Method and device for acquiring state of charge of battery

The battery curve is corrected through the pre-trained target neural network model, which solves the problem that traditional SOC calculation methods are difficult to accurately estimate battery capacity, improves the accuracy and efficiency of battery state of charge estimation, and is suitable for a variety of battery types and scenarios.

CN118914858APending Publication Date: 2024-11-08GOODWE TECHNOLOGIES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410998015.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Traditional SOC calculation methods are difficult to accurately estimate the real battery capacity, resulting in inaccurate battery display and SOC jump.

Method used

The pre-trained target neural network model predicts dynamic and static SOC-OCV curves, and establishes a functional relationship between the battery curve and the number of cycles, corrects the SOC-OCV curve in actual use, and obtains the current state of charge of the battery.

Benefits of technology

It improves the efficiency and accuracy of SOC estimation, is suitable for different types of batteries and usage scenarios, is versatile and scalable, avoids errors caused by inaccurate reference capacity, and enhances the reliability and stability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118914858A_ABST
    Figure CN118914858A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of power batteries, in particular to a method and a device for acquiring the state of charge of a battery. The method comprises the following steps: under a target cycle index of a target battery, firstly obtaining actual second dynamic and second static OCV-SOV curves in each time period; correcting the SOC-OCV curve according to the function relationship between the battery curve and the cycle index to generate a corrected third dynamic SOC-OCV curve and a corrected third static SOC-OCV curve; performing mapping processing on the third dynamic SOC-OCV curve based on a voltage interval corresponding to the second dynamic SOC-OCV curve to obtain the actual capacity C2 of the current battery cell; and estimating the state of charge of the battery based on the third static SOC-OCV curve and the actual capacity C2 of the current battery cell to obtain the current state of charge of the battery. According to the invention, the efficiency and precision of SOC estimation are improved, the electric quantity display is more precise, and the condition of SOC jump is avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power batteries, and in particular to a method and device for acquiring a battery state of charge. Background Art

[0002] Rechargeable batteries such as lithium-ion batteries and sodium-ion batteries are widely used in battery systems such as electric vehicles and hybrid vehicles, which require high energy density, long life and stable performance.

[0003] As the battery is used and the charge and discharge cycles increase, a series of chemical reactions and changes in material structure will occur inside the battery, which will affect the performance of the battery. Among them, one of the most obvious phenomena is the attenuation of battery capacity, that is, the amount of electricity that the battery can store gradually decreases. At the same time, the internal resistance of the battery may also increase, resulting in reduced efficiency of the battery during the charge and discharge process. SOC (State of Charge) is a parameter that describes the ratio of the remaining battery power to the rated capacity. Traditional SOC calculation methods do rely on multiple parameters such as battery voltage, current, temperature, and corresponding algorithms. However, due to the influence of complex factors such as battery aging, temperature changes, self-discharge, and increased internal resistance, these traditional SOC calculation methods are often difficult to accurately estimate the true capacity of the battery.

[0004] Therefore, in actual applications, inaccurate power display and SOC jumps may occur. Summary of the invention

[0005] In view of this, the present invention provides a method and device for obtaining the state of charge of a battery to solve the problem that traditional SOC calculation methods are often difficult to accurately estimate the actual capacity of the battery, and in actual applications, inaccurate power display and SOC jumps may occur.

[0006] In a first aspect, the present invention provides a method for obtaining a battery state of charge, the method comprising:

[0007] Predicting the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions through the pre-trained target neural network model, and establishing a functional relationship between the battery curve and the number of cycles based on the prediction results;

[0008] Under the target cycle number of the target battery, obtain the actual second dynamic SOC-OCV curve and the second static OCV-SOV curve in each time period;

[0009] According to the functional relationship between the battery curve and the number of cycles, the second dynamic SOC-OCV curve and the second static OCV-SOV curve are corrected, and a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve are generated;

[0010] Mapping the third dynamic SOC-OCV curve based on the voltage interval corresponding to the second dynamic SOC-OCV curve to obtain the current actual capacity C2 of the target battery cell;

[0011] A battery state of charge estimation process is performed based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to obtain the current battery state of charge of the target battery.

[0012] The above scheme predicts the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions based on the pre-trained target neural network model, and establishes a functional relationship between the battery curve and the number of cycles. In actual use, the second dynamic SOC-OCV curve and the second static OCV-SOV curve under the target number of cycles are first obtained through the initial SOC algorithm, and then the second dynamic SOC-OCV curve and the second static OCV-SOV curve are corrected through the established functional relationship between the battery curve and the number of cycles to obtain a complete charge and discharge curve that is closer to the actual use situation. The current battery state of charge of the target battery can be obtained through the complete charge and discharge curve. The present invention takes into account factors such as battery aging and temperature changes, and uses the predictive ability of the target neural network model to correct the curve. The corrected curve can be quickly generated, which improves the efficiency and accuracy of SOC estimation. It is suitable for different types of batteries and different usage scenarios, and has strong versatility and scalability.

[0013] In an optional embodiment, before predicting the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions by using the pre-trained target neural network model, the method further includes:

[0014] The fourth dynamic SOC-OCV curve and the fourth static SOC-OCV curve under different conditions obtained by testing in the initial state are input into the target neural network model for training, and the trained target neural network model is obtained.

[0015] The above scheme can train an accurate target neural network model based on the test data of the initial state, and use the model to correct the battery curve in actual use, thereby improving the accuracy and efficiency of battery state of charge estimation.

