Battery capacity grading method and device and electronic equipment

Abstract

The invention provides a battery capacity grading method and device and electronic equipment, and relates to the technical field of batteries, and the method comprises an obtaining module which is used for obtaining a to-be-graded battery of a target model; the charging module is used for charging the battery to be subjected to capacity grading to a fully charged battery; the discharging module is used for discharging the full-charge-state battery to a preset factory state and obtaining a parameter sequence of the battery to be subjected to capacity grading; the interpolation module is used for determining a capacity interpolation sequence containing a preset number of capacity interpolation points; the construction module is used for determining a voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence, and constructing an input sequence based on the capacity interpolation points and the voltage interpolation points; the capacity grading module is used for outputting capacity grading capacity through a capacity grading model; according to the battery capacity grading method and device and the electronic equipment provided by the invention, the link of battery emptying and recharging can be avoided in a capacity grading mode through the capacity grading model, so that the capacity grading process is shortened, the energy consumption is reduced, and meanwhile, the capacity grading efficiency is also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of batteries, and in particular to a battery capacity division method, device and electronic equipment. Background Art

[0002] In the lithium-ion battery production process, the capacity grading process is a key step in evaluating the actual battery capacity. The existing capacity grading process generally uses the following process: the formed battery is charged to a full state, then discharged at a specified constant current rate to a lower voltage limit, and the fully discharged capacity is recorded. Finally, the battery is recharged to the shipping voltage or target state of charge (SoC). This process, which involves fully discharging to the lower voltage limit before recharging to the shipping state, not only wastes energy but also reduces capacity grading efficiency. Summary of the Invention

[0003] In view of this, an object of the present invention is to provide a battery capacity division method, device and electronic device to alleviate the above technical problems.

[0004] In a first aspect, an embodiment of the present invention provides a battery capacity division device, the device comprising: an acquisition module for acquiring a target model of a battery to be divided; wherein the battery to be divided is a battery that has completed a formation process; a charging module for charging the battery to be divided to a fully charged state according to a pre-configured charging mode; a discharging module for discharging the fully charged state battery to a preset factory state according to a pre-configured discharge mode, and recording the capacity parameters and voltage parameters of the battery to be divided under the discharge mode according to a pre-configured sampling frequency to obtain a parameter sequence of the battery to be divided; an interpolation module for determining a capacity including a preset number of capacity interpolation points based on the nominal capacity of the battery to be divided A capacity interpolation sequence is provided, wherein the starting value of the capacity interpolation sequence is a preset value and the ending value is the capacity value corresponding to the nominal capacity; a construction module is used to determine the voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence based on the parameter sequence of the battery to be capacity-separated, and to construct an input sequence based on the capacity interpolation points and the voltage interpolation points; a capacity division module is used to input the input sequence into a pre-trained capacity division model, and output the corresponding divided capacity based on the input sequence through the capacity division model; wherein the capacity division model is a capacity division model that matches the target model, and the training samples for training the capacity division model are constructed based on the battery to be capacity-separated of the target model.

[0005] In combination with the first aspect, an embodiment of the present invention provides a first possible implementation of the first aspect, wherein, in the above-mentioned interpolation module, the step of determining a capacity interpolation sequence including a preset number of capacity interpolation points based on the nominal capacity of the battery to be divided includes: taking the preset value as the starting value and the value corresponding to the preset percentage of the nominal capacity as the end value, linearly interpolating a preset number of capacity interpolation points between the starting value and the end value to obtain the capacity interpolation sequence.

[0006] In combination with the first aspect, an embodiment of the present invention provides a second possible implementation of the first aspect, wherein, in the above-mentioned construction module, the step of determining the voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence based on the parameter sequence of the battery to be capacity divided includes: generating a reference curve based on the parameter sequence of the battery to be capacity divided; wherein the abscissa of the reference curve is the capacity parameter, and the ordinate is the voltage parameter; in the reference curve, determining the voltage parameter corresponding to the capacity parameter of each capacity interpolation point respectively, and determining the determined voltage parameter as the voltage interpolation point corresponding to each capacity interpolation point.

