Battery capacity prediction method and device, equipment and storage medium

By constructing linear functions and using training models, combined with reference battery data, accurate prediction of the battery capacity to be measured is achieved, the problems of difficulty in obtaining data and high cost in the prior art are solved, and the battery capacity prediction process is simplified.

CN118962453APending Publication Date: 2024-11-15SHENZHEN BAK POWER BATTERY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411013628.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Existing battery capacity prediction technologies require a large amount of data to be acquired, which makes it costly and difficult to achieve accurate predictions.

Method used

By obtaining the characteristic data of the battery to be tested, an initial linear function is constructed, and the preset training model outputs slope and intercept is used to calculate the target linear function, and query the actual capacity with reference battery data to achieve capacity prediction.

Benefits of technology

It greatly reduces the difficulty of data acquisition and calculation cost, simplifies the battery capacity prediction process, and improves prediction efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118962453A_ABST
    Figure CN118962453A_ABST
Patent Text Reader

Abstract

The invention provides a battery capacity prediction method and device, equipment and a storage medium, and the method comprises the steps: obtaining reference battery data and to-be-detected battery data, extracting to-be-detected battery feature data from the to-be-detected battery data, and constructing an initial linear function; inputting the characteristic data of the to-be-detected battery into a preset training model, and outputting the slope and intercept of an initial linear function corresponding to the characteristic data of the to-be-detected battery; substituting the slope and the intercept into the initial linear function to obtain a target linear function; obtaining a test SOC of the to-be-tested battery from the target interval; substituting the test SOC into the target linear function to obtain a test voltage corresponding to the test SOC; and querying a reference SOC corresponding to the test voltage from the reference battery data, and calculating the actual capacity of the to-be-tested battery according to the reference SOC. According to the method, the battery capacity can be predicted according to a small amount of data, and on a production line, a large amount of resources can be saved at the cost of sacrificing relatively low precision, and the calculation complexity is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of lithium-ion batteries, and in particular to a battery capacity prediction method, device, equipment and storage medium. Background Art

[0002] Lithium iron battery is a lithium-ion battery with high energy density, long life, low self-discharge rate and high safety performance. Therefore, it is widely used in electric vehicles, energy storage systems and electric bicycles. In order to ensure the service life of lithium iron batteries, the capacity of lithium iron batteries is predicted before they leave the factory to remove unqualified batteries. However, the existing battery capacity prediction technology is very difficult to predict capacity because too much data needs to be obtained. Summary of the invention

[0003] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and to provide a battery capacity prediction method, device, equipment and storage medium, by comparing the data of the battery to be tested with the reference battery data, so as to predict the capacity of the battery to be tested.

[0004] The present invention provides the following technical solutions:

[0005] In a first aspect, the present application provides a battery capacity prediction method, comprising:

[0006] Acquire reference battery data and test battery data, and extract test battery characteristic data from the test battery data; the reference battery data includes a reference SOC and a reference voltage;

[0007] An initial linear function is constructed with the voltage of the battery to be tested as a dependent variable and the SOC of the battery to be tested as an independent variable; the effective interval of the initial linear function is a target interval;

[0008] Constructing a preset training model according to the reference battery data, inputting the characteristic data of the battery to be tested into the preset training model, and outputting the slope and intercept of the initial linear function corresponding to the characteristic data of the battery to be tested;

[0009] Substituting the slope and the intercept into the initial linear function to obtain a target linear function;

[0010] Acquire the test SOC of the battery to be tested from the target interval, substitute the test SOC into the target linear function, and obtain a test voltage corresponding to the test SOC;

[0011] The reference SOC corresponding to the test voltage is queried from the reference battery data, and the actual capacity of the battery to be tested is calculated according to the reference SOC.

[0012] In one implementation, after obtaining the reference battery data, the following steps are included:

[0013] Preprocessing the reference battery data to obtain preprocessed data, and acquiring reference battery characteristic data from the preprocessed data;

[0014] A reference battery data table is constructed according to the reference battery characteristic data; the reference battery data table includes the reference battery characteristic data, the reference battery intercept and the reference battery slope.

