Capacity balancing management method, device, equipment and medium for battery management system

By real-time monitoring and dynamic grouping of battery packs, and by optimizing the grouping configuration of the battery management system using predictive models, the problem of the inability to adjust the capacity balancing strategy in traditional battery management systems in a timely manner is solved, thus achieving accurate capacity balancing and stability of the battery packs.

CN118693376BActive Publication Date: 2024-11-12SHENZHEN FENIKI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411163433.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-11-12
Estimated Expiration
2044-08-23

AI Technical Summary

Technical Problem

Traditional battery management systems cannot effectively consider the dynamic changes in the capacity characteristics of individual battery cells, resulting in the inability to adjust and optimize capacity balancing strategies in a timely manner. They also lack effective predictive models and cannot achieve accurate capacity balancing.

Method used

The battery management system monitors the battery pack in real time, acquires individual cell monitoring data, analyzes capacity characteristics to dynamically group the cells, executes balancing strategies, uses predictive models to predict capacity change trends, generates target predictive balancing strategies, and finally optimizes the initial grouping configuration.

Benefits of technology

It achieves precise balancing of individual battery cell capacity, improves the overall capacity consistency and lifespan of the battery pack, and ensures the stability and performance of the battery pack.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118693376B_ABST
    Figure CN118693376B_ABST
Patent Text Reader

Abstract

The present invention relates to a capacity balancing management method, device, equipment and medium of a battery management system. The method includes real-time monitoring of a battery pack through a battery management system to obtain the single-cell monitoring data of each battery cell; analyzing the capacity characteristic information based on the single-cell monitoring data, dynamically grouping the battery cells according to the capacity characteristic information to obtain battery subgroups, and obtaining historical subgroup data; obtaining subgroup data, executing a corresponding single balancing strategy or a subgroup balancing strategy according to the subgroup data to perform balancing operation processing on the battery subgroup to obtain balancing capacity information; predicting the capacity change trend of the battery cell according to the balancing capacity information, real-time subgroup data and historical subgroup data, and generating a target prediction balancing strategy according to the capacity change trend; optimizing the initial grouping configuration of the battery management system to obtain grouping configuration data. The present invention can predict the change trend of the battery cell capacity and achieve accurate capacity balancing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of battery management systems, and in particular to a capacity balancing management method, device, equipment and medium for a battery management system. Background Art

[0002] With the rapid development and widespread application of battery technology, capacity balancing management of battery management systems (BMS) has become crucial. Each battery cell in a battery pack has different capacity characteristics. As the usage time increases, the capacity difference between battery cells will further expand. Therefore, it is of great significance to develop an efficient capacity balancing management method for battery management systems. However, the traditional static grouping method cannot fully consider the dynamic changes in the capacity characteristics of battery cells and cannot achieve accurate capacity balancing. Secondly, there is a lack of effective prediction models to predict the changing trend of battery cell capacity, which makes it impossible to adjust and optimize the balancing strategy in a timely manner. Summary of the invention

[0003] The main purpose of the present invention is to provide a capacity balancing management method, device, equipment and medium for a battery management system, which can predict the change trend of battery cell capacity and achieve accurate capacity balancing.

[0004] To achieve the above object, the present invention provides a capacity balancing management method for a battery management system, which is characterized by comprising:

[0005] Monitor the battery pack in real time through the battery management system to obtain the cell monitoring data of each battery cell in the battery pack;

[0006] Analyzing the capacity characteristic information of each battery cell based on the cell monitoring data, dynamically grouping the battery cells according to the capacity characteristic information to obtain battery subgroups, and obtaining historical subgroup data of the battery subgroups;

[0007] Obtain subgroup data of the battery subgroup, execute a corresponding single balancing strategy or a subgroup balancing strategy to perform balancing operation processing on the battery subgroup according to the subgroup data, and obtain balancing capacity information of the battery subgroup after balancing processing;

[0008] The prediction model is used to predict the capacity change trend of battery cells based on the balanced capacity information, real-time subgroup data and historical subgroup data, and a target prediction balanced strategy is generated based on the capacity change trend;

[0009] The initial grouping configuration of the battery management system is optimized according to the target prediction balancing strategy to obtain grouping configuration data.

[0010] Furthermore, the real-time monitoring of the battery pack by the battery management system to obtain the cell monitoring data of each battery cell in the battery pack includes:

[0011] By means of monitoring equipment deployed in the battery management system, the battery pack is monitored in real time to obtain the battery pack topology and comprehensive monitoring data of the battery pack, and the battery cell number, current monitoring data and voltage monitoring data of the battery cell;

[0012] Extract charge and discharge data from the comprehensive monitoring data to obtain battery pack charge and discharge data, and perform single-cell charge and discharge analysis on the battery pack charge and discharge data based on the battery pack topology and battery cell number to obtain charge and discharge monitoring data;

[0013] According to the preset detection requirements, check whether the charge and discharge monitoring data, current monitoring data, and voltage monitoring data meet the data requirements;

[0014] When any one of the charge and discharge monitoring data, current monitoring data, and voltage monitoring data does not meet the data requirements, the corresponding data is re-acquired for detection; when the charge and discharge monitoring data, current monitoring data, and voltage monitoring data all meet the data requirements, the charge and discharge monitoring data, current monitoring data, and voltage monitoring data are integrated into the corresponding single-cell monitoring data of the battery cell.

[0015] Furthermore, the capacity characteristic information of each battery cell is analyzed based on the cell monitoring data, and the battery cells are dynamically grouped according to the capacity characteristic information to obtain battery subgroups, including:

[0016] Extracting the charge and discharge monitoring data, the current monitoring data and the voltage monitoring data from the single-cell monitoring data, extracting the number of full discharges and the charge and discharge time from the charge and discharge monitoring data, calculating the battery capacity value of the battery single-cell based on the number of charge and discharges for the current monitoring data, verifying and calculating the battery capacity value through the voltage monitoring data to obtain a verification value, judging whether the verification value meets a preset verification threshold, and when the verification value meets the preset verification threshold, calculating the capacity attenuation rate of the battery single-cell based on the charge and discharge time and the battery capacity value, and integrating the battery capacity value and the capacity attenuation rate into capacity characteristic information;

[0017] The capacity characteristic information is compared according to a preset grouping rule, and the battery cells whose capacity characteristic information is within the same preset comparison range are grouped into the same battery subgroup.