[0007] In combination with the first aspect, an embodiment of the present invention provides a third possible implementation of the first aspect, wherein the capacity sizing model is obtained based on training of a neural network model; training samples used to train the capacity sizing model are constructed in the following manner: charging the target model battery to be sizing to a fully charged state according to a preconfigured charging mode; and discharging the fully charged battery to a preset lower limit state according to a preconfigured discharge mode; recording the capacity parameter and voltage parameter of the battery to be sizing under the discharge mode according to a preconfigured sampling frequency to obtain a parameter sequence of the battery to be sizing; and extracting the maximum value of the capacity parameter in the parameter sequence as a target capacity value; determining a capacity interpolation sequence including a preset number of capacity interpolation points based on the nominal capacity of the battery to be sizing, wherein the starting value of the capacity interpolation sequence is a preset value and the ending value is the capacity value corresponding to the nominal capacity; determining the voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence based on the parameter sequence of the battery to be sizing, and constructing an input sequence based on the capacity interpolation points and the voltage interpolation points; and constructing training samples for the capacity sizing model based on the input sequence and the target capacity value.

[0008] In combination with the third possible implementation of the first aspect, an embodiment of the present invention provides a fourth possible implementation of the first aspect, wherein the above-mentioned neural network model is a BP neural network model, or a CNN neural network model; the device is also used to: train the neural network model in the initial state with the input sequence as the input parameter and the target capacity value as the output parameter until the neural network model converges to obtain the capacity separation model.

[0009] In combination with the first aspect, an embodiment of the present invention provides a fifth possible implementation of the first aspect, wherein, in the above-mentioned charging module, the step of charging the battery to be divided into capacity to a fully charged battery according to a pre-configured charging mode includes: adopting a constant current and constant voltage charging mode according to a preset first rate to charge the battery to be divided into capacity to the upper limit voltage and cutoff current of the fully charged state, and performing a static treatment on the charged battery according to a pre-configured static time to obtain the fully charged battery; the step of discharging the fully charged battery to a preset factory state according to a pre-configured discharge mode includes: adopting a constant current discharge mode according to a pre-configured second rate to discharge the fully charged battery to the factory voltage value corresponding to the preset factory state.

[0010] In combination with the third possible implementation of the first aspect, an embodiment of the present invention provides a sixth possible implementation of the first aspect, wherein the above-mentioned step of charging the target model of the battery to be divided into capacity to a fully charged battery according to a preconfigured charging mode includes: adopting a constant current and constant voltage charging mode according to a preset first rate to charge the battery to be divided into capacity to the upper limit voltage and cutoff current of the fully charged state, and performing a static treatment on the charged battery according to a preconfigured static time to obtain the fully charged battery; the step of discharging the fully charged battery to a preset lower limit state according to a preconfigured discharge mode includes: adopting a constant current discharge mode according to a preconfigured second rate to discharge the fully charged battery to a preset lower limit voltage.

[0011] In a second aspect, an embodiment of the present invention further provides a battery capacity division method, the method comprising: obtaining a target model of a battery to be divided; wherein the battery to be divided is a battery that has completed a formation process; charging the battery to be divided to a fully charged state according to a pre-configured charging mode; discharging the fully charged battery to a preset factory state according to a pre-configured discharge mode, and recording the capacity parameters and voltage parameters of the battery to be divided under the discharge mode according to a pre-configured sampling frequency to obtain a parameter sequence of the battery to be divided; determining a capacity interpolation sequence containing a preset number of capacity interpolation points based on the nominal capacity of the battery to be divided, wherein In the method, the starting value of the capacity interpolation sequence is a preset value, and the ending value is the capacity value corresponding to the nominal capacity; based on the parameter sequence of the battery to be capacity-separated, the voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence is determined, and an input sequence is constructed based on the capacity interpolation points and the voltage interpolation points; the input sequence is input into a pre-trained capacity separation model, and the capacity separation model outputs the corresponding capacity separation capacity based on the input sequence; wherein the capacity separation model is a capacity separation model that matches the target model, and the training samples for training the capacity separation model are constructed based on the target model of the battery to be capacity-separated.

[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method described in the second aspect.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method described in the second aspect.