[0016] In an optional embodiment, the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions are predicted by the pre-trained target neural network model, and a functional relationship between the battery curve and the cycle number is established based on the prediction result, including:

[0017] The first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions are predicted by the pre-trained target neural network model, and a first functional relationship between the first dynamic SOC-OCV curve and the temperature and the number of cycles is established, and a second functional relationship between the first static SOC-OCV curve and the temperature and the number of cycles is established.

[0018] The above solution can significantly improve the performance of the battery management system, reduce maintenance costs, and enhance user experience by training the target neural network model to predict the battery curve and establish a functional relationship with temperature and cycle number.

[0019] In an optional implementation, the obtaining of the actual second dynamic SOC-OCV curve and the second static OCV-SOV curve in each time period includes:

[0020] Accumulating the local dynamic SOC-OCV curves in each time period obtained based on the initial SOC algorithm to generate the second dynamic SOC-OCV curve;

[0021] The current open circuit voltage OCV of the target battery at the target cycle number is obtained, and based on the current open circuit voltage OCV, the corresponding initial battery state of charge is extracted from the fourth static SOC-OCV curve to obtain the second static OCV-SOV curve.

[0022] The above scheme can generate a complete second dynamic SOC-OCV curve by accumulating the local dynamic SOC-OCV curves in each time period obtained based on the initial SOC algorithm, and can integrate the data of each time period to form a more comprehensive and accurate description of the battery charging and discharging behavior, thereby improving the accuracy of SOC estimation. In addition, by directly measuring the current open circuit voltage OCV of the target battery at the target number of cycles, and extracting the corresponding initial battery state of charge from the known fourth static SOC-OCV curve based on the OCV, an accurate first static OCV-SOV curve can be obtained, avoiding complex calculation or estimation processes, ensuring the accuracy of the static curve, and providing a reliable basis for subsequent SOC estimation.

[0023] In an optional embodiment, the second dynamic SOC-OCV curve and the second static OCV-SOV curve are corrected according to the functional relationship between the battery curve and the number of cycles, and a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve are generated, including:

[0024] According to the first functional relationship, the second dynamic SOC-OCV curve is corrected, and a corrected third dynamic SOC-OCV curve is generated;

[0025] The first static OCV-SOV curve is corrected according to the second functional relationship, and a corrected third static SOC-OCV curve is generated.

[0026] The above scheme can accurately correct the second dynamic SOC-OCV curve and the second static OCV-SOV curve actually measured by utilizing the functional relationship between the battery curve and the number of cycles. It takes into account the changes in battery performance during the cycle use process, so as to more accurately reflect the current actual state of the battery. The corrected third dynamic SOC-OCV curve and the third static SOC-OCV curve will more accurately guide the estimation of the battery state of charge (SOC) and improve the estimation accuracy.

[0027] In an optional implementation, the step of correcting the second dynamic SOC-OCV curve according to the first functional relationship and generating a corrected third dynamic SOC-OCV curve includes:

[0028] Obtain the charge and discharge data for each time period currently captured;

[0029] generating a fifth dynamic SOC-OCV curve according to the charge and discharge data through the first functional relationship;

[0030] The second dynamic SOC-OCV curve is compared and corrected based on the fifth dynamic SOC-OCV curve to obtain a corrected third dynamic SOC-OCV curve.

[0031] The above solution corrects the second dynamic SOC-OCV curve according to the first functional relationship, thereby improving the accuracy of the dynamic SOC-OCV curve and improving the reliability and stability of the system.

[0032] In an optional implementation, the first static OCV-SOV curve is corrected according to the second functional relationship, and a corrected third static SOC-OCV curve is generated, including:

[0033] Obtain the charge and discharge data for each time period currently captured;

[0034] generating a fifth static SOC-OCV curve according to the charge and discharge data by using the second functional relationship;

[0035] The first static OCV-SOV curve is compared and corrected based on the fifth static SOC-OCV curve to obtain a corrected third static SOC-OCV curve.

[0036] The above solution corrects the first static OCV-SOV curve according to the second functional relationship, improves the accuracy of the static SOC-OCV curve, optimizes the battery state estimation result, and enhances the reliability and stability of the system.

[0037] In an optional implementation, mapping the third dynamic SOC-OCV curve based on the voltage interval corresponding to the second dynamic SOC-OCV curve to obtain the current actual cell capacity C2 of the target battery includes:

[0038] The voltage interval corresponding to the second dynamic SOC-OCV curve is mapped to the SOC interval corresponding to the third dynamic SOC-OCV curve to obtain the current actual capacity C2 of the battery cell of the target battery.

[0039] The above scheme maps the third dynamic SOC-OCV curve based on the voltage range corresponding to the second dynamic SOC-OCV curve, thereby improving the accuracy of estimating the actual capacity of the battery cell.

[0040] In an optional implementation, the performing battery state of charge estimation processing based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to obtain the current battery state of charge of the target battery includes:

[0041] Performing a covering and replacing process on the initial reference capacity of the initial SOC algorithm by using the current actual capacity C2 of the battery cell to obtain a final reference capacity;

[0042] Performing secondary coverage replacement processing on the fourth static SOC-OCV curve by using the third static SOC-OCV curve, and obtaining a secondary coverage result;

[0043] Based on the secondary coverage result and the final reference capacity, correcting the initial SOC algorithm to generate a corrected SOC algorithm;

[0044] A battery state of charge estimation process is performed based on the corrected SOC algorithm to obtain a current battery state of charge of the target battery.