[0018] Further, the acquiring of subgroup data of the battery subgroup, executing a corresponding single balancing strategy or a subgroup balancing strategy to perform balancing operation processing on the battery subgroup according to the subgroup data, and acquiring balancing capacity information of the battery subgroup after balancing processing, includes:

[0019] Acquire real-time battery data of the battery subgroup, the real-time battery data including real-time voltage data and real-time current data of all the battery cells, and calculate a real-time internal resistance value based on the real-time voltage data and real-time current data;

[0020] Obtain a historical voltage-charge relationship curve, map the real-time voltage data to the historical voltage-charge relationship curve, and perform charge calculation on the historical voltage-charge relationship curve according to a preset charge algorithm to obtain a corresponding charge estimation value, and perform data correction on the charge estimation value according to a correction algorithm based on the real-time internal resistance value to obtain a real-time charge value;

[0021] Determine whether the real-time internal resistance value and the real-time charge value meet the preset balancing threshold range, and when either the real-time internal resistance value or the real-time charge value does not meet the balancing threshold range, obtain the corresponding preset single balancing strategy, the single balancing strategy includes the internal resistance balancing strategy and the charge balancing strategy, and perform a single balancing operation on the battery subgroup according to the single balancing strategy, and obtain the balancing capacity information after the single balancing process;

[0022] When both the real-time internal resistance value and the real-time charge value do not meet the balancing threshold range, the corresponding preset subgroup balancing strategy is obtained, and the overall balancing operation processing is performed on the battery subgroup according to the subgroup balancing strategy, and the balancing capacity information after the overall balancing processing is obtained;

[0023] Among them, the calculation formula of the charge algorithm includes:

[0024] Charge estimate = (OCV2-OCV1)*((V-V1) / (V2-V1))+SOC1;

[0025] OCV1 is the first historical voltage value of the historical voltage-charge relationship curve data point, OCV2 is the second historical voltage value of the historical voltage-charge relationship curve data point, V1 is the first charge-discharge state of the historical voltage-charge relationship curve data point, V2 is the second charge-discharge state of the historical voltage-charge relationship curve data point, V is the real-time voltage value of the real-time battery, and SOC1 is the charge-discharge state corresponding to the historical voltage-charge relationship curve data point;

[0026] The calculation formula of the correction algorithm includes:

[0027] Real-time charge value = charge estimation value * (1-α*R);

[0028] α is the correction coefficient, which indicates the influence of internal resistance on the charge estimation value, and R is the real-time internal resistance value.

[0029] Furthermore, the prediction model predicts the capacity change trend of the battery cell according to the balanced capacity information, subgroup data and historical subgroup data, generates an initial prediction balance strategy according to the capacity change trend, optimizes the initial prediction balance strategy based on the balance strategy, and obtains a target prediction balance strategy, including:

[0030] Generate a corresponding capacity characteristic curve according to the balanced capacity information through the prediction model, generate a simulated change time according to the historical subgroup data and the subgroup data, simulate the change of the capacity characteristic curve within the simulated change time based on the historical subgroup data and the subgroup data, record the simulated data of the capacity characteristic curve during the simulation process, and perform trend analysis on the capacity characteristic curve and the simulated data after the simulation to obtain the capacity change trend;

[0031] According to the capacity change trend, the battery subgroups are dynamically simulated and grouped to obtain simulation groups, and a balancing operation plan for the corresponding battery subgroup is generated based on the balancing capacity information and the capacity change trend. The balancing operation plan includes a balancing period, a balancing plan and a balancing operation timing. The simulation group and the balancing operation plan are integrated to obtain the initial predicted balancing strategy, and the capacity balancing effect of the initial predicted balancing strategy is evaluated;

[0032] When the capacity balancing effect does not meet the preset effect threshold, the simulation group and the balancing operation plan of the initial prediction balancing strategy are iteratively optimized and adjusted based on the balancing strategy; when the capacity balancing effect meets the preset effect threshold, the corresponding target prediction balancing strategy is output.

[0033] Furthermore, the initial grouping configuration of the battery management system is optimized according to the target prediction balancing strategy to obtain initial grouping data, including:

[0034] According to the target prediction balancing strategy, the initial grouping configuration is simulated and the configuration parameters are adjusted, wherein the adjusted configuration parameters include the number of subgroups, the total capacity range of each subgroup, and the range of the difference in the single cell capacity of the subgroup battery;

[0035] Perform a simulated initial grouping based on the adjusted initial grouping configuration, obtain simulated capacity data of the simulated battery subgroup, determine whether the simulated capacity data meets the preset capacity health threshold, and when the simulated capacity data does not meet the capacity health threshold, re-adjust the simulated configuration parameters of the initial grouping configuration; when the simulated capacity data meets the capacity health threshold, optimize the configuration parameters of the initial grouping configuration of the battery management system based on the target prediction balancing strategy, and after the optimization is completed, re-acquire the grouping configuration data of the battery management system.

[0036] The present invention further provides a capacity balancing management device for a battery management system, which is applied to any one of the capacity balancing management methods for the battery management system described above, and the device comprises:

[0037] An acquisition module, the acquisition module is used to monitor the battery pack in real time through a battery management system and acquire cell monitoring data of each battery cell in the battery pack;

[0038] An analysis module, the analysis module is used to analyze the capacity characteristic information of each battery cell based on the cell monitoring data, dynamically group the battery cells according to the capacity characteristic information to obtain battery subgroups, and obtain historical subgroup data of the battery subgroups;

[0039] An execution module, the execution module is used to obtain subgroup data of the battery subgroup, execute a corresponding single balancing strategy or a subgroup balancing strategy according to the subgroup data to perform a balancing operation on the battery subgroup, and obtain balancing capacity information of the battery subgroup after the balancing operation;

[0040] A processing module, the processing module is used to predict the capacity change trend of the battery cells according to the balanced capacity information, the real-time subgroup data and the historical subgroup data through a prediction model, and generate a target prediction balanced strategy according to the capacity change trend;

[0041] The control module is used to optimize the initial grouping configuration of the battery management system according to the target prediction balancing strategy to obtain grouping configuration data.

[0042] The present invention also provides a capacity balancing management device for a battery management system, comprising:

[0043] Memory, used to store programs;

[0044] The processor is used to execute the program to implement each step of the capacity balancing management method of a battery management system described in any one of the above.

[0045] The present invention also provides a medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0046] The battery management system monitors the battery pack in real time and obtains the single-cell monitoring data of each battery cell, which enables the system to understand the status and capacity characteristics of the battery cell in real time, which helps to accurately evaluate the overall performance of the battery pack. Based on the analysis of the capacity characteristic information of the battery cell based on the single-cell monitoring data, the system can dynamically group the battery cells and execute the corresponding balancing strategy. This helps to balance the capacity differences between battery cells, improve the overall capacity consistency of the battery pack, and extend the life of the battery pack. Through the prediction model combined with the balanced capacity information, real-time subgroup data and historical subgroup data, the system can predict the capacity change trend of the battery cell and generate a target prediction balancing strategy. This helps to discover and respond to the trend of battery cell capacity decline in advance, adjust the balancing strategy in time, and maintain the stability and performance of the battery pack. Based on the target prediction balancing strategy, the system optimizes the initial grouping configuration. This means that after the battery pack is assembled or the system is reset, the system can perform the best grouping configuration based on a variety of factors (such as battery cell capacity characteristics, historical data, etc.) to ensure the balance and efficiency of the entire battery management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of a capacity balancing method of a battery management system provided by the present invention;

[0048] Figure 2 It is a structural diagram of a capacity balancing device of a battery management system provided by the present invention;

[0049] Figure 3 The present invention provides a structure diagram of a capacity balancing device for a battery management system.