[0014] The embodiments of the present invention bring the following beneficial effects: The embodiments of the present invention provide a battery capacity division method, device, and electronic device, which can charge a battery to be divided into capacities to a fully charged state according to a pre-configured charging mode; discharge the fully charged battery to a preset factory state according to a pre-configured discharge mode, and record the capacity parameters and voltage parameters of the battery to be divided into capacities under the discharge mode according to a pre-configured sampling frequency to obtain a parameter sequence of the battery to be divided into capacities; determine a capacity interpolation sequence containing a preset number of capacity interpolation points based on the nominal capacity of the battery to be divided into capacities, and determine the capacity interpolation points in the capacity interpolation sequence based on the parameter sequence of the battery to be divided into capacities Each capacity interpolation point corresponds to a voltage interpolation point, and an input sequence is constructed based on the capacity interpolation points and the voltage interpolation points; the input sequence is input into a pre-trained capacity division model, and the capacity division model outputs the corresponding capacity division based on the input sequence; wherein, the capacity division model is a capacity division model that matches the target model, and the training samples for training the capacity division model are constructed based on the target model of batteries to be divided. The capacity division method using the capacity division model can avoid the process of discharging the battery and then recharging it, which not only shortens the capacity division process, but also reduces energy consumption, while also improving the capacity division efficiency.

[0015] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic structural diagram of a battery capacity division device provided in an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a neural network model provided by an embodiment of the present invention; Figure 3 A schematic diagram of a result provided by an embodiment of the present invention; Figure 4 A schematic diagram of a result provided by an embodiment of the present invention; Figure 5 A schematic diagram of a result provided by an embodiment of the present invention; Figure 6 A schematic diagram of a result provided by an embodiment of the present invention; Figure 7 A flow chart of a battery capacity division method provided by an embodiment of the present invention; Figure 8 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0020] At present, the capacity grading process of lithium batteries requires that the batteries be fully discharged to the lower limit voltage and then recharged to the storage state, resulting in double waste of energy. In addition, the entire charging and discharging process takes several hours, which seriously restricts the equipment turnover efficiency.

[0021] Based on this, the embodiments of the present invention provide a battery capacity division method, device, and electronic device, which can avoid the process of discharging and then recharging in the existing capacity division process, thereby improving the capacity division efficiency.

[0022] To facilitate understanding of this embodiment, a battery capacity division device disclosed in an embodiment of the present invention is first introduced in detail.

[0023] In a possible implementation, the present invention provides a battery capacity division device, such as Figure 1 The schematic diagram of a battery capacity division device shown in FIG. 1 includes the following structures: An acquisition module 10 is used to acquire target model batteries to be divided into different capacities; The battery to be capacity-divided in the embodiment of the present invention is a chemical battery that has completed the formation process, such as a lithium iron phosphate-lithium ion battery, a ternary lithium ion battery, a sodium ion battery, and the like.

[0024] The charging module 12 is used to charge the battery to be divided into different capacities to a fully charged state according to a pre-configured charging mode; The discharge module 14 is configured to discharge the fully charged battery to a preset factory state according to a pre-configured discharge mode, and record the capacity parameters and voltage parameters of the battery to be capacity-separated under the discharge mode according to a pre-configured sampling frequency to obtain a parameter sequence of the battery to be capacity-separated; In a specific implementation, in the above-mentioned charging module 12, when charging, a constant current and constant voltage charging mode can be adopted according to a preset first rate to charge the battery to be divided to the upper limit voltage and cutoff current of the fully charged state, and the charged battery can be left to rest according to a pre-configured rest time to obtain a fully charged battery; for example, a constant current and constant voltage mode can be adopted to charge to the upper limit voltage V1 according to a rate C1, with a cutoff current of I1, and then the battery is left to rest for a time of t1 to obtain a fully charged battery.

[0025] Furthermore, in the above-mentioned discharge module 14, when discharging, a constant current discharge mode can be adopted according to the pre-configured second rate to discharge the fully charged battery to the factory voltage value V3 corresponding to the preset factory state or the specified capacity. For example, the fully charged battery is discharged at a constant current rate of C2 to the factory voltage value V3 corresponding to the factory state, and then the capacity parameters and voltage parameters of the discharge process are recorded to obtain a parameter sequence, which is recorded as , where N is the number of data points.

[0026] In actual use, during the recording process, the capacity parameters and voltage parameters are recorded simultaneously as a set of data. For example, after the discharge mode is started, as the discharge time continues to pass, multiple sets of data can be recorded in sequence according to the pre-set sampling frequency, such as (q1, v1), (q2, v2)... (q N , v N ), and then organized into the above parameter sequence. That is, the capacity parameters and voltage parameters are in a one-to-one correspondence.