[0015] In one embodiment, the battery data to be tested includes mid-process data, post-process data and formation data of the battery to be tested; and extracting the characteristic data of the battery to be tested from the battery data to be tested includes:

[0016] The characteristic data of the battery to be tested are extracted from the mid-process data, the back-process data and the formation data; the characteristic data of the battery to be tested include ACR internal resistance, battery cell weight, voltage characteristics and temperature characteristics.

[0017] In one implementation, the training process of the preset training model includes:

[0018] Step 1: Build the initial training model;

[0019] Step 2: inputting the reference battery characteristic data into the initial training model, obtaining the output of the initial training model, and determining whether the output of the initial training model is the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data;

[0020] Step 3: If the output of the initial training model is not the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data, adjust the parameters of the initial training model to obtain an intermediate training model, and use the intermediate training model to replace the initial training model;

[0021] Step 4: Repeat step 2 to step 3 until the output of the intermediate training model is the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data, then stop training to obtain the preset training model.

[0022] In one implementation, the step of obtaining the test SOC of the battery to be tested from the target interval includes:

[0023] A plurality of test SOCs are obtained from the target interval according to a preset sampling interval.

[0024] In one implementation, obtaining a test voltage corresponding to the test SOC includes:

[0025] The test voltage corresponding to each of the test SOCs is calculated through the target linear function.

[0026] In one implementation, querying the reference SOC corresponding to the test voltage from the reference battery data and calculating the actual capacity of the battery to be tested according to the reference SOC includes:

[0027] Querying the actual voltage corresponding to each of the test voltages from the reference battery data table; the difference between the actual voltage and the test voltage is less than a preset difference;

[0028] Obtaining a reference SOC corresponding to each of the actual voltages from the reference battery data table;

[0029] A reference capacity is calculated according to each reference SOC, and a weighted average is performed on a plurality of the reference capacities to obtain the actual capacity of the battery to be tested.

[0030] In a second aspect, the present application provides a battery capacity prediction device, comprising:

[0031] An acquisition module is used to acquire reference battery data and test battery data, and extract test battery characteristic data from the test battery data; the reference battery data includes a reference capacity SOC and a reference voltage;

[0032] A construction module is used to construct an initial linear function with the voltage of the battery to be tested as a dependent variable and the SOC of the battery to be tested as an independent variable; the effective interval of the initial linear function is a target interval;

[0033] An output module, used to construct a preset training model according to the reference battery data, input the characteristic data of the battery to be tested into the preset training model, and output the slope and intercept of the initial linear function corresponding to the characteristic data of the battery to be tested;

[0034] A substitution module, used for substituting the slope and the intercept into the initial linear function to obtain a target linear function;

[0035] A calculation module, used for obtaining a test SOC of the battery to be tested from the target interval, substituting the test SOC into the target linear function, and obtaining a test voltage corresponding to the test SOC;

[0036] The query module is used to query the reference SOC corresponding to the test voltage from the reference battery data, and calculate the actual capacity of the battery according to the reference SOC.

[0037] In a third aspect, the present application provides an electronic device comprising a memory and at least one processor, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the battery capacity prediction method as described in the first aspect.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed, the battery capacity prediction method as described in the first aspect is implemented.

[0039] The embodiments of the present invention have the following beneficial effects: the battery capacity prediction method provided by the present invention extracts characteristic data of the battery to be tested, constructs a linear function based on the characteristic data, then samples the test capacity of the battery to be tested in the capacity test interval, calculates the test voltage corresponding to the test capacity using the linear function, and then searches the corresponding capacity from the data of the reference battery through the test voltage, thereby obtaining the actual capacity of the capacitor to be tested. The present invention only needs to obtain a small amount of data of the battery to be tested to complete the capacity prediction of the battery to be tested, the calculation method is simple, and the calculation cost is greatly saved.

[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 A schematic diagram of a battery capacity prediction method flow is shown;

[0043] Figure 2 A schematic diagram of a preset model training method flow is shown;

[0044] Figure 3 A schematic diagram of a method for calculating actual capacity is shown;

[0045] Figure 4 A schematic diagram of the framework structure of a battery capacity prediction device is shown.

[0046] Description of main component symbols:

[0047] 400, battery capacity prediction device; 401, acquisition module; 402, construction module; 403, output module; 404, substitution module; 405, determination module; 406, calculation module; 407, query module. DETAILED DESCRIPTION

[0048] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0049] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of the template are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0051] The manufacturing process of lithium batteries includes mixing active materials, binders and conductive agents into slurry and coating them on copper or aluminum current collectors to make dry electrode particle coatings, compacting and densifying, cutting or striping. The positive and negative electrodes and separators are assembled into battery cells, electrolytes are injected, and charge and discharge activation is performed to finally form battery products.