[0050] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0053] Reference Figure 1 As shown, the present invention provides a capacity balancing management method for a battery management system, characterized by comprising:

[0054] Step S1: real-time monitoring of the battery pack through the battery management system to obtain the cell monitoring data of each battery cell in the battery pack;

[0055] Step S2: analyzing the capacity characteristic information of each battery cell based on the cell monitoring data, dynamically grouping the battery cells according to the capacity characteristic information to obtain battery subgroups, and obtaining historical subgroup data of the battery subgroups;

[0056] Step S3: obtaining subgroup data of the battery subgroup, executing a corresponding single balancing strategy or a subgroup balancing strategy according to the subgroup data to perform a balancing operation on the battery subgroup, and obtaining balancing capacity information of the battery subgroup after the balancing operation;

[0057] Step S4: predicting the capacity change trend of the battery cells according to the balanced capacity information, real-time subgroup data and historical subgroup data through the prediction model, and generating a target prediction balanced strategy according to the capacity change trend;

[0058] Step S5: Optimize the initial grouping configuration of the battery management system according to the target prediction balancing strategy to obtain grouping configuration data.

[0059] Based on the above steps, the detailed embodiment steps are as follows:

[0060] Step S1: Connect the battery management system (BMS) to the battery pack so that the status information of each battery cell can be monitored in real time. The battery management system obtains the monitoring data of each battery cell in the battery pack through sensors or other monitoring devices, including voltage, temperature, current, etc. The battery management system usually consists of a master control unit and multiple slave control units. The master control unit is responsible for collecting and processing the monitoring data of the battery cells, and the slave control unit is responsible for communicating with the battery cells and transmitting the data to the master control unit.

[0061] The battery management system collects the status information of the battery cells through sensors or other monitoring devices, and processes the collected monitoring data. The type and amount of monitoring data depend on the function and configuration of the battery management system. Usually, the monitoring data includes the voltage, temperature, current and other related parameters of the battery cells.

[0062] The battery management system is used to monitor the battery pack in real time and obtain the cell monitoring data of each battery cell in the battery pack.

[0063] Step S2: The battery management system extracts the capacity characteristic information of each battery cell from the acquired single cell monitoring data. The capacity characteristic information refers to the change rules of the discharge capacity and charging capacity of the battery cell under different working environments. By analyzing and processing the single cell monitoring data, the battery management system obtains the capacity characteristic curve of the battery cell. Based on the capacity characteristic information, the battery management system will dynamically group the battery cells. Dynamic grouping is to divide the battery cells into battery subgroups with similar capacity characteristics according to their capacity characteristics. The battery management system will place battery cells with similar capacities in the same subgroup according to the similarity and difference of the capacity characteristic curves.

[0064] After obtaining the battery subgroup, the battery management system will also obtain the historical subgroup data of the battery subgroup. The historical subgroup data includes the capacity information of the battery subgroup, the charge and discharge process records, etc. The battery management system will format the historical subgroup data to obtain the historical subgroup data that meets the data format requirements.

[0065] Step S3: The battery management system will obtain the subgroup data of the battery subgroup, and execute the corresponding single balancing strategy or subgroup balancing strategy according to the subgroup data to perform balancing operation on the battery subgroup. Subsequently, the battery management system will obtain the balancing capacity information of the battery subgroup after the balancing process.

[0066] The battery management system obtains subgroup data of the battery subgroup, and the subgroup data includes status information of each battery cell in the battery subgroup, such as voltage, temperature, current, etc. The battery management system obtains the status information by communicating with each battery cell and integrates it into subgroup data.

[0067] Based on the subgroup data, the battery management system will execute the corresponding balancing strategy to perform balancing operations on the battery subgroups. The balancing strategy is divided into two types: single balancing strategy and subgroup balancing strategy.

[0068] The single balancing strategy refers to performing a separate balancing operation on each battery cell in the battery subgroup. The battery management system will adjust the balancing current according to the capacity difference and health status of each battery cell to minimize the capacity difference between battery cells to achieve balancing.

[0069] The subgroup balancing strategy refers to the balancing operation of the entire battery subgroup. The battery management system adjusts the balancing current according to the capacity differences and health conditions of the battery cells in the battery subgroup to make the capacity distribution within the battery subgroup uniform to achieve balancing.

[0070] After executing the balancing strategy, the battery management system will obtain the balanced capacity information of the battery subgroup after the balancing process. The balanced capacity information refers to the capacity value of the battery subgroup after the balancing operation, including but not limited to each battery cell. The battery management system will record these capacity values ​​and use them in subsequent operations and analysis.

[0071] Step S4: The battery management system will use the balanced capacity information, real-time subgroup data and historical subgroup data to train the prediction model. The balanced capacity information includes the capacity value of each battery cell after the battery subgroup is balanced, the real-time subgroup data includes the status information of each battery cell in the battery subgroup, and the historical subgroup data includes the capacity change record of the battery subgroup. The battery management system inputs these data into the prediction model to train the model to learn the law and trend of battery cell capacity change.

[0072] Next, the battery management system uses the trained prediction model to predict the capacity change trend of the battery cells. Based on the real-time subgroup data and historical subgroup data, the battery management system will obtain the current status information of the battery cells and combine the prediction model to predict the capacity change. The prediction model will consider factors such as the capacity characteristics of the battery cells, the working environment, and the charge and discharge history to generate accurate capacity change prediction results.

[0073] Based on the predicted results of the capacity change trend, the battery management system will generate a target prediction balancing strategy. The target prediction balancing strategy refers to formulating a reasonable balancing strategy to achieve capacity balancing of the battery subgroup based on the predicted change trend of the battery cell capacity. For example, if it is predicted that the capacity of a battery cell will decrease, the battery management system adjusts the balancing current and increases the charge of the battery cell to keep its capacity balanced with other battery cells.

[0074] The training process of the prediction model is as follows: it is necessary to collect and prepare data sets for training, including balanced capacity information, real-time subgroup data, and historical subgroup data. These data are organized into a format suitable for machine learning algorithms, usually in the form of a data table or matrix, where each row represents a sample and each column represents a feature or attribute. At the same time, the sample data needs to be divided into a training set and a validation set for model training and model performance evaluation.