[0027] Among them, the upper limit voltage V1 is the design parameter of the upper limit voltage corresponding to the target model, which can be obtained according to the design specification of the product. The factory voltage value corresponding to the factory state can be set according to the actual usage; The value range is usually 0.1C-1C, The value range is 0.01C-0.1C; The value range is 0.1C-3C, where C is the design parameter of the charge and discharge rate of the target battery model, which can also be obtained from the product design specification; The value range of is usually 1min-360min, and can be set according to actual usage, which is not limited in the embodiment of the present invention.

[0028] An interpolation module 16 is configured to determine a capacity interpolation sequence comprising a preset number of capacity interpolation points based on the nominal capacity of the battery to be capacity-separated; The starting value of the capacity interpolation sequence is a preset value, and the end value is the capacity value corresponding to the nominal capacity. In specific implementation, the end value is determined according to the preset percentage of the nominal capacity, for example, Indicates the nominal capacity, the end point value is usually set to The nominal capacity can be obtained from the product design specifications.

[0029] In specific implementation, the process is a process of linearly generating a capacity interpolation sequence according to the nominal capacity of the target model of battery to be divided, that is, taking the preset value as the starting value and the value corresponding to the preset percentage of the nominal capacity as the end value, a preset number of capacity interpolation points are linearly inserted between the starting value and the end value to obtain the capacity interpolation sequence.

[0030] Furthermore, for the convenience of analysis, the above preset values ​​can be set to 0, that is, the starting value is 0 and the end value is a preset percentage of the nominal capacity. , n is the number of interpolation sequence points, that is, the number of capacity interpolation points. Usually, n is less than the number of data points N in the above parameter sequence. The capacity interpolation sequence is a linear sequence, for example, is the starting value, The capacity interpolation sequence is obtained by linearly interpolating n-2 interpolation points between the start value and the end value. The specific start value and end value can be set according to actual usage, and the embodiment of the present invention does not limit this.

[0031] A construction module 18 is used to determine the voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence based on the parameter sequence of the battery to be capacity-separated, and to construct an input sequence based on the capacity interpolation points and the voltage interpolation points; Among them, since the capacity parameter and the voltage parameter are in a one-to-one correspondence, this process is the process of interpolating the voltage parameter, that is, based on the parameter sequence of the battery to be divided, the voltage interpolation point corresponding to each capacity interpolation point is obtained. At this time, the input sequence obtained can be expressed as ,in, represents the voltage interpolation point, and and One-to-one correspondence, i.e. capacity interpolation points The corresponding voltage interpolation point is , capacity interpolation point The corresponding voltage interpolation point is etc.

[0032] The capacity division module 20 is used to input the input sequence into a pre-trained capacity division model, and output the corresponding capacity division capacity based on the input sequence through the capacity division model; In actual use, in the above-mentioned construction module 18, the process of interpolating and constructing the input sequence based on the parameter sequence of the battery to be divided is actually based on the discharge curve of the battery to be divided, that is, the relationship between the voltage parameter and the capacitance parameter. That is, a reference curve is generated based on the parameter sequence of the battery to be divided; wherein the horizontal axis of the reference curve is the capacity parameter and the vertical axis is the voltage parameter, and the reference curve is also called the discharge curve; in the reference curve, the voltage parameter corresponding to the capacity parameter of each capacity interpolation point is determined respectively, and the determined voltage parameter is determined as the voltage interpolation point corresponding to each capacity interpolation point. For example, in the reference curve, the horizontal axis is determined in sequence. The corresponding voltage parameters , the horizontal axis is Corresponding voltage parameters , until you get Corresponding voltage parameters .

[0033] Typically, the above-mentioned discharge curve contains key information such as design parameters, temperature response, and aging characteristics. In the embodiment of the present invention, based on this discharge curve as a reference curve, the parameter sequence of this interval when the fully charged battery is discharged to the preset factory voltage value is recorded to obtain the reference curve. Then, through the trained capacity classification model, implicit features are extracted from the partial discharge curve interval and a mapping relationship between it and the full discharge capacity is established.

[0034] Furthermore, the capacity sizing model in the embodiments of the present invention is tailored to the target model, and the training samples used to train the capacity sizing model are constructed based on the target model's batteries to be sizing. In other words, the battery sizing device provided by the embodiments of the present invention, which uses the capacity sizing model for sizing, avoids the need to drain and recharge batteries, shortening the sizing process and reducing energy consumption while also improving sizing efficiency.

