, the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the above method is implemented when the processor executes the computer program.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0033] The beneficial effects of the present invention are:

[0034] The lithium battery life prediction method provided by the present invention constructs an initial cycle life prediction model based on the degradation mechanism of the SEI film of the lithium battery during the charge and discharge process, and constructs an initial storage life prediction model based on the degradation mechanism of the SEI film of the lithium battery during the storage process. The different aging rates of the SEI film during the charge and discharge process and the storage process are taken into account, and the battery capacity loss of the lithium battery during the charge and discharge process and the storage process can be more accurately predicted and calculated, which is beneficial to improving the accuracy of the lithium battery life prediction; in the life prediction of the lithium battery to be tested, the working mode of the lithium battery to be tested is also combined, and the battery capacity loss during the charge and discharge process and the storage process under different working modes can be coupled, thereby improving the accuracy of the lithium battery life prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a lithium battery life prediction method in one embodiment of the present application;

[0036] Figure 2 A schematic diagram of the fitting effect of a cycle life prediction model in one embodiment of the present application;

[0037] Figure 3 This is a schematic diagram of the fitting effect of the storage life model in one embodiment of the present application;

[0038] Figure 4 This is a schematic diagram of a lithium battery operating mode in one embodiment of the present application;

[0039] Figure 5 This is a schematic diagram of the structure of a lithium battery life prediction device in one embodiment of the present application;

[0040] Figure 6 This is a schematic diagram of the structure of a terminal device in one embodiment of the present application. DETAILED DESCRIPTION

[0041] In view of the problem that the traditional lithium battery life prediction method does not take into account the influence of different SEI film aging rates at different stages under different working modes on the lithium battery life prediction, and the lithium battery life prediction has low accuracy, the invention provides a lithium battery life prediction method, device, terminal equipment and medium. The lithium battery life prediction method constructs an initial cycle life prediction model based on the degradation mechanism of the lithium battery SEI film during the charging and discharging process, and constructs an initial storage life prediction model based on the degradation mechanism of the lithium battery SEI film during the storage process. The different aging rates of the SEI film during the charging and discharging process and the storage process are taken into account, and the battery capacity loss of the lithium battery during the charging and discharging process and the storage process can be more accurately predicted and calculated, which is conducive to improving the accuracy of the lithium battery life prediction; in the life prediction of the lithium battery to be tested, the working mode of the lithium battery to be tested is also combined, and the battery capacity loss during the charging and discharging process and the storage process under different working modes can be coupled, thereby improving the accuracy of the lithium battery life prediction.

[0042] The lithium battery life prediction method provided by the present invention is described below.

[0043] like Figure 1 As shown, the lithium battery life prediction method includes steps 11 to 14.

[0044] Step 11, constructing an initial cycle life prediction model based on the degradation mechanism of the SEI film of the lithium battery during the charge and discharge process.

[0045] It should be noted that the above initial cycle life prediction model is used to describe the correlation between battery capacity loss and temperature and charge and discharge rate.

[0046] It should be understood that the SEI film (solid electrolyte interface film) is a very thin and stable film layer formed during the charge and discharge process of lithium-ion batteries, especially on the surface of the negative electrode. It is generated by the reaction of electrolytes and electrode materials, and is usually composed of organic and inorganic compounds. During the charge and discharge cycle of the battery, the SEI film on the surface of the negative electrode is continuously formed, destroyed and regenerated (repaired). Specifically, when the lithium battery is charged, the negative electrode potential is high, and the SEI film may rupture or disintegrate, causing the electrolyte and the electrode material to contact, thereby inducing side reactions, such as lithium metal deposition; when the lithium battery is discharged, the negative electrode potential decreases, and the SEI film will be partially repaired to generate a new protective layer, thereby maintaining the stability of the negative electrode material. This process is dynamic, and the quality and thickness of the SEI film will change with the increase in the number of charge and discharge cycles. After multiple charge and discharge cycles, the thickness of the SEI film will gradually increase. This is because during each charge and discharge process, some parts of the film may rupture or be affected by chemical reactions, and need to be continuously regenerated or repaired. Although this thickened film layer can protect the negative electrode, it will also increase the internal resistance and affect the capacity and cycle performance of the lithium battery.

