Intelligent control method and system based on consistency of energy storage batteries

Abstract

The invention discloses an intelligent control method and system based on energy storage battery consistency, and relates to the technical field of energy storage batteries. Comprising the following steps: acquiring battery monomer charge state difference data of energy storage battery packs with different battery monomer numbers at different constant temperatures and total capacity change data of the energy storage battery packs caused by charge state difference influence, and constructing a first historical data set; constructing an energy storage battery pack total capacity change prediction model based on machine learning; acquiring the real-time temperature of the energy storage battery pack, the number of single batteries and the real-time charge state of each single battery, and predicting the total capacity change data of the energy storage battery pack according to the total capacity change prediction model of the energy storage battery pack; evaluating the predicted total capacity change data of the energy storage battery pack to obtain total capacity influence data of the energy storage battery pack; and judging the total capacity influence grade of the energy storage battery pack according to the total capacity influence data of the energy storage battery pack, and processing the single batteries. The method is used for solving the problem of influence judgment caused by SOC inconsistency of the energy storage battery pack.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage batteries, and more specifically, to an intelligent control method and system based on the consistency of energy storage batteries. Background Art

[0002] Energy storage battery packs are usually composed of multiple single cells. The voltage, capacity, internal resistance and other characteristics of the single cells may vary to a certain extent. Good battery consistency is crucial to the stability and safety of the energy storage system.

[0003] Battery state of charge (SOC) is an important indicator for evaluating battery performance, managing battery life, and optimizing the charging and discharging process. It is widely used in electric vehicles, mobile devices, and renewable energy storage systems. By monitoring SOC in real time, it is possible to effectively prevent overcharging or over-discharging of the battery, ensuring safe and reliable operation of the battery.

[0004] With the rapid development of neural network technology, the ability to process complex data for accurate prediction is constantly improving, and its application in various fields is becoming more and more extensive. The SOC estimation model built based on the extreme learning machine neural network algorithm can estimate the battery SOC more accurately under specific temperature conditions.

[0005] However, at a specific temperature, the degree of SOC inconsistency between energy storage battery cells has a significant impact on the overall performance and life of the energy storage battery pack, and the impact of SOC inconsistency at different temperatures is also different. The impact of a slight SOC inconsistency on the overall energy storage battery pack can be ignored, and a higher SOC inconsistency will have a serious impact on the overall energy storage battery pack; this impact is highly correlated with the temperature when the SOC is inconsistent.

[0006] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an intelligent control method and system based on the consistency of energy storage batteries, which predicts the total capacity change data of the energy storage battery group, evaluates the total capacity change data of the energy storage battery group to generate the total capacity impact data of the energy storage battery group, and determines the total capacity impact level of the energy storage battery group, so as to solve the problem of determining the impact caused by the inconsistent SOC of the energy storage battery group.

[0008] To achieve the above object, the present invention provides the following technical solutions: An intelligent control method and system based on the consistency of energy storage batteries include the following steps: obtaining battery cell charge state difference data of energy storage battery groups with different numbers of battery cells at different constant temperatures, and total capacity change data of the energy storage battery group caused by the charge state difference, to construct a first historical data set; using the first historical data set as a training set, to construct a total capacity change prediction model of the energy storage battery group based on machine learning; obtaining the real-time temperature of the energy storage battery group, the number of battery cells and the real-time charge state of each battery cell, and predicting the total capacity change data of the energy storage battery group according to the total capacity change prediction model of the energy storage battery group; evaluating the predicted total capacity change data of the energy storage battery group according to a preset total capacity change data evaluation formula, to obtain the total capacity impact data of the energy storage battery group; determining the total capacity impact level of the energy storage battery group according to the total capacity impact data of the energy storage battery group, and processing the battery cells.

[0009] In a preferred embodiment, the battery cell state of charge difference data includes the battery cell state of charge deviation; the energy storage battery group total capacity change data includes the energy storage battery group total capacity change value; the energy storage battery group total capacity influence data includes the energy storage battery group total capacity influence coefficient.

