Lithium battery capacity prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a lithium battery capacity prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the formation charging of a lithium battery, so as to collect a plurality of key indexes in the formation charging process; and inputting the plurality of key indexes into a preset capacity fitting model to obtain a predicted capacity value of the lithium battery output by the capacity fitting model. Through the data acquired in the formation process and the capacity fitting model, the capacity value of the lithium battery can be directly predicted, a capacity grading process does not need to be repeatedly carried out, the electric power, manpower and time costs in the lithium battery capacity measurement process are reduced, and the test efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a capacity prediction method, device, electronic device and storage medium for a lithium battery. Background Art

[0002] At present, the new energy market is developing rapidly, and the market demand for lithium-ion batteries as key energy storage components is growing. In the existing lithium-ion battery production process, the manufacturing cost of the back-end process accounts for the highest proportion. In the back-end process, the battery needs to be charged and discharged many times to complete the battery activation and capacity and other key parameters testing, which consumes a lot of electricity, manpower and time resources. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a capacity prediction method, device, electronic device and storage medium for a lithium battery, so as to reduce the power, manpower and time costs of the lithium battery capacity measurement process and improve the test efficiency.

[0004] In a first aspect, the present invention provides a method for predicting the capacity of a lithium battery, the method comprising: performing formation charging on the lithium battery to collect parameter values ​​corresponding to multiple key indicators during the formation charging process; inputting the parameter values ​​corresponding to the multiple key indicators into a preset capacity fitting model to obtain a predicted capacity value of the lithium battery output by the capacity fitting model.

[0005] In an optional embodiment, a capacity fitting model is generated in the following manner: a first preset number of lithium batteries are formed and charged according to preset process steps to collect preset indicators during the formation and charging process of each lithium battery; based on the correlation between the preset indicators and the capacity value of the lithium battery, key indicators are screened out from the preset indicators; based on the key indicators and the corresponding divided capacity values, a capacity fitting model is constructed.

[0006] In an optional embodiment, the preset indicators include the stage capacity values ​​and static voltage drops of the lithium battery under multiple voltage stages. For each lithium battery, the preset indicators during the formation and charging process of the lithium battery are collected in the following manner: the lithium battery is charged with a constant current of 0.05C to a voltage cutoff of 3100mV, the lithium battery is charged with a constant current of 0.1C to a voltage cutoff of 3400mV, and the lithium battery is charged with a constant current of 0.2C to a voltage cutoff of 3700mV. When the lithium battery is charged to a voltage stage of 2600mV, the stage capacity value of the lithium battery is collected at a step interval of 100mV. The lithium battery is left to stand for 10 minutes, and the static voltage drop of the lithium battery during the standing stage is collected.

[0007] In an optional embodiment, based on the correlation between the preset indicators and the capacity value of the lithium battery, the step of screening out key indicators from the preset indicators specifically includes: for each preset indicator, calculating the partial correlation coefficient between the preset indicator and the capacity value of the lithium battery; based on the size of the partial correlation coefficient corresponding to the preset indicator, determining a second preset number of key indicators.

[0008] In an optional embodiment, based on the correlation between the preset indicators and the capacity value of the lithium battery, the step of screening out key indicators from the preset indicators specifically includes: performing multivariate linear fitting based on all the preset indicators and the capacity value of the lithium battery to determine the P value corresponding to each preset indicator; based on the size of the P value corresponding to the preset indicator, determining a second preset number of key indicators.

[0009] In an optional implementation, fitting is also performed based on the key indicators and the corresponding sub-capacity values ​​to construct a capacity fitting model, and the capacity fitting model is expressed as:

[0010] Y=θ1X1+2X2+,……,+θ n X n +;

[0011] Among them, Y is the predicted capacity value of the lithium battery, X n is the parameter value of the nth key indicator, θ n is the constant coefficient corresponding to the nth key indicator, and ε is the compensation coefficient.

[0012] In a second aspect, the present invention provides a capacity prediction device for a lithium battery, the device comprising:

[0013] The acquisition module is used to charge the lithium battery to collect multiple key indicators during the charging process;

[0014] The prediction module is used to input multiple key indicators into a preset capacity fitting model to obtain the predicted capacity value of the lithium battery output by the capacity fitting model.

