Battery cell classification method based on k-nearest neighbor algorithm and related device

Abstract

The embodiment of the invention relates to the field of data processing and battery cell classification, and provides a battery cell classification method based on a k-nearest neighbor algorithm and a related device, and the method comprises the steps: obtaining the charging information of a to-be-detected battery cell after standing for a first preset time period when the to-be-detected battery cell is charged according to a preset charging parameter; obtaining discharge information when the to-be-detected battery cell is discharged after the to-be-detected battery cell is charged and stands for a first preset duration; determining a first reference cell capacity value by adopting a k-nearest neighbor algorithm according to the charging information, and determining a second reference cell capacity value by adopting the k-nearest neighbor algorithm according to the discharging information; performing weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the to-be-detected cell; according to the method, classification processing is carried out according to the target cell capacity value to obtain the category information of the to-be-detected cell, the cell capacity value of the to-be-detected cell can be rapidly determined by adopting a k-nearest neighbor algorithm and classification processing is carried out, and the cell classification efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing and battery cell classification, and specifically to a battery cell classification method and related devices based on a k-nearest neighbor algorithm. Background Art

[0002] In the existing screening and classification of battery cells, the battery cells are usually screened and classified by methods such as capacity testing, internal resistance testing, and self-discharge rate testing. However, the above methods are complicated in the screening and classification process, which takes a long time and leads to low efficiency in the process. Summary of the invention

[0003] The embodiment of the present application provides a battery cell classification method and related device based on the k-nearest neighbor algorithm, which can use the k-nearest neighbor algorithm to quickly determine the capacity value of the battery cell to be detected and perform classification processing, thereby improving the efficiency of battery cell classification.

[0004] A first aspect of an embodiment of the present application provides a cell classification method based on a k-nearest neighbor algorithm, the method comprising:

[0005] Acquire charging information when the battery cell to be tested is charged according to preset charging parameters after being left stationary for a first preset time period;

[0006] Obtaining discharge information when the battery cell to be detected is discharged after the battery cell to be detected is charged and left to stand for the first preset time period;

[0007] Determine a first reference cell capacity value using a k-nearest neighbor algorithm based on the charging information, and determine a second reference cell capacity value using a k-nearest neighbor algorithm based on the discharging information;

[0008] Performing weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected;

[0009] Classification processing is performed according to the target battery cell capacity value to obtain category information of the battery cell to be detected.

[0010] In this example, by obtaining the charging information of the battery cell to be detected when it is charged according to preset charging parameters after being left standing for a first preset time, obtaining the discharge information of the battery cell to be detected when it is discharged after the charging of the battery cell to be detected is completed and the battery cell is left standing for the first preset time, a first reference battery cell capacity value is determined by using a k-nearest neighbor algorithm according to the charging information, and a second reference battery cell capacity value is determined by using a k-nearest neighbor algorithm according to the discharge information, weight calculation is performed on the first reference battery cell capacity value and the second reference battery cell capacity value to obtain a target battery cell capacity value for the battery cell to be detected, classification processing is performed according to the target battery cell capacity value to obtain category information of the battery cell to be detected, therefore, the k-nearest neighbor algorithm can be used to quickly determine the battery cell capacity value of the battery cell to be detected and perform classification processing, thereby improving the efficiency of battery cell classification.

[0011] A second aspect of an embodiment of the present application provides a battery cell classification device based on a k-nearest neighbor algorithm, the device comprising:

[0012] A first acquisition unit is used to acquire charging information when the battery cell to be tested is charged according to preset charging parameters after being left stationary for a first preset time period;

[0013] A second acquisition unit is used to acquire discharge information when the battery cell to be detected is discharged after the battery cell to be detected is charged and left to stand for the first preset time period;

[0014] A determination unit, configured to determine a first reference cell capacity value by using a k-nearest neighbor algorithm according to the charging information, and to determine a second reference cell capacity value by using a k-nearest neighbor algorithm according to the discharging information;

[0015] A calculation unit, used for performing weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected;

[0016] The classification unit is used to perform classification processing according to the target battery cell capacity value to obtain category information of the battery cell to be detected.

