Method, device, storage medium and electronic device for obtaining discharge capacity of battery cell

Abstract

The present disclosure relates to a method, apparatus, storage medium and electronic device for obtaining the discharge capacity of an electric core. The method includes: obtaining formation parameter information of the electric core during a target time period in the formation process, where the target time period includes the time period from the start of the formation of the electric core to before the first full discharge; extracting formation characteristic parameter information from the formation parameter information; and obtaining the discharge capacity of the electric core after formation through a capacity prediction model according to the formation characteristic parameter information. It is possible to first obtain the formation parameter information of the time period from the start of the formation of the electric core to before the first full discharge. After extracting the formation characteristic parameter information from the formation parameter information, by inputting the formation characteristic parameter information into the capacity prediction model, the discharge capacity of the electric core after formation can be obtained. Without waiting for the electric core to be fully discharged, the discharge capacity of the electric core after formation can be obtained. In this way, the time required in the formation process of the electric core can be saved, thereby reducing the production cost of the electric core.

Description

Technical Field

[0001] The present disclosure relates to the technical field of batteries, and in particular, to a method, device, storage medium, and electronic device for obtaining the discharge capacity of a battery cell. Background Art

[0002] During the production process of battery cells, formation is required to activate the battery cells after injecting electrolyte. Through charge and discharge, chemical reactions occur inside the battery cells to form a SEI (Solid Electrolyte Interphase) film, ensuring the safety, reliability, and long cycle life of the subsequent battery cells during charge and discharge cycles. However, the entire formation stage includes a series of processes such as multiple charging, discharging, and detection, resulting in a relatively high production cost of the battery. Summary of the Invention

[0003] To solve the above problems, the present disclosure provides a method, device, storage medium, and electronic device for obtaining the discharge capacity of a battery cell.

[0004] In a first aspect, the present disclosure provides a method for obtaining the discharge capacity of a battery cell, the method including:

[0005] Obtaining formation parameter information of the battery cell within a target time period during the formation process, where the target time period includes the time period from the start of formation of the battery cell to before the first full discharge;

[0006] Extracting formation characteristic parameter information from the formation parameter information;

[0007] According to the formation characteristic parameter information, obtaining the discharge capacity of the battery cell after formation through a capacity prediction model, where the capacity prediction model is pre-trained by a gradient boosting regression tree.

[0008] Optionally, the capacity prediction model is trained in the following manner:

[0009] Obtaining sample parameter information of multiple sample battery cells within a preset time period during the formation process, where the preset time period includes the time period from the start of formation of the sample battery cells to the end of the first full discharge;

[0010] Extracting sample characteristic parameter information from the sample parameter information;

[0011] Training the gradient boosting regression tree through the sample characteristic parameter information to obtain the capacity prediction model.

[0012] Optionally, the formation parameter information includes multiple formation charging capacities, multiple formation voltage values, multiple formation ambient temperatures, and charging duration of the battery cell, and the formation characteristic parameter information includes formation characteristic charging capacity, formation characteristic voltage value, formation characteristic ambient temperature, and the charging duration; extracting the formation characteristic parameter information from the formation parameter information includes:

[0013] Extracting the formation characteristic charging capacity from multiple formation charging capacities;

[0014] Extracting the formation characteristic voltage value from multiple formation voltage values;

[0015] Extracting the formation characteristic ambient temperature from multiple formation ambient temperatures.

[0016] Optionally, obtaining the discharge capacity of the battery cell after formation according to the formation characteristic parameter information through a capacity prediction model includes:

[0017] Obtaining the discharge capacity of the battery cell after formation through the capacity prediction model according to the formation characteristic charging capacity, the formation characteristic voltage value, the formation characteristic ambient temperature, and the charging duration.

[0018] Optionally, before extracting the formation characteristic parameter information from the formation parameter information, the method further includes:

[0019] Determining qualified formation parameter information according to the formation parameter information and a preset parameter threshold range;

[0020] Extracting the formation characteristic parameter information from the formation parameter information includes:

[0021] Extracting the formation characteristic parameter information from the qualified formation parameter information.

[0022] Optionally, the expression of the capacity prediction model is:

[0023]

[0024] Wherein, is the discharge capacity of the battery cell after formation, f m ( x ) represents m functions f(x) , represents the m th regression tree, is the parameter of the m th regression tree, M is the number of regression trees, A is the number of leaf nodes of the regression tree, ,L ( y , f m-1 ( x ) +c ) is the loss function, , y b is x b the output corresponding to the regression tree, R a is the a th region of the regression tree, R ma is the value of the feature splitting point, , m The value range of M is (1, a The value range of A is (1, M and A are non-zero real numbers.