[0035] In actual use, in order to obtain the mapping relationship between the implicit characteristics of the above-mentioned partial discharge curve interval and the full discharge capacity, it is usually necessary to pre-construct training samples that meet this characteristic to train the capacity classification model, so that the capacity classification model can accurately predict the capacity of the battery to be classified.

[0036] In specific implementation, for target batteries that have completed the formation process, i.e., batteries to be capacity-separated, a portion of the target batteries is usually separated as training batteries to construct training samples, so as to train and obtain a capacity-separated model. Furthermore, the capacity-separated model in the embodiment of the present invention is obtained through training of a neural network model; therefore, in the embodiment of the present invention, the training samples used to train the capacity-separated model are constructed in the following manner: (1) charging the target model of the battery to be divided into different capacities according to a pre-configured charging mode to a fully charged state; and discharging the fully charged battery to a preset lower limit state according to a pre-configured discharging mode; (2) recording the capacity parameters and voltage parameters of the battery to be divided in the discharge mode according to a pre-configured sampling frequency to obtain a parameter sequence of the battery to be divided; and extracting the maximum value of the capacity parameter in the parameter sequence as the target capacity value; In actual use, the charging process in (1) is similar to the charging process in the aforementioned charging module 12, that is, the battery to be divided is charged to the upper limit voltage and cutoff current of the fully charged state according to the constant current and constant voltage charging mode at a preset first rate, and the charged battery is left to rest according to a pre-configured resting time to obtain a fully charged battery; and the discharge process in (2) is different from that in the aforementioned discharge module 14 in that, when constructing the training sample, the discharge process does not discharge the fully charged battery to the preset factory state, but discharges the fully charged battery to the lower limit voltage state, that is, the fully charged battery is discharged to the preset lower limit voltage by using the constant current discharge mode at a pre-configured second rate. The lower limit voltage can be expressed as V2, which can usually be obtained according to the product design specification or set according to an empirical value, such as V2 = 2V-2.75V for lithium-ion batteries and V2 = 1.5V-2V for sodium-ion batteries. When constructing training samples, the discharge process in (2) above is designed to ultimately extract the maximum value of the capacity parameter, which is the target capacity value and can also be used as the full discharge capacity. Therefore, the above discharge process requires the battery to be discharged from the full charge state to the lower limit voltage state.

[0037] (3) Determining a capacity interpolation sequence containing a preset number of capacity interpolation points based on the nominal capacity of the battery to be divided, wherein the starting value of the capacity interpolation sequence is a preset value and the ending value is the capacity value corresponding to the nominal capacity; (4) Based on the parameter sequence of the battery to be divided, determine the voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence, and construct the input sequence based on the capacity interpolation points and voltage interpolation points; The process of constructing the capacity interpolation sequence in (3) and (4) and inputting the sequence can refer to the execution process of the aforementioned interpolation module 16 and construction module 18.

[0038] (5) Construct training samples of the capacity classification model based on the input sequence and target capacity value.

[0039] In actual use, the above target capacity value can be expressed as , the input sequence constructed in (4) is also called the training sequence and can be expressed as: =

[0040] Furthermore, when training the capacity separation model based on the above training samples, the neural network model in the initial state is trained with the above input sequence (i.e., training sequence) as input parameters and the target capacity value as output parameters until the neural network model converges to obtain the capacity separation model.

[0041] Specifically, the value range of n in the above training sequence is usually 50-500, preferably 100 and 200; the number of target model batteries to be divided used in the above construction of training samples is usually required to be greater than 200 to facilitate model convergence. In addition, the neural network model in the embodiment of the present invention is a BP neural network model or a CNN neural network model. Furthermore, for the BP neural network model, the number of hidden layers is usually greater than 10, the number of input layer features is the same as n, and the loss function can be mean square error, mean absolute error, total absolute error, total square error, etc., preferably mean square error. The specific setting can be based on actual usage, and the embodiment of the present invention does not limit this.

[0042] Furthermore, in order to confirm that the capacity separation method using the capacity separation model in the embodiment of the present invention is effective and feasible, the capacity separation results obtained by the capacity separation model in the embodiment of the present invention are also evaluated under laboratory conditions. Specifically, the evaluation formula is explained using relative error and mean square error as examples. The calculation formula can be expressed as follows:

[0043]

[0044] in, Represents the relative error, represents the mean square error, For battery test capacity, for example, the capacity obtained by traditional capacity division method, The estimated capacity is the capacity output by the capacity division model using the method provided in the embodiment of the present invention.