[0075] In the feature engineering stage, the raw data needs to be processed and transformed to extract features that are meaningful to the prediction target, including data cleaning, feature selection, feature transformation, feature combination, etc. For example, the capacity difference between battery cells, temperature change rate, etc. can be calculated as features, and historical data can be converted into statistical features such as mean, variance, etc. These features will be used to train the prediction model.

[0076] Select a suitable machine learning model based on the nature of the prediction task and the characteristics of the data. Common prediction models include linear regression, decision tree, support vector machine, neural network, etc. Depending on the complexity of the problem and performance requirements, you can choose a single model or integrate multiple models. At the same time, you need to define model evaluation indicators, such as mean square error (MSE), mean absolute error (MAE), etc., to evaluate the performance of the model.

[0077] Use the training set to train the selected model. The training process is to adjust the parameters of the model by minimizing the loss function so that it can better fit the training data. The specific training algorithm and optimization method depend on the selected model. During the training process, cross-validation and other techniques are used to further optimize the generalization performance of the model.

[0078] Step S5: The battery management system will group the battery cells according to the predicted capacity change trend in the balancing strategy. The purpose of this grouping is to put battery cells with similar capacity characteristics and predicted change trends in the same group for subsequent balancing operations. The battery management system will group battery cells with similar capacities into the same group according to the predicted capacity change trend for better balancing operations.

[0079] Next, the battery management system will optimize the initial grouping configuration of the battery management system based on the grouping configuration goal. This process is regarded as an optimization problem, which requires finding the best grouping configuration solution under certain constraints. The optimization goal is to make the capacity of the battery management system as balanced as possible, reduce capacity differences, and improve system performance and life. The battery management system searches for the optimal grouping configuration solution by using mathematical optimization algorithms, such as genetic algorithms and simulated annealing algorithms.

[0080] During the optimization process, the battery management system will consider multiple factors, such as the capacity, internal resistance, temperature and other characteristics of the battery cells, as well as the operating conditions and performance requirements of the battery management system. The battery management system will weigh and adjust these factors to find the best grouping configuration so that the capacity of each group is as balanced as possible and meets the performance requirements of the system.

[0081] Finally, the battery management system will perform initial group configuration of the battery management system based on the group configuration data obtained from the optimization results. These data include information such as the battery cell number and capacity value in each group.

[0082] A capacity balancing management method for a battery management system provided by the present invention monitors the battery pack in real time through the battery management system and obtains the single-cell monitoring data of each battery cell, which enables the system to understand the state and capacity characteristics of the battery cell in real time, and helps to accurately evaluate the overall performance of the battery pack. Based on the single-cell monitoring data, the capacity characteristic information of the battery cell is analyzed, and the system can dynamically group the battery cells and execute the corresponding balancing strategy. This helps to balance the capacity differences between the battery cells, improve the overall capacity consistency of the battery pack, and extend the life of the battery pack. Through the prediction model combined with the balanced capacity information, real-time subgroup data and historical subgroup data, the system can predict the capacity change trend of the battery cell and generate a target prediction balancing strategy. This helps to discover and respond to the trend of battery cell capacity decline in advance, adjust the balancing strategy in time, and maintain the stability and performance of the battery pack. According to the target prediction balancing strategy, the system performs initial grouping configuration optimization. This means that after the battery pack is assembled or the system is reset, the system can perform the best grouping configuration based on multiple factors (such as battery cell capacity characteristics, historical data, etc.) to ensure the balance and efficiency of the entire battery management system.

[0083] In one embodiment, the battery pack is monitored in real time by a battery management system to obtain cell monitoring data of each battery cell in the battery pack, including:

[0084] The battery pack is monitored in real time by the monitoring equipment deployed in the battery management system to obtain the battery pack topology and comprehensive monitoring data of the battery pack. The battery pack topology includes the connection relationship between the battery cells, and the battery cell number, current monitoring data and voltage monitoring data of the battery cell are obtained.

[0085] The charging and discharging data are extracted from the comprehensive monitoring data to obtain the battery pack charging and discharging data. Based on the battery pack topology and the battery cell number, the battery pack charging and discharging data is analyzed by single cell charging and discharging to obtain the charging and discharging monitoring data.

[0086] According to the preset detection requirements, the charge and discharge monitoring data, current monitoring data, and voltage monitoring data are detected to see whether they meet the data requirements. The data requirements include but are not limited to data range, volatility, stability, etc.

[0087] When any one of the charge and discharge monitoring data, current monitoring data, and voltage monitoring data does not meet the data requirements, the corresponding data is re-acquired for testing; when the charge and discharge monitoring data, current monitoring data, and voltage monitoring data all meet the data requirements, the charge and discharge monitoring data, current monitoring data, and voltage monitoring data are integrated into the corresponding single-cell monitoring data of the battery cell.

[0088] This embodiment can monitor the status of the battery pack and the monitoring data of each battery cell in real time through the monitoring equipment deployed in the battery management system. This allows the system to obtain real-time information of the battery pack in a timely manner, which helps to implement timely fault diagnosis and processing. The topological structure and comprehensive monitoring data of the battery pack, as well as the current and voltage monitoring data of the battery cell are obtained through the monitoring equipment. These data can provide a comprehensive understanding of the internal state of the battery pack and help the system to conduct in-depth analysis and evaluation. By extracting the charging and discharging data from the comprehensive monitoring data, the charging and discharging data of the battery pack are obtained. These data can reflect the charging and discharging history and behavior of the battery pack, which helps the system to estimate capacity and analyze faults. The charging and discharging monitoring data, current monitoring data, and voltage monitoring data are tested to ensure the accuracy and reliability of the data. When the data meets the requirements, they are integrated into the corresponding single-cell monitoring data of the battery cell to facilitate subsequent analysis and application.

[0089] In one embodiment, the capacity characteristic information of each battery cell is analyzed based on the cell monitoring data, and the battery cells are dynamically grouped according to the capacity characteristic information to obtain battery subgroups, including:

[0090] The charge and discharge monitoring data, current monitoring data and voltage monitoring data are extracted from the single-cell monitoring data. The charge and discharge monitoring data include but are not limited to the number of full discharges and the charge and discharge time. For example, the number of charge and discharge cycles of each battery cell and the duration of each charge and discharge are recorded.

[0091] Next, the current monitoring data is calculated according to the number of charge and discharge cycles to obtain the battery capacity value of the battery cell. The average charge and discharge time is obtained by adding the charge and discharge time and then dividing it by the number of charge and discharge cycles. Assuming that a battery cell undergoes 3 charge and discharge cycles, with each charge and discharge time of 1 hour, 2 hours, and 3 hours respectively, the average charge and discharge time is (1+2+3) / 3 = 2 hours.