[0015] In an optional embodiment, a fitting module is further included, which is used to generate a capacity fitting model in the following manner:

[0016] A first preset number of lithium batteries are formed and charged according to preset process steps to collect preset indicators during the formation and charging process of each lithium battery; based on the correlation between the preset indicators and the capacity value of the lithium battery, key indicators are screened out from the preset indicators; based on the key indicators and the corresponding capacity values, a capacity fitting model is constructed.

[0017] In a third aspect, the present invention provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus, and the processor executes the machine-readable instructions to perform the steps of the capacity prediction method of a lithium battery in any of the aforementioned embodiments.

[0018] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the capacity prediction method for a lithium battery in any of the aforementioned embodiments are executed.

[0019] The present application provides a method, device, electronic device and storage medium for predicting the capacity of a lithium battery, wherein the method includes performing formation charging on the lithium battery to collect multiple key indicators during the formation charging process; inputting the multiple key indicators into a preset capacity fitting model to obtain the predicted capacity value of the lithium battery output by the capacity fitting model. Through the data collected during the formation process and the capacity fitting model, the capacity value of the lithium battery can be directly predicted without repeatedly performing the capacity division process, thereby reducing the power, manpower and time costs of the lithium battery capacity measurement process and improving the test efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application 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 paying creative work.

[0021] Figure 1 A flow chart of a method for predicting the capacity of a lithium battery provided in an embodiment of the present application;

[0022] Figure 2 A flowchart of steps for generating a capacity fitting model provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of the results of a partial correlation analysis provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of the P value result of a linear regression provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of the fitting results of a capacity fitting model provided in an embodiment of the present application;

[0026] Figure 6A schematic diagram of the structure of a lithium battery capacity prediction device provided in an embodiment of the present application;

[0027] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] First, the application scenario of the present application is described. The technical solution of the present application is applicable to the prediction of the discharge capacity of lithium batteries during production.

[0029] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0030] Figure 1 A flow chart of a method for predicting the capacity of a lithium battery provided in an embodiment of the present application. Figure 1 As shown, the present application provides a method for predicting the capacity of a lithium battery, the method comprising:

[0031] S1. Perform formation charging on the lithium battery to collect parameter values ​​corresponding to multiple key indicators in the formation charging process.

[0032] Here, the lithium battery is subjected to formation charging, i.e., the first charging, and key indicators in the formation process are collected.

[0033] The main indicators that affect the capacity value of lithium-ion batteries include the current size during constant current discharge, cut-off voltage, quality of active materials, internal resistance of the battery, etc. The key indicators here are those that are highly correlated with the capacity value of lithium batteries.

[0034] S2. Inputting parameter values ​​corresponding to the multiple key indicators into a preset capacity fitting model to obtain a predicted capacity value of the lithium battery output by the capacity fitting model.

[0035] The present application provides a method for predicting the capacity of a lithium battery. The method can directly predict the capacity value of a lithium battery through data collected during the formation process and a capacity fitting model, without the need to repeatedly perform the capacity division process. This reduces the electricity, manpower and time costs of the lithium battery capacity measurement process and improves test efficiency.

[0036] In one embodiment of the present application, the process of creating a capacity fitting model is described. Here, the capacity fitting model can be fitted by identifying key indicators with high correlation with the capacity of lithium battery sub-capacity.

[0037] Figure 2 A flowchart of steps for generating a capacity fitting model provided in an embodiment of the present application.

[0038] like Figure 2 As shown, the capacity fitting model can be generated in the following way:

[0039] S10, performing formation charging on a first preset number of lithium batteries according to preset process steps to collect preset indicators during the formation charging process of each lithium battery.

[0040] During the formation process of lithium-ion batteries, collect indicators such as time, current, voltage, charging capacity, rest time between steps, voltage change during rest time, etc. Time includes step time and total process time. Charging capacity includes charging capacity of each step, total charging capacity over time, charging capacity between different voltages, etc.

[0041] Furthermore, the formation process may use a current between 0.02C and 0.5C, with voltage cutoff or time cutoff between working steps, and a standing time between working steps of 5min to 60min.