[0045] further, Figure 2 The figure shows a schematic diagram of the structure of a neural network model, which includes 10 hidden layers and one output layer. Figure 2 Where W represents a weight parameter, b represents a bias parameter, and specific parameter settings are adjusted based on training results, which is not limited in the embodiment of the present invention.

[0046] Specifically, assuming that the target model of battery to be capacity-classified is a 54Ah lithium iron phosphate-lithium ion battery, the number of training samples is 1897; further, Set to 0.05C, Set to 3.85V, To set 0.02C, Set to 5 minutes, Set to 0.5C, Set to 2.5V, factory voltage value is 3V, n is 200, Nominal capacity 50%; Based on the above setting parameters, the capacity classification model is trained and Figure 1 The method shown in the figure is used to obtain the divided capacity. The maximum relative error calculated is: , .

[0047] further, Figure 3 A schematic diagram of the results is also shown, wherein Figure 3 (a) is the relative error Statistical distribution diagram; (b) is the absolute error statistical distribution diagram; (c) is a statistical distribution comparison diagram of the capacity division capacity actually measured by the traditional method and the capacity division capacity output by the capacity division model in the embodiment of the present invention, wherein "pre" represents the estimated capacity, that is, the capacity division capacity output by the capacity division model in the embodiment of the present invention; "true" represents the capacity division capacity actually measured; (d) is a regression fitting diagram of the capacity division capacity actually measured by the traditional method and the capacity division capacity output by the capacity division model in the embodiment of the present invention, the horizontal axis is the measured capacity, the vertical axis is the estimated capacity, the solid line "Fit" is the linear regression curve of the measured capacity and the estimated capacity, the dotted line "Y=T" represents the straight line when the test value (e.g., measured capacity) and the predicted value (e.g., estimated capacity) are completely equal, and the more hollow circles fall on the dotted line, the higher the accuracy of the capacity division model result.

[0048] based on Figure 3 It can be seen that the result of the divided capacity obtained by the battery capacity division device provided in the embodiment of the present invention is within the allowable range, indicating that the battery capacity division device provided in the embodiment of the present invention can effectively estimate the divided capacity of the battery.

[0049] Further, based on the above example, modify Nominal capacity 25% of the maximum relative error , ,as well as, Figure 4 The comparison results shown are Figure 4 It can be seen that when the end point value of the capacity interpolation sequence is adjusted, the battery's capacity can also be effectively estimated.

[0050] Furthermore, assuming that the target model of battery to be classified is a 5Ah ternary lithium-ion battery, the number of training samples is 512; further assuming that 0.2C, is 4.2V, 0.01C, For 10 minutes, 0.5C, is 2.5V, is 2.5Ah, n is 100, Nominal capacity 50%; also using Figure 2 The neural network model shown in the figure is expressed as Figure 5 , that is, the maximum relative error , Rsq=0.936, which is within the allowable range, indicating that the battery capacity division device provided in the embodiment of the present invention can effectively estimate the capacity division of the ternary lithium-ion battery.

[0051] Furthermore, assuming that the target model of battery to be capacity-classified is 1.3Ah sodium-ion battery, the number of training samples is 564; further assuming that 0.5C, is 3.95V, 0.03C, For 5 minutes, 0.5C, is 1.5V, is 0.65Ah, n is 150, Nominal capacity 50%; also using Figure 2 The neural network model shown in the figure is expressed as Figure 6 , at this time, the maximum relative error , , within the allowable range, indicating that the battery capacity division device provided by the embodiment of the present invention can effectively estimate the capacity division of the sodium ion battery.