[0092] The calculated battery capacity value is then verified by using the voltage monitoring data to obtain a verification value. The accuracy of the battery capacity value is determined by monitoring the voltage stability of the battery after the charge and discharge cycle. For example, if the voltage remains stable, then the calculated battery capacity value is valid.

[0093] Next, determine whether the verification value meets the preset verification threshold. The verification threshold is set according to actual needs and is used to determine the accuracy of the battery capacity value. If the verification value meets the preset verification threshold, proceed to the next step. For example, if the verification threshold is set to a tolerance range between 1 hour and 3 hours, and the calculated battery capacity value is 2 hours, then the verification value meets the preset verification threshold.

[0094] When the verification value meets the preset verification threshold, the capacity decay rate of the battery cell is calculated based on the charge and discharge time and the battery capacity value. The capacity decay rate reflects the change of battery capacity over time. The capacity decay rate is obtained by calculating (charge and discharge time - battery capacity value) / charge and discharge time. For example, assuming that the charge and discharge time of a battery cell is 10 hours, and the calculated battery capacity value is 2 hours, then the capacity decay rate is (10-2) / 10=0.8.

[0095] Finally, the battery capacity value and capacity decay rate are integrated into capacity characteristic information, which is used for further analysis and management. For example, the battery capacity value calculated in the above example is charged for 2 hours and the capacity decay rate is 0.8, which is integrated into capacity characteristic information.

[0096] According to the preset grouping rules, the capacity characteristic information is compared, and the battery cells within the same preset comparison range are divided into the same battery subgroup. These grouping rules can be set according to actual needs. For example, the comparison range is set to the battery capacity value between 1 hour and 3 hours of charging, and the capacity decay rate is between 0.5 and 1. Battery cells that meet this range will be divided into the same battery subgroup.

[0097] For example, suppose there is a group of battery cells, where cell A is charged and discharged 5 times, and the charge and discharge times are 2 hours, 3 hours, 2 hours, 2 hours, and 3 hours respectively. The average charge and discharge time per time is calculated to be (2+3+2+2+3) / 5=2.4 hours. Then, the calculated battery capacity value is verified using voltage monitoring data, and the verification value is 2.3 hours, which meets the preset verification threshold.

[0098] This embodiment can accurately evaluate the capacity state of the battery by analyzing the capacity characteristic information of the battery cells. This helps to timely discover capacity attenuation, predict the life of the battery, and take corresponding management measures. By dynamically grouping according to the capacity characteristic information, battery cells with similar capacity characteristics can be combined together. This helps to rationally utilize battery resources and improve the overall performance and life of the battery pack. The accuracy of the battery capacity value can be verified by verification calculation. This helps to improve the reliability of capacity calculation and ensure accurate evaluation of the battery capacity state. By calculating the capacity attenuation rate, it is possible to understand how the battery capacity changes over time. This helps to predict the life of the battery and formulate corresponding maintenance and replacement plans. By dividing the battery cells according to the preset grouping rules, the battery can be better managed and maintained. This helps to increase the service life of the battery, reduce the risk of failure, and optimize the performance of the battery pack.

[0099] In one embodiment, subgroup data of a battery subgroup is obtained, a corresponding single balancing strategy or a subgroup balancing strategy is executed according to the subgroup data to perform a balancing operation on the battery subgroup, and balancing capacity information of the battery subgroup after the balancing operation is obtained, including:

[0100] The real-time battery data of the battery subgroup is obtained, including the real-time voltage data and real-time current data of all battery cells. Based on these real-time data, the real-time internal resistance value is calculated to measure the internal resistance of the battery.

[0101] At the same time, a historical voltage-charge relationship curve is obtained. The historical voltage-charge relationship curve is obtained by performing charge and discharge experiments on the battery, and describes the law of how the battery voltage changes with charge.

[0102] The real-time voltage data is mapped to the historical curve to obtain the corresponding charge estimation value. The charge of the historical curve is calculated by a preset charge algorithm, and the charge estimation value is corrected according to the correction algorithm based on the real-time internal resistance value to obtain the real-time charge value.

[0103] Next, determine whether the real-time internal resistance value and the real-time charge value meet the preset balancing threshold range. If any of the values ​​is not within the threshold range, the corresponding single balancing strategy is executed. The single balancing strategy includes the internal resistance balancing strategy and the charge balancing strategy. The internal resistance balancing strategy makes the internal resistance value more uniform by adjusting the internal resistance difference between battery cells. The charge balancing strategy makes the charge distribution more balanced by adjusting the charge difference between battery cells. After executing a single balancing operation, the balanced capacity information after the balancing process is obtained.

[0104] If both the real-time internal resistance value and the real-time charge value do not meet the balancing threshold range, it is necessary to execute the subgroup balancing strategy, which is a balancing operation that comprehensively considers the entire battery subgroup. It adjusts the connection method between battery cells or applies an external power supply for overall balancing operation to achieve the purpose of balancing the battery subgroup. After executing the subgroup balancing operation, the balanced capacity information after the overall balancing process is obtained.

[0105] Let's take an example to illustrate the process of this embodiment. Assume that there is a battery subgroup, which contains 10 battery cells. We obtain the real-time voltage and current data of each battery cell through sensors, and calculate the real-time internal resistance value. At the same time, we also have a historical voltage-charge relationship curve, and we can map the real-time voltage data to the curve and calculate the real-time charge value.

[0106] Assume that at a certain moment, the real-time internal resistance of one battery cell exceeds the preset threshold, and the real-time charge values ​​of other battery cells are also unbalanced. Based on this situation, we execute the internal resistance balancing strategy to adjust the internal resistance of the battery cell to make it closer to the other cells. At the same time, according to the charge balancing strategy, we adjust the charge distribution of other battery cells to make the charge of the entire battery subgroup more balanced.

[0107] After a single balancing operation, the balanced capacity information of the battery subgroup is recalculated. If the real-time internal resistance and real-time charge values ​​of all battery cells meet the preset threshold range, the balancing operation is completed. If there are still cases that do not meet the threshold range, the subgroup balancing strategy will be executed to perform overall balancing operations on the entire battery subgroup. Finally, the balanced capacity information after overall balancing is obtained.

