A method and related equipment for calculating the battery capacity balance difference in a battery system.

Abstract

This application discloses a method, apparatus, electronic device, and computer-readable storage medium for calculating the battery capacity equalization difference in a battery system. The battery system includes several batteries connected in series. The method includes: acquiring the charging state data of each battery during the charging process of the battery system; and calculating the open-circuit voltage V of each battery at the end of charging. end V end <V th2 All batteries were identified as Class I batteries; [V th1 V th2 [V] represents the range of significant capacity decay for the same type of battery; for the first type of battery, calculations are performed within [V]... th1 V end The first charging capacity value during the period; the difference between the standard charging capacity value and the first charging capacity value is used as the capacity balancing characteristic value of the first type of battery; the first balancing difference identification model is called to determine the true capacity difference between the first type of battery and the standard battery. This application can intuitively reflect the actual capacity balancing difference of the battery, improve the accuracy of capacity balancing calculation and simplify the calculation.

Description

Technical Field

[0001] This application relates to the field of battery management technology, and in particular to a method, apparatus, electronic device, and computer-readable storage medium for calculating the battery capacity balance difference of a battery system. Background Technology

[0002] Lithium-ion (Li-ion) batteries play a key role in transportation electrification and renewable energy systems as one of the main energy storage devices for electric vehicles and power plants.

[0003] Generally, a battery system consists of dozens or even thousands of individual cells stacked in a complex series-parallel structure. Excessive capacity decay or excessively high / low state of charge (SOC) in one or a few cells can significantly reduce the total usable capacity of the battery system. Therefore, capacity balancing in battery systems is crucial. Existing methods for calculating battery capacity balancing are mostly based on empirical or physical models, which either have low data estimation accuracy or require extensive computation, rendering them impractical.

[0004] Therefore, providing a solution to the above-mentioned technical problems has become a matter of great concern to those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, electronic device and computer-readable storage medium for calculating the battery capacity balance difference of a battery system, so as to intuitively reflect the balance difference of the actual capacity of each battery through accurate data, improve the accuracy of the results and simplify the calculation.

[0006] To address the aforementioned technical problems, this application discloses a method for calculating the battery capacity balance difference in a battery system, wherein the battery system comprises a plurality of batteries connected in series, and the method includes:

[0007] Acquire the charging status data of each battery during the charging process of the battery system;

[0008] Based on the charging state data, calculate the open-circuit voltage V of each battery at the end of charging. end ;

[0009] V end <V th2 All batteries were identified as Class I batteries; [V th1 V th2 [This represents the range of significant capacity decay for batteries of the same model;]

[0010] For each type I battery, calculate in [V th1 V end The first charging capacity value during the period;

[0011] The difference between the standard charging capacity value and the first charging capacity value is used as the capacity balancing characteristic value of the first type of battery; the standard charging capacity value is the standard battery at [V th1 V th2 The charging capacity value during the period;

[0012] The first equalization difference identification model is invoked to determine the true capacity difference between the first type of battery and the standard battery based on the capacity equalization feature value; the first equalization difference identification model is pre-trained and generated based on sample test data.

[0013] Optionally, the standard battery is V in each battery pack of the battery system. end The largest battery, or one of them.

[0014] Optionally, the invocation of the first equilibrium difference identification model includes:

[0015] Based on the location of the first type of battery in the battery pack, the corresponding first balance difference identification model is invoked; the parameters in the first balance difference identification model are different due to the differences in the environment of different battery packs.

[0016] Optionally, the first equilibrium difference identification model is determined in advance through the following process:

[0017] Multiple charge-discharge cycles were performed on sample batteries of the same model with known actual total capacity, and charging status data was monitored in real time.

[0018] The corresponding open-circuit voltage value is obtained in real time through normalization calculation;

[0019] Calculate the standard sample battery when the open-circuit voltage is [V] th1 V th2 The standard charging capacity value during the period, and the open-circuit voltage of the first type of sample battery when it is within [V] th1 V end The first charging capacity value during the period, and the difference between the two;

[0020] The first balanced difference recognition model is trained and generated by using the difference corresponding to each of the first type of sample batteries as the sample input data and the actual capacity difference between each of the first type of sample batteries and the standard sample battery as the sample output data.

[0021] Optionally, after training to generate the first equilibrium difference recognition model, the method further includes:

[0022] Obtain large amounts of historical charging and discharging data for battery systems composed of the same type of batteries;

[0023] The first equilibrium difference identification model was optimized and adjusted based on big data analysis technology.