[0052] Furthermore, based on the above embodiment, the present invention also provides a battery capacity division method, which is applied to the above battery capacity division device such as Figure 7 A flow chart of a battery capacity division method is shown, the method comprising: Step S702, obtaining target model batteries to be capacity-separated; wherein the batteries to be capacity-separated are batteries that have completed the formation process; Step S704, charging the battery to be divided into different capacities to a fully charged state according to a pre-configured charging mode; Step S706, discharging the fully charged battery to a preset factory state according to a pre-configured discharge mode, and recording the capacity parameters and voltage parameters of the battery to be capacity-separated under the discharge mode according to a pre-configured sampling frequency to obtain a parameter sequence of the battery to be capacity-separated; Step S708: determining a capacity interpolation sequence including a preset number of capacity interpolation points based on the nominal capacity of the battery to be capacity-separated, wherein the starting value of the capacity interpolation sequence is a preset value and the ending value is the capacity value corresponding to the nominal capacity; Step S710: Based on the parameter sequence of the battery to be capacity-separated, determine the voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence, and construct an input sequence based on the capacity interpolation points and the voltage interpolation points; Step S712: Input the input sequence into a pre-trained capacity classification model, and output the corresponding capacity classification capacity based on the input sequence through the capacity classification model; wherein the capacity classification model is a capacity classification model that matches the target model, and the training samples for training the capacity classification model are constructed based on the target model of batteries to be classified.

[0053] The battery capacity division method provided in the embodiment of the present invention has the same technical features as the battery capacity division device provided in the above embodiment, and therefore can solve the same technical problems and achieve the same technical effects.

[0054] Furthermore, an embodiment of the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0055] An embodiment of the present invention further 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 the above method are executed.

[0056] Furthermore, an embodiment of the present invention also provides a structural diagram of an electronic device, such as Figure 8 As shown, it is a structural diagram of the electronic device, wherein the electronic device includes a processor 81 and a memory 80, the memory 80 stores computer executable instructions that can be executed by the processor 81, and the processor 81 executes the computer executable instructions to implement the above method.

[0057] exist Figure 8 In the illustrated embodiment, the electronic device further includes a bus 82 and a communication interface 83 , wherein the processor 81 , the communication interface 83 and the memory 80 are connected via the bus 82 .

[0058] Among them, the memory 80 may include high-speed random access memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 83 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 82 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 82 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0059] Processor 81 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be performed by hardware integrated logic circuits within processor 81 or by software instructions. The processor 81 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software module may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or the like. The storage medium is located in the memory, and the processor 81 reads the information in the memory and completes the above method in combination with its hardware.

[0060] The embodiments of the present invention provide a battery capacity division method, device, and computer program product for an electronic device, including a computer-readable storage medium storing program code. The program code includes instructions that can be used to execute the methods described in the previous method embodiments. For specific implementation, please refer to the method embodiments and will not be repeated here.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the method described above can refer to the corresponding process in the aforementioned embodiment and will not be repeated here.

[0062] In addition, in the description of the embodiments of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0063] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0064] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0065] Finally, it should be noted that the above embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A battery capacity division device, characterized in that: The device comprises: An acquisition module is used to acquire target-type batteries to be capacity-separated; wherein the batteries to be capacity-separated are batteries that have completed a formation process; A charging module, configured to charge the battery to be divided into different capacities to a fully charged state according to a pre-configured charging mode; a discharge module, configured to discharge the fully charged battery to a preset factory state according to a pre-configured discharge mode, and record the capacity parameters and voltage parameters of the battery to be capacity-separated under the discharge mode according to a pre-configured sampling frequency to obtain a parameter sequence of the battery to be capacity-separated; an interpolation module, configured to determine a capacity interpolation sequence comprising a preset number of capacity interpolation points based on the nominal capacity of the battery to be capacity-separated, wherein a starting value of the capacity interpolation sequence is a preset value and an ending value is a capacity value corresponding to the nominal capacity; A construction module, configured to determine, based on the parameter sequence of the battery to be capacity-separated, a voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence, and construct an input sequence based on the capacity interpolation points and the voltage interpolation points; The capacity division module is configured to input the input sequence into a pre-trained capacity division model, and output the corresponding capacity division capacity based on the input sequence through the capacity division model; wherein the capacity division model is a capacity division model that matches the target model, and the training samples for training the capacity division model are constructed based on the target model of batteries to be divided.

2. The device according to claim 1, characterized in that In the interpolation module, the step of determining a capacity interpolation sequence including a preset number of capacity interpolation points based on the nominal capacity of the battery to be divided includes: The preset value is used as a starting value, the value corresponding to the preset percentage of the nominal capacity is used as an end value, and a preset number of capacity interpolation points are linearly interpolated between the starting value and the end value to obtain the capacity interpolation sequence.