[0025] In a second aspect, the present disclosure provides a device for obtaining the discharge capacity of a battery cell. The device includes:

[0026] A parameter information acquisition module, configured to acquire formation parameter information of the battery cell during a target time period in the formation process, where the target time period includes the time period from the start of formation of the battery cell to before the first full discharge;

[0027] A parameter information extraction module, configured to extract formation feature parameter information from the formation parameter information;

[0028] A discharge capacity acquisition module, configured to obtain the discharge capacity of the battery cell after formation according to the formation feature parameter information through a capacity prediction model, where the capacity prediction model is pre-trained by a gradient boosting regression tree.

[0029] Optionally, the device further includes:

[0030] A model training module, configured to acquire sample parameter information of a plurality of sample battery cells during a preset time period in the formation process, where the preset time period includes the time period from the start of formation of the sample battery cells to the end of the first full discharge; extract sample feature parameter information from the sample parameter information; and train the gradient boosting regression tree through the sample feature parameter information to obtain the capacity prediction model.

[0031] Optionally, the formation parameter information includes a plurality of formation charging capacities, a plurality of formation voltage values, a plurality of formation ambient temperatures, and a charging duration of the battery cell, and the formation characteristic parameter information includes a formation characteristic charging capacity, a formation characteristic voltage value, a formation characteristic ambient temperature, and the charging duration; the parameter information extraction module is further configured to:

[0032] Extract the formation characteristic charging capacity from the plurality of formation charging capacities;

[0033] Extract the formation characteristic voltage value from the plurality of formation voltage values;

[0034] Extract the formation characteristic ambient temperature from the plurality of formation ambient temperatures.

[0035] Optionally, the discharge capacity acquisition module is further configured to:

[0036] Obtain the discharge capacity of the battery cell after formation through the capacity prediction model according to the formation characteristic charging capacity, the formation characteristic voltage value, the formation characteristic ambient temperature, and the charging duration.

[0037] Optionally, the device further includes:

[0038] A qualified information determination module, configured to determine qualified formation parameter information according to the formation parameter information and a preset parameter threshold range;

[0039] The parameter information extraction module is further configured to:

[0040] Extract the formation characteristic parameter information from the qualified formation parameter information.

[0041] Optionally, the expression of the capacity prediction model is:

[0042]

[0043] Wherein, Is the discharge capacity of the battery cell after formation, f m ( x ) represents m Functions f(x) , Represents the m Regression tree, Is the parameter of the m Regression tree, M Is the number of regression trees, A Is the number of leaf nodes of the regression tree, , L ( y , f m-1 (x ) +c ) is the loss function, , y b is x b the corresponding output on the regression tree, R a is the a th region of the regression tree, R ma is the value of the feature splitting point, , m The value range of is (1, M ), a The value range of is (1, A ), M and A are non-zero real numbers.

[0044] Thirdly, the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in the first aspect of the present disclosure are implemented.

[0045] Fourthly, the present disclosure provides an electronic device, including: a memory on which a computer program is stored; a processor for executing the computer program in the memory to implement the steps of the method described in the first aspect of the present disclosure.

[0046] Through the above technical solutions, by obtaining the formation parameter information of the battery cell during the formation process in a target time period, the target time period includes the time period from the start of the formation of the battery cell to before the first full discharge; extracting the formation characteristic parameter information from the formation parameter information; according to the formation characteristic parameter information, obtaining the discharge capacity of the battery cell after formation through a capacity prediction model, and the capacity prediction model is pre-trained by a gradient boosting regression tree. That is to say, the formation parameter information of the battery cell in the time period from the start of the formation to before the first full discharge can be obtained first, the formation characteristic parameter information is extracted from the formation parameter information, and after the formation characteristic parameter information is input into the capacity prediction model, the discharge capacity of the battery cell after formation can be obtained. Without waiting for the battery cell to be fully discharged, the discharge capacity of the battery cell after formation can be obtained. In this way, the time required for the formation of the battery cell can be saved, and thus the production cost of the battery cell can be reduced.