[0042] Among the cells that have been formed, sample cells are randomly selected for capacity division, and the capacity during the capacity division process is collected. The selection of sample cells should take into account multiple factors such as batch and time. After the production batch is changed, sample cells are reselected for model calibration. The capacity division process uses a current between 0.1C and 1.0C for full charging and discharging, and the capacity division is the full discharge capacity.

[0043] Specifically, the preset indicators here include the stage capacity value and static voltage drop of the lithium battery at multiple voltage stages. For each lithium battery, the preset indicators in the formation and charging process of the lithium battery are collected in the following manner:

[0044] The lithium battery was charged with a constant current of 0.05C to a voltage cut-off of 3100mV, the lithium battery was charged with a constant current of 0.1C to a voltage cut-off of 3400mV, and the lithium battery was charged with a constant current of 0.2C to a voltage cut-off of 3700mV. When the lithium battery was charged to the voltage stage of 2600mV, the stage capacity value of the lithium battery was collected at a step interval of 100mV. The lithium battery was left standing for 10 minutes, and the static voltage drop of the lithium battery in the static stage was collected.

[0045] S20. Based on the correlation between the preset indicators and the capacity value of the lithium battery, select key indicators from the preset indicators.

[0046] The preset indicator parameters of the formation process collected by the sample battery in S10 are used to perform correlation analysis with the capacity measured by the capacity division, and the key indicator parameters of the formation process are determined according to the correlation coefficient. In order to meet the accuracy of the model while reducing the difficulty of data fitting, the number of key indicator parameters can be between 2 and 5.

[0047] In one case, partial correlation analysis can be used. Based on the correlation between the preset indicators and the capacity value of the lithium battery, the steps of selecting key indicators from the preset indicators include:

[0048] For each preset indicator, a partial correlation coefficient between the preset indicator and the capacity value of the lithium battery is calculated. Based on the magnitude of the partial correlation coefficient corresponding to the preset indicator, a second preset number of key indicators is determined.

[0049] In another case, a linear regression fitting method can be used. Based on the correlation between the preset indicators and the capacity value of the lithium battery, the steps of selecting key indicators from the preset indicators specifically include:

[0050] Based on all the preset indicators and the capacity value of the lithium battery, a multivariate linear fitting is performed to determine the P value corresponding to each preset indicator. Based on the size of the P value corresponding to the preset indicator, a second preset number of key indicators is determined.

[0051] S30. Construct a capacity fitting model based on the key indicators and the corresponding sub-capacity values.

[0052] In step S30, fitting is performed based on the key indicators and the corresponding sub-capacity values ​​to construct a capacity fitting model. The capacity fitting model is expressed as:

[0053] Y=θ1X1+2X2+,……,+θ n X n +;

[0054] Among them, Y is the predicted capacity value of the lithium battery, X n is the parameter value of the nth key indicator, θ n is the constant coefficient corresponding to the nth key indicator, and ε is the compensation coefficient.

[0055] In a specific embodiment, for a ternary system battery cell, the capacity of the divided capacity can be predicted by the following method:

[0056] In the first step, 40 sample cells were selected to complete the lithium battery formation process in the following way, and the index parameters of the formation process were collected, including the capacity value of each voltage stage and the voltage drop of the static step, and then the capacity was divided:

[0057] (1) 0.05C constant current charging until the voltage reaches 3100mV;

[0058] (2) Charge at a constant current of 0.1C until the voltage reaches 3400mV;

[0059] (3) Charge at 0.2C constant current until the voltage is cut off at 3700mV;

[0060] (4) Let stand for 10 minutes;

[0061] (5)End.

[0062] The parameter values ​​of the collected indicator parameters can be found in Table 1.

[0063] Table 1

[0064]

[0065]

[0066]

[0067]

[0068] The second step is to analyze the correlation between the parameter values ​​of the collected indicator parameters and the capacity, and screen and identify key data points. This step can adopt two data processing methods, both of which can achieve the effect of screening indicators.

[0069] The first processing method is to directly calculate the correlation between the data. In order to reduce the interference between the independent variable data, partial correlation data analysis is used. The results are shown in Figure 3 .