[0010] In a preferred embodiment, the battery cell state of charge difference data of the energy storage battery group with different numbers of battery cells at different constant temperatures, and the total capacity change data of the energy storage battery group caused by the difference in state of charge, are obtained by a specific acquisition method: determine a number N of battery cells in a preset value range to select battery cells to form an energy storage battery group, and before operating the energy storage battery group, obtain the total capacity of the first energy storage battery group; place the energy storage battery group in a constant temperature environment to obtain the state of charge of each battery cell; obtain the state of charge deviation of the battery cell according to a preset deviation calculation formula; make the energy storage battery group undergo a complete charge / discharge process, obtain the total capacity of the second energy storage battery group, and calculate the total capacity change value of the energy storage battery group according to the total capacities of the first and second energy storage battery groups; change the temperature of the constant temperature environment, repeat the above steps, and obtain the state of charge deviation of the battery cell at different constant temperatures and the corresponding total capacity change value of the energy storage battery group; change the number of battery cells N, repeat the above steps, and obtain the state of charge deviation of the battery cell at different numbers and different constant temperatures and the corresponding total capacity change value of the energy storage battery group.

[0011] In a preferred embodiment, the method of determining the total capacity influence level of the energy storage battery group and processing the battery cell according to the total capacity influence data of the energy storage battery group is specifically as follows: evaluating the total capacity change data of the energy storage battery group in the first historical data set according to a preset total capacity change data evaluation formula to obtain the total capacity influence coefficient of the historical energy storage battery group; pre-processing the value range of the total capacity influence coefficient of the historical energy storage battery group, and dividing it into no less than two sub-intervals according to a preset division standard; presetting the total capacity influence level of the energy storage battery group, and one total capacity influence level of the energy storage battery group corresponds to one sub-interval of the total capacity influence coefficient of the energy storage battery group; determining the total capacity influence level of the energy storage battery group according to the total capacity influence coefficient of the energy storage battery group obtained by real-time evaluation; and taking measures to process the battery cell according to the total capacity influence level of the energy storage battery group.

[0012] In a preferred embodiment, the battery cell state of charge deviation is specifically obtained by: obtaining the average state of charge of the energy storage battery pack according to the state of charge of each battery cell; obtaining the state of charge deviation of each battery cell according to the average state of charge; assigning weights to each battery cell according to its position in the energy storage battery pack, aggregating the state of charge deviations of all battery cells, and obtaining the battery cell state of charge deviation.

[0013] In a preferred embodiment, the weight is assigned according to the position of each battery cell in the energy storage battery pack, and the specific method for obtaining the weight is: obtaining the number of battery cells between the first target battery cell and one end of the energy storage battery pack; charging / discharging the energy storage battery pack until the charge state change of the battery cell closest to the other end of the energy storage battery pack is C, and then stopping charging / discharging; obtaining the ratio of the charge state change of the first target battery cell to the charge state change of all battery cells as the position weight of the first target battery cell.

[0014] The system of the intelligent control method based on the consistency of energy storage batteries comprises a model construction module, an information collection and prediction module, a data evaluation module and a judgment processing module, and there are connections between the modules; the model construction module is used to obtain the battery cell charge state difference data of the energy storage battery group with different battery cell numbers at different constant temperatures, and the total capacity change data of the energy storage battery group caused by the charge state difference, construct a first historical data set, use the first historical data set as a training set, and construct a total capacity change prediction model of the energy storage battery group based on machine learning; the information collection and prediction module is used to obtain the real-time temperature of the energy storage battery group, the number of battery cells and the real-time charge state of each battery cell, and predict the total capacity change data of the energy storage battery group according to the total capacity change prediction model of the energy storage battery group; the data evaluation module is used to evaluate the predicted total capacity change data of the energy storage battery group according to a preset total capacity change data evaluation formula, and obtain the total capacity impact data of the energy storage battery group; the judgment processing module is used to determine the total capacity impact level of the energy storage battery group according to the total capacity impact data of the energy storage battery group, and process the battery cells.