[0045] The above scheme replaces the initial reference capacity of the initial SOC algorithm with the actual capacity C2 of the current battery cell, ensuring that the reference capacity used by the SOC algorithm is consistent with the actual battery cell capacity, thereby avoiding the SOC estimation error caused by inaccurate reference capacity, and using the third static SOC-OCV curve to perform a secondary replacement on the fourth static SOC-OCV curve, a SOC-OCV relationship curve that is more in line with the characteristics of the current battery cell can be obtained, effectively improving the accuracy and adaptability of the SOC estimation.

[0046] In a second aspect, the present invention provides a device for obtaining a battery state of charge, the device comprising:

[0047] A functional relationship establishment module, used to predict the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions through a pre-trained target neural network model, and establish a functional relationship between the battery curve and the number of cycles based on the prediction results;

[0048] A first curve acquisition module, used for acquiring an actual second dynamic SOC-OCV curve and a second static OCV-SOV curve in each time period under a target cycle number of a target battery;

[0049] A second curve acquisition module, used for correcting the second dynamic SOC-OCV curve and the second static OCV-SOV curve according to the functional relationship between the battery curve and the number of cycles, and generating a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve;

[0050] A current cell actual capacity C2 module, configured to map the third dynamic SOC-OCV curve based on the voltage interval corresponding to the second dynamic SOC-OCV curve, to obtain the current cell actual capacity C2 of the target battery;

[0051] The current battery state of charge acquisition module is used to perform battery state of charge estimation processing based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to obtain the current battery state of charge of the target battery.

[0052] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes a method for obtaining a battery charge state according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute a method for obtaining a battery state of charge according to the first aspect or any corresponding embodiment thereof.

[0054] In a fifth aspect, the present invention provides a computer program product, including computer instructions, where the computer instructions are used to enable a computer to execute a method for obtaining a battery state of charge according to the first aspect or any corresponding embodiment thereof.

[0055] The technical solution provided by the present invention may include the following beneficial effects:

[0056] The present invention predicts the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions based on the pre-trained target neural network model, and establishes a functional relationship between the battery curve and the number of cycles. In actual use, the second dynamic SOC-OCV curve and the second static OCV-SOV curve under the target number of cycles are first obtained through the initial SOC algorithm, and then the second dynamic SOC-OCV curve and the second static OCV-SOV curve are corrected through the established functional relationship between the battery curve and the number of cycles to obtain a complete charge and discharge curve that is closer to the actual use situation. The current battery charge state of the target battery can be obtained through the complete charge and discharge curve. The present invention takes into account factors such as battery aging and temperature changes, and uses the prediction ability of the target neural network model to correct the curve, which can quickly generate a corrected curve, improve the efficiency and accuracy of SOC estimation, and is suitable for different types of batteries and different usage scenarios, with strong versatility and scalability.

[0057] In addition, the present invention can generate a complete second dynamic SOC-OCV curve by accumulating the local dynamic SOC-OCV curves in each time period obtained based on the initial SOC algorithm, and can integrate the data of each time period to form a more comprehensive and accurate description of the battery charging and discharging behavior, thereby improving the accuracy of SOC estimation. In addition, by directly measuring the current open circuit voltage OCV of the target battery at the target number of cycles, and extracting the corresponding initial battery state of charge from the known fourth static SOC-OCV curve based on the OCV, an accurate first static OCV-SOV curve can be obtained, avoiding complex calculation or estimation processes, ensuring the accuracy of the static curve, and providing a reliable basis for subsequent SOC estimation.

[0058] Furthermore, the present invention replaces the initial reference capacity of the initial SOC algorithm with the current actual capacity C2 of the battery cell, thereby ensuring that the reference capacity used by the SOC algorithm is consistent with the actual battery cell capacity, thereby avoiding the SOC estimation error caused by inaccurate reference capacity, and using the third static SOC-OCV curve to perform a secondary replacement of the fourth static SOC-OCV curve, it is possible to obtain a SOC-OCV relationship curve that is more in line with the current battery cell characteristics, thereby effectively improving the accuracy and adaptability of SOC estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 is a flow chart of a method for obtaining a battery state of charge according to an embodiment of the present invention;

[0061] Figure 2 is a flow chart of another method for obtaining a battery state of charge according to an embodiment of the present invention;

[0062] Figure 3 is a flow chart of another method for obtaining a battery state of charge according to an embodiment of the present invention;

[0063] Figure 4 is a schematic diagram of a second dynamic SOC-OCV curve according to an embodiment of the present invention;

[0064] Figure 5 is a schematic diagram of a third dynamic SOC-OCV curve according to an embodiment of the present invention;

[0065] Figure 6 is a structural block diagram of a device for acquiring a battery state of charge according to an embodiment of the present invention;

[0066] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0068] According to an embodiment of the present invention, an embodiment of a method for obtaining a battery state of charge is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0069] In this embodiment, a method for obtaining a battery state of charge is provided. Figure 1 is a flow chart of a method for obtaining a battery state of charge according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0070] Step S101, predicting a first dynamic SOC-OCV curve and a first static SOC-OCV curve under different conditions through a pre-trained target neural network model, and establishing a functional relationship between the battery curve and the number of cycles based on the prediction results.