[0024] Optionally, it also includes:

[0025] V end ≥V th2 All batteries were identified as Class II batteries;

[0026] For each type II battery, calculate in [V th1 V th2 The second charging capacity value during the period;

[0027] The difference between the standard charging capacity value and the second charging capacity value is used as the capacity balance characteristic value of the second type of battery;

[0028] The second equalization difference identification model is invoked to determine the true capacity difference between the second type of battery and the standard battery based on the capacity equalization feature value; the second equalization difference identification model is pre-trained and generated based on sample test data.

[0029] Optionally, the second equilibrium difference identification model is determined in advance through the following process:

[0030] Multiple charge-discharge cycles were performed on sample batteries of the same model with known actual total capacity, and charging status data was monitored in real time.

[0031] The corresponding open-circuit voltage value is obtained in real time through normalization calculation;

[0032] Calculate the standard sample battery when the open-circuit voltage is [V] th1 V th2 The standard charging capacity value during the period, and the open-circuit voltage of the second type of sample battery when it is within [V] th1 V th2 The second charging capacity value during the period, and the difference between the two;

[0033] The second balanced difference recognition model is trained and generated by using the difference corresponding to each of the second type of sample batteries as the sample input data and the actual capacity difference between each of the second type of sample batteries and the standard sample battery as the sample output data.

[0034] In another aspect, this application discloses a battery capacity equalization difference calculation device for a battery system, the battery system comprising a plurality of batteries connected in series, the device comprising:

[0035] The data acquisition module is used to acquire the charging status data of each battery during the charging process of the battery system;

[0036] The equalization classification module is used to calculate the open-circuit voltage V of each battery at the end of charging based on the charging state data. end V end <V th2 All batteries were identified as Class I batteries; [V th1 V th2 [This represents the range of significant capacity decay for batteries of the same model;]

[0037] The feature calculation module is used to calculate the feature value in [V] for each type of first-class battery. th1 V end The first charging capacity value during the period is used as the difference between the standard charging capacity value and the first charging capacity value, which is taken as the capacity balancing characteristic value of the first type of battery; the standard charging capacity value is the standard battery at [V th1 V th2 The charging capacity value during the period;

[0038] The equalization calculation module is used to call the first equalization difference identification model to determine the actual capacity difference between the first type of battery and the standard battery based on the capacity equalization feature value; the first equalization difference identification model is pre-trained and generated based on sample test data.

[0039] Optionally, the standard battery is V in each battery pack of the battery system. end The largest battery, or one of them.

[0040] Optionally, the equalization calculation module is specifically used for:

[0041] Based on the location of the first type of battery in the battery pack, the corresponding first balance difference identification model is invoked; the parameters in the first balance difference identification model are different due to the differences in the environment of different battery packs.

[0042] Optionally, it also includes:

[0043] The model training module is used to perform multiple charge-discharge cycles on sample batteries of the same model with known actual total capacity values, and monitor the charging status data in real time; it obtains the corresponding open-circuit voltage value in real time through normalization calculation; and it calculates the open-circuit voltage of the standard sample battery when the open-circuit voltage is within [V]. th1 V th2 The standard charging capacity value during the period, and the open-circuit voltage of the first type of sample battery when it is within [V] th1 V end The first charging capacity value during the period and the difference between the two; using the difference corresponding to each of the first type of sample batteries as sample input data and the actual capacity difference between each of the first type of sample batteries and the standard sample battery as sample output data, the first balanced difference recognition model is trained and generated.

[0044] Optionally, after training and generating the first equilibrium difference recognition model, the model training module is further configured to:

[0045] Obtain historical charging and discharging data of battery systems composed of the same type of batteries; optimize and adjust the first equalization difference identification model based on big data analysis technology.

[0046] Optionally, the balanced classification module is further configured to: classify V end ≥V th2 All batteries were identified as Class II batteries;

[0047] The feature calculation module is also used to: for each type of second battery, calculate [V] th1 V th2 The second charging capacity value during the period; the difference between the standard charging capacity value and the second charging capacity value is used as the capacity balance characteristic value of the second type of battery;

[0048] The equalization calculation module is also used to: call the second equalization difference identification model to determine the actual capacity difference between the second type of battery and the standard battery based on the capacity equalization feature value; the second equalization difference identification model is pre-trained and generated based on sample test data.