[0052] According to the core package molding form, it can be divided into cylindrical, square and soft-pack batteries, and their production processes are slightly different. The overall process can be divided into three stages: the front process (electrode sheet manufacturing), the middle process (battery synthesis) and the back process (formation and packaging). Among them, formation is also called activation, which is the process of activating the internal positive and negative electrode materials through a certain charging and discharging method after the battery is manufactured to improve the overall performance of the battery.

[0053] The existing technology for predicting battery capacity requires not only data from the entire formation stage, but also data from the entire capacity separation stage, which makes data acquisition difficult. Capacity separation is the process of capacity sorting and performance screening of batteries. By charging and discharging each lithium battery, the computer records the data of each test point, and thus obtains data such as the capacity and internal resistance of each battery to determine the quality grade of the lithium battery. This process is called capacity separation. The entire capacity prediction process requires a large amount of data, resulting in high costs.

[0054] Example 1

[0055] See also Figure 1 , Figure 1 A battery capacity prediction method provided in this embodiment can be used to predict the capacity of various iron-lithium batteries by collecting a small amount of data. The method includes:

[0056] S101, obtaining reference battery data and test battery data, and extracting test battery characteristic data from the test battery data; the reference battery data includes a reference SOC and a reference voltage.

[0057] Among them, the reference battery data is standard data. Usually, when the battery is tested for capacity, it is necessary to perform charging and discharging processing. During the charging and discharging process, the battery will produce temperature changes, which will cause the measured capacity to be inconsistent with the actual capacity. The existing technology usually requires capacity compensation for the measured capacity to obtain the actual capacity. However, this process requires a lot of data and is costly. Therefore, it is impossible to sample this method for each battery to be tested for capacity testing. Therefore, other characteristic information of the reference battery can be matched with the actual capacity to obtain a reference data table. The reference battery data table includes the voltage, SOC, reference battery characteristic data, reference battery intercept and reference battery slope of the reference battery. Each voltage corresponds to an SOC, characteristic data, intercept and slope. The data in this table is used as standard data for capacity prediction of the battery to be tested. There is a close relationship between the battery SOC (State of Charge) and the battery capacity, which reflects the ratio between the remaining capacity and the total capacity of the battery.

[0058] Then obtain the data of the battery to be tested, such as the data in the middle and back stages of the process, and part of the data in the formation stage. The data that must be obtained in the middle and back stages of the process include ACR internal resistance and battery cell weight. The data in the formation stage only needs to obtain the voltage and temperature of the battery before the SOC is 30%.

[0059] Not all the data of the battery to be tested are complete or correct data. Therefore, after obtaining the data of the battery to be tested, it is necessary to pre-process the reference battery data to obtain pre-processed data.

[0060] Then, reference battery characteristic data is obtained from the preprocessed data. The reference battery characteristic data includes data such as ACR internal resistance, battery cell weight, voltage characteristics and temperature characteristics, which correspond to the characteristic data in the reference data table.

[0061] S102, constructing an initial linear function with the voltage of the battery to be tested as a dependent variable and the SOC of the battery to be tested as an independent variable; the effective interval of the initial linear function is a target interval.

[0062] According to the characteristics of lithium iron batteries, when the SOC of the lithium iron battery is between 2.8% and 3.2%, there is an obvious linear relationship between the battery voltage and SOC. Therefore, when predicting the actual capacity of the battery to be tested, the prediction can be made based on the characteristics of the battery in the target range.

[0063] Therefore, we can first construct an initial linear function based on the relationship between voltage and SOC:

[0064] Y=KX+M,

[0065] Among them, Y is voltage, X is SOC, K is slope, and M is intercept.

[0066] For this function, the most important thing is to obtain the values ​​of K and M, which can be predicted based on the characteristic data of the battery to be tested. The characteristic data can be obtained from the data of the middle and late stages of the process of the battery to be tested, as well as part of the data of the formation stage. Therefore, less data needs to be obtained and the difficulty of obtaining is lower.