[0047] Based on the degradation mechanism of the SEI film of lithium batteries during the above-mentioned charging and discharging process, the expression of the initial cycle life prediction model constructed by the present invention is as follows:

[0048]

[0049] Among them, Q loss1 It represents the battery capacity loss of lithium battery during the charging and discharging process, A represents the pre-exponential factor, E represents the a represents activation energy, T represents temperature, C rate represents the cycle rate, Ah represents the accumulated ampere-hour, which is the product of the current and the charge and discharge time, and R represents the ideal gas constant. represents the additional temperature rise caused by rate stress, a represents the rate change factor under the influence of rate, z represents the cycle basic attenuation rate, m represents the temperature amplitude adjustment factor, n represents the rate amplitude adjustment factor, A, E a ,m,n,a,z are the parameters to be solved for the initial cycle life prediction model.

[0050] Step 12: construct an initial storage life prediction model based on the degradation mechanism of the SEI film of the lithium battery during storage.

[0051] It should be noted that the above initial storage life prediction model is used to describe the correlation between battery capacity loss and battery storage state of charge.

[0052] It should be understood that when a lithium battery is in storage, the SEI film changes slowly because there is no charge or discharge, but it is still affected by the battery storage state of charge. If the lithium battery maintains a high SOC (such as a fully charged state) during storage, the negative electrode potential is high, and the SEI film may undergo a strong chemical reaction, resulting in damage or instability of the film, thereby accelerating the aging of the battery; in a low SOC state, the negative electrode potential is low, and the damage and change of the SEI film are relatively small, but lithium dendrite deposition may occur, affecting the safety and capacity of the lithium battery. Lithium batteries may experience self-discharge during storage, resulting in a voltage drop, which in turn changes the electrochemical environment of the negative electrode and affects the stability of the SEI film.

[0053] Based on the degradation mechanism of the SEI film of the lithium battery during the storage process, the initial storage life prediction model constructed by the present invention is expressed as follows:

[0054]

[0055] Among them, Q loss2 It represents the battery capacity loss of lithium battery during storage, A0 represents the calendar decay basic amplitude factor, Bs represents the SOC independent impact factor, SOC represents the battery storage state of charge, and the battery storage state of charge is the ratio between the current stored electric energy of the lithium battery and its maximum battery capacity, C s represents the composite influencing factor of SOC and temperature, k represents the Boltzmann constant, Z represents the empirical constant, t represents the calendar storage time in days, A0, Bs, E a0 ,C s are the parameters to be solved for the initial storage life prediction model.

[0056] Step 13, for either the initial cycle life model or the initial storage life model, obtain experimental battery data for model verification of one of the two, and use the experimental battery data to perform fitting training on the one to obtain a cycle life model and a storage life model that are trained to convergence.

[0057] It should be noted that the purpose of step 13 is to fit and solve the parameters to be solved in the initial cycle life prediction model and the initial storage life prediction model.

[0058] In one embodiment of the present invention, for the initial cycle life model, the experimental battery data includes: performing aging cycles at different temperatures and different rates and measuring the capacity every 50 cyc to obtain the change of capacity decay rate with the number of cycles;

[0059] For the initial storage life model, the experimental battery data includes: storage aging under different temperature and SOC conditions, and capacity measurement every 30 days to obtain the change of capacity decay rate with storage time.

[0060] The fitting solution process is described below.

[0061] Exemplarily, the parameters to be solved are initialized, and the initialized parameter values ​​to be solved are used as population individuals. Through a genetic algorithm, the parameter values ​​corresponding to the optimal population individuals are used as the final parameter values ​​to be solved to obtain a storage life prediction model and a cycle life model; the fitness of the population is negatively correlated with the difference between the model prediction results and the actual results.