[0047] Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification, and are used to explain the present disclosure together with the following specific implementation manners, but do not constitute a limitation to the present disclosure. In the drawings:

[0049] Figure 1 is a flowchart of a method for obtaining the discharge capacity of a battery cell shown according to an exemplary embodiment;

[0050] Figure 2 is a flowchart of another method for obtaining the discharge capacity of a battery cell shown according to an exemplary embodiment;

[0051] Figure 3 is a schematic structural diagram of a device for obtaining the discharge capacity of a battery cell shown according to an exemplary embodiment;

[0052] Figure 4 is a schematic structural diagram of a second device for obtaining the discharge capacity of a battery cell shown according to an exemplary embodiment;

[0053] Figure 5 is a schematic structural diagram of a third device for obtaining the discharge capacity of a battery cell shown according to an exemplary embodiment;

[0054] Figure 6 is a block diagram of an electronic device shown according to an exemplary embodiment. Detailed implementation manners

[0055] The following will describe the detailed implementation manners of the present disclosure with reference to the accompanying drawings. It should be understood that the detailed implementation manners described herein are only for explaining and illustrating the present disclosure, and are not used to limit the present disclosure.

[0056] First, the application scenario of the present disclosure will be described. The present disclosure can be applied to the battery cell formation stage. In the existing battery cell production process, the primary battery cell formation includes: standing, constant current constant voltage charging, standing, constant current discharging, standing, constant current constant voltage charging, and standing. Among them, there are two full charges and one full discharge, and the full discharge time is approximately 42% of the total time of the entire formation process. The inventor found that if a related method is used to replace the process from constant current discharging, standing, constant current constant voltage charging, and standing in the formation process (the fourth to seventh steps in the formation process), the total time of the formation process can be reduced to half of the existing total time.

[0057] To solve the above problems, the present disclosure provides a method, a device, a storage medium, and an electronic device for obtaining the discharge capacity of a battery cell. First, the formation parameter information of the battery cell during the period from the start of formation to before the first full discharge can be obtained. The formation characteristic parameter information is extracted from the formation parameter information. After the formation characteristic parameter information is input into the capacity prediction model, the discharge capacity of the battery cell after formation can be obtained. Without waiting for the battery cell to perform a full discharge, the discharge capacity of the battery cell after formation can be obtained. In this way, the time required for the formation process of the battery cell can be saved, and thus the production cost of the battery cell can be reduced.

[0058] The present disclosure will be described below in conjunction with specific embodiments.

[0059] Figure 1 is a flowchart of a method for obtaining the discharge capacity of a battery cell according to an exemplary embodiment, as Figure 1 shown, the method may include:

[0060] S101. Obtain the formation parameter information of the battery cell during a target time period in the formation process.

[0061] Among them, the target time period may include the time period from the start of the formation of the battery cell to before the first full discharge. Exemplarily, in the case where the formation process includes standing, constant current and constant voltage charging, standing, constant current discharging, standing, constant current and constant voltage charging, and standing, the target time period may be the time period from the start of the first standing to the end of the second standing; the formation parameter information may include multiple formation charging capacities, multiple formation voltage values, multiple formation ambient temperatures, and the charging duration of the battery cell.

[0062] In this step, after the formation of the battery cell starts, the formation charging capacity, formation voltage value, and formation ambient temperature corresponding to the battery cell may be periodically collected. The period for collecting the formation charging capacity and the formation voltage value may be 1 s, and the period for collecting the formation ambient temperature may be 100 ms. The present disclosure does not limit this.

[0063] S102. Extract the formation characteristic parameter information from the formation parameter information.

[0064] Among them, the formation characteristic parameter information may include the formation characteristic charging capacity, formation characteristic voltage value, formation characteristic ambient temperature, and charging duration. The formation characteristic charging capacity may include the average charging capacity, the final charging capacity (the capacity at the end of charging), the charging capacity mode (the charging capacity that appears most frequently in the formation parameter information), and the maximum charging capacity. The formation characteristic voltage value may include the voltage mode (the voltage value that appears most frequently in the formation parameter information), the average voltage value, the maximum voltage value, and the initial voltage value (the voltage value when the battery cell starts charging). The formation characteristic ambient temperature may include the initial ambient temperature, the final ambient temperature, and the average ambient temperature.

[0065] The parameters included in the above formation characteristic parameter information are only examples. The present disclosure may also include other formation characteristic parameter information. For example, the formation characteristic voltage value may also include the minimum voltage value, and the formation characteristic ambient temperature may also include the maximum ambient temperature, the minimum ambient temperature, etc. The present disclosure does not limit this.