[0108] Among them, the calculation formula of the charge algorithm includes:

[0109] Charge estimate = (OCV2-OCV1)*((V-V1) / (V2-V1))+SOC1;

[0110] OCV1 is the first historical voltage value of the historical voltage-charge relationship curve data point, OCV2 is the second historical voltage value of the historical voltage-charge relationship curve data point, V1 is the first charge-discharge state of the historical voltage-charge relationship curve data point, V2 is the second charge-discharge state of the historical voltage-charge relationship curve data point, V is the real-time voltage value of the real-time battery, and SOC1 is the charge-discharge state corresponding to the historical voltage-charge relationship curve data point;

[0111] The calculation formula of the correction algorithm includes:

[0112] Real-time charge value = charge estimation value * (1-α*R);

[0113] α is the correction coefficient, which indicates the influence of internal resistance on the charge estimation value, and R is the real-time internal resistance value.

[0114] This embodiment can monitor the working state of the battery in real time, including charging and discharging conditions and load changes, by acquiring the current and voltage data of the battery cell in real time. This helps to improve the understanding and monitoring of the battery state and detect abnormal conditions in time. The real-time internal resistance value is calculated by the real-time current and voltage data, and the change of the internal resistance of the battery can be evaluated in time. This helps to judge the health of the battery, take maintenance measures in time, and extend the life of the battery. By obtaining the historical voltage-charge relationship curve, the charge state of the battery can be estimated more accurately. This helps to improve the accuracy of charge estimation, so as to better perform battery balancing and management. The charge estimation value is corrected based on the real-time internal resistance value, and the real-time charge value of the battery can be calculated more accurately. This helps to improve the accurate evaluation of the battery state, so as to better perform balancing operations and battery management. According to whether the real-time internal resistance value and the real-time charge value meet the preset balancing threshold range, a suitable single balancing strategy is selected for operation and processing. This helps to take suitable balancing measures for different battery states and improve the balancing effect of the battery. When both the real-time internal resistance value and the real-time charge value do not meet the balancing threshold range, the subgroup balancing strategy is executed to perform balancing operations on the entire battery subgroup. This helps to resolve imbalance issues across the battery sub-pack, improving the overall performance and life of the battery pack.

[0115] In one embodiment, the capacity change trend of the battery cell is predicted by the prediction model according to the balanced capacity information, subgroup data and historical subgroup data, and an initial prediction balance strategy is generated according to the capacity change trend. The initial prediction balance strategy is optimized based on the balance strategy to obtain a target prediction balance strategy, including:

[0116] The corresponding capacity characteristic curve is generated according to the balanced capacity information through the prediction model, the simulation change time is generated according to the historical subgroup data and the subgroup data, the change of the capacity characteristic curve is simulated within the simulation change time based on the historical subgroup data and the subgroup data, the simulation data of the capacity characteristic curve during the simulation process is recorded, and the capacity characteristic curve and the simulation data after the simulation are trend analyzed to obtain the capacity change trend.

[0117] According to the capacity change trend, the battery subgroups are dynamically simulated and grouped to obtain simulation groups. Based on the balanced capacity information and the capacity change trend, the corresponding battery subgroup balanced operation plan is generated. The balanced operation plan includes the balanced cycle, balanced plan and balanced operation timing. The simulation group and the balanced operation plan are integrated to obtain the initial predicted balanced strategy, and the capacity balanced effect of the initial predicted balanced strategy is evaluated.

[0118] When the capacity balancing effect does not meet the preset effect threshold, the simulation group and balancing operation plan of the initial prediction balancing strategy are iteratively optimized and adjusted based on the balancing strategy; when the capacity balancing effect meets the preset effect threshold, the corresponding target prediction balancing strategy is output.

[0119] This embodiment accurately predicts the capacity change trend of battery cells through the prediction model, provides the ability to predict the change of battery capacity over time, and helps users better understand the life and performance of the battery. Dynamic simulation grouping can reasonably group battery subgroups according to the capacity change trend and balanced capacity information of battery cells, and realize effective management of battery capacity balancing. The initial prediction balancing strategy can provide guidance on the balancing cycle, balancing plan and balancing operation timing of each subgroup according to the simulation group and the balancing operation plan, and realize targeted balancing operations on battery subgroups. The capacity balancing effect evaluation can evaluate the initial prediction balancing strategy, help users understand the impact of the balancing strategy on the capacity balancing effect, and provide a basis for adjustment and optimization. Iterative optimization adjustment can adjust and optimize the initial prediction balancing strategy according to the results of the capacity balancing effect evaluation, realize continuous improvement of the balancing strategy, and improve the effect of battery capacity balancing.

[0120] In one embodiment, the initial grouping configuration of the battery management system is optimized according to the target prediction balancing strategy to obtain initial grouping data, including:

[0121] According to the target prediction balancing strategy, the initial group configuration is simulated and the configuration parameters are adjusted. The adjusted configuration parameters include the number of subgroups, the total capacity range of each subgroup, and the range of the difference in the single cell capacity of the subgroup battery;

[0122] The initial grouping is simulated based on the adjusted initial grouping configuration, and the simulated capacity data of the simulated battery subgroup is obtained to determine whether the simulated capacity data meets the preset capacity health threshold. When the simulated capacity data does not meet the capacity health threshold, the simulation configuration parameters of the initial grouping configuration are re-adjusted; when the simulated capacity data meets the capacity health threshold, the configuration parameters of the initial grouping configuration of the battery management system are optimized based on the target prediction balancing strategy. After the optimization is completed, the grouping configuration data of the battery management system is re-obtained.

[0123] This embodiment can optimize the initial grouping configuration of the battery management system and improve the effect of battery capacity balancing by applying the target prediction balancing strategy. The simulation configuration parameter adjustment can find the best initial grouping configuration by adjusting parameters such as the number of subgroups, the total capacity range, and the monomer capacity difference range, thereby improving the effect of battery capacity balancing. The application of simulating the initial grouping can obtain the capacity data of the simulated battery subgroup and determine whether it meets the preset capacity health threshold, providing a basis for evaluating and adjusting the grouping configuration. The setting of the capacity health threshold can determine whether the capacity of the battery subgroup is balanced, helping users understand the effect of the grouping configuration and make timely adjustments and optimizations. The application of re-simulating the configuration parameter adjustment processing of the initial grouping configuration can dynamically adjust the parameters of the grouping configuration according to the situation of the simulated capacity data to optimize the effect of battery capacity balancing. Configuration parameter optimization can further adjust the parameters of the initial grouping configuration according to the situation of the simulated capacity data to achieve better capacity balancing effect. The grouping configuration data finally obtained can provide the optimal battery subgroup grouping configuration to ensure that the battery management system has good capacity balancing performance.