[0071] Furthermore, this embodiment uses training data (such as SOC-OCV curves of different batteries and different cycle times) to train the target neural network model. After the training is completed, different conditions (such as new temperature, discharge rate and cycle times) can be input into the target neural network to predict the corresponding SOC-OCV curve (i.e., the first dynamic SOC-OCV curve and the first static SOC-OCV curve). In addition to predicting the SOC-OCV curve, this embodiment also analyzes the change trend of the SOC-OCV curve under different cycle times. Based on the results of data analysis, mathematical methods (such as polynomial regression, curve fitting, etc.) are used to establish a functional relationship between the battery curve and the cycle number to obtain the impact of battery aging on the SOC-OCV relationship.

[0072] Step S102 , obtaining the actual second dynamic SOC-OCV curve and the second static OCV-SOV curve in each time period under the target cycle number of the target battery.

[0073] Furthermore, the present embodiment first performs a charge and discharge cycle test on the target battery at a target cycle number of the target battery (the target cycle number may be any cycle number), collects the SOC (battery state of charge) and OCV (open circuit voltage) data of the battery in each time period, and draws a second dynamic SOC-OCV curve. At the same time, the OCV (open circuit voltage) is measured after the battery is left to rest, the corresponding SOC (battery state of charge) is recorded, and a first static OCV-SOV curve is drawn.

[0074] Step S103, according to the functional relationship between the battery curve and the cycle number, the second dynamic SOC-OCV curve and the second static SOC-SOV curve are corrected, and a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve are generated.

[0075] Furthermore, the present embodiment pre-trains a target neural network model, and based on the prediction results of the target neural network model, establishes a functional relationship between the battery curve and the number of cycles, so that the change in battery performance can be predicted based on the number of battery cycles, and the curve can be corrected. The present embodiment takes the second dynamic SOC-OCV curve and the second static OCV-SOV curve as input, and uses the functional relationship to correct the second dynamic SOC-OCV curve and the second static OCV-SOV curve to generate corrected new curves, namely the third dynamic SOC-OCV curve and the third static SOC-OCV curve.

[0076] Step S104 , mapping the third dynamic SOC-OCV curve based on the voltage range corresponding to the second dynamic SOC-OCV curve to obtain the current actual cell capacity C2 of the target battery.

[0077] Furthermore, this embodiment determines each voltage interval from the second dynamic SOC-OCV curve, and maps the third dynamic SOC-OCV curve based on each voltage interval. During the mapping process, the actual capacity C2 of the current battery cell can be estimated based on the charging capacity under the voltage interval and the width of the corresponding SOC interval.

[0078] Step S105 , performing battery state of charge estimation processing based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to obtain the current battery state of charge of the target battery.

[0079] Furthermore, since the actual cell capacity C2 may change with use, this embodiment considers the impact of this change on SOC estimation; and since the third static SOC-OCV curve already contains information about changes in battery performance with the number of cycles, it can be used to estimate the battery state of charge. This embodiment uses the current actual cell capacity C2 as an important parameter, combined with the third static SOC-OCV curve for estimation, to obtain the current battery state of charge.

[0080] In summary, the present invention predicts the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions based on the pre-trained target neural network model, and establishes a functional relationship between the battery curve and the number of cycles. In actual use, the second dynamic SOC-OCV curve and the second static OCV-SOV curve under the target number of cycles are first obtained through the initial SOC algorithm, and then the second dynamic SOC-OCV curve and the second static OCV-SOV curve are corrected through the established functional relationship between the battery curve and the number of cycles to obtain a complete charge and discharge curve that is closer to the actual use situation. The current battery state of charge of the target battery can be obtained through the complete charge and discharge curve. The present invention takes into account factors such as battery aging and temperature changes, and uses the prediction ability of the target neural network model to correct the curve. The corrected curve can be quickly generated, which improves the efficiency and accuracy of SOC estimation. It is suitable for different types of batteries and different usage scenarios, and has strong versatility and scalability.

[0081] In this embodiment, another method for obtaining the battery state of charge is provided. Figure 2 is a flow chart of another method for obtaining the battery state of charge according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0082] Step S201, inputting the fourth dynamic SOC-OCV curve and the fourth static SOC-OCV curve under different conditions obtained by testing in the initial state into the target neural network model for training, and obtaining the trained target neural network model.

[0083] For further information, see Figure 3 A flowchart of another method for acquiring the state of charge of a battery is shown. In this embodiment, the initial data of the target battery is first collected. The initial data includes detailed information such as charge and discharge voltage, capacity, SOC, temperature, number of cycles, charge and discharge current, etc. These initial data can form a fourth dynamic SOC-OCV curve and a fourth static SOC-OCV curve of the target battery under different cycle numbers. The above different conditions include different cycle numbers, different charge and discharge currents, and different temperatures.

[0084] Step S202, predicting a first dynamic SOC-OCV curve and a first static SOC-OCV curve under different conditions through a pre-trained target neural network model, and establishing a functional relationship between the battery curve and the number of cycles based on the prediction results.

[0085] In an optional implementation, step S202 includes:

[0086] The first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions are predicted by the pre-trained target neural network model, and a first functional relationship between the first dynamic SOC-OCV curve and the temperature and the number of cycles is established, and a second functional relationship between the first static SOC-OCV curve and the temperature and the number of cycles is established.