[0066] In this step, it should be noted that after collecting the formation parameter information of the battery cell during the target time period of the formation process, the qualified formation parameter information can be determined according to the formation parameter information and the preset parameter threshold range, and the formation characteristic parameter information can be extracted from the qualified formation parameter information. The preset parameter threshold ranges corresponding to different formation parameter information are different.

[0067] S103. According to the formation characteristic parameter information, obtain the discharge capacity of the battery cell after formation through the capacity prediction model.

[0068] Among them, the capacity prediction model can be pre-trained through a gradient boosting regression tree.

[0069] In this step, after extracting the formation characteristic parameter information, the formation characteristic parameter information can be input into the capacity prediction model to obtain the discharge capacity of the battery cell after formation.

[0070] Among them, the capacity prediction model can be trained in the following way: obtain the sample parameter information of multiple sample battery cells during the preset time period of the formation process. The preset time period includes the time period from the start of formation of the sample battery cell to the end of the first full discharge; extract the sample characteristic parameter information from the sample parameter information, and train the gradient boosting regression tree through the sample characteristic parameter information to obtain the capacity prediction model.

[0071] By using the above method, the formation parameter information of the time period from the start of formation of the battery cell to before the first full discharge can be obtained first, the formation characteristic parameter information can be extracted from the formation parameter information, and after inputting the formation characteristic parameter information into the capacity prediction model, the discharge capacity of the battery cell after formation can be obtained. Without waiting for the battery cell to be fully discharged, the discharge capacity of the battery cell after formation can be obtained. In this way, the time required for the formation process of the battery cell can be saved, and thus the production cost of the battery cell can be reduced.

[0072] Figure 2 is a flowchart of another method for obtaining the discharge capacity of a battery cell shown according to an exemplary embodiment. As Figure 2 shown, the method may include:

[0073] S201. Obtain the formation parameter information of the battery cell during the target time period of the formation process.

[0074] Among them, the target time period may include the time period from the start of formation of the battery cell to before the first full discharge. The formation process may include standing, constant current and constant voltage charging, standing, constant current discharging, standing, constant current and constant voltage charging, and standing. The target time period may be the time period from the start of the first standing to the end of the second standing; the formation parameter information may include multiple formation charging capacities, multiple formation voltage values, multiple formation ambient temperatures, and charging duration of the battery cell.

[0075] Exemplarily, the specific process of forming may include: standing still for 1 minute; constant current and constant voltage charging for 75 - 90 minutes, with a constant current of 52000 mA during charging, a rate of 0.5 C, and constant voltage charging after reaching the rated voltage, with the current gradually decreasing to 5200 mA and a rate of 0.05 C; standing still for 1 minute; constant current discharging for 60 - 120 minutes, with a constant current of 52000 mA or 104000 mA during discharging, a rate of 0.5 C when the constant current is 52000 mA, and a rate of 1 C when the constant current is 104000 mA; standing still for 1 minute; constant current and constant voltage charging for 75 - 90 minutes, with a constant current of 52000 mA during charging, a rate of 0.5 C, and constant voltage charging after reaching the rated voltage, with the current gradually decreasing to 5200 mA and a rate of 0.05 C; standing still for 1 minute.

[0076] S202. Extract the forming characteristic charging capacity from multiple forming charging capacities.

[0077] Among them, the forming characteristic charging capacity may include the average charging capacity, the final charging capacity (the capacity at the end of charging), the charging capacity mode (the charging capacity that appears most frequently in the forming parameter information), and the maximum charging capacity.

[0078] In this step, during the forming process of the battery cell, since the internal resistance of the battery cell is inversely proportional to the capacity of the battery cell, that is, the greater the internal resistance of the battery cell, the smaller the capacity. Therefore, during the constant voltage and constant current charging process of the battery cell, the charging capacity of the battery cell does not increase linearly with time, and during the constant voltage and constant current discharging process of the battery cell, the discharging capacity of the battery cell does not decrease linearly with time. The voltage curve of the battery cell during charging and discharging is approximately symmetric, and the magnitude of the tangent slope determines the speed at which the battery cell reaches the rated voltage. That is to say, the greater the slope, the faster the battery cell is fully charged, and the battery cell can also reach the rated voltage faster during discharging. Based on the above reasons, in a possible implementation manner, the forming characteristic charging capacity can be calculated by the following formula:

[0079] C t = dC / dt (1)

[0080] Among them, C t is the forming characteristic charging capacity, C is the forming charging capacity.

[0081] S203. Extract the forming characteristic voltage value from multiple forming voltage values.