[0062] In another embodiment of the present invention, the parameters to be solved of the initial cycle life prediction model and the initial storage life prediction model can be back-propagated according to the loss function until the loss value of the model is less than a preset loss threshold, thereby obtaining the storage life prediction model and the cycle life model. The loss function can be a cross entropy loss function.

[0063] In order to further verify the accuracy of the cycle life prediction model and storage life model provided by the present invention, in one embodiment of the present invention, fitting verification is performed based on the 45°C+1P degradation data of the laboratory self-tested samples, and the fitting results are as follows: Figure 2 , Figure 3 As shown. Figure 2 The schematic diagram of the fitting effect of the cycle life prediction model is shown in Figure 2. Figure 2 It can be seen that the cycle life prediction model provided by the present invention has good fitting ability, and the fitting degree reaches 0.9304. Figure 3 This is a schematic diagram of the storage life model fitting effect. The horizontal axis is storage time, and the vertical axis is the capacity decay percentage. The black curve is the decay curve based on the actual measurement point, and the colored curve is the model fitting curve. Figure 3 It can be seen that the fitting effect of the storage life model provided by the present invention is highly consistent with the actual situation, which further verifies the accuracy of the storage life model provided by the present invention.

[0064] Step 14, obtaining the calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge and working mode of the lithium battery to be tested, combining the cycle life model and the storage life model to predict the life of the lithium battery to be tested in the working mode.

[0065] It should be understood that the working mode of a lithium battery includes at least one stage. The stage is a charging and discharging stage or a storage stage. Figure 4 Considering the influence of different SEI film aging rates at different stages under different working modes on the life prediction of lithium batteries, the present invention can accurately predict the life according to the actual working mode of the lithium battery.

[0066] Specifically, it includes step 14.1 to step 14.2.

[0067] Step 14.1, for each stage in turn, the battery capacity loss of the previous stage is used as the initial battery capacity loss of the current stage; if the current stage is the charge and discharge stage, the temperature data and the charge and discharge rate are input into the cycle life model to obtain the current battery capacity loss of the lithium battery to be tested in the current stage, and the total battery capacity loss of the lithium battery to be tested in the current stage is calculated according to the initial battery capacity loss and the current battery capacity loss, and the predicted life of the lithium battery to be tested in the current stage is calculated through the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested; if the current stage is the storage stage, the battery storage charge state is input into the storage life model to obtain the current battery capacity loss of the lithium battery to be tested in the current stage, and the total battery capacity loss of the lithium battery to be tested in the current stage is calculated according to the initial battery capacity loss and the current battery capacity loss, and the predicted life of the lithium battery to be tested in the current stage is calculated through the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested.

[0068] The predicted life of the lithium battery to be tested at the current stage is calculated by the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested, including steps I to II.

[0069] Step I: Calculate the capacity loss rate of the lithium battery to be tested based on the calibrated battery capacity and the total battery capacity loss.

[0070]

[0071] Step II, by calculating the formula

[0072]

[0073] Get the predicted life span.

[0074] Step 14.2, determining the predicted life of the last stage as the predicted life of the lithium battery to be tested in the working mode.

[0075] It is worth mentioning that the present invention combines the working mode of the lithium battery to be tested, and can couple the battery capacity loss in the charging and discharging process and the storage process under different working modes, thereby improving the accuracy of lithium battery life prediction.

[0076] The lithium battery life prediction device provided by the present invention is described below.