[0017] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0018] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0019] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic flow chart of a method for classifying battery cells based on a k-nearest neighbor algorithm is provided for an embodiment of the present application;

[0022] Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0023] Figure 3 A structural schematic diagram of a battery cell classification device based on a k-nearest neighbor algorithm is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0027] In order to better understand the battery cell classification method based on the k-nearest neighbor algorithm provided in the embodiment of the present application, the existing battery cell classification method is first briefly introduced below. In the existing scheme, when the battery cells are subjected to factory classification, secondary recycling classification, etc., they are usually classified and processed by a more complex battery cell classification method. For example, the battery cells are subjected to capacity testing, internal resistance testing, self-discharge rate testing, etc., to obtain corresponding results. After obtaining the test results, the classification is carried out according to the test results combined with a complex classification algorithm to obtain the final classification results. However, since the number of battery cells will be very large when they are shipped or recycled for the second time, and they have a high order of magnitude, when the above method is used for classification, the time spent on a single battery cell is relatively long, so that when the overall number is large, the time for the overall classification will be very long, resulting in low efficiency in classification, affecting the efficiency of subsequent processing.

[0028] In order to solve the above problems, an embodiment of the present application provides a battery cell classification method based on a k-nearest neighbor algorithm, which can quickly determine the battery cell capacity value to be tested and classify it through the collected charging information and discharging information and the k-nearest neighbor algorithm, thereby eliminating the need for complex data detection and subsequent complex data classification processing, and can quickly classify the battery cells to be tested, thereby improving the efficiency of battery cell classification.

[0029] See also Figure 1 , Figure 1 A schematic diagram of a process flow of a cell classification method based on a k-nearest neighbor algorithm is provided for an embodiment of the present application. Figure 1 As shown, the method includes:

[0030] 101. Obtain charging information when the battery cell to be tested is charged according to preset charging parameters after being left stationary for a first preset time period.

[0031] Among them, the first preset duration can be understood as the length of time that can make the state of the battery cell stable. Specifically, the first preset duration can be a duration pre-set by experience value or historical data, for example, 60 seconds. Of course, the first preset duration can also be dynamically determined in combination with the current environmental information and the property information of the battery cell. Specifically, since different battery cells have different factory properties and properties after use, and different environmental information has different effects on the stability of their states, the first preset duration is dynamically determined in combination with the above factors, which can improve the efficiency of classification and reduce the situation where the time required for actual stabilization is much less than the set time, which leads to an increase in classification time. Charging information includes the number of charges, charging temperature, starting voltage, charging voltage difference, etc.

[0032] 102. Obtain discharge information when the battery cell to be detected is discharged after the battery cell to be detected is charged and left to stand for the first preset time period.

[0033] The discharge information of the battery cell to be tested during the discharge process may include the number of discharges, discharge temperature, starting voltage, discharge voltage difference, etc. Specifically, the battery cell may be left at rest after the charging test is completed, so as to perform the discharge process in a stable state.

[0034] 103. Determine a first reference cell capacity value by using a k-nearest neighbor algorithm according to the charging information, and determine a second reference cell capacity value by using a k-nearest neighbor algorithm according to the discharging information.

[0035] Among them, the k value in the k nearest neighbor algorithm is determined to obtain a first value, and then the first value and charging information are used to determine a reference charging voltage difference set corresponding to the charging voltage difference, and finally the first reference battery cell capacity value is determined based on the reference charging voltage difference set. When the reference charging voltage difference set corresponding to the charging voltage difference is determined using the first value and charging information, it is determined using pre-stored data samples. The second reference battery cell capacity value determined using the k nearest neighbor algorithm based on the discharge information can be determined using the same method as that for determining the first reference battery cell capacity value, which will not be repeated here.