[0067] S103, constructing a preset training model according to the reference battery data, inputting the characteristic data of the battery to be tested into the preset training model, and outputting the slope and intercept of the initial linear function corresponding to the characteristic data of the battery to be tested.

[0068] See also Figure 2 , the training process of the preset training model includes:

[0069] S1031. Build an initial training model.

[0070] Since the model is used to predict the slope and intercept of the linear function corresponding to the battery to be tested through the characteristic information of the battery to be tested, the initial training model can be a linear model or a deep learning model.

[0071] S1032. Input the reference battery characteristic data into the initial training model, obtain the output of the initial training model, and determine whether the output of the initial training model is the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data.

[0072] The reference battery and the battery to be tested are batteries of the same type and manufactured using the same process. Therefore, the reference battery also has the same properties as the battery to be tested. The relationship between the change in voltage and SOC of the reference battery also conforms to a linear function within the target range. In order to ensure that the model can accurately predict the intercept and slope of the battery to be tested, the initial training model can be trained using the characteristic data of the reference battery. Since the characteristic data, intercept and slope of the reference battery are all known data, the reference battery characteristic data can be input into the initial training model, and then the output of the initial training model is obtained to determine whether the output is the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data.

[0073] S1033. If the output of the initial training model is not the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data, adjust the parameters of the initial training model to obtain an intermediate training model, and use the intermediate training model to replace the initial training model.

[0074] If not, it means that the model has not been trained yet. At this time, the parameters of the model can be adjusted according to the training process to obtain an intermediate training model, and then the intermediate training model is used to replace the initial training model.

[0075] S1034, repeatedly executing step 2 to step 3 until the output of the intermediate training model is the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data, then stopping the training to obtain the preset training model.

[0076] The intermediate training model continues to be repeatedly trained through steps 2 and 3, and the output of the direct model is the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data, indicating that the model training is completed at this time, and the model at this time is used as the preset training model.

[0077] In order to ensure the prediction accuracy of the model, the preset training model can be evaluated by calculating the loss function, etc., until the accuracy of the preset training model meets the requirements.

[0078] Then, the characteristic data of the battery to be tested is input into a preset training model, and the slope and intercept of the initial linear function corresponding to the characteristic data of the battery to be tested can be output.

[0079] S104: Substitute the slope and the intercept into the initial linear function to obtain a target linear function.

[0080] Substituting the slope K and the intercept M of the initial linear function into the initial linear function Y=KX+M, the target linear function can be obtained.

[0081] S105 , acquiring a test SOC of the battery to be tested from the target interval, substituting the test SOC into the target linear function, and obtaining a test voltage corresponding to the test SOC.

[0082] Since the iron-lithium battery has a linear relationship between SOC of 2.8% and 3.2%, 2.8%-3.2% is used as the target interval, and then multiple test SOCs are collected within the target interval as the test SOC of the target linear function, that is, X, for example, the values ​​of X = 0.028, 0.029, 0.030, 0.031 and 0.032 respectively. Users can also sample other sampling rules in the target interval according to actual conditions.

[0083] Then, X=0.028, 0.029, 0.030, 0.031 and 0.032 are respectively substituted into the target linear function to obtain the Y value corresponding to each X, that is, the test voltage value.

[0084] S106: query the reference SOC corresponding to the test voltage from the reference battery data, and calculate the actual capacity of the battery to be tested according to the reference SOC.

[0085] See also Figure 3 , step S106 includes:

[0086] S1061. Query the actual voltage corresponding to each of the test voltages from the reference battery data table; the difference between the actual voltage and the test voltage is less than a preset difference.

[0087] Since the test voltage calculated by the linear function may have a certain deviation, after obtaining the test voltage, the actual voltage can be obtained by querying the reference data table, where the preset difference can be a set value, and the voltage whose difference between the reference data table and the test voltage is less than the preset difference is taken as the actual voltage, or the voltage value closest to the test voltage is directly selected as the real voltage.

[0088] S1062: Obtain a reference SOC corresponding to each of the actual voltages from the reference battery data table.

[0089] S1063: Calculate a reference capacity according to each reference SOC, and perform weighted averaging on a plurality of the reference capacities to obtain an actual capacity of the battery to be tested.