[0049] Optionally, the model training module is further configured to:

[0050] Multiple charge-discharge cycles were performed on sample batteries of the same model with known actual total capacity, and charging status data was monitored in real time; the corresponding open-circuit voltage value was obtained in real time through normalization calculation; the open-circuit voltage of the standard sample battery was calculated when it was within [V]. th1 V th2 The standard charging capacity value during the period, and the open-circuit voltage of the second type of sample battery when it is within [V] th1 V th2 The second charging capacity value during the period and the difference between the two; using the difference corresponding to each of the second type of sample batteries as sample input data and the actual capacity difference between each of the second type of sample batteries and the standard sample battery as sample output data, the second balanced difference recognition model is trained and generated.

[0051] In another aspect, this application also discloses an electronic device, comprising:

[0052] Memory, used to store computer programs;

[0053] A processor for executing the computer program to implement the steps of the battery capacity equalization difference calculation method for any of the battery systems described above.

[0054] In another aspect, this application also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of the battery capacity equalization difference calculation method for any of the battery systems described above.

[0055] The beneficial effects of the battery capacity equalization difference calculation method, apparatus, electronic device, and computer-readable storage medium provided in this application are as follows: For the first type of battery where battery capacity decay is not negligible, this application uses the difference between the charging capacity value and the standard charging capacity value within a specified interval before the battery system triggers the cutoff as the estimation basis, and calculates the corresponding battery capacity equalization difference based on the identification model. This intuitively reflects the actual capacity equalization difference of the battery, facilitates battery replacement or repair by maintenance personnel, ensures the safe operation of the battery system, effectively improves the accuracy of capacity equalization calculation, and simplifies the calculation workload. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the prior art and the embodiments of this application, the accompanying drawings used in the description of the prior art and the embodiments of this application will be briefly introduced below. Of course, the accompanying drawings described below with respect to the embodiments of this application are only a part of the embodiments in this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort, and such other drawings also fall within the protection scope of this application.

[0057] Figure 1 This is a flowchart of a method for calculating the battery capacity balance difference of a battery system disclosed in an embodiment of this application;

[0058] Figure 2 This is a schematic diagram of the capacity balance difference of a first type of battery provided in an embodiment of this application;

[0059] Figure 3 This is a flowchart of a method for training and generating a first equilibrium difference recognition model disclosed in an embodiment of this application;

[0060] Figure 4 This is a flowchart of a method for training and generating a second equilibrium difference recognition model disclosed in an embodiment of this application;

[0061] Figure 5 This is a structural block diagram of a battery capacity balance difference calculation device for a battery system disclosed in an embodiment of this application;

[0062] Figure 6 This is a structural block diagram of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0063] The core of this application is to provide a method, apparatus, electronic device, and computer-readable storage medium for calculating the battery capacity balance difference of a battery system, so as to intuitively reflect the balance difference of the actual capacity of each battery through accurate data, improve the accuracy of the results, and simplify the calculation.

[0064] To provide a clearer and more complete description of the technical solutions in the embodiments of this application, the technical solutions in the embodiments of this application will be described below with reference to the accompanying drawings. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0065] Currently, lithium-ion (Li-ion) batteries play a crucial role in transportation electrification and renewable energy systems as one of the main energy storage devices for electric vehicles and power stations. Generally, a battery system consists of dozens or even thousands of individual cells stacked in a complex series-parallel structure. Excessive capacity decay or excessively high / low state of charge (SOC) in one or a few cells can significantly reduce the total usable capacity of the battery system. Therefore, the capacity balancing problem of battery systems is extremely important. Existing methods for calculating battery capacity balancing are mostly based on empirical or physical models, which either have low data estimation accuracy or require large amounts of computation, making them impractical. In view of this, this application provides a battery capacity balancing difference calculation scheme for battery systems, which can effectively solve the above problems.

[0066] See Figure 1 As shown in the embodiment of this application, a method for calculating the battery capacity balance difference of a battery system is disclosed. The battery system includes several batteries connected in series. The method mainly includes:

[0067] S101: Obtain the charging status data of each battery during the charging process of the battery system.

[0068] S102: Calculate the open-circuit voltage V of each battery at the end of charging based on the state-of-charge data. end .

[0069] S103: V end <V th2 All batteries were identified as Class I batteries; [V th1 V th2 [This represents the range of significant capacity decay for batteries of the same model.]

[0070] Specifically, a battery system is generally composed of dozens or even thousands of individual battery cells stacked together in a complex series-parallel structure. In other words, a battery system must include several batteries connected in series. The voltage of a single battery cell is generally less than 4V, and a battery system needs to connect dozens or hundreds of batteries in series to achieve a voltage platform of 500 to 1500V.