[0036] Pre-stored data samples can be obtained by the following method:

[0037] First, prepare cells with different real capacities according to the specifications and models of the cells to be screened. You can prepare cells according to the ratio of real capacity to rated capacity, such as 10% to 100%, with a gradient change of 1%, that is, 10%, 11%, 12%, and then to 100%. Secondly, set different cell test environment temperatures to carry out the subsequent tests, such as setting the temperature to -10℃~50℃ with a gradient change of 5℃. Set different starting voltages for the cells to carry out charge and discharge tests, such as setting the starting voltage to 3V~3.5V with a gradient change of 0.1V. Let the cells stand for a standing time of T1, such as 60s. Under the premise of specifying the temperature and starting voltage, charge the cells with a charging current of I, such as 1C, and a charging time of T2, such as 10s, and calculate the voltage difference before and after charging. Let the cells stand for a standing time of T1, such as 60s. Discharge the battery cell with a discharge current of I, such as 1C, and a discharge time of T2, such as 10s, and calculate the voltage difference before and after discharge.

[0038] Determine whether the specified number of charge and discharge times, such as 5 times, has been reached. If not, continue to charge and discharge. If the number of charge and discharge times has been reached, determine whether the test of different starting voltages has been completed. If not, change the initial voltage to continue the above test. If the test of different starting voltages is completed, determine whether the test of different ambient temperatures is completed. If not, change the ambient temperature to continue the above test. If the test of different ambient temperatures is completed, determine whether the test of cells with different real capacities is completed. If not, replace the cell and continue the above test. If the test of cells with different real capacities is completed, the charge and discharge voltage difference data of cells with different real capacities can be obtained, and these voltage difference data are used as the data set for cell screening. Among them, there are 5 data for fixed capacity, temperature, starting voltage, and charge and discharge voltage difference.

[0039] 104. Perform weight calculation on the first reference battery cell capacity value and the second reference battery cell capacity value to obtain a target battery cell capacity value of the battery cell to be tested.

[0040] The weights corresponding to the first reference battery cell capacity value and the second reference battery cell capacity value may be obtained respectively, and the corresponding weights are used to perform weight calculation to obtain the target battery cell capacity value.

[0041] 105. Perform classification processing according to the target battery cell capacity value to obtain category information of the battery cell to be detected.

[0042] Classification processing can be performed according to the capacity value interval where the target battery cell capacity value is located. Different capacity value intervals have corresponding analog information, so that the category information corresponding to the capacity value interval where the target battery cell capacity value is located can be determined as the category information of the battery cell to be detected.

[0043] In this example, by obtaining the charging information of the battery cell to be detected when it is charged according to preset charging parameters after being left standing for a first preset time, obtaining the discharge information of the battery cell to be detected when it is discharged after the charging of the battery cell to be detected is completed and the battery cell is left standing for the first preset time, a first reference battery cell capacity value is determined by using a k-nearest neighbor algorithm according to the charging information, and a second reference battery cell capacity value is determined by using a k-nearest neighbor algorithm according to the discharge information, weight calculation is performed on the first reference battery cell capacity value and the second reference battery cell capacity value to obtain a target battery cell capacity value for the battery cell to be detected, classification processing is performed according to the target battery cell capacity value to obtain category information of the battery cell to be detected, therefore, the k-nearest neighbor algorithm can be used to quickly determine the battery cell capacity value of the battery cell to be detected and perform classification processing, thereby improving the efficiency of battery cell classification.

[0044] In one possible implementation, a method for determining a first reference cell capacity value using a k-nearest neighbor algorithm according to the charging information includes:

[0045] A1. Determine the k value in the k nearest neighbor algorithm to obtain a first value;

[0046] A2. Determine a reference charging voltage difference set corresponding to the charging voltage difference in the charging information using a k-nearest neighbor algorithm according to the first value;

[0047] A3. Determine the first reference battery cell capacity value according to the reference charging voltage difference set.

[0048] The k value may be determined by empirical values ​​or historical data to obtain a first value, which may be, for example, 3.

[0049] A k-nearest neighbor algorithm may be used to determine a reference charging voltage difference set corresponding to the charging voltage difference in the charging information from pre-stored data samples. The number of elements in the reference charging voltage difference set is a first value.