[0077] like Figure 5 As shown, the lithium battery life prediction device 500 includes:

[0078] The cycle life prediction module 501 constructs an initial cycle life prediction model based on the degradation mechanism of the SEI film of the lithium battery during the charge and discharge process; the initial cycle life prediction model is used to describe the correlation between battery capacity loss and temperature and charge and discharge rate;

[0079] The storage life prediction module 502 constructs an initial storage life prediction model based on the degradation mechanism of the SEI film of the lithium battery during storage; the initial storage life prediction model is used to describe the correlation between the battery capacity loss and the battery storage charge state;

[0080] The model training module 503 is used to obtain experimental battery data for model verification of either the initial cycle life model or the initial storage life model, and perform fitting training on the model using the experimental battery data to obtain a cycle life model and a storage life model that are trained to convergence;

[0081] The life prediction module 504 is used to obtain the calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge and working mode of the lithium battery to be tested, and combine the cycle life model and storage life model to predict the life of the lithium battery to be tested in the working mode.

[0082] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are not related to the implementation method of the present application.

[0083] The examples are based on the same concept, and their specific functions and technical effects can be specifically referred to in the method embodiment section, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit, and the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0084] like Figure 6 As shown, an embodiment of the present invention provides a terminal device, such as Figure 6 As shown, the terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 6Only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, wherein the processor D100 implements the steps of any of the above-mentioned method embodiments when executing the computer program D102.

[0085] Specifically, when the processor D100 executes the computer program D102, an initial cycle life prediction model is constructed based on the degradation mechanism of the SEI film of the lithium battery during the charging and discharging process; an initial storage life prediction model is constructed based on the degradation mechanism of the SEI film of the lithium battery during the storage process; for either the initial cycle life model or the initial storage life model, experimental battery data for model verification of the one is obtained, and the one is fit-trained using the experimental battery data to obtain a cycle life model and a storage life model that are trained to convergence; the calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge, and working mode of the lithium battery to be tested are obtained, and the life of the lithium battery to be tested in the working mode is predicted in combination with the cycle life model and the storage life model. The lithium battery life prediction method provided by the present invention constructs an initial cycle life prediction model based on the degradation mechanism of the SEI film of the lithium battery during the charge and discharge process, and constructs an initial storage life prediction model based on the degradation mechanism of the SEI film of the lithium battery during the storage process. The different aging rates of the SEI film during the charge and discharge process and the storage process are taken into account, and the battery capacity loss of the lithium battery during the charge and discharge process and the storage process can be more accurately predicted and calculated, which is beneficial to improving the accuracy of the lithium battery life prediction; in the life prediction of the lithium battery to be tested, the working mode of the lithium battery to be tested is also combined, and the battery capacity loss during the charge and discharge process and the storage process under different working modes can be coupled, thereby improving the accuracy of the lithium battery life prediction.

[0086] The processor D100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0087] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk, a smart memory card (SMC, SmartMedia Card), a secure digital (SD, Secure Digital) card, a flash card (Flash Card), etc. equipped on the terminal device D10. Further, the memory D101 may also include both an internal storage unit of the terminal device D10 and an external storage device. The memory D101 is used to store an operating system, an application program, a boot loader (BootLoader), data and other programs, such as the program code of the computer program, etc. The memory D101 may also be used to temporarily store data that has been output or is to be output.

[0088] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0089] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0090] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of protection of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0091] One or more embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A lithium battery life prediction method, characterized in that: include: Based on the degradation mechanism of SEI film of lithium battery during charging and discharging, an initial cycle life prediction model is constructed; The initial cycle life prediction model is used to describe the correlation between battery capacity loss and temperature and charge and discharge rate; Based on the degradation mechanism of the SEI film of the lithium battery during storage, an initial storage life prediction model is constructed; the initial storage life prediction model is used to describe the correlation between battery capacity loss and battery storage state of charge; For either the initial cycle life model or the initial storage life model, respectively, obtaining experimental battery data for model verification of the one, and performing fitting training on the one using the experimental battery data to obtain a cycle life model and a storage life model trained to convergence; The calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge and working mode of the lithium battery to be tested are obtained, and the life of the lithium battery to be tested under the working mode is predicted by combining the cycle life model and the storage life model.