[0015] The technical effects and advantages of the intelligent control method and system based on the consistency of energy storage batteries of the present invention are as follows: The present invention trains a model based on the difference data of the state of charge of the battery cells of the energy storage battery pack with different numbers of battery cells at different constant temperatures and the impact caused by the difference in advance, predicts the total capacity change data of the energy storage battery pack in real time, evaluates the total capacity change data of the energy storage battery pack to generate the total capacity impact data of the energy storage battery pack, determines the total capacity impact level of the energy storage battery pack, and takes targeted measures according to the impact level, thereby determining the impact caused by the inconsistent state of charge of the battery cells in the energy storage battery pack before the overall capacity of the energy storage battery pack decreases, so as to take measures in time. In addition, by introducing position weights, the influence of the position of the battery cell on the difference data of the state of charge of the battery cell is considered, so that the deviation of the state of charge of the battery cell obtained according to the state of charge deviation of the battery cell is more accurately associated with the total capacity change value of the energy storage battery pack, thereby realizing a more accurate prediction of the total capacity change value of the energy storage battery pack by the prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the intelligent control method based on the consistency of energy storage batteries of the present invention.

[0017] Figure 2 It is a schematic diagram of the system structure of the intelligent control method based on the consistency of energy storage batteries of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1, Figure 1 The present invention provides an intelligent control method based on the consistency of energy storage batteries, comprising the following steps: Acquire charge state difference data of battery cells of energy storage battery groups with different numbers of battery cells at different constant temperatures, and total capacity change data of the energy storage battery groups caused by the charge state difference, to construct a first historical data set; The first historical data set is used as a training set, and a total capacity change prediction model of the energy storage battery group is constructed based on machine learning; Obtain the real-time temperature of the energy storage battery pack, the number of battery cells and the real-time state of charge of each battery cell, and predict the total capacity change data of the energy storage battery pack based on the total capacity change prediction model of the energy storage battery pack; Evaluate the predicted total capacity change data of the energy storage battery group according to a preset total capacity change data evaluation formula to obtain the total capacity impact data of the energy storage battery group; According to the total capacity impact data of the energy storage battery group, determine the total capacity impact level of the energy storage battery group and process the battery cells.

[0020] The battery state of charge estimation model built based on the extreme learning machine neural network algorithm mainly predicts the battery SOC quickly through efficient training methods. The extreme learning machine neural network (ELM) is a single hidden layer feedforward neural network. Its characteristics are that the connection weights and biases between the input layer and the hidden layer are randomly generated and fixed, and the training is completed only by optimizing the weights of the output layer. Compared with traditional neural network training methods, ELM significantly improves computational efficiency and training speed. In SOC estimation, the ELM model can fully exploit the nonlinear characteristics of the battery, adapt to the dynamic changes of the battery under different working conditions, and has good robustness to noise and data uncertainty. The ELM model is particularly suitable for efficient and accurate SOC estimation in real-time battery management systems due to its low computational complexity, fast training speed, strong generalization ability and high estimation accuracy.

[0021] In this embodiment, the battery cell state of charge difference data includes a battery cell state of charge deviation; The energy storage battery group total capacity change data includes the energy storage battery group total capacity change value; The energy storage battery group total capacity impact data includes the energy storage battery group total capacity impact coefficient.

[0022] In this embodiment, the method for obtaining the charge state difference data of the battery cells of the energy storage battery pack with different numbers of battery cells at different constant temperatures, and the total capacity change data of the energy storage battery pack caused by the charge state difference, is as follows: Determine a number N of battery cells selected from a preset number value range to form an energy storage battery group, and obtain a total capacity of the first energy storage battery group before operating the energy storage battery group; The energy storage battery pack is placed in a constant temperature environment to obtain the state of charge of each battery cell; Obtaining the state of charge deviation of the battery cell according to a preset deviation calculation formula; Allow the energy storage battery group to undergo a complete charge / discharge process, obtain the total capacity of the second energy storage battery group, and calculate the total capacity change value of the energy storage battery group according to the total capacities of the first and second energy storage battery groups; Changing the temperature of the constant temperature environment, repeating the above steps, and obtaining the charge state deviation of the battery cells and the corresponding total capacity change value of the energy storage battery pack at different constant temperatures; The number of battery cells N is changed, and the above steps are repeated to obtain the state of charge deviation of battery cells with different numbers and different constant temperatures and the corresponding total capacity change value of the energy storage battery pack.