[0071] It's easy to understand that because the capacity decay of different battery cells is inconsistent, their battery voltages are also inconsistent. For a battery system with a series structure, during a complete charging process, the battery cell with the higher voltage will be fully charged first, thus triggering the battery management system to execute a charging cut-off action. At this time, the battery cell with the lower voltage will not be fully charged due to the charging cut-off action.

[0072] In a series-connected battery system, batteries with different capacity decay rates will reach different voltages after the battery system performs a charging cut-off operation. To facilitate the calculation of capacity balancing differences among the batteries, this application first classifies the batteries based on their open-circuit voltage values ​​at the charging cut-off point.

[0073] Specifically, such as the open-circuit voltage V of the battery after charging is complete. end Smaller, i.e., V end <V th2 If so, the battery can be classified as a Class I battery. Every Class I battery experiences a certain degree of capacity decay, which is not negligible. It is precisely because of this capacity decay that its open-circuit voltage after charging is cut off generally cannot reach V. th2 .

[0074] Among them, [V th1 V th2 [This represents the range of significant capacity decay for batteries of the same model.] It should be noted that this range of significant capacity decay is a range of values ​​for the battery's open-circuit voltage. When the battery's open-circuit voltage falls within this range, it is evident that the battery's capacity decay changes significantly with the number of charge-discharge cycles. That is, the dQ / dV-V curves for different charge-discharge cycles will show a clear non-overlapping phenomenon within this preset voltage range. Here, Q represents the battery capacity, and V represents the battery voltage. The range of significant capacity decay corresponds to the charging voltage plateau period in the battery's charging voltage curve.

[0075] S104: For each type I battery, calculate in [V th1 V end The first charging capacity value during the period.

[0076] S105: The difference between the standard charging capacity value and the first charging capacity value is used as the capacity balancing characteristic value of the first type of battery; the standard charging capacity value is the standard battery at [V th1 V th2 The charging capacity value during the period.

[0077] S106: Call the first equalization difference identification model to determine the true capacity difference between the first type of battery and the standard battery based on the capacity equalization feature value; the first equalization difference identification model is pre-trained and generated based on sample test data.

[0078] Specifically, for the first type of battery, this application can pre-train and generate a corresponding first equalization difference recognition model in order to accurately estimate the actual capacity difference between the first type of battery and the standard battery, and use it as the capacity equalization difference of the first type of battery.

[0079] In this application, the standard battery is a battery pre-selected as a reference standard, and the capacity balance difference of other batteries is calculated based on the standard battery. It is easy to understand that the battery with the best performance, i.e., the smallest capacity decay, can be used as the standard battery.

[0080] Because battery systems typically contain a large number of batteries, multiple batteries are usually integrated into a battery pack (battery module), and these battery packs together constitute the entire battery system. For a large number of widely distributed battery packs, the environmental conditions (especially ambient temperature and humidity) significantly affect battery capacity degradation. Therefore, a standard battery can be provided for each battery pack. Thus, in a specific embodiment, the V... end The largest battery serves as the standard battery for the other batteries in the battery pack; when V end When multiple largest batteries exist, one of them can be selected as the standard battery for the other batteries in the battery pack.

[0081] Standard batteries in [V th1 V th2 The charging capacity during this period can be denoted as Q0. [V] th1 V th2 That is, the range of significant capacity decay, within [V] th1 V th2 The charging capacity value during the period corresponds to the actual capacity of the battery to a certain extent. Therefore, this application uses the Q0 of the standard battery as a comparison basis for calculating the capacity balance difference of other batteries.

[0082] However, because the open-circuit voltage of the first type of battery does not reach V after the battery system triggers the charging cutoff... th2 Therefore, it is impossible to obtain and utilize the first type of battery in [V th1 Vth2 The charging capacity value during the [V] period is included in the calculation. Therefore, this application specifically targets the first type of battery, specifically its charging capacity value during [V] period. th1 V end Let's denote the first charging capacity value during this period as Q1, and use it in the calculation.

[0083] See Figure 2 , Figure 2 This is a schematic diagram illustrating the capacity balancing difference of a first-type battery according to an embodiment of this application. For each first-type battery, this application subtracts the Q1 of the first-type battery from the Q0 of the standard battery to obtain Q. s =Q0-Q1 is used as the capacity balance feature value of the first type of battery. Then, the true capacity difference ΔQ between the first type of battery and the standard battery is calculated by using the pre-trained first balance difference recognition model.