[0050] The average value of the reference cell capacity values ​​corresponding to the reference charging voltage differences in the reference charging voltage set may be determined as the first reference cell capacity value;

[0051] Alternatively, a reference cell capacity value corresponding to a minimum charging voltage difference having a deviation value between the charging voltage difference in the data sample and the charging voltage difference of the battery cell to be detected may be determined as the first reference cell capacity value.

[0052] In this example, a reference charging voltage set can be quickly determined according to the k-nearest neighbor algorithm, and a first reference cell capacity value can be determined according to a reference charging voltage difference set, thereby improving the efficiency of determining the first reference cell capacity value.

[0053] In a possible implementation, a method for performing weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected includes:

[0054] B1. Obtain a first weight corresponding to a first reference battery cell capacity value, and obtain a second weight corresponding to a second reference battery cell capacity, wherein the sum of the first weight and the second weight is 1;

[0055] B2. The first weight and the second weight are used to perform weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected.

[0056] The first weight and the second weight can be set by experience value or historical data, and the sum of the first weight and the second weight is 1.

[0057] The target cell capacity value can be obtained by performing weight calculation using the method shown in the following formula:

[0058] Q = Q1*m+Q2*(1-m);

[0059] Among them, Q is the target battery cell capacity value, Q1 is the first reference battery cell capacity, Q2 is the second reference battery cell capacity, m is the first weight, and 1-m is the second weight.

[0060] In one possible implementation, since the target cell capacity value is classified using a capacity value interval, when the target cell capacity value is very close to the endpoint of the capacity value interval, there may be a classification deviation. For example, the target cell capacity value is within an interval, but its actual category should be classified into another adjacent category. Therefore, in order to improve the accuracy of classification, the target cell capacity value of this type can be re-discriminated to improve the accuracy of the final classification. Specifically, a method for performing classification processing according to the target cell capacity value to obtain the category information of the cell to be detected includes:

[0061] C1. Determine the capacity value interval in which the target battery cell capacity value is located to obtain a first capacity value interval;

[0062] C2. Obtain the difference between the target cell capacity value and two interval endpoints of the first capacity value interval to obtain a first difference and a second difference;

[0063] C3. If the first difference or the second difference is less than a first preset threshold, obtaining a first variance of the voltage difference in the reference charging voltage difference set, and obtaining a second variance of the voltage difference in the reference discharge voltage difference set corresponding to the second reference battery cell capacity value;

[0064] C4. If the first variance and / or the second variance is greater than a second preset threshold, extracting a first reference charging voltage difference having a minimum deviation from the charging voltage difference in the charging information, and extracting a first reference discharge voltage difference having a minimum deviation from the discharge voltage difference in the charging information;

[0065] C5. Determine a reference cell capacity value according to the first reference charging voltage difference and the second reference charging voltage difference;

[0066] C6. If the reference cell capacity value is in a first capacity value interval, determining the type information corresponding to the first capacity value interval as the category information of the cell to be detected;

[0067] C7. If the reference cell capacity value is in a second capacity value interval, determine the type information corresponding to the second capacity value interval as the category information of the cell to be detected.

[0068] The first difference and the second difference may be absolute values ​​of the difference corresponding to the left endpoint and the right endpoint of the first capacity value interval, respectively. The first preset threshold is set by empirical value or historical data.

[0069] By obtaining the first variance of the voltage difference in the reference charging voltage difference set and the second variance of the voltage difference in the reference discharge voltage difference set, the degree of discreteness of the voltage difference in the reference charging voltage difference set can be determined. When the degree of discreteness is low, the possibility of abnormal classification is low. When the degree of discreteness is large, the possibility of abnormal classification is high. Therefore, setting the second preset threshold can be used to determine whether there is a possibility of abnormal classification in its degree of discreteness. If it is higher than the second preset threshold, it can be considered that the possibility of abnormal classification is high. At this time, subsequent processing can be performed. If it is less than the second preset threshold, it is considered to be correctly classified. At this time, the category information corresponding to the first capacity value interval can be determined as the category information of the battery cell to be detected.