[0023] In this embodiment, the preset quantity value range is:

[0024] In the formula, 2 is the lower limit of the preset range of the number of battery cells, and the maximum number of battery cells n that the energy storage battery pack can accommodate is the upper limit of the preset range of the number of battery cells.

[0025] In this embodiment, the battery cell charge state deviation is specifically obtained by: According to the state of charge of each battery cell, the average state of charge of the energy storage battery pack is obtained; Obtaining a state of charge deviation of each battery cell according to the average state of charge; A weight is assigned to each battery cell according to its position in the energy storage battery pack, and the state of charge deviation of all battery cells is aggregated to obtain the state of charge deviation of the battery cell.

[0026] In this embodiment, the weight is assigned according to the position of each battery cell in the energy storage battery pack, and the specific method for obtaining the weight is: Obtaining the number of battery cells spaced between a first target battery cell and one end of an energy storage battery pack; The energy storage battery pack is charged / discharged until the charge state of the battery cell closest to the other end of the energy storage battery pack changes by C, and then the charging / discharging is stopped; The ratio of the charge state change of the first target battery cell to the charge state change of all battery cells is obtained as the position weight of the first target battery cell.

[0027] It should be noted that the change C of the state of charge of the battery cell is much smaller than the total capacity of the battery cell.

[0028] In this embodiment, the preset deviation calculation formula is specifically:

[0029] In the formula, is the charge state deviation of the battery cell, N is the number of battery cells in the energy storage battery pack, is the position weight of the ith battery cell, is the state of charge of the ith battery cell, is the average state of charge of N battery cells.

[0030] In this embodiment, the total capacity impact level of the energy storage battery group is determined according to the total capacity impact data of the energy storage battery group, and the battery cells are processed, specifically: Evaluate the total capacity change data of the energy storage battery group in the first historical data set according to a preset total capacity change data evaluation formula to obtain a total capacity influence coefficient of the historical energy storage battery group; Preprocessing the value range of the total capacity influence coefficient of the historical energy storage battery group, and dividing it into no less than two sub-intervals according to a preset division standard; The total capacity impact level of the energy storage battery group is preset, and one total capacity impact level of the energy storage battery group corresponds to one total capacity impact coefficient sub-interval of the energy storage battery group; Determine the total capacity impact level of the energy storage battery group according to the total capacity impact coefficient of the energy storage battery group obtained by real-time evaluation; Take measures to handle the battery cells according to the impact level of the total capacity of the energy storage battery pack.

[0031] In this embodiment, the value range of the total capacity influence coefficient of the historical energy storage battery group is divided into three sub-intervals according to the preset division standard, namely , and ; The three energy storage battery group total capacity impact levels are preset to be weak impact, strong impact and severe impact, and the three energy storage battery group total capacity impact levels correspond to the three sub-intervals; According to the total capacity impact coefficient of the energy storage battery group obtained by real-time evaluation, the total capacity impact level of the energy storage battery group is determined. If the value of the total capacity impact coefficient of the energy storage battery group is within the sub-interval , then the corresponding total capacity impact level of the energy storage battery group is considered to be weak impact; According to the impact level of the total capacity of the energy storage battery pack, measures are taken to process the battery cells; if the impact level of the total capacity of the energy storage battery pack is determined to be a weak impact, the charging / discharging process of the energy storage battery pack is not intervened; if the impact level of the total capacity of the energy storage battery pack is determined to be a strong impact, the battery cell corresponding to the maximum value after the position weight is assigned to the battery cell state of charge deviation is replaced; if the impact level of the total capacity of the energy storage battery pack is determined to be a serious impact, the charging / discharging process of the energy storage battery pack is immediately stopped and an alarm is issued.

[0032] In this embodiment, the preset total capacity change data evaluation formula is specifically calculated as follows:

[0033] In the formula, is the total capacity influence coefficient of the energy storage battery pack, is the total capacity change of the energy storage battery pack, is the total capacity of the first energy storage battery group.