[0084] Among them, the first equilibrium difference identification model is based on the relevant test data of a large number of sample batteries with known real capacity, and according to the Q of each sample battery. s The value is generated in advance through the correspondence between ΔQ and the battery. Therefore, this application can quickly, efficiently and accurately obtain the true capacity difference between each battery and the standard battery, that is, the battery capacity balance difference, through simple charging capacity calculation and model recognition.

[0085] It should also be noted that the capacity balancing judgment method of the battery system provided in this application embodiment can be applied to the battery management system of power battery, vehicle-mounted testing terminal equipment or cloud platform, and those skilled in the art can set it according to the actual application situation.

[0086] As can be seen, the battery capacity equalization difference calculation method provided in this application, for the first type of battery where battery capacity decay is not negligible, uses the difference between the charging capacity value and the standard charging capacity value within a specified interval before the battery system triggers the cutoff as the estimation basis. Based on the identification model, the corresponding battery capacity equalization difference is calculated, which intuitively reflects the actual capacity equalization difference of the battery. This facilitates battery replacement or repair by maintenance personnel, ensures the safe operation of the battery system, effectively improves the accuracy of capacity equalization calculation, and simplifies the calculation workload.

[0087] As a specific embodiment, the battery capacity balance difference calculation method for a battery system provided in this application, based on the above content, calls the first balance difference identification model, including:

[0088] Based on the location of the first type of battery in the battery pack, the corresponding first equalization difference identification model is invoked; the parameters in the first equalization difference identification model are different due to the differences in the environment of different battery packs.

[0089] Specifically, in this embodiment, considering that the environmental conditions of the battery pack at different locations are different and the average capacity decay level of the battery is different, different parameters can be selected by referring to the environmental conditions when establishing the first equalization difference identification model, so as to further improve the calculation accuracy of the battery capacity equalization difference.

[0090] See Figure 3 As a specific embodiment, the battery capacity balance difference calculation method of the battery system provided in this application embodiment is based on the above content, and the first balance difference identification model is determined in advance through the following process:

[0091] S201: Perform multiple charge-discharge cycles on a sample battery of the same model with a known actual total capacity, and monitor the charging status data in real time.

[0092] S202: Obtain the corresponding open-circuit voltage value in real time through normalization calculation.

[0093] S203: Calculate the open-circuit voltage of a standard sample battery when it is [V]. th1 V th2 The standard charging capacity value during the period, and the open-circuit voltage of the first type of sample battery when it is within [V] th1 V end The first charging capacity value during the period, and the difference between the two.

[0094] S204: Using the difference between each first-class sample battery as the sample input data and the actual capacity difference between each first-class sample battery and the standard sample battery as the sample output data, train and generate the first balanced difference recognition model.

[0095] Specifically, when conducting multiple charge-discharge cycles on the same type of battery with a known total capacity, different temperature and charging current conditions can be set separately to conduct charge-discharge tests under different environmental conditions and obtain matching model parameters.

[0096] Furthermore, to eliminate interference from multiple factors and avoid inaccurate calculation results, each charge-discharge test of the sample battery can be conducted at a constant temperature and constant current to calculate the charging capacity value within the corresponding range under that constant temperature and constant current conditions. Then, by changing only one variable among temperature and current, test data under various conditions can be obtained to train the first equalization difference recognition model, ensuring more accurate results under different conditions.

[0097] As a specific embodiment, the battery capacity equalization difference calculation method for a battery system provided in this application, based on the above content, further includes the following after training and generating the first equalization difference recognition model:

[0098] Obtain large amounts of historical charging and discharging data for battery systems composed of the same type of batteries;

[0099] The first equilibrium difference identification model was optimized and adjusted based on big data analysis technology.

[0100] Specifically, in order to reduce the impact of actual data accuracy and model accuracy on imbalance judgment, after the initial training of the model, a large amount of historical data of the battery system (data such as voltage and current at the beginning and end of the charging and discharging process) can be selected for big data analysis, and algorithms such as k-means clustering, Fuzzy C-means (FCM) clustering, decision tree, support vector machine, random forest, logistic regression, etc. can be used to optimize the model.

[0101] As a specific embodiment, the battery capacity balance difference calculation method for the battery system provided in this application, based on the above content, further includes:

[0102] V end ≥V th2 All batteries were identified as Class II batteries;

[0103] For each type II battery, calculate in [V th1 V th2 The second charging capacity value during the period;

[0104] The difference between the standard charging capacity value and the second charging capacity value is used as the capacity balance characteristic value of the second type of battery.

[0105] The second equalization difference identification model is invoked to determine the true capacity difference between the second type of battery and the standard battery based on the capacity equalization feature value; the second equalization difference identification model is pre-trained and generated based on sample test data.