3. The device according to claim 1, characterized in that In the construction module, the step of determining the voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence based on the parameter sequence of the battery to be capacity-divided comprises: Generate a reference curve based on the parameter sequence of the battery to be capacity divided; wherein the abscissa of the reference curve is the capacity parameter and the ordinate is the voltage parameter; In the reference curve, the voltage parameter corresponding to the capacity parameter of each capacity interpolation point is determined respectively, and the determined voltage parameter is determined as the voltage interpolation point corresponding to each capacity interpolation point.

4. The device according to claim 1, characterized in that The capacity separation model is obtained based on the training of the neural network model; The training samples used to train the capacity segmentation model are constructed in the following way: Charging the target model of battery to be divided into different capacities according to a pre-configured charging mode to a fully charged battery; and, discharging the fully charged battery to a preset lower limit state according to a pre-configured discharge mode; Recording the capacity parameter and voltage parameter of the battery to be capacity-separated under the discharge mode according to a preconfigured sampling frequency to obtain a parameter sequence of the battery to be capacity-separated; and extracting the maximum value of the capacity parameter in the parameter sequence as the target capacity value; Determining a capacity interpolation sequence comprising a preset number of capacity interpolation points based on the nominal capacity of the battery to be capacity-divided, wherein a starting value of the capacity interpolation sequence is a preset value and an ending value is a capacity value corresponding to the nominal capacity; Based on the parameter sequence of the battery to be capacity-separated, determining a voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence, and constructing an input sequence based on the capacity interpolation points and the voltage interpolation points; A training sample of the capacity classification model is constructed based on the input sequence and the target capacity value.

5. The device according to claim 4, characterized in that The neural network model is a BP neural network model or a CNN neural network model; The device is also used for: The neural network model in the initial state is trained with the input sequence as an input parameter and the target capacity value as an output parameter until the neural network model converges to obtain the capacity separation model.

6. The device according to claim 1, characterized in that In the charging module, the step of charging the battery to be divided into different capacities to a fully charged state according to a pre-configured charging mode includes: charging the battery to be divided into different capacities in a constant current and constant voltage charging mode according to a preset first rate to an upper limit voltage and a cutoff current of a fully charged state, and placing the charged battery in a static state for a pre-configured static time to obtain the fully charged battery; The step of discharging the fully charged battery to a preset factory state according to a pre-configured discharge mode includes: The fully charged battery is discharged to a factory voltage value corresponding to a preset factory state by adopting a constant current discharge mode according to a pre-configured second rate.

7. The device according to claim 4, characterized in that The step of charging the target model of the battery to be divided into different capacities according to a pre-configured charging mode to a fully charged battery includes: charging the battery to be divided into different capacities in a constant current and constant voltage charging mode according to a preset first rate to an upper limit voltage and a cutoff current of a fully charged state, and placing the charged battery in a static state for a pre-configured static time to obtain the fully charged battery; The step of discharging the fully charged battery to a preset lower limit state according to a preconfigured discharge mode includes: The fully charged battery is discharged to a preset lower voltage limit by adopting a constant current discharge mode according to a pre-configured second rate.

8. A battery capacity division method, characterized in that: Applied to the device according to any one of claims 1 to 7, the method comprises: Obtaining a target model of batteries to be capacity-separated; wherein the batteries to be capacity-separated are batteries that have completed a formation process; Charging the battery to be divided into different capacities to a fully charged state according to a pre-configured charging mode; Discharging the fully charged battery to a preset factory state according to a pre-configured discharge mode, and recording the capacity parameters and voltage parameters of the battery to be capacity-separated under the discharge mode according to a pre-configured sampling frequency to obtain a parameter sequence of the battery to be capacity-separated; Determining a capacity interpolation sequence comprising a preset number of capacity interpolation points based on the nominal capacity of the battery to be capacity-divided, wherein a starting value of the capacity interpolation sequence is a preset value and an ending value is a capacity value corresponding to the nominal capacity; Based on the parameter sequence of the battery to be capacity-separated, determining a voltage interpolation point corresponding to each capacity interpolation point in the capacity interpolation sequence, and constructing an input sequence based on the capacity interpolation points and the voltage interpolation points; The input sequence is input into a pre-trained capacity classification model, and the capacity classification model outputs the corresponding capacity classification capacity based on the input sequence; wherein the capacity classification model is a capacity classification model that matches the target model, and the training samples for training the capacity classification model are constructed based on the target model of batteries to be classified.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method of claim 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when called and executed by a processor, prompt the processor to implement the method of claim 8.

Images