[0087] Furthermore, the neural network model can predict the SOC-OCV curve of the battery at different temperatures, charge and discharge currents and number of cycles by learning historical data. Therefore, this embodiment learns and obtains the first dynamic SOC-OCV curve and the first static SOC-OCV curve at different temperatures, different charge and discharge currents and different number of cycles through the target neural network model, and establishes the functional relationship between the first dynamic SOC-OCV curve and the temperature and number of cycles (i.e., the first functional relationship between the above-mentioned first dynamic SOC-OCV curve and the temperature and number of cycles): f2(SOC-OCV)=f(T, C); and the functional relationship between the first static SOC-OCV curve and the temperature and number of cycles (i.e., the second functional relationship between the above-mentioned first static SOC-OCV curve and the temperature and number of cycles): fb(SOC-OCV)=f(T, C). The target neural network model can choose to use structures such as multi-layer perceptron (MLP), convolutional neural network (CNN) or recurrent neural network (RNN) according to actual conditions.

[0088] Step S203, obtaining the actual second dynamic SOC-OCV curve and the second static OCV-SOV curve in each time period under the target cycle number of the target battery.

[0089] In an optional implementation, step S203 includes:

[0090] Accumulating the local dynamic SOC-OCV curves in each time period obtained based on the initial SOC algorithm to generate the second dynamic SOC-OCV curve;

[0091] The current open circuit voltage OCV of the target battery at the target cycle number is obtained, and based on the current open circuit voltage OCV, the corresponding initial battery state of charge is extracted from the fourth static SOC-OCV curve to obtain the first static OCV-SOV curve.

[0092] Furthermore, in actual use, the present embodiment can intercept a second dynamic SOC-OCV curve (obtained based on the current ampere-hour integration method) and a second static SOC-OCV curve (based on the static SOC-OCV initially input by the system, input the current OCV, obtain the SOC by looking up the table, and draw the obtained curve) in each time period T1, T2, T3, T4... within a period of time or a certain number of cycles at a certain cycle number C. The above-mentioned initial SOC algorithm can be a conventional ampere-hour integration method (Ah-counting method).

[0093] That is, this embodiment uses the Ah-counting method to estimate the SOC of the battery, measures the charge and discharge current of the target battery, and estimates the SOC by time integration, and records the OCV value of the battery (the OCV value can be measured after the battery has been stationary for a period of time to ensure that the target battery is in an open circuit state), and then pairs and accumulates the SOC and OCV values ​​in each time period to draw the above-mentioned second dynamic SOC-OCV curve. In addition, this embodiment is also based on the fourth static SOC-OCV curve initially input by the system (the fourth static SOC-OCV curve can be a lookup table or a fitting curve), so when it is necessary to obtain the second static SOC-OCV curve, the currently measured OCV value is input into the fourth static SOC-OCV curve, and the corresponding SOC value can be obtained through the lookup table or the fitting curve, and the second static SOC-OCV curve is drawn.

[0094] Furthermore, in this embodiment, the system initially inputs dynamic and static SOC-OCV curves after different numbers of cycles, obtains SOC-OCV curves at different temperatures and different numbers of cycles through machine learning, and establishes a connection with factors such as temperature and number of cycles (i.e., the functional relationship between the above-mentioned battery curve and the number of cycles). After a period of time, at a certain number of cycles C, for a period of time, or within a certain number of cycles (such as C±10 cycles, it is assumed that the charging and discharging trends are roughly the same within this period), the charging and discharging curves at each time period of T1, T2, T3, T4... are intercepted, and the SOC-OCV curve is obtained according to the SOC-OCV algorithm of the current system, and superimposed to generate the following: Figure 4 The second dynamic SOC-OCV curve shown in FIG. 1 is then corrected according to the corresponding relationship between the number of cycles and the cycle SOC-OCV obtained by machine learning to obtain the second dynamic SOC-OCV curve under the existing number of cycles. Figure 5 The third dynamic SOC-OCV curve ( Figure 5 The dotted line in the figure corresponds to the above-mentioned completed data).

[0095] Step S204, according to the functional relationship between the battery curve and the cycle number, the second dynamic SOC-OCV curve and the second static SOC-SOV curve are corrected, and a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve are generated.

[0096] In an optional implementation, the step S204 includes:

[0097] Step S2041 : According to the first functional relationship, the second dynamic SOC-OCV curve is corrected, and a corrected third dynamic SOC-OCV curve is generated.

[0098] In an optional implementation, the step S2041 includes:

[0099] Obtain the charge and discharge data for each time period currently captured;

[0100] According to the charge and discharge data, a fifth dynamic SOC-OCV curve is generated by the first functional relationship;

[0101] The second dynamic SOC-OCV curve is compared and corrected based on the fifth dynamic SOC-OCV curve to obtain a corrected third dynamic SOC-OCV curve.

[0102] Step S2042: According to the second functional relationship, the first static OCV-SOV curve is corrected, and a corrected third static SOC-OCV curve is generated.

[0103] In an optional implementation, step S2042 includes:

[0104] Obtain the charge and discharge data for each time period currently captured;

[0105] According to the charge and discharge data, a fifth static SOC-OCV curve is generated by the second functional relationship;

[0106] The first static OCV-SOV curve is compared and corrected based on the fifth static SOC-OCV curve to obtain a corrected third static SOC-OCV curve.