[0090] X=0.028, 0.029, 0.030, 0.031 and 0.032, corresponding to a predicted voltage respectively, and then the real voltages corresponding to the five predicted voltages are queried respectively, and the corresponding reference SOC is queried according to each real voltage, and five final capacities are calculated according to the five reference SOCs, and then the five final capacities are weighted averaged to obtain the actual capacity of the battery to be tested.

[0091] For example: when the test voltage X is 0.028, that is, the SOC of the battery to be tested is 2.8%, input X=0.028 into the target linear function, and calculate the predicted voltage Y=2.91V. Then you can return to the data table to query and get the reference SOC of 3Ah when the voltage is 2.91V in the data table. At this time, use 3 / 0.028=107.1428Ah to get the final capacity of the battery to be tested. Similarly, X=0.029, 0.030, 0.031 and 0.032 can also be calculated to get a final capacity.

[0092] Through the above method, five slightly different final capacities corresponding to the battery to be tested can be calculated, and at this time, a weighted average is needed. For example, the final capacity calculated with X=0.030 is a high weight, and 0.028 and 0.032 are averaged with lower weights to obtain the actual capacity of the battery to be tested.

[0093] This embodiment obtains a small amount of data from the process stage and the formation stage of the battery to be tested, and extracts the characteristic data of the battery to be tested from it, calculates the slope and intercept of the battery to be tested according to the characteristic data of the battery to be tested, thereby obtaining the target linear function, and then substitutes the test voltage into the target linear function to obtain the test voltage, and finally obtains the actual capacity of the battery to be tested by querying the reference data table. This embodiment only needs a small amount of data to complete the capacity prediction of the battery to be tested, which greatly reduces the demand for data and reduces the complexity and cost of battery capacity calculation.

[0094] Example 2

[0095] See also Figure 4 , Figure 4 A battery capacity prediction device 400 provided in this embodiment includes:

[0096] The acquisition module 401 is used to acquire reference battery data and test battery data, and extract test battery characteristic data from the test battery data; the reference battery data includes a reference SOC and a reference voltage;

[0097] A construction module 402 is used to construct an initial linear function with the voltage of the battery to be tested as a dependent variable and the SOC of the battery to be tested as an independent variable; the effective interval of the initial linear function is a target interval;

[0098] The output module 403 is used to construct a preset training model according to the reference battery data, input the characteristic data of the battery to be tested into the preset training model, and output the slope and intercept of the initial linear function corresponding to the characteristic data of the battery to be tested;

[0099] A substitution module 404 is used to substitute the slope and the intercept into the initial linear function to obtain a target linear function;

[0100] A calculation module 405 is used to obtain the test SOC of the battery to be tested from the target interval, substitute the test SOC into the target linear function, and obtain a test voltage corresponding to the test SOC;

[0101] The query module 406 is used to query the reference SOC corresponding to the test voltage from the reference battery data, and calculate the actual capacity of the battery according to the reference SOC.

[0102] It can be understood that the implementation method of the battery capacity prediction method described in the above embodiment 1 is also applicable to this embodiment, so it will not be repeated here.

[0103] Example 3

[0104] The embodiment of the present application also provides a computer device, for example, the computer device can be, but is not limited to, a desktop computer, a notebook, etc., and its existence form is not limited, mainly depending on whether it needs to support the interface display function of the browser web page, etc. Exemplarily, the computer device includes a memory and at least one processor, the memory stores a computer program, and the processor is used to execute the computer program to implement the battery capacity prediction method described in the above embodiment 1.

[0105] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU) and a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. At least one of the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0106] The memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0107] Furthermore, the memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data (such as iteration data, version data, etc.) created according to the use of the computer device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0108] Example 4

[0109] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the battery capacity prediction method described in the above embodiment 1.

[0110] It can be understood that the implementation method of the battery capacity prediction method described in the above embodiment 1 is also applicable to this embodiment, so it will not be repeated here.

[0111] The computer-readable storage medium may be either a non-volatile storage medium or a volatile storage medium. For example, the computer-readable storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0112] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0113] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0114] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0115] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the 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.

[0116] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limiting, and thus other examples of the exemplary embodiments may have different values.