[0070] Determining the reference cell capacity value according to the first reference charging voltage difference and the second reference charging voltage difference may be performed using the method corresponding to determining the target cell capacity value in the aforementioned embodiment, which will not be described in detail here.

[0071] In this example, when the target cell capacity value is very close to the end point of the capacity value range, classification deviation may occur. For example, the target cell capacity value is within one range, but its actual category should be classified into another adjacent category. Therefore, in order to improve the accuracy of classification, this type of target cell capacity value can be re-discriminated to improve the accuracy of the final classification.

[0072] In a possible implementation, before acquiring charging information when the battery cell to be detected is charged according to preset charging parameters after being left at rest for a preset time, the method further includes:

[0073] D1. Obtaining the property information of the battery cell to be tested;

[0074] D2. determining a reference static time length during static placement according to the attribute information;

[0075] D3. Get the current test environment information;

[0076] D4. Determine duration adjustment information according to the current test environment information;

[0077] D5. Use the duration adjustment information to adjust the reference static duration to obtain the first preset duration.

[0078] The attribute information of the battery cell to be tested may include inherent factory attribute information, usage information, etc.

[0079] If the battery to be tested is a newly-made battery, the corresponding reference standing time can be determined based on the inherent factory attribute information, and the reference standing time can be determined by the mapping relationship between the preset inherent factory attribute information and the standing time; if the battery to be tested is a used battery, the reference standing time can be determined by combining the inherent factory attribute information and usage information, and a standing time can be determined by the mapping relationship between the preset inherent factory attribute information and the standing time, and then the standing time can be adjusted by the usage information to obtain the reference standing time. The usage information may include the usage time. Specifically, the longer the usage time, the greater the adjustment strength of the corresponding adjustment information, and the shorter the usage time, the greater the adjustment strength of the corresponding adjustment information. The adjustment strength can be understood as the increase in the time.

[0080] Since the time for the battery cell to recover to a stable state varies under different environments, the corresponding time adjustment information can be determined according to the test environment information. The sum of the time adjustment information and the reference static time can be determined as the first preset time.

[0081] In this example, since different battery cells have different factory properties and properties after use, and different environmental information has different effects on their state stability, dynamically determining the first preset time duration based on the above factors can improve the efficiency of classification and reduce the situation where the classification time is increased because the actual time required for stabilization is much shorter than the set time duration.

[0082] For the above embodiments, please refer to Figure 2 , Figure 2A schematic diagram of the structure of a terminal provided in an embodiment of the present application, as shown in the figure, includes a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0083] Acquire charging information when the battery cell to be tested is charged according to preset charging parameters after being left stationary for a first preset time period;

[0084] Obtaining discharge information when the battery cell to be detected is discharged after the battery cell to be detected is charged and left to stand for the first preset time period;

[0085] Determine a first reference cell capacity value using a k-nearest neighbor algorithm based on the charging information, and determine a second reference cell capacity value using a k-nearest neighbor algorithm based on the discharging information;

[0086] Performing weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected;

[0087] Classification processing is performed according to the target battery cell capacity value to obtain category information of the battery cell to be detected.

[0088] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0089] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0090] In line with the above, see Figure 3 , Figure 3 The present invention provides a schematic diagram of a battery cell classification device based on a k-nearest neighbor algorithm. Figure 3 As shown, the device comprises:

[0091] The first acquisition unit 301 is used to acquire charging information when the battery cell to be detected is charged according to preset charging parameters after being left to stand for a first preset time;

[0092] The second acquisition unit 302 is used to acquire discharge information when the battery cell to be detected is discharged after the battery cell to be detected is charged and left to stand for the first preset time period;

[0093] A determination unit 303 is used to determine a first reference cell capacity value by using a k-nearest neighbor algorithm according to the charging information, and to determine a second reference cell capacity value by using a k-nearest neighbor algorithm according to the discharging information;

[0094] A calculation unit 304 is used to perform weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected;

[0095] The classification unit 305 is used to perform classification processing according to the target battery cell capacity value to obtain category information of the battery cell to be detected.