[0107] Furthermore, this embodiment learns and predicts the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions according to the target neural network model, and establishes a functional relationship between the battery curve and the number of cycles f(SOC-OCV)=f(T, C) (including the first functional relationship and the second functional relationship), and corrects the dynamic SOC-OCV curve and the static SOC-OCV curve accumulated at the current number of cycles, and finally obtains the fifth dynamic SOC-OCV curve and the fifth static SOC-OCV curve under the corrected number of cycles.

[0108] To obtain the corrected third dynamic SOC-OCV curve under the number of cycles, the following steps are specifically included:

[0109] A1. Input the data of charge and discharge voltage, current, temperature, current cycle times, etc. (i.e. the above-mentioned charge and discharge data) in each time period of T1, T2, T3, T4, etc.;

[0110] B1. Calculate the corresponding dynamic SOC data through the target neural network model, and make the fifth dynamic SOC-OCV curve. For the blank charge and discharge curve segment, calculate the SOC through the target neural network model by inputting the missing voltage to complete the data;

[0111] C1. Compare and correct the fifth dynamic SOC-OCV curve with the second dynamic SOC-OCV curve to obtain a corrected third dynamic SOC-OCV curve.

[0112] To obtain the corrected third static SOC-OCV curve under the cycle number, the following steps are specifically included:

[0113] A2, input the data of charge and discharge voltage, current, temperature, current cycle times, etc. (i.e. the above-mentioned charge and discharge data) in each time period of T1, T2, T3, T4, etc.;

[0114] B2. Calculate the corresponding static SOC data through the target neural network model, and make a fifth static SOC-OCV curve. For the blank charge and discharge curve segment, calculate the SOC through the target neural network model by inputting the missing voltage to complete the data;

[0115] C2. Compare and correct the fifth static SOC-OCV curve with the second static SOC-OCV curve to obtain a corrected third static SOC-OCV curve.

[0116] Step S205 , mapping the voltage interval corresponding to the second dynamic SOC-OCV curve to the SOC interval corresponding to the third dynamic SOC-OCV curve to obtain the current actual cell capacity C2 of the target battery.

[0117] Furthermore, this embodiment first determines the voltage range (such as 3.2-3.4V) on the second dynamic SOC-OCV curve, and finds the SOC range (such as 20%-60%) corresponding to this voltage range in the third dynamic SOC-OCV curve, and then uses the ampere-hour integration method to obtain the charging capacity C1 in the voltage range, and calculates the current battery cell actual capacity C2 according to the width of the SOC range. The current battery cell actual capacity C2 = C1 / (60%-20%).

[0118] Step S206 , performing battery state of charge estimation processing based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to obtain the current battery state of charge of the target battery.

[0119] In an optional implementation, step S206 includes:

[0120] Perform a replacement process on the initial reference capacity of the initial SOC algorithm by using the current actual capacity C2 of the battery cell to obtain a final reference capacity;

[0121] Performing secondary coverage replacement processing on the fourth static SOC-OCV curve through the third static SOC-OCV curve, and obtaining a secondary coverage result;

[0122] Based on the secondary coverage result and the final reference capacity, correcting the initial SOC algorithm to generate a corrected SOC algorithm;

[0123] A battery state of charge estimation process is performed based on the corrected SOC algorithm to obtain the current battery state of charge of the target battery.

[0124] Furthermore, this embodiment uses the calculated actual capacity C2 of the current battery cell as the new reference capacity, which is overwritten with the initial capacity C0 (i.e., the initial reference capacity) in the ampere-hour integration method, so that the subsequent updated ampere-hour integration will be based on this more accurate reference capacity. In addition, this embodiment overwrites the third static SOC-OCV curve with the fourth static SOC-OCV curve as the calculation basis for the ampere-hour integration SOC0; the new calculation method is:

[0125]

[0126] Wherein, SOC0 represents the initial state of charge of the battery, which is calculated and obtained by the third static SOC-OCV curve.

[0127] In summary, the present invention predicts the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions based on the pre-trained target neural network model, and establishes a functional relationship between the battery curve and the number of cycles. In actual use, the second dynamic SOC-OCV curve and the second static OCV-SOV curve under the target number of cycles are first obtained through the initial SOC algorithm, and then the second dynamic SOC-OCV curve and the second static OCV-SOV curve are corrected through the established functional relationship between the battery curve and the number of cycles to obtain a complete charge and discharge curve that is closer to the actual use situation. The current battery state of charge of the target battery can be obtained through the complete charge and discharge curve. The present invention takes into account factors such as battery aging and temperature changes, and uses the prediction ability of the target neural network model to correct the curve. The corrected curve can be quickly generated, which improves the efficiency and accuracy of SOC estimation. It is suitable for different types of batteries and different usage scenarios, and has strong versatility and scalability.

[0128] In addition, the present invention can generate a complete second dynamic SOC-OCV curve by accumulating the local dynamic SOC-OCV curves in each time period obtained based on the initial SOC algorithm, and can integrate the data of each time period to form a more comprehensive and accurate description of the battery charging and discharging behavior, thereby improving the accuracy of SOC estimation. In addition, by directly measuring the current open circuit voltage OCV of the target battery at the target number of cycles, and extracting the corresponding initial battery state of charge from the known fourth static SOC-OCV curve based on the OCV, an accurate first static OCV-SOV curve can be obtained, avoiding complex calculation or estimation processes, ensuring the accuracy of the static curve, and providing a reliable basis for subsequent SOC estimation.