[0070] According to the correlation coefficient between capacity and respective variables, it can be determined that the key indicator parameters are arranged in order of priority: voltage drop, capacity C11 at 3600mV, and capacity C2 at 2700mV.

[0071] The second processing method is to perform a multivariate linear regression fit on the capacity and all independent variable factors, make a judgment based on the P value of each factor in the fitting model, and add or remove the independent variable factors to select the parameter value that becomes the key indicator. The P value result of the fitting model in this embodiment can be found in Figure 4 .

[0072] According to the P value, the priority of the key data points is: voltage drop, capacity C11 at 3600mV, and capacity C2 at 2700mV.

[0073] The third step is to generate a capacity fitting model. The capacity and voltage drop, the capacity C11 at 3600mV, and the capacity C2 at 2700mV are fitted. The fitting results are shown in Figure 5 .

[0074] Then, we can obtain the capacity fitting model Y=θ1X1+2X2+3X3+, where X1, X2, and X3 are the parameter values ​​corresponding to the capacity value C11, the capacity value C2, and the voltage drop, respectively. The values ​​of θ1, θ2, and θ3 are 1.7893, 3.8663, and 151.5369, respectively, and the value of ε is 39252.8255.

[0075] Figure 6 This is a schematic diagram of the structure of a lithium battery capacity prediction device provided in an embodiment of the present application. Figure 6As shown, based on the same inventive concept, the present application also provides a capacity prediction device 600 for a lithium battery, the device comprising:

[0076] The acquisition module 610 is used to perform formation charging on the lithium battery to collect parameter values ​​corresponding to multiple key indicators in the formation charging process;

[0077] The prediction module 620 is used to input parameter values ​​corresponding to a plurality of key indicators into a preset capacity fitting model to obtain a predicted capacity value of the lithium battery output by the capacity fitting model.

[0078] In a preferred embodiment, a fitting module (not shown in the figure) is also included, which is used to generate a capacity fitting model in the following manner: a first preset number of lithium batteries are formed and charged according to preset steps to collect preset indicators during the formation and charging process of each lithium battery; based on the correlation between the preset indicators and the capacity value of the lithium battery, key indicators are screened out from the preset indicators; based on the key indicators and the corresponding divided capacity values, a capacity fitting model is constructed.

[0079] In a preferred embodiment, the preset indicators include the stage capacity values ​​and static voltage drops of the lithium battery at multiple voltage stages. For each lithium battery, the fitting module collects the preset indicators during the formation charging process of the lithium battery in the following manner: charging the lithium battery with a constant current of 0.05C to a voltage cutoff of 3100mV, charging the lithium battery with a constant current of 0.1C to a voltage cutoff of 3400mV, and charging the lithium battery with a constant current of 0.2C to a voltage cutoff of 3700mV, wherein, when the lithium battery is charged to the voltage stage of 2600mV, the stage capacity value of the lithium battery is collected at a step interval of 100mV; the lithium battery is left to stand for 10 minutes, and the static voltage drop of the lithium battery during the standing stage is collected.

[0080] In a preferred embodiment, the fitting module is specifically used to calculate the partial correlation coefficient between each preset indicator and the capacity value of the lithium battery; based on the size of the partial correlation coefficient corresponding to the preset indicator, determine a second preset number of key indicators.

[0081] In a preferred embodiment, the fitting module is specifically used to perform multivariate linear fitting based on all preset indicators and the capacity value of the lithium battery to determine the P value corresponding to each preset indicator; based on the size of the P value corresponding to the preset indicator, determine a second preset number of key indicators.

[0082] In a preferred embodiment, the fitting module is further used to perform fitting based on the key indicators and the corresponding sub-capacity values ​​to construct a capacity fitting model. The capacity fitting model is expressed as:

[0083] Y=θ1X1+2X2+,……,+θ n X n+;

[0084] Among them, Y is the predicted capacity value of the lithium battery, X n is the parameter value of the nth key indicator, θ n is the constant coefficient corresponding to the nth key indicator, and ε is the compensation coefficient.

[0085] See also Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 7 As shown in , the electronic device 700 includes a processor 710 , a memory 720 and a bus 730 .