[0106] Specifically, if the open-circuit voltage of the battery meets the following condition when the battery system triggers charging cutoff: V end ≥V th2 If so, this battery can be classified as a second-class battery. For second-class batteries, their performance in [V] can be directly utilized. th1 V th2 The second charging capacity value during this period, let's call it Q2, will be used in the calculation.

[0107] For each type II battery, this application subtracts the Q2 of the type II battery from the Q0 of the standard battery to obtain Q. s=Q0-Q2 is used as the capacity balancing characteristic value of this second type of battery. Then, a pre-trained second balancing difference recognition model is used to calculate the true capacity difference ΔQ between this second type of battery and the standard battery. The second balancing difference recognition model is based on relevant test data from a large number of second-type sample batteries with known true capacities, and on the Q of each second-type sample battery. s It is generated in advance through the correspondence between ΔQ and ΔQ.

[0108] See Figure 4 As a specific embodiment, the battery capacity balance difference calculation method of the battery system provided in this application embodiment is based on the above content, and the second balance difference identification model is determined in advance through the following process:

[0109] S301: Perform multiple charge-discharge cycles on a sample battery of the same model with a known actual total capacity, and monitor the charging status data in real time.

[0110] S302: Obtain the corresponding open-circuit voltage value in real time through normalization calculation.

[0111] S303: Calculate the open-circuit voltage of a standard sample battery when it is [V]. th1 V th2 The standard charging capacity value during the period, and the open-circuit voltage of the second type of sample battery when it is within [V] th1 V th2 The second charging capacity value during the period, and the difference between the two.

[0112] S304: Using the difference between each second-class sample battery as the sample input data and the actual capacity difference between each second-class sample battery and the standard sample battery as the sample output data, train and generate a second equilibrium difference recognition model.

[0113] Furthermore, after obtaining the battery capacity balance difference between the first and second types of batteries, the batteries can be further classified according to the magnitude of the battery capacity balance difference. For example, they can be specifically divided into three categories: high SOC, medium SOC, and low SOC. This provides users with intuitive classification results and serves as guidance for subsequent operations on different types of batteries.

[0114] See Figure 5 As shown in the figure, this application discloses a battery capacity balance difference calculation device for a battery system. The battery system includes a plurality of batteries connected in series. The device includes:

[0115] The data acquisition module 401 is used to acquire the charging status data of each battery during the charging process of the battery system;

[0116] The equalization classification module 402 is used to calculate the open-circuit voltage V of each battery at the end of charging based on the charging state data. end V end <V th2 All batteries were identified as Class I batteries; [V th1 V th2 [This represents the range of significant capacity decay for batteries of the same model;]

[0117] Feature calculation module 403 is used to calculate, for each type of first battery, in [V th1 V end The first charging capacity value during the period is used as the difference between the standard charging capacity value and the first charging capacity value, which is taken as the capacity balancing characteristic value of the first type of battery; the standard charging capacity value is the standard battery at [V th1 V th2 The charging capacity value during the period;

[0118] The equalization calculation module 404 is used to call the first equalization difference identification model to determine the actual capacity difference between the first type of battery and the standard battery based on the capacity equalization feature value; the first equalization difference identification model is pre-trained and generated based on sample test data.

[0119] As can be seen, the battery capacity equalization difference calculation device for the battery system disclosed in this application, for the first type of battery whose battery capacity decay is not negligible, uses the difference between the charging capacity value and the standard charging capacity value in a specified interval before the battery system is triggered to calculate the corresponding battery capacity equalization difference based on the identification model. This intuitively reflects the actual capacity equalization difference of the battery, which facilitates maintenance personnel to replace or repair the battery, ensures the safe operation of the battery system, effectively improves the accuracy of capacity equalization calculation, and simplifies the calculation workload.

[0120] For details regarding the battery capacity balance difference calculation device for the aforementioned battery system, please refer to the aforementioned detailed introduction to the battery capacity balance difference calculation method for the battery system, which will not be repeated here.

[0121] As a specific embodiment, the battery capacity balance difference calculation device for the battery system disclosed in this application, based on the above content, uses a standard battery as V in each battery pack of the battery system. end The largest battery, or one of them.

[0122] As a specific embodiment, the battery capacity equalization difference calculation device for the battery system disclosed in this application, based on the above content, has the equalization calculation module 404 specifically used for:

[0123] Based on the location of the first type of battery in the battery pack, the corresponding first equalization difference identification model is invoked; the parameters in the first equalization difference identification model are different due to the differences in the environment of different battery packs.