[0129] Furthermore, the present invention replaces the initial reference capacity of the initial SOC algorithm with the current actual capacity C2 of the battery cell, thereby ensuring that the reference capacity used by the SOC algorithm is consistent with the actual battery cell capacity, thereby avoiding the SOC estimation error caused by inaccurate reference capacity, and using the third static SOC-OCV curve to perform a secondary replacement of the fourth static SOC-OCV curve, it is possible to obtain a SOC-OCV relationship curve that is more in line with the current battery cell characteristics, thereby effectively improving the accuracy and adaptability of SOC estimation.

[0130] In this embodiment, a device for acquiring the state of charge of a battery is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0131] This embodiment provides a device for obtaining the state of charge of a battery. Figure 6 As shown, including:

[0132] A functional relationship establishing module 601 is used to predict the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions through a pre-trained target neural network model, and establish a functional relationship between the battery curve and the number of cycles based on the prediction results;

[0133] A first curve acquisition module 602 is used to acquire an actual second dynamic SOC-OCV curve and a second static OCV-SOV curve in each time period under a target cycle number of a target battery;

[0134] A second curve acquisition module 603, for correcting the second dynamic SOC-OCV curve and the second static OCV-SOV curve according to the functional relationship between the battery curve and the cycle number, and generating a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve;

[0135] The current cell actual capacity C2 module 604 is used to map the third dynamic SOC-OCV curve based on the voltage range corresponding to the second dynamic SOC-OCV curve to obtain the current cell actual capacity C2 of the target battery;

[0136] The current battery state of charge acquisition module 605 is used to perform battery state of charge estimation processing based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to acquire the current battery state of charge of the target battery.

[0137] In some optional embodiments, the device is further used for:

[0138] The fourth dynamic SOC-OCV curve and the fourth static SOC-OCV curve under different conditions obtained by testing in the initial state are input into the target neural network model for training, and the trained target neural network model is obtained.

[0139] In some optional implementations, the functional relationship establishing module 601 is further used to:

[0140] The first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions are predicted by the pre-trained target neural network model, and a first functional relationship between the first dynamic SOC-OCV curve and the temperature and the number of cycles is established, and a second functional relationship between the first static SOC-OCV curve and the temperature and the number of cycles is established.

[0141] In some optional implementations, the first curve acquisition module 602 is further used to:

[0142] Accumulating the local dynamic SOC-OCV curves in each time period obtained based on the initial SOC algorithm to generate the second dynamic SOC-OCV curve;

[0143] The current open circuit voltage OCV of the target battery at the target cycle number is obtained, and based on the current open circuit voltage OCV, the corresponding initial battery state of charge is extracted from the fourth static SOC-OCV curve to obtain the first static OCV-SOV curve.

[0144] In some optional implementations, the second curve acquisition module 603 is further used to:

[0145] According to the first functional relationship, the second dynamic SOC-OCV curve is corrected, and a corrected third dynamic SOC-OCV curve is generated;

[0146] The first static OCV-SOV curve is corrected according to the second functional relationship, and a corrected third static SOC-OCV curve is generated.

[0147] In some optional implementations, the second curve acquisition module 603 is further used to:

[0148] Obtain the charge and discharge data for each time period currently captured;

[0149] According to the charge and discharge data, a fifth dynamic SOC-OCV curve is generated by the first functional relationship;

[0150] The second dynamic SOC-OCV curve is compared and corrected based on the fifth dynamic SOC-OCV curve to obtain a corrected third dynamic SOC-OCV curve.

[0151] In some optional implementations, the second curve acquisition module 603 is further used to:

[0152] Obtain the charge and discharge data for each time period currently captured;

[0153] According to the charge and discharge data, a fifth static SOC-OCV curve is generated by the second functional relationship;

[0154] The first static OCV-SOV curve is compared and corrected based on the fifth static SOC-OCV curve to obtain a corrected third static SOC-OCV curve.

[0155] In some optional implementations, the current cell actual capacity C2 module 604 is used to:

[0156] The voltage interval corresponding to the second dynamic SOC-OCV curve is mapped to the SOC interval corresponding to the third dynamic SOC-OCV curve to obtain the current actual cell capacity C2 of the target battery.

[0157] In some optional implementations, the current battery state of charge acquisition module 605 is used to:

[0158] Perform a replacement process on the initial reference capacity of the initial SOC algorithm by using the current actual capacity C2 of the battery cell to obtain a final reference capacity;

[0159] Performing secondary coverage replacement processing on the fourth static SOC-OCV curve through the third static SOC-OCV curve, and obtaining a secondary coverage result;

[0160] Based on the secondary coverage result and the final reference capacity, correcting the initial SOC algorithm to generate a corrected SOC algorithm;

[0161] A battery state of charge estimation process is performed based on the corrected SOC algorithm to obtain the current battery state of charge of the target battery.

[0162] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0163] In this embodiment, a battery charge status acquisition device is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0164] The embodiment of the present invention also provides a computer device having the above Figure 6 A device for obtaining a battery state of charge is shown.