2. The lithium battery life prediction method according to claim 1, characterized in that: The expression of the initial cycle life prediction model is as follows: Among them, Q loss1 It represents the battery capacity loss of lithium battery during the charging and discharging process, A represents the pre-exponential factor, E represents the a represents activation energy, T represents temperature, C rate represents the cycle rate, Ah represents the accumulated ampere-hour, which is the product of the current and the charge and discharge time, R represents the ideal gas constant, represents the additional temperature rise caused by rate stress, a represents the rate change factor under the influence of rate, z represents the cycle basic attenuation rate, m represents the temperature amplitude adjustment factor, n represents the rate amplitude adjustment factor, A, E a ,m,n,a,z are the parameters to be solved for the initial cycle life prediction model.

3. The lithium battery life prediction method according to claim 2, characterized in that: The expression of the initial storage life prediction model is as follows: Among them, Q loss2 represents the battery capacity loss of the lithium battery during storage, A0 represents the calendar decay basic amplitude factor, Bs represents the SOC independent impact factor, SOC represents the battery storage state of charge, and the battery storage state of charge is the ratio between the current stored electric energy of the lithium battery and its maximum battery capacity, C s represents the composite influencing factor of SOC and temperature, k represents the Boltzmann constant, Z represents the empirical constant, t represents the calendar storage time in days, A0, Bs, E a0 ,C s are the parameters to be solved for the initial storage life prediction model.

4. The lithium battery life prediction method according to claim 3, characterized in that: The working mode includes at least one stage; the stage is a charging and discharging stage or a storage stage.

5. The lithium battery life prediction method according to claim 4, characterized in that: The obtaining of the calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge and working mode of the lithium battery to be tested, and combining the cycle life model and the storage life model to predict the life of the lithium battery to be tested under the working mode, includes: For each stage in turn, the battery capacity loss of the previous stage is used as the initial battery capacity loss of the current stage; if the current stage is the charge and discharge stage, the temperature data and the charge and discharge rate are input into the cycle life model to obtain the current battery capacity loss of the lithium battery to be tested in the current stage, and the total battery capacity loss of the lithium battery to be tested in the current stage is calculated according to the initial battery capacity loss and the current battery capacity loss, and the predicted life of the lithium battery to be tested in the current stage is calculated through the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested; if the current stage is the storage stage, the battery storage state of charge is input into the storage life model to obtain the current battery capacity loss of the lithium battery to be tested in the current stage, and the total battery capacity loss of the lithium battery to be tested in the current stage is calculated according to the initial battery capacity loss and the current battery capacity loss, and the predicted life of the lithium battery to be tested in the current stage is calculated through the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested; The predicted life of the last stage is determined as the predicted life of the lithium battery to be tested in the working mode.

6. The lithium battery life prediction method according to claim 5, characterized in that: The calculating the predicted life of the lithium battery to be tested at the current stage by using the total battery capacity loss and the calibrated battery capacity of the lithium battery to be tested includes: Calculating the capacity loss rate of the lithium battery to be tested according to the calibrated battery capacity and the total battery capacity loss; By calculating the formula The predicted lifespan is obtained.

7. A lithium battery life prediction device, characterized in that: include: The cycle life prediction module builds an initial cycle life prediction model based on the degradation mechanism of the SEI film of lithium batteries during the charging and discharging process; The initial cycle life prediction model is used to describe the correlation between battery capacity loss and temperature and charge and discharge rate; A storage life prediction module, which constructs an initial storage life prediction model based on the degradation mechanism of the SEI film of the lithium battery during storage; the initial storage life prediction model is used to describe the correlation between battery capacity loss and battery storage charge state; A model training module, for obtaining experimental battery data for model verification of either the initial cycle life model or the initial storage life model, and performing fitting training on the either of the initial cycle life model and the initial storage life model using the experimental battery data to obtain a cycle life model and a storage life model trained to convergence; The life prediction module is used to obtain the calibrated battery capacity, temperature data, charge and discharge rate, battery storage state of charge and working mode of the lithium battery to be tested, and combine the cycle life model and the storage life model to predict the life of the lithium battery to be tested under the working mode.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images