[0086] The memory 720 stores machine-readable instructions executable by the processor 710. When the electronic device 700 is running, the processor 710 communicates with the memory 720 via the bus 730. When the machine-readable instructions are executed by the processor 710, the steps of a capacity prediction method for a lithium battery in the above-mentioned method embodiment can be executed. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0087] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a lithium battery capacity prediction method in the above method embodiment can be executed. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0089] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0090] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] Furthermore, the functional modules 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.

[0092] It should be noted that 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 essentially be embodied in the form of a software product, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be 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: U disk, mobile hard disk, read-only memory (ROM) random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0093] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0094] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting the capacity of a lithium battery, characterized in that: The method comprises: Perform formation charging on the lithium battery to collect parameter values ​​corresponding to multiple key indicators in the formation charging process; The parameter values ​​corresponding to the multiple key indicators are input into a preset capacity fitting model to obtain a predicted capacity value of the lithium battery output by the capacity fitting model.

2. The method according to claim 1, characterized in that The capacity fitting model is generated by: Performing formation charging on a first preset number of lithium batteries according to preset process steps to collect preset indicators during the formation charging process of each lithium battery; Based on the correlation between the preset indicators and the capacity value of the lithium battery, the key indicators are screened out from the preset indicators; Based on the key indicators and the corresponding capacity values, the capacity fitting model is constructed.

3. The method according to claim 1, characterized in that The preset indicators include the stage capacity value and static voltage drop of the lithium battery at multiple voltage stages. For each lithium battery, the preset indicators during the formation and charging process of the lithium battery are collected in the following ways: The lithium battery is charged with a constant current of 0.05C to a voltage cutoff of 3100mV, the lithium battery is charged with a constant current of 0.1C to a voltage cutoff of 3400mV, and the lithium battery is charged with a constant current of 0.2C to a voltage cutoff of 3700mV. When the lithium battery is charged to the voltage stage of 2600mV, the stage capacity value of the lithium battery is collected at a step interval of 100mV. The lithium battery was left to stand for 10 minutes, and the static voltage drop of the lithium battery during the static stage was collected.

4. The method according to claim 1, characterized in that: The step of selecting key indicators from the preset indicators based on the correlation between the preset indicators and the capacity value of the lithium battery specifically includes: For each preset indicator, calculate the partial correlation coefficient between the preset indicator and the capacity value of the lithium battery; Based on the size of the partial correlation coefficient corresponding to the preset indicator, a second preset number of key indicators is determined.

5. The method according to claim 1, characterized in that The step of selecting key indicators from the preset indicators based on the correlation between the preset indicators and the capacity value of the lithium battery specifically includes: Perform multivariate linear fitting based on all preset indicators and the capacity value of the lithium battery to determine the P value corresponding to each preset indicator; Based on the size of the P value corresponding to the preset indicator, a second preset number of key indicators is determined.

6. The method according to claim 1, characterized in that Also includes: Fitting is performed based on key indicators and corresponding sub-capacity values ​​to construct a capacity fitting model, which is expressed as: Y=θ1X1+θ2X2+,……,+θ n X n +e; Among them, Y is the predicted capacity value of the lithium battery, X n is the parameter value of the nth key indicator, θ n is the constant coefficient corresponding to the nth key indicator, and ε is the compensation coefficient.

7. A capacity prediction device for a lithium battery, characterized in that: The device comprises: The acquisition module is used to charge the lithium battery to collect parameter values ​​corresponding to multiple key indicators in the charging process; The prediction module is used to input parameter values ​​corresponding to multiple key indicators into a preset capacity fitting model to obtain the predicted capacity value of the lithium battery output by the capacity fitting model.

8. The device according to claim 7, characterized in that The system also includes a fitting module for generating the capacity fitting model in the following manner: Performing formation charging on a first preset number of lithium batteries according to preset process steps to collect preset indicators during the formation charging process of each lithium battery; Based on the correlation between the preset indicators and the capacity value of the lithium battery, the key indicators are screened out from the preset indicators; Based on the key indicators and the corresponding capacity values, the capacity fitting model is constructed.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the capacity prediction method of a lithium battery as described in any one of claims 1 to 6.

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 by a processor, the steps of the capacity prediction method of a lithium battery as claimed in any one of claims 1 to 6 are executed.

Images