[0096] In a possible implementation, in determining the first reference cell capacity value by using a k-nearest neighbor algorithm according to the charging information, the determining unit 303 is used to:

[0097] Determine the k value in the k nearest neighbor algorithm to obtain a first value;

[0098] Determine a reference charging voltage difference set corresponding to the charging voltage difference in the charging information by using a k-nearest neighbor algorithm according to the first value;

[0099] The first reference cell capacity value is determined according to the reference charging voltage difference set.

[0100] In a possible implementation, the computing unit 304 is used to:

[0101] Obtaining a first weight corresponding to a first reference battery cell capacity value, and obtaining a second weight corresponding to a second reference battery cell capacity, wherein a sum of the first weight and the second weight is 1;

[0102] The first weight and the second weight are used to perform weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected.

[0103] In a possible implementation, the classification unit 305 is specifically configured to:

[0104] Determine the capacity value interval in which the target battery cell capacity value is located to obtain a first capacity value interval;

[0105] Obtaining a difference between the target cell capacity value and two interval endpoints of the first capacity value interval to obtain a first difference and a second difference;

[0106] If the first difference or the second difference is less than a first preset threshold, obtaining a first variance of the voltage difference in the reference charging voltage difference set, and obtaining a second variance of the voltage difference in the reference discharge voltage difference set corresponding to the second reference battery cell capacity value;

[0107] If the first variance and / or the second variance is greater than a second preset threshold, extracting a first reference charging voltage difference having a minimum deviation from the charging voltage difference in the charging information, and extracting a first reference discharge voltage difference having a minimum deviation from the discharge voltage difference in the charging information;

[0108] Determine a reference cell capacity value according to the first reference charging voltage difference and the second reference charging voltage difference;

[0109] If the reference cell capacity value is in a first capacity value interval, determining the type information corresponding to the first capacity value interval as the category information of the cell to be detected;

[0110] If the reference cell capacity value is in a second capacity value interval, the type information corresponding to the second capacity value interval is determined as the category information of the cell to be detected.

[0111] In a possible implementation, before acquiring charging information when the battery cell to be detected is charged according to preset charging parameters after being left at rest for a preset time, the device is further used to:

[0112] Acquiring the property information of the battery cell to be detected;

[0113] Determine a reference static time length when static according to the attribute information;

[0114] Get the current test environment information;

[0115] Determine duration adjustment information according to the current test environment information;

[0116] The reference static time length is adjusted using the time length adjustment information to obtain the first preset time length.

[0117] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the cell classification methods based on the k-nearest neighbor algorithm as recorded in the above method embodiments.

[0118] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any one of the cell classification methods based on the k-nearest neighbor algorithm recorded in the above method embodiments.

[0119] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0120] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0124] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0125] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0126] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A cell classification method based on k-nearest neighbor algorithm, characterized in that: The method comprises: Acquire charging information when the battery cell to be tested is charged according to preset charging parameters after being left stationary for a first preset time period; Acquiring discharge information when the battery cell to be detected is discharged after the battery cell to be detected is charged and left to stand for the first preset time period; Determine a first reference cell capacity value using a k-nearest neighbor algorithm based on the charging information, and determine a second reference cell capacity value using a k-nearest neighbor algorithm based on the discharging information; Performing weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected; Classification processing is performed according to the target battery cell capacity value to obtain category information of the battery cell to be detected.

2. The battery cell classification method based on the k-nearest neighbor algorithm according to claim 1, characterized in that: The step of determining the first reference cell capacity value by using a k-nearest neighbor algorithm according to the charging information includes: Determine the k value in the k nearest neighbor algorithm to obtain a first value; Determine a reference charging voltage difference set corresponding to the charging voltage difference in the charging information by using a k-nearest neighbor algorithm according to the first value; The first reference cell capacity value is determined according to the reference charging voltage difference set.