[0034] This embodiment trains a model based on the difference data of the state of charge of the battery cells of the energy storage battery pack with different numbers of battery cells at different constant temperatures and the impact caused by the difference in advance, predicts the total capacity change data of the energy storage battery pack in real time, evaluates the total capacity change data of the energy storage battery pack to generate the total capacity impact data of the energy storage battery pack, determines the impact level of the total capacity of the energy storage battery pack, and takes targeted measures according to the impact level, thereby determining the impact caused by the inconsistent state of charge of the battery cells in the energy storage battery pack before the overall capacity of the energy storage battery pack decreases, so as to take timely measures. In addition, by introducing position weights, the influence of the position of the battery cell on the difference data of the state of charge of the battery cell is considered, so that the deviation of the state of charge of the battery cell obtained according to the state of charge deviation of the battery cell is more accurately associated with the total capacity change value of the energy storage battery pack, thereby realizing a more accurate prediction of the total capacity change value of the energy storage battery pack by the prediction model.

[0035] Embodiment 2, Figure 2 A system of an intelligent control method based on the consistency of energy storage batteries in the present invention is provided, comprising a model building module, an information collection and prediction module, a data evaluation module and a determination processing module, and there are connections between the modules; A model building module is used to obtain the charge state difference data of battery cells of energy storage battery packs with different numbers of battery cells at different constant temperatures, and the total capacity change data of the energy storage battery pack caused by the charge state difference, build a first historical data set, use the first historical data set as a training set, and build a total capacity change prediction model of the energy storage battery pack based on machine learning; The information collection and prediction module is used to obtain the real-time temperature of the energy storage battery pack, the number of battery cells and the real-time state of charge of each battery cell, and predict the total capacity change data of the energy storage battery pack according to the total capacity change prediction model of the energy storage battery pack; A data evaluation module is used to evaluate the predicted total capacity change data of the energy storage battery group according to a preset total capacity change data evaluation formula to obtain the total capacity impact data of the energy storage battery group; The determination processing module is used to determine the total capacity impact level of the energy storage battery group according to the total capacity impact data of the energy storage battery group and process the battery cells.

[0036] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0037] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0038] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0039] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0040] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0041] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent control method and system based on the consistency of energy storage batteries, characterized in that: The following steps are involved: Acquire charge state difference data of battery cells of energy storage battery groups with different numbers of battery cells at different constant temperatures, and total capacity change data of the energy storage battery groups caused by the charge state difference, to construct a first historical data set; The first historical data set is used as a training set, and a total capacity change prediction model of the energy storage battery group is constructed based on machine learning; Obtain the real-time temperature of the energy storage battery pack, the number of battery cells and the real-time state of charge of each battery cell, and predict the total capacity change data of the energy storage battery pack based on the total capacity change prediction model of the energy storage battery pack; Evaluate the predicted total capacity change data of the energy storage battery group according to a preset total capacity change data evaluation formula to obtain the total capacity impact data of the energy storage battery group; According to the total capacity impact data of the energy storage battery group, determine the total capacity impact level of the energy storage battery group and process the battery cells.

2. The intelligent control method and system based on energy storage battery consistency according to claim 1, characterized in that: The battery cell state of charge difference data includes a battery cell state of charge deviation; The energy storage battery group total capacity change data includes the energy storage battery group total capacity change value; The energy storage battery group total capacity impact data includes the energy storage battery group total capacity impact coefficient.

3. The intelligent control method and system based on energy storage battery consistency according to claim 2 is characterized in that: The specific acquisition method for obtaining the charge state difference data of the battery cells of the energy storage battery pack with different numbers of battery cells at different constant temperatures, and the total capacity change data of the energy storage battery pack caused by the charge state difference is as follows: Determine a number N of battery cells selected from a preset number value range to form an energy storage battery group, and obtain a total capacity of the first energy storage battery group before operating the energy storage battery group; The energy storage battery pack is placed in a constant temperature environment to obtain the state of charge of each battery cell; Obtaining the state of charge deviation of the battery cell according to a preset deviation calculation formula; Allow the energy storage battery group to undergo a complete charge / discharge process, obtain the total capacity of the second energy storage battery group, and calculate the total capacity change value of the energy storage battery group according to the total capacities of the first and second energy storage battery groups; Changing the temperature of the constant temperature environment, repeating the above steps, and obtaining the charge state deviation of the battery cells and the corresponding total capacity change value of the energy storage battery pack at different constant temperatures; The number of battery cells N is changed, and the above steps are repeated to obtain the state of charge deviation of battery cells with different numbers and different constant temperatures and the corresponding total capacity change value of the energy storage battery pack.