[0124] As a specific embodiment, the battery capacity balance difference calculation device for the battery system disclosed in this application, based on the above content, further includes:

[0125] The model training module is used to perform multiple charge-discharge cycles on sample batteries of the same model with known actual total capacity values, and monitor the charging status data in real time; it obtains the corresponding open-circuit voltage value in real time through normalization calculation; and it calculates the open-circuit voltage of the standard sample battery when the open-circuit voltage is within [V]. th1 V th2 The standard charging capacity value during the period, and the open-circuit voltage of the first type of sample battery when it is within [V] th1 V end The first charging capacity value during the period and the difference between the two; using the difference corresponding to each first type of sample battery as the sample input data and the actual capacity difference between each first type of sample battery and the standard sample battery as the sample output data, a first balanced difference recognition model is trained and generated.

[0126] As a specific embodiment, the battery capacity equalization difference calculation device for the battery system disclosed in this application, based on the above content, further includes the following: After the model training module trains and generates the first equalization difference recognition model, it is also used for:

[0127] Obtain historical charging and discharging data of battery systems composed of the same type of batteries; optimize and adjust the first equalization difference identification model based on big data analysis technology.

[0128] As a specific embodiment, the battery capacity balance difference calculation device for the battery system disclosed in this application, based on the above content, further includes a balance classification module 402 used to: calculate V end ≥V th2 All batteries were identified as Class II batteries;

[0129] The feature calculation module 403 is also used to: calculate, for each second-class battery, in [V th1 V th2 The second charging capacity value during the period; the difference between the standard charging capacity value and the second charging capacity value is used as the capacity balance characteristic value of the second type of battery;

[0130] The equalization calculation module 404 is also used to: call the second equalization difference identification model to determine the actual capacity difference between the second type of battery and the standard battery based on the capacity equalization feature value; the second equalization difference identification model is pre-trained and generated based on sample test data.

[0131] As a specific embodiment, the battery capacity equalization difference calculation device for the battery system disclosed in this application, based on the above content, further includes a model training module used for:

[0132] Multiple charge-discharge cycles were performed on sample batteries of the same model with known actual total capacity, and charging status data was monitored in real time; the corresponding open-circuit voltage value was obtained in real time through normalization calculation; the open-circuit voltage of the standard sample battery was calculated when it was within [V]. th1 V th2 The standard charging capacity value during the period, and the open-circuit voltage of the second type of sample battery when it is within [V] th1 V th2 The second charging capacity value during the period and the difference between the two; using the difference corresponding to each second type of sample battery as the sample input data and the actual capacity difference between each second type of sample battery and the standard sample battery as the sample output data, a second equilibrium difference recognition model is trained and generated.

[0133] See Figure 6 As shown in the figure, an embodiment of this application discloses an electronic device, including:

[0134] Memory 501 is used to store computer programs;

[0135] Processor 502 is configured to execute the computer program to implement the steps of the battery capacity balance difference calculation method for any of the battery systems described above.

[0136] Furthermore, embodiments of this application also disclose a computer-readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of the battery capacity equalization difference calculation method for any of the battery systems described above.

[0137] For details regarding the aforementioned electronic devices and computer-readable storage media, please refer to the detailed introduction above regarding the calculation method for battery capacity balance difference in battery systems; further details will not be repeated here.

[0138] The various embodiments in this application are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0139] It should also be noted that in this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0140] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this application. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A battery capacity equalization difference calculation method of a battery system, characterized by, The battery system comprises a plurality of series-connected batteries, and the method comprises: obtaining the charging state data of each battery in the charging process of the battery system; calculating an open circuit voltage value V of each battery at the end of charging based on the state of charge data end ; V end <V th2 The battery is identified as a first type of battery;[V th1 , V th2 ] is a significant change interval of capacity attenuation of the same type of battery; the significant change interval of capacity attenuation is a value interval of open circuit voltage of the battery; For each first type battery, a first charge capacity value is calculated over the interval [V th1 , V end ] differences between the standard charging capacity value and the first charging capacity value as the capacity equalization characteristic value of the first type of battery; the standard charging capacity value is the charging capacity value of a standard battery during [V th1 , V th2 ] calling a first equalization difference identification model to determine the real capacity difference between the first type of battery and the standard battery according to the capacity equalization characteristic value; the first equalization difference identification model is generated by pre-training based on sample test data; wherein the first equalization difference identification model is determined by the following process: multiple cyclic charging and discharging tests are performed on sample batteries of the same type with known actual total capacity values, and the charging state data is monitored in real time; the corresponding open circuit voltage value is obtained in real time through normalization calculation; the standard charge capacity value of the standard sample battery when the open circuit voltage is within the range of [V th1 , V th2 ], the first charge capacity value of the first sample battery when the open circuit voltage is within the range of [V th1 , V end ], and the difference between the two; the first equalization difference identification model is trained and generated by taking the difference value corresponding to each first type of sample battery as sample input data and taking the real capacity difference between each first type of sample battery and the standard sample battery as sample output data.