[0117] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0118] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A battery capacity prediction method, characterized in that: include: Acquire reference battery data and test battery data, and extract test battery characteristic data from the test battery data; The reference battery data includes a reference SOC and a reference voltage; An initial linear function is constructed with the voltage of the battery to be tested as a dependent variable and the SOC of the battery to be tested as an independent variable; the effective interval of the initial linear function is a target interval; Building a preset training model according to the reference battery data, inputting the characteristic data of the battery to be tested into the preset training model, and outputting the slope and intercept of the initial linear function corresponding to the characteristic data; Substituting the slope and the intercept into the initial linear function to obtain a target linear function; Acquire the test SOC of the battery to be tested from the target interval, substitute the test SOC into the target linear function, and obtain a test voltage corresponding to the test SOC; The reference SOC corresponding to the test voltage is queried from the reference battery data, and the actual capacity of the battery to be tested is calculated according to the reference SOC.

2. The battery capacity prediction method according to claim 1, characterized in that: After obtaining the reference battery data, the method includes: Preprocessing the reference battery data to obtain preprocessed data, and acquiring reference battery characteristic data from the preprocessed data; A reference battery data table is constructed according to the reference battery characteristic data; the reference battery data table includes the reference battery characteristic data, the reference battery intercept and the reference battery slope.

3. The battery capacity prediction method according to claim 2, characterized in that: The battery data to be tested includes mid-process data, post-process data and formation data of the battery to be tested; extracting the characteristic data of the battery to be tested from the battery data to be tested includes: The characteristic data of the battery to be tested are extracted from the mid-process data, the back-process data and the formation data; the characteristic data of the battery to be tested include ACR internal resistance, battery cell weight, voltage characteristics and temperature characteristics.

4. The battery capacity prediction method according to claim 3, characterized in that: The training process of the preset training model includes: Step 1: Build the initial training model; Step 2: inputting the reference battery characteristic data into the initial training model, obtaining the output of the initial training model, and determining whether the output of the initial training model is the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data; Step 3: If the output of the initial training model is not the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data, adjust the parameters of the initial training model to obtain an intermediate training model, and use the intermediate training model to replace the initial training model; Step 4: Repeat step 2 to step 3 until the output of the intermediate training model is the reference battery intercept and the reference battery slope corresponding to the reference battery characteristic data, then stop training to obtain the preset training model.

5. The battery capacity prediction method according to claim 4, characterized in that: The obtaining the test SOC of the battery to be tested from the target interval includes: A plurality of test SOCs are obtained from the target interval according to a preset sampling interval.

6. The battery capacity prediction method according to claim 5, characterized in that: The obtaining of a test voltage corresponding to the test SOC includes: The test voltage corresponding to each of the test SOCs is calculated through the target linear function.

7. The battery capacity prediction method according to claim 6, characterized in that: The querying the reference SOC corresponding to the test voltage from the battery data and calculating the actual capacity of the battery according to the reference SOC includes: Querying the actual voltage corresponding to each of the test voltages from the reference battery data table; the difference between the actual voltage and the test voltage is less than a preset difference; Obtaining a reference SOC corresponding to each of the actual voltages from the reference battery data table; A reference capacity is calculated according to each reference SOC, and a weighted average is performed on a plurality of the reference capacities to obtain the actual capacity of the battery to be tested.

8. A battery capacity prediction device, characterized in that: include: An acquisition module, used to acquire reference battery data and test battery data, and extract test battery characteristic data from the test battery data; The reference battery data includes a reference SOC and a reference voltage; A construction module is used to construct an initial linear function with the voltage of the battery to be tested as a dependent variable and the SOC of the battery to be tested as an independent variable; the effective interval of the initial linear function is a target interval; An output module, used to construct a preset training model according to the reference battery data, input the characteristic data of the battery to be tested into the preset training model, and output the slope and intercept of the initial linear function corresponding to the characteristic data of the battery to be tested; A substitution module, used for substituting the slope and the intercept into the initial linear function to obtain a target linear function; A calculation module, used for obtaining a test SOC of the battery to be tested from the target, substituting the test SOC into the target linear function, and obtaining a test voltage corresponding to the test SOC; The query module is used to query the reference SOC corresponding to the test voltage from the reference battery data, and calculate the actual capacity of the battery according to the reference SOC.

9. An electronic device, characterized in that: The method comprises a memory and at least one processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the battery capacity prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the battery capacity prediction method according to any one of claims 1 to 7 is implemented.