[0124] Reference Figure 2 As shown, the present invention also provides a capacity balancing management device for a battery management system, which is applied to any of the above-mentioned capacity balancing management methods for a battery management system, and the device includes:

[0125] An acquisition module, which is used to monitor the battery pack in real time through a battery management system and acquire the cell monitoring data of each battery cell in the battery pack;

[0126] An analysis module, which is used to analyze the capacity characteristic information of each battery cell based on the cell monitoring data, dynamically group the battery cells according to the capacity characteristic information to obtain battery subgroups, and obtain historical subgroup data of the battery subgroups;

[0127] An execution module, the execution module is used to obtain subgroup data of the battery subgroup, execute a corresponding single balancing strategy or a subgroup balancing strategy according to the subgroup data to perform a balancing operation on the battery subgroup, and obtain balancing capacity information of the battery subgroup after the balancing operation;

[0128] A processing module, the processing module is used to predict the capacity change trend of the battery cells according to the balanced capacity information, real-time subgroup data and historical subgroup data through a prediction model, and generate a target prediction balanced strategy according to the capacity change trend;

[0129] The control module is used to optimize the initial grouping configuration of the battery management system according to the target prediction balancing strategy to obtain grouping configuration data.

[0130] A capacity balancing management method for a battery management system provided by the present invention monitors the battery pack in real time through the battery management system and obtains the single-cell monitoring data of each battery cell, which enables the system to understand the state and capacity characteristics of the battery cell in real time, and helps to accurately evaluate the overall performance of the battery pack. Based on the single-cell monitoring data, the capacity characteristic information of the battery cell is analyzed, and the system can dynamically group the battery cells and execute the corresponding balancing strategy. This helps to balance the capacity differences between the battery cells, improve the overall capacity consistency of the battery pack, and extend the life of the battery pack. Through the prediction model combined with the balanced capacity information, real-time subgroup data and historical subgroup data, the system can predict the capacity change trend of the battery cell and generate a target prediction balancing strategy. This helps to discover and respond to the trend of battery cell capacity decline in advance, adjust the balancing strategy in time, and maintain the stability and performance of the battery pack. According to the target prediction balancing strategy, the system performs initial grouping configuration optimization. This means that after the battery pack is assembled or the system is reset, the system can perform the best grouping configuration based on multiple factors (such as battery cell capacity characteristics, historical data, etc.) to ensure the balance and efficiency of the entire battery management system.

[0131] Reference Figure 3 As shown, the present invention also provides a capacity balancing management device for a battery management system, comprising:

[0132] Memory, used to store programs;

[0133] The processor is used to execute a program to implement each step of any one of the above-mentioned capacity balancing management methods for a battery management system.

[0134] In this embodiment, the processor and the memory may be connected via a bus or other means. The memory may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk, or a solid-state drive. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present invention.

[0135] The present invention also provides a medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0136] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0137] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A capacity balancing management method for a battery management system, characterized in that: include: Monitor the battery pack in real time through the battery management system to obtain the cell monitoring data of each battery cell in the battery pack; Analyzing the capacity characteristic information of each battery cell based on the cell monitoring data, dynamically grouping the battery cells according to the capacity characteristic information to obtain battery subgroups, and obtaining historical subgroup data of the battery subgroups; Obtain subgroup data of the battery subgroup, execute a corresponding single balancing strategy or a subgroup balancing strategy to perform balancing operation processing on the battery subgroup according to the subgroup data, and obtain balancing capacity information of the battery subgroup after balancing processing; The prediction model is used to predict the capacity change trend of battery cells based on the balanced capacity information, real-time subgroup data and historical subgroup data, and a target prediction balancing strategy is generated based on the capacity change trend; Optimize the initial grouping configuration of the battery management system according to the target prediction balancing strategy to obtain grouping configuration data; The subgroup data includes the status information of each battery cell in the battery subgroup, and the historical subgroup data includes the capacity information and charging and discharging process records of the battery subgroup; The method of predicting the capacity change trend of the battery cells according to the balanced capacity information, the real-time subgroup data and the historical subgroup data through the prediction model, and generating a target prediction and balancing strategy according to the capacity change trend, includes: Generate a corresponding capacity characteristic curve according to the balanced capacity information through the prediction model, generate a simulated change time according to the historical subgroup data and the subgroup data, simulate the change of the capacity characteristic curve within the simulated change time based on the historical subgroup data and the subgroup data, record the simulated data of the capacity characteristic curve during the simulation process, and perform trend analysis on the capacity characteristic curve and the simulated data after the simulation to obtain the capacity change trend; According to the capacity change trend, the battery subgroups are dynamically simulated and grouped to obtain simulation groups, and a balancing operation plan for the corresponding battery subgroup is generated based on the balancing capacity information and the capacity change trend. The balancing operation plan includes a balancing period, a balancing plan and a balancing operation timing. The simulation group and the balancing operation plan are integrated to obtain an initial predicted balancing strategy, and a capacity balancing effect evaluation is performed on the initial predicted balancing strategy; When the capacity balancing effect does not meet the preset effect threshold, the simulation group and the balancing operation plan of the initial prediction balancing strategy are iteratively optimized and adjusted based on the balancing strategy; when the capacity balancing effect meets the preset effect threshold, the corresponding target prediction balancing strategy is output.

2. The capacity balancing management method of a battery management system according to claim 1, characterized in that: The battery management system is used to monitor the battery pack in real time to obtain the cell monitoring data of each battery cell in the battery pack, including: By means of monitoring equipment deployed in the battery management system, the battery pack is monitored in real time to obtain the battery pack topology and comprehensive monitoring data of the battery pack, and the battery cell number, current monitoring data and voltage monitoring data of the battery cell; Extract charge and discharge data from the comprehensive monitoring data to obtain battery pack charge and discharge data, and perform single-cell charge and discharge analysis on the battery pack charge and discharge data based on the battery pack topology and battery cell number to obtain charge and discharge monitoring data; According to the preset detection requirements, check whether the charge and discharge monitoring data, current monitoring data, and voltage monitoring data meet the data requirements; When any one of the charge and discharge monitoring data, current monitoring data, and voltage monitoring data does not meet the data requirements, the corresponding data is re-acquired for detection; when the charge and discharge monitoring data, current monitoring data, and voltage monitoring data all meet the data requirements, the charge and discharge monitoring data, current monitoring data, and voltage monitoring data are integrated into the corresponding single-cell monitoring data of the battery cell.

3. The capacity balancing management method of a battery management system according to claim 2, characterized in that: The method of analyzing the capacity characteristic information of each battery cell based on the cell monitoring data and dynamically grouping the battery cells according to the capacity characteristic information to obtain battery subgroups includes: Extracting the charge and discharge monitoring data, the current monitoring data and the voltage monitoring data from the single-cell monitoring data, extracting the number of full discharges and the charge and discharge time from the charge and discharge monitoring data, calculating the battery capacity value of the battery single-cell based on the number of charge and discharges for the current monitoring data, verifying and calculating the battery capacity value through the voltage monitoring data to obtain a verification value, judging whether the verification value meets a preset verification threshold, and when the verification value meets the preset verification threshold, calculating the capacity attenuation rate of the battery single-cell based on the charge and discharge time and the battery capacity value, and integrating the battery capacity value and the capacity attenuation rate into capacity characteristic information; The capacity characteristic information is compared according to a preset grouping rule, and the battery cells whose capacity characteristic information is within the same preset comparison range are grouped into the same battery subgroup.