[0165] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0166] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0167] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0168] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0170] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0171] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, etc. The above display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0172] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0173] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0174] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for obtaining a battery state of charge, characterized in that: The method comprises: Predicting the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions through the pre-trained target neural network model, and establishing a functional relationship between the battery curve and the number of cycles based on the prediction results; Under the target cycle number of the target battery, obtain the actual second dynamic SOC-OCV curve and the second static OCV-SOV curve in each time period; According to the functional relationship between the battery curve and the number of cycles, the second dynamic SOC-OCV curve and the second static OCV-SOV curve are corrected, and a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve are generated; based on the voltage range corresponding to the second dynamic SOC-OCV curve, the third dynamic SOC-OCV curve is mapped to obtain the current actual cell capacity C2 of the target battery; A battery state of charge estimation process is performed based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to obtain the current battery state of charge of the target battery.

2. The method according to claim 1, characterized in that Before predicting the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions by the pre-trained target neural network model, the method further includes: The fourth dynamic SOC-OCV curve and the fourth static SOC-OCV curve under different conditions obtained by testing in the initial state are input into the target neural network model for training, and the trained target neural network model is obtained.

3. The method according to claim 1, characterized in that The method predicts the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions by using the pre-trained target neural network model, and establishes a functional relationship between the battery curve and the number of cycles based on the prediction results, including: The first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions are predicted by the pre-trained target neural network model, and a first functional relationship between the first dynamic SOC-OCV curve and the temperature and the number of cycles is established, and a second functional relationship between the first static SOC-OCV curve and the temperature and the number of cycles is established.

4. The method according to claim 2, characterized in that: The obtaining of the actual second dynamic SOC-OCV curve and the second static OCV-SOV curve in each time period includes: Accumulating the local dynamic SOC-OCV curves in each time period obtained based on the initial SOC algorithm to generate the second dynamic SOC-OCV curve; The current open circuit voltage OCV of the target battery at the target cycle number is obtained, and based on the current open circuit voltage OCV, the corresponding initial battery state of charge is extracted from the fourth static SOC-OCV curve to obtain the second static OCV-SOV curve.

5. The method according to claim 3, characterized in that: The method of correcting the second dynamic SOC-OCV curve and the second static OCV-SOV curve according to the functional relationship between the battery curve and the number of cycles, and generating a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve, comprises: According to the first functional relationship, the second dynamic SOC-OCV curve is corrected, and a corrected third dynamic SOC-OCV curve is generated; The second static OCV-SOV curve is corrected according to the second functional relationship, and a corrected third static SOC-OCV curve is generated.

6. The method according to claim 5, characterized in that The step of correcting the second dynamic SOC-OCV curve according to the first functional relationship and generating a corrected third dynamic SOC-OCV curve includes: Obtain the charge and discharge data for each time period currently captured; generating a fifth dynamic SOC-OCV curve according to the charge and discharge data through the first functional relationship; The second dynamic SOC-OCV curve is compared and corrected based on the fifth dynamic SOC-OCV curve to obtain a corrected third dynamic SOC-OCV curve.

7. The method according to claim 5, characterized in that The step of correcting the first static OCV-SOV curve according to the second functional relationship and generating a corrected third static SOC-OCV curve includes: Obtain the charge and discharge data for each time period currently captured; generating a fifth static SOC-OCV curve according to the charge and discharge data by using the second functional relationship; The first static OCV-SOV curve is compared and corrected based on the fifth static SOC-OCV curve to obtain a corrected third static SOC-OCV curve.

8. The method according to any one of claims 4 to 7, characterized in that: The mapping process of the third dynamic SOC-OCV curve based on the voltage interval corresponding to the second dynamic SOC-OCV curve to obtain the current actual cell capacity C2 of the target battery includes: The voltage interval corresponding to the second dynamic SOC-OCV curve is mapped to the SOC interval corresponding to the third dynamic SOC-OCV curve to obtain the current actual capacity C2 of the battery cell of the target battery.

9. The method according to claim 4, characterized in that The performing battery state of charge estimation processing based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to obtain the current battery state of charge of the target battery includes: Performing a covering and replacing process on the initial reference capacity of the initial SOC algorithm by using the current actual capacity C2 of the battery cell to obtain a final reference capacity; Performing secondary coverage replacement processing on the fourth static SOC-OCV curve by using the third static SOC-OCV curve, and obtaining a secondary coverage result; Based on the secondary coverage result and the final reference capacity, correcting the initial SOC algorithm to generate a corrected SOC algorithm; A battery state of charge estimation process is performed based on the corrected SOC algorithm to obtain a current battery state of charge of the target battery.

10. A device for obtaining a battery state of charge, characterized in that: The device comprises: A functional relationship establishment module, used to predict the first dynamic SOC-OCV curve and the first static SOC-OCV curve under different conditions through a pre-trained target neural network model, and establish a functional relationship between the battery curve and the number of cycles based on the prediction results; A first curve acquisition module, used for acquiring an actual second dynamic SOC-OCV curve and a second static OCV-SOV curve in each time period under a target cycle number of a target battery; A second curve acquisition module, used for correcting the second dynamic SOC-OCV curve and the second static OCV-SOV curve according to the functional relationship between the battery curve and the number of cycles, and generating a corrected third dynamic SOC-OCV curve and a third static SOC-OCV curve; A current cell actual capacity C2 module, configured to map the third dynamic SOC-OCV curve based on the voltage interval corresponding to the second dynamic SOC-OCV curve, to obtain the current cell actual capacity C2 of the target battery; The current battery state of charge acquisition module is used to perform battery state of charge estimation processing based on the third static SOC-OCV curve and the current actual capacity C2 of the battery cell to obtain the current battery state of charge of the target battery.