Method and device for identifying abnormal battery cell, storage medium and program product

Abstract

The invention relates to a method and device for identifying an abnormal battery cell, a non-transitory computer readable storage medium and a computer program product. The invention provides a method for identifying an abnormal battery cell in one aspect. The method comprises the following steps: acquiring voltage difference data among battery cells in a plurality of first charging periods, voltage drop data of the battery cells in a plurality of first standing periods, capacity data of the battery cells in a plurality of second charging periods and voltage drop data of the battery cells in a plurality of second standing periods; determining a first risk value based on the voltage difference data between the battery cells in the plurality of first charging periods, and determining a second risk value based on the voltage drop data of the battery cells in the plurality of first standing periods, determining a third risk value based on the capacity data of the battery cells in the plurality of second charging periods, and determining a fourth risk value based on the voltage drop data of the battery cells in the plurality of second standing periods; and identifying an abnormal cell based on the first risk value, the second risk value, the third risk value and the fourth risk value.

Description

Technical Field

[0001] The present application relates to the field of vehicles, and more particularly to a method for identifying abnormal battery cells, an apparatus for identifying abnormal battery cells, a non-transitory computer-readable storage medium, and a computer program product. Background Art

[0002] The core power source of an electric vehicle is the power battery, and the performance of the power battery directly affects the performance, endurance, and safety of the entire vehicle. The health of the power battery is one of the important indicators for evaluating the performance of the power battery. During the use of an electric vehicle, the health of the power battery can be regularly fed back to the user so that the user can take necessary fault troubleshooting and repair measures in a timely manner to improve vehicle driving safety.

[0003] The health of the power battery can be reflected in multiple aspects, such as the temperature, voltage, current, etc. of the battery. Currently, an evaluation strategy for battery health is adopted in the battery management system of electric vehicles. However, this evaluation strategy generally evaluates the battery health based on the real-time data of the vehicle and cannot comprehensively evaluate the true state of the battery, resulting in difficulty in accurately evaluating the health state of the battery under different working conditions. Summary of the Invention

[0004] To solve or at least alleviate one or more of the above problems, the following technical solutions are provided.

[0005] According to a first aspect of the present application, there is provided a method for identifying abnormal battery cells, the method including the following steps: obtaining differential pressure data between battery cells during a plurality of first charging periods, voltage drop data of battery cells during a plurality of first static periods, capacity data of battery cells during a plurality of second charging periods, and voltage drop data of battery cells during a plurality of second static periods; determining a first risk value based on the differential pressure data between battery cells during the plurality of first charging periods, determining a second risk value based on the voltage drop data of battery cells during the plurality of first static periods, determining a third risk value based on the capacity data of battery cells during the plurality of second charging periods, and determining a fourth risk value based on the voltage drop data of battery cells during the plurality of second static periods; and identifying abnormal battery cells based on the first risk value, the second risk value, the third risk value, and the fourth risk value.

[0006] According to the method for identifying abnormal battery cells according to an embodiment of the present application, obtaining differential pressure data between battery cells during a plurality of first charging periods includes: determining the plurality of first charging periods based on a charging start time and a charging end time; determining the voltage of each battery cell during the plurality of first charging periods; and obtaining the differential pressure data between battery cells during the plurality of first charging periods based on the voltage of each battery cell.

[0007] The method for identifying abnormal battery cells according to an embodiment of the present application or any of the above embodiments, wherein obtaining the voltage drop data of the battery cells in multiple first static periods includes: determining multiple candidate first static periods based on the current of the battery cells; determining the multiple first static periods according to the time interval lengths between the multiple candidate first static periods; and obtaining the voltage drop data of the battery cells in the multiple first static periods based on the difference between the voltage of the battery cells at the start time of each first static period and the voltage of the battery cells at the end time of each first static period.

[0008] The method for identifying abnormal battery cells according to an embodiment of the present application or any of the above embodiments, wherein obtaining the capacity data of the battery cells in multiple second charging periods includes: determining multiple candidate second charging periods based on the start time and end time of charging; determining the multiple second charging periods according to the voltage range of the battery cells in each candidate second charging period; and obtaining the capacity data of the battery cells in the multiple second charging periods based on the current of the battery cells within each second charging period.

[0009] The method for identifying abnormal battery cells according to an embodiment of the present application or any of the above embodiments, wherein obtaining the voltage drop data of the battery cells in multiple second static periods includes: determining multiple candidate second static periods based on the end time of charging and a predetermined duration; determining the multiple second static periods according to the current of the battery cells and the vehicle speed within each candidate second static period; and obtaining the voltage drop data of the battery cells in the multiple second static periods based on the difference between the voltage of the battery cells at the start time of each second static period and the voltage of the battery cells at the end time of each second static period.

[0010] The method for identifying abnormal battery cells according to an embodiment of the present application or any of the above embodiments, wherein determining the first risk value based on the pressure difference data between the battery cells in the multiple first charging periods includes: determining the operating condition characteristic scores of the multiple first charging periods based on the deviation degree between the pressure difference data between the battery cells in each first charging period and the average value of the pressure difference data between the battery cells in the multiple first charging periods; and determining the first risk value according to the operating condition characteristic scores of the multiple first charging periods.

[0011] The method for identifying abnormal battery cells according to an embodiment of the present application or any of the above embodiments, wherein determining the second risk value based on the voltage drop data of the battery cells in the multiple first static periods includes: determining the characteristic deviation score and the operating condition characteristic separation ratio based on the deviation degree between the voltage drop data of the battery cells in each first static period and the average value of the voltage drop data of the battery cells in the multiple first static periods; and determining the second risk value according to the maximum value of the voltage drop data of the battery cells in the multiple first static periods, the characteristic deviation score, and the operating condition characteristic separation ratio.

[0012] The method for identifying an abnormal battery cell according to an embodiment of the present application or any of the above embodiments, wherein determining a third risk value based on the capacity data of the battery cells in the plurality of second charging periods includes: determining a characteristic deviation score based on the degree of deviation between the capacity data of the battery cells in each second charging period and the average value of the capacity data of the battery cells in the plurality of second charging periods; and determining the third risk value according to the minimum value of the capacity data of the battery cells in the plurality of second charging periods and the characteristic