4. The capacity balancing management method of a battery management system according to claim 1, characterized in that: The obtaining of subgroup data of the battery subgroup, executing a corresponding single balancing strategy or a subgroup balancing strategy to perform balancing operation processing on the battery subgroup according to the subgroup data, and obtaining balancing capacity information of the battery subgroup after balancing processing, includes: Acquire real-time battery data of the battery subgroup, the real-time battery data including real-time voltage data and real-time current data of all the battery cells, and calculate a real-time internal resistance value based on the real-time voltage data and real-time current data; Obtain a historical voltage-charge relationship curve, map the real-time voltage data to the historical voltage-charge relationship curve, and perform charge calculation on the historical voltage-charge relationship curve according to a preset charge algorithm to obtain a corresponding charge estimation value, and perform data correction on the charge estimation value according to a correction algorithm based on the real-time internal resistance value to obtain a real-time charge value; Determine whether the real-time internal resistance value and the real-time charge value meet the preset balancing threshold range, and when either the real-time internal resistance value or the real-time charge value does not meet the balancing threshold range, obtain the corresponding preset single balancing strategy, the single balancing strategy includes the internal resistance balancing strategy and the charge balancing strategy, and perform a single balancing operation on the battery subgroup according to the single balancing strategy, and obtain the balancing capacity information after the single balancing process; When both the real-time internal resistance value and the real-time charge value do not meet the balancing threshold range, the corresponding preset subgroup balancing strategy is obtained, and the overall balancing operation processing is performed on the battery subgroup according to the subgroup balancing strategy, and the balancing capacity information after the overall balancing processing is obtained; Among them, the calculation formula of the charge algorithm includes: Charge estimate = (OCV2-OCV1)*((V-V1) / (V2-V1))+SOC1; OCV1 is the first historical voltage value of the historical voltage-charge relationship curve data point, OCV2 is the second historical voltage value of the historical voltage-charge relationship curve data point, V1 is the first charge-discharge state of the historical voltage-charge relationship curve data point, V2 is the second charge-discharge state of the historical voltage-charge relationship curve data point, V is the real-time voltage value of the real-time battery, and SOC1 is the charge-discharge state corresponding to the historical voltage-charge relationship curve data point; The calculation formula of the correction algorithm includes: Real-time charge value = charge estimation value * (1-α*R); α is the correction coefficient, which indicates the influence of internal resistance on the charge estimation value, and R is the real-time internal resistance value.

5. The capacity balancing management method of a battery management system according to claim 1, characterized in that: The initial grouping configuration optimization of the battery management system is performed according to the target prediction balancing strategy to obtain grouping configuration data, including: According to the target prediction balancing strategy, the initial grouping configuration is simulated and the configuration parameters are adjusted, wherein the adjusted configuration parameters include the number of subgroups, the total capacity range of each subgroup, and the range of the difference in the single cell capacity of the subgroup battery; Perform a simulated initial grouping based on the adjusted initial grouping configuration, obtain simulated capacity data of the simulated battery subgroup, determine whether the simulated capacity data meets the preset capacity health threshold, and when the simulated capacity data does not meet the capacity health threshold, re-adjust the simulated configuration parameters of the initial grouping configuration; when the simulated capacity data meets the capacity health threshold, optimize the configuration parameters of the initial grouping configuration of the battery management system based on the target prediction balancing strategy, and after the optimization is completed, re-acquire the grouping configuration data of the battery management system.

6. A capacity balancing management device for a battery management system, applied to the capacity balancing management method for a battery management system according to any one of claims 1 to 5, characterized in that: The device comprises: An acquisition module, the acquisition module is used to monitor the battery pack in real time through a battery management system and acquire cell monitoring data of each battery cell in the battery pack; An analysis module, the analysis module is used to analyze the capacity characteristic information of each battery cell based on the cell monitoring data, dynamically group the battery cells according to the capacity characteristic information to obtain battery subgroups, and obtain historical subgroup data of the battery subgroups; An execution module, the execution module is used to obtain subgroup data of the battery subgroup, execute a corresponding single balancing strategy or a subgroup balancing strategy according to the subgroup data to perform a balancing operation on the battery subgroup, and obtain balancing capacity information of the battery subgroup after the balancing operation; A processing module, the processing module is used to predict the capacity change trend of the battery cells according to the balanced capacity information, the real-time subgroup data and the historical subgroup data through a prediction model, and generate a target prediction balanced strategy according to the capacity change trend; A control module, wherein the control module is used to optimize the initial group configuration of the battery management system according to the target prediction balancing strategy to obtain group configuration data; The subgroup data includes the status information of each battery cell in the battery subgroup, and the historical subgroup data includes the capacity information and charging and discharging process records of the battery subgroup; The method of predicting the capacity change trend of the battery cells according to the balanced capacity information, the real-time subgroup data and the historical subgroup data through the prediction model, and generating a target prediction and balancing strategy according to the capacity change trend, includes: Generate a corresponding capacity characteristic curve according to the balanced capacity information through the prediction model, generate a simulated change time according to the historical subgroup data and the subgroup data, simulate the change of the capacity characteristic curve within the simulated change time based on the historical subgroup data and the subgroup data, record the simulated data of the capacity characteristic curve during the simulation process, and perform trend analysis on the capacity characteristic curve and the simulated data after the simulation to obtain the capacity change trend; According to the capacity change trend, the battery subgroups are dynamically simulated and grouped to obtain simulation groups, and a balancing operation plan for the corresponding battery subgroup is generated based on the balancing capacity information and the capacity change trend. The balancing operation plan includes a balancing period, a balancing plan and a balancing operation timing. The simulation group and the balancing operation plan are integrated to obtain an initial predicted balancing strategy, and a capacity balancing effect evaluation is performed on the initial predicted balancing strategy; When the capacity balancing effect does not meet the preset effect threshold, the simulation group and the balancing operation plan of the initial prediction balancing strategy are iteratively optimized and adjusted based on the balancing strategy; when the capacity balancing effect meets the preset effect threshold, the corresponding target prediction balancing strategy is output.

7. A capacity balancing management device for a battery management system, characterized in that: include: Memory, used to store programs; The processor is used to execute the program to implement the various steps of the capacity balancing management method of a battery management system as described in any one of claims 1 to 5.

8. A medium, characterized in that Computer instructions are stored, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 5.