[0082] Among them, the formation characteristic voltage value may include the voltage mode (the voltage value that appears most frequently in the formation parameter information), the average voltage value, the maximum voltage value, and the initial voltage value (the voltage value when the battery cell starts charging).

[0083] In this step, the characteristic formation voltage value can be calculated by the following formula:

[0084] V t = dV / dt (2)

[0085] Among them, V t is the characteristic formation voltage value, V is the formation voltage value.

[0086] S204. Extract the characteristic formation ambient temperature from multiple formation ambient temperatures.

[0087] Among them, the characteristic formation ambient temperature may include the initial ambient temperature, the final ambient temperature, and the average ambient temperature.

[0088] In this step, the characteristic formation ambient temperature can be calculated by the following formula:

[0089] T t = dT / dt (3)

[0090] Among them, T t is the characteristic formation ambient temperature, T is the formation ambient temperature.

[0091] It should be noted that before performing the above steps S202 to S204, the preset capacity threshold range, the preset voltage threshold range, and the preset temperature threshold range can be obtained first. Then, according to multiple formation charging capacities and the preset capacity threshold range, the qualified formation charging capacity can be determined. According to multiple formation voltage values and the preset voltage threshold range, the qualified formation voltage value can be determined. According to multiple formation ambient temperatures and the preset temperature threshold range, the qualified formation ambient temperature can be determined. For example, the formation charging capacities within the preset capacity threshold range among multiple formation charging capacities can be used as the qualified formation charging capacities, the formation voltage values within the preset voltage threshold range among multiple formation voltage values can be used as the qualified formation voltage values, and the formation ambient temperatures within the preset temperature threshold range among multiple formation ambient temperatures can be used as the qualified formation ambient temperatures.

[0092] Further, after determining the qualified charging capacity, the qualified voltage value, and the qualified ambient temperature, the characteristic charging capacity for formation can be extracted from the qualified charging capacity, the characteristic voltage value for formation can be extracted from the qualified voltage value, and the characteristic ambient temperature for formation can be extracted from the qualified ambient temperature. In this way, unqualified data in the collected formation parameter information can be filtered out, thereby improving the accuracy of capacity prediction.

[0093] S205. According to the characteristic charging capacity for formation, the characteristic voltage value for formation, the characteristic ambient temperature for formation, and the charging duration, obtain the discharge capacity of the battery cell after formation through the capacity prediction model.

[0094] In this step, after obtaining the characteristic charging capacity for formation, the characteristic voltage value for formation, the characteristic ambient temperature for formation, and the charging duration, the characteristic charging capacity for formation, the characteristic voltage value for formation, the characteristic ambient temperature for formation, and the charging duration can be input into the capacity prediction model to obtain the discharge capacity of the battery cell after formation.

[0095] Among them, the capacity prediction model can be trained in the following manner:

[0096] Obtain the sample parameter information of multiple sample battery cells during a preset time period in the formation process. The preset time period includes the time period from the start of formation of the sample battery cell to the end of the first full discharge, and train the gradient boosting regression tree through the sample parameter information to obtain the capacity prediction model.

[0097] Exemplarily, after obtaining the sample parameter information, extract the sample characteristic parameter information from the sample parameter information. The method of extracting the sample characteristic parameter information can refer to the method of extracting the characteristic parameter information for formation in steps S202 to S204, which will not be elaborated here. Preprocess the sample characteristic parameter information and divide the preprocessed sample characteristic parameter information into a training set and a test set according to a preset ratio. The preset ratio can be 9:1, and the present disclosure does not limit this. The loss function of the gradient boosting regression tree is L ( y , c ) The output gradient boosting regression tree is f(x) Initialize the gradient boosting regression tree to obtain a tree with only one root node f m ( x ) Among them,

[0098] (4)

[0099] After that, let m = 1, 2, 3,..., M and let n = 1, 2, 3,..., N for solution. M andN is a non - zero real number. Calculate the negative gradient value of the loss function of the current model, and use the calculated negative gradient value as the estimated value of the residual. Here, M is the number of regression trees, N is the number of sample feature parameter information, and the calculated negative gradient value is:

[0100] (5)

[0101] Furthermore, a linear search can be performed on the fitted regression tree to obtain the leaf node of the m - th tree R ma , and estimate the value of the leaf node through the following formula c ma :

[0102] (6)

[0103] where , y b is x b the output corresponding to on the regression tree, R a is the a th region of the regression tree, a The value range of is (1, A ).