3. The battery cell classification method based on the k-nearest neighbor algorithm according to claim 2, characterized in that: The weighted calculation of the first reference cell capacity value and the second reference cell capacity value to obtain the target cell capacity value of the cell to be detected includes: Obtaining a first weight corresponding to a first reference battery cell capacity value, and obtaining a second weight corresponding to a second reference battery cell capacity, wherein a sum of the first weight and the second weight is 1; The first weight and the second weight are used to perform weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected.

4. The battery cell classification method based on the k-nearest neighbor algorithm according to claim 2 or 3, characterized in that: The classifying process is performed according to the target cell capacity value to obtain the category information of the cell to be detected, including: Determine the capacity value interval in which the target battery cell capacity value is located to obtain a first capacity value interval; Obtaining a difference between the target cell capacity value and two interval endpoints of the first capacity value interval to obtain a first difference and a second difference; If the first difference or the second difference is less than a first preset threshold, obtaining a first variance of the voltage difference in the reference charging voltage difference set, and obtaining a second variance of the voltage difference in the reference discharge voltage difference set corresponding to the second reference battery cell capacity value; If the first variance and / or the second variance is greater than a second preset threshold, extracting a first reference charging voltage difference having a minimum deviation from the charging voltage difference in the charging information, and extracting a first reference discharge voltage difference having a minimum deviation from the discharge voltage difference in the charging information; Determine a reference cell capacity value according to the first reference charging voltage difference and the second reference charging voltage difference; If the reference cell capacity value is in a first capacity value interval, determining the type information corresponding to the first capacity value interval as the category information of the cell to be detected; If the reference cell capacity value is in a second capacity value interval, the type information corresponding to the second capacity value interval is determined as the category information of the cell to be detected.

5. The method according to any one of claims 1 to 4, characterized in that: Before acquiring charging information when the battery cell to be detected is charged according to preset charging parameters after being left at rest for a preset time, the method further includes: Obtaining property information of the battery cell to be detected; Determine a reference static time length when static according to the attribute information; Get the current test environment information; Determine duration adjustment information according to the current test environment information; The reference static time length is adjusted using the time length adjustment information to obtain the first preset time length.

6. A battery cell classification device based on a k-nearest neighbor algorithm, characterized in that: The device comprises: A first acquisition unit is used to acquire charging information when the battery cell to be tested is charged according to preset charging parameters after being left stationary for a first preset time period; A second acquisition unit is used to acquire discharge information when the battery cell to be detected is discharged after the battery cell to be detected is charged and left to stand for the first preset time period; A determination unit, configured to determine a first reference cell capacity value by using a k-nearest neighbor algorithm according to the charging information, and to determine a second reference cell capacity value by using a k-nearest neighbor algorithm according to the discharging information; A calculation unit, used for performing weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected; The classification unit is used to perform classification processing according to the target battery cell capacity value to obtain category information of the battery cell to be detected.

7. The battery cell classification device based on the k-nearest neighbor algorithm according to claim 6, characterized in that: In the aspect of determining the first reference cell capacity value by using a k-nearest neighbor algorithm according to the charging information, the determining unit is used to: Determine the k value in the k nearest neighbor algorithm to obtain a first value; Determine a reference charging voltage difference set corresponding to the charging voltage difference in the charging information by using a k-nearest neighbor algorithm according to the first value; The first reference cell capacity value is determined according to the reference charging voltage difference set.

8. The battery cell classification device based on the k-nearest neighbor algorithm according to claim 7, characterized in that: The computing unit is used for: Obtaining a first weight corresponding to a first reference battery cell capacity value, and obtaining a second weight corresponding to a second reference battery cell capacity, wherein a sum of the first weight and the second weight is 1; The first weight and the second weight are used to perform weight calculation on the first reference cell capacity value and the second reference cell capacity value to obtain a target cell capacity value of the cell to be detected.

9. A terminal, characterized in that: It includes a processor, an input device, an output device and a memory, which are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the battery cell classification method based on the k-nearest neighbor algorithm as described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the battery cell classification method based on the k-nearest neighbor algorithm as described in any one of claims 1 to 5.

Images