4. The intelligent control method and system based on energy storage battery consistency according to claim 3 is characterized in that: The total capacity impact level of the energy storage battery group is determined according to the total capacity impact data of the energy storage battery group, and the battery cells are processed, specifically: Evaluate the total capacity change data of the energy storage battery group in the first historical data set according to a preset total capacity change data evaluation formula to obtain a total capacity influence coefficient of the historical energy storage battery group; Preprocessing the value range of the total capacity influence coefficient of the historical energy storage battery group, and dividing it into no less than two sub-intervals according to a preset division standard; The total capacity impact level of the energy storage battery group is preset, and one total capacity impact level of the energy storage battery group corresponds to one total capacity impact coefficient sub-interval of the energy storage battery group; Determine the total capacity impact level of the energy storage battery group according to the total capacity impact coefficient of the energy storage battery group obtained by real-time evaluation; According to the impact level of the total capacity of the energy storage battery pack, measures are taken to handle the battery cells.

5. The intelligent control method and system based on energy storage battery consistency according to claim 4 is characterized in that: The specific method for obtaining the battery cell charge state deviation is as follows: According to the state of charge of each battery cell, the average state of charge of the energy storage battery pack is obtained; Obtaining a state of charge deviation of each battery cell according to the average state of charge; A weight is assigned to each battery cell according to its position in the energy storage battery pack, and the state of charge deviation of all battery cells is aggregated to obtain the state of charge deviation of the battery cell.

6. The intelligent control method and system based on energy storage battery consistency according to claim 5 is characterized in that: The weight is assigned according to the position of each battery cell in the energy storage battery pack, and the specific method for obtaining the weight is: Obtaining the number of battery cells spaced between a first target battery cell and one end of an energy storage battery pack; The energy storage battery pack is charged / discharged until the charge state of the battery cell closest to the other end of the energy storage battery pack changes by C, and then the charging / discharging is stopped; The ratio of the charge state change of the first target battery cell to the charge state change of all battery cells is obtained as the position weight of the first target battery cell.

7. The intelligent control method and system based on energy storage battery consistency according to claim 6 is characterized in that: The preset deviation calculation formula is specifically: In the formula, is the charge state deviation of the battery cell, N is the number of battery cells in the energy storage battery pack, is the position weight of the ith battery cell, is the state of charge of the ith battery cell, is the average state of charge of N battery cells.

8. The intelligent control method and system based on energy storage battery consistency according to claim 7, characterized in that: The preset total capacity change data evaluation formula is specifically calculated as follows: In the formula, is the total capacity influence coefficient of the energy storage battery pack, is the total capacity change of the energy storage battery pack, is the total capacity of the first energy storage battery group.

9. The system of the intelligent control method based on the consistency of energy storage batteries according to claims 1-8, characterized in that: It includes a model building module, an information collection and prediction module, a data evaluation module and a judgment processing module, and there are connections between the modules; A model building module is used to obtain the charge state difference data of battery cells of energy storage battery packs with different numbers of battery cells at different constant temperatures, and the total capacity change data of the energy storage battery pack caused by the charge state difference, build a first historical data set, use the first historical data set as a training set, and build a total capacity change prediction model of the energy storage battery pack based on machine learning; The information collection and prediction module is used to obtain the real-time temperature of the energy storage battery pack, the number of battery cells and the real-time state of charge of each battery cell, and predict the total capacity change data of the energy storage battery pack according to the total capacity change prediction model of the energy storage battery pack; A data evaluation module is used to evaluate the predicted total capacity change data of the energy storage battery group according to a preset total capacity change data evaluation formula to obtain the total capacity impact data of the energy storage battery group; The determination processing module is used to determine the total capacity impact level of the energy storage battery group according to the total capacity impact data of the energy storage battery group and process the battery cells.

Images