2. The battery capacity equalization difference calculation method according to claim 1, characterized by, The standard battery is the V end The largest battery or one of them.

3. The battery capacity equalization difference calculation method of claim 1, wherein, The calling of the first equalization difference identification model comprises: according to the position of the battery pack where the first type of battery is located, the corresponding first equalization difference identification model is called; the parameters in the first equalization difference identification model are different due to the difference in the environment of different battery packs.

4. The battery capacity equalization difference calculation method of claim 1, wherein, After the first equalization difference identification model is trained and generated, the following steps are further included: obtaining the charging and discharging history data of a battery system composed of batteries of the same type; optimizing and adjusting the first equalization difference identification model based on big data analysis technology.

5. The battery capacity equalization difference calculation method according to any one of claims 1 to 4, characterized by, Further comprising: V end ≥V th2 The batteries of V end ≥V th2 are all identified as the second type of battery; for each second type of battery, calculating a second charge capacity value over the interval [V th1 , V th2 ] taking the difference between the standard charging capacity value and the second charging capacity value as the capacity equalization characteristic value of the second type of battery; calling a second equalization difference identification model to determine the real capacity difference between the second type of battery and the standard battery according to the capacity equalization characteristic value; the second equalization difference identification model is generated by pre-training based on sample test data; correspondingly, the second equalization difference identification model is determined by the following process: multiple cyclic charging and discharging tests are performed on sample batteries of the same type with known actual total capacity values, and the charging state data is monitored in real time; the corresponding open circuit voltage value is obtained in real time through normalization calculation; the standard charge capacity value of the standard sample battery when the open circuit voltage is within the range of [V th1 , V th2 ], the second charge capacity value of the second sample battery when the open circuit voltage is within the range of [V th1 , V th2 ], and the difference between the two; the second equalization difference identification model is trained and generated by taking the difference value corresponding to each second type of sample battery as sample input data and taking the real capacity difference between each second type of sample battery and the standard sample battery as sample output data.

6. A battery capacity equalization difference calculating device of a battery system, characterized by comprising: The battery system comprises a plurality of series-connected batteries, and the device comprises: a data acquisition module for obtaining the charging state data of each battery in the charging process of the battery system; An equalization classification module is configured to calculate the open circuit voltage value V of each battery at the end of charging based on the charging state data end ; identify the batteries with V end <V th2 as the first type of batteries; and th1 , V th2 ] as the significant variation interval of capacity attenuation of the same type of batteries; the significant variation interval of capacity attenuation is an open circuit voltage value interval of the batteries. a feature calculation module, configured to calculate, for each first-type battery, a first charging capacity value within the period of [V th1 , V end ], and take a difference between a standard charging capacity value and the first charging capacity value as a capacity equalization feature value of the first-type battery; the standard charging capacity value is a charging capacity value of a standard battery within the period of [V th1 , V th2 ]. an equalization calculation module for calling a first equalization difference identification model to determine the real capacity difference between the first type of battery and the standard battery according to the capacity equalization characteristic value; the first equalization difference identification model is generated by pre-training based on sample test data; wherein the first equalization difference identification model is determined by the following process: multiple cyclic charging and discharging tests are performed on sample batteries of the same type with known actual total capacity values, and the charging state data is monitored in real time; the corresponding open circuit voltage value is obtained in real time through normalization calculation; the standard charge capacity value of the standard sample battery when the open circuit voltage is within the range of [V th1 , V th2 ], the first charge capacity value of the first sample battery when the open circuit voltage is within the range of [V th1 , V end ], and the difference between the two; The first equalization difference identification model is trained by taking the difference value corresponding to each first-type sample battery as sample input data and taking the real capacity difference value between each first-type sample battery and the standard sample battery as sample output data.

7. An electronic device, comprising: Comprise: A memory for storing a computer program; A processor for executing the computer program to implement the steps of the battery capacity equalization difference calculation method of the battery system according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the battery capacity equalization difference calculation method of the battery system according to any one of claims 1 to 5.

Images