[0104] Repeat the above steps. Finally, the expression of the capacity prediction model is:

[0105] (7)

[0106] where is the discharge capacity of the battery cell after formation, represents the m th regression tree, f m ( x ) represents m functions f(x) ,,[[]] R ma is the value of the feature splitting point, is the parameter of the m th regression tree, M is the number of regression trees, A is the number of leaf nodes of the regression tree, , m The value range of is (1, M ), M and A are non - zero real numbers.

[0107] Exemplarily, as described in Table 1, data corresponding to 5 embodiments are listed. Each embodiment includes the calculated average charging capacity, final charging capacity, charging capacity mode, maximum charging capacity, voltage mode, average voltage value, maximum voltage value, initial voltage value, initial ambient temperature, final ambient temperature, average ambient temperature, charging duration, the predicted discharge capacity of the cell after formation obtained through the capacity prediction model based on the data of each embodiment, and the true discharge capacity of the cell.

[0108] Table 1

[0109] Example 1 Example 2 Example 3 Example 4 Example 5 Average charging capacity (unit: mAh) 12.626 12.633 12.665 12.648 12.562 Final charging capacity (unit: mAh) 58959.418 59352.368 59983.347 59273.88 58902.365 Mode of charging capacity (unit: mAh) 14.444 14.444 14.444 14.445 14.444 Maximum charging capacity (unit: mAh) 14.445 14.445 14.445 14.445 14.444 Mode of voltage (unit: mv) 0.133 0.1 0.1 0.1 0.133 Average voltage value (unit: mv) 0.116 0.115 0.114 0.114 0.116 Maximum voltage value (unit: mv) 1 1.3 1.1 1.5 0.95 Initial voltage value (unit: mv) 3657.6 3659.5 3658.3 3662.3 3656.3 Initial ambient temperature (unit: °C) 22.4 25.5 19.9 24.3 24.6 Final ambient temperature (unit: °C) 23.3 26.4 21.2 25.4 25 Average ambient temperature (unit: °C) 23.133 25.916 21.016 24.95 25.05 Charging duration (unit: seconds) 4656 4697 4735 4685 4666 Predicted discharge capacity (unit: mAh) 104386.754 104703.78 105789.39 104772.229 103548.086 Actual discharge capacity (unit: mAh) 104795.758 104733.445 105744.628 104983.673 103665.623

[0110] By using the above method, the formation parameter information of the cell in the time period from the start of formation to before the first full discharge can be obtained first. The formation characteristic parameter information is extracted from the formation parameter information. After the formation characteristic parameter information is input into the capacity prediction model, the discharge capacity of the cell after formation can be obtained, without waiting for the cell to be fully discharged, so that the discharge capacity of the cell after formation can be obtained. In this way, the time required in the formation process of the cell can be saved, and thus the production cost of the cell can be reduced.

[0111] Figure 3 FIG. is a schematic structural diagram of a device for obtaining the discharge capacity of a cell shown according to an exemplary embodiment. As Figure 3 shown, the device may include:

[0112] A parameter information acquisition module 301, configured to acquire formation parameter information of the cell in a target time period during the formation process, where the target time period includes the time period from the start of formation of the cell to before the first full discharge;

[0113] A parameter information extraction module 302, configured to extract formation characteristic parameter information from the formation parameter information;

[0114] A discharge capacity acquisition module 303, configured to obtain the discharge capacity of the cell after formation through the capacity prediction model according to the formation characteristic parameter information, where the capacity prediction model is pre-trained by a gradient boosting regression tree.

[0115] Optionally, Figure 4 FIG. is a schematic structural diagram of a second device for obtaining the discharge capacity of a cell shown according to an exemplary embodiment. As Figure 4 shown, the device further includes:

[0116] The model training module 304 is configured to obtain sample parameter information of a plurality of sample battery cells during a preset time period in the formation process, where the preset time period includes the time period from the start of formation of the sample battery cell to the end of the first full discharge; extract sample feature parameter information from the sample parameter information; and train the gradient boosting regression tree with the sample feature parameter information to obtain the capacity prediction model.

[0117] Optionally, the formation parameter information includes a plurality of formation charging capacities, a plurality of formation voltage values, a plurality of formation ambient temperatures, and a charging duration of the battery cell, and the formation feature parameter information includes a formation feature charging capacity, a formation feature voltage value, a formation feature ambient temperature, and the charging duration; the parameter information extraction module 302 is further configured to:

[0118] Extract the formation feature charging capacity from the plurality of formation charging capacities;

[0119] Extract the formation feature voltage value from the plurality of formation voltage values;

[0120] Extract the formation feature ambient temperature from the plurality of formation ambient temperatures;

[0121] Optionally, the discharge capacity acquisition module 303 is further configured to:

[0122] Obtain the discharge capacity of the battery cell after formation through the capacity prediction model according to the formation feature charging capacity, the formation feature voltage value, the formation feature ambient temperature, and the charging duration.

[0123] Optionally, Figure 5 is a schematic structural diagram of a third device for obtaining the discharge capacity of a battery cell shown according to an exemplary embodiment, as Figure 5 shown, the device further includes:

[0124] The qualification information determination module 305 is configured to determine qualified formation parameter information according to the formation parameter information and a preset parameter threshold range;

[0125] The parameter information extraction module 302 is further configured to:

[0126] Extract the formation feature parameter information from the qualified formation parameter information.

[0127] Optionally, the expression of the capacity prediction model is:

[0128]

[0129] Wherein, is the discharge capacity of the battery cell after formation, f m ( x ) represents m functionsf(x) , represents the m th regression tree, is the parameter of the m th regression tree, M is the number of regression trees, A is the number of leaf nodes of the regression tree, , L ( y , f m-1 ( x ) +c ) is the loss function, , y b is x b the output corresponding to on the regression tree, R a is the a th region of the regression tree, R ma is the value of the feature splitting point, , m 's value range is (1, M ), a 's value range is (1, A ), M and A are non - zero real numbers.

[0130] Through the above - mentioned device, the formation parameter information of the battery cell during the period from the start of formation to the first full discharge can be obtained first. After extracting the formation feature parameter information from the formation parameter information and inputting the formation feature parameter information into the capacity prediction model, the discharge capacity of the battery cell after formation can be obtained. Without waiting for the battery cell to be fully discharged, the discharge capacity of the battery cell after formation can be obtained. In this way, the time required during the formation process of the battery cell can be saved, and thus the production cost of the battery cell can be reduced.

[0131] Regarding the device in the above - mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment related to the method, and will not be elaborated here in detail.

[0132] Figure 6 is a block diagram of an electronic device 600 shown according to an exemplary embodiment. As Figure 6 shown, the electronic device 600 may include: a processor 601, a memory 602. The electronic device 600 may further include one or more of a multimedia component 603, an I / O interface 604, and a communication component 605.

[0133] Among them, the processor 601 is used to control the overall operation of the electronic device 600 to complete all or part of the steps in the above method for obtaining the discharge capacity of the battery cell. The memory 602 is used to store various types of data to support the operation of the electronic device 600. These data may include, for example, instructions for any application program or method operating on the electronic device 600, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, and so on. The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc. The multimedia component 603 may include a screen and an audio component. Among them, the screen may be a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, and the microphone is used to receive external audio signals. The received audio signals may be further stored in the memory 602 or sent through the communication component 605. The audio component further includes at least one speaker for outputting audio signals. The I / O interface 604 provides an interface between the processor 601 and other interface modules, and the above other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 605 is used for wired or wireless communication between the electronic device 600 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, 4G, or 5G, NB-IoT (Narrow Band Internet of Things), or a combination of one or more of them. Therefore, the corresponding communication component 605 may include: a Wi-Fi module, a Bluetooth module, and an NFC module.

[0134] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the method for obtaining the discharge capacity of the battery cell as described above.

[0135] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When the program instructions are executed by a processor, the steps of the method for obtaining the discharge capacity of the battery cell as described above are implemented. For example, the computer-readable storage medium may be the memory 602 including the program instructions as described above, and the program instructions may be executed by the processor 601 of the electronic device 600 to complete the method for obtaining the discharge capacity of the battery cell as described above.

[0136] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a programmable device, and the computer program has a code part for executing the method for obtaining the discharge capacity of the battery cell as described above when executed by the programmable device.

[0137] The preferred embodiments of the present disclosure have been described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure. In addition, it should be noted that, among the various specific technical features described in the above specific embodiments, without conflict, they can be combined in any appropriate manner. To avoid unnecessary repetition, the present disclosure will not separately describe various possible combination methods.

[0138] In addition, any combination can be made between various different embodiments of the present disclosure, as long as it does not violate the idea of the present disclosure, and it should also be regarded as the content disclosed by the present disclosure.

Claims

1. A method for obtaining the discharge capacity of an electric core, characterized in that, the method includes: Obtaining the formation parameter information of the electric core within a target time period, where the target time period includes the time period from the start of formation of the electric core to before the first full discharge. The process from the start of formation of the electric core to before the first full discharge includes standing, constant current and constant voltage charging, and standing. The formation parameter information includes multiple formation charging capacities, multiple formation voltage values, multiple formation ambient temperatures, and the charging duration of the electric core; wherein, after the electric core undergoes standing, constant current and constant voltage charging, and standing, it does not undergo constant current discharge, standing, constant current and constant voltage charging, and standing; Extracting formation characteristic parameter information from the formation parameter information, where the formation characteristic parameter information includes formation characteristic charging capacity, formation characteristic voltage value, formation characteristic ambient temperature, and the charging duration; According to the formation characteristic parameter information, obtaining the discharge capacity of the electric core after formation through a capacity prediction model, where the capacity prediction model is pre-trained through a gradient boosting regression tree.

2. The method according to claim 1, characterized in that, the capacity prediction model is trained through the following method: Obtaining sample parameter information of multiple sample electric cores within a preset time period during the formation process, where the preset time period includes the time period from the start of formation of the sample electric core to the end of the first full discharge; Extracting sample characteristic parameter information from the sample parameter information; Training the gradient boosting regression tree through the sample characteristic parameter information to obtain the capacity prediction model.

3. The method according to claim 1, characterized in that, the extracting formation characteristic parameter information from the formation parameter information includes: Extracting the formation characteristic charging capacity from multiple formation charging capacities; Extracting the formation characteristic voltage value from multiple formation voltage values; Extracting the formation characteristic ambient temperature from multiple formation ambient temperatures.

4. The method according to claim 3, characterized in that, the obtaining the discharge capacity of the electric core after formation through a capacity prediction model according to the formation characteristic parameter information includes: According to the formation characteristic charging capacity, the formation characteristic voltage value, the formation characteristic ambient temperature, and the charging duration, obtaining the discharge capacity of the electric core after formation through the capacity prediction model.

5. The method according to claim 1, characterized in that, before the extracting formation characteristic parameter information from the formation parameter information, the method further includes: Determining qualified formation parameter information according to the formation parameter information and a preset parameter threshold range; the extracting formation characteristic parameter information from the formation parameter information includes: Extracting the formation characteristic parameter information from the qualified formation parameter information.

6. The method according to any one of claims 1 to 5, characterized in that, the expression of the capacity prediction model is: Among them, is the discharge capacity after formation of the battery cell, fm(x) represents m functions f(x), represents the m-th regression tree, is the parameter of the m-th regression tree, M is the number of regression trees, A is the number of leaf nodes of the regression tree, , L(y, fm-1(x)+c) is the loss function, , yb is the output corresponding to xb on the regression tree, Ra is the a-th region of the regression tree, , Rma is the value of the feature splitting point, , the value range of m is (1, M), the value range of a is (1, A), and M and A are non-zero real numbers.

7. A device for obtaining the discharge capacity of an electric core, characterized in that, the device includes: A parameter information acquisition module, configured to acquire formation parameter information of an electric core within a target time period, where the target time period includes the time period from the start of formation of the electric core to before the first full discharge, and the process from the start of formation of the electric core to before the first full discharge includes standing still, constant current and constant voltage charging, and standing still; the formation parameter information includes multiple formation charging capacities, multiple formation voltage values, multiple formation ambient temperatures, and charging duration of the electric core; wherein, after the electric core stands still, undergoes constant current and constant voltage charging, and stands still, it does not undergo constant current discharging, standing still, constant current and constant voltage charging, and standing still; A parameter information extraction module, configured to extract formation characteristic parameter information from the formation parameter information, where the formation characteristic parameter information includes formation characteristic charging capacity, formation characteristic voltage value, formation characteristic ambient temperature, and the charging duration; A discharge capacity acquisition module, configured to obtain the discharge capacity of the electric core after formation through a capacity prediction model according to the formation characteristic parameter information, and the capacity prediction model is pre-trained by a gradient boosting regression tree.

8. The apparatus according to claim 7, wherein, the apparatus further includes: A model training module, configured to obtain sample parameter information of a plurality of sample electric cores within a preset time period during the formation process, where the preset time period includes the time period from the start of formation of the sample electric core to the end of the first full discharge; extract sample characteristic parameter information from the sample parameter information; and train the gradient boosting regression tree through the sample characteristic parameter information to obtain the capacity prediction model.

9. A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the steps of the method according to any one of claims 1-6 are implemented.

10. An electronic device, wherein, comprising: a memory, on which a computer program is stored; a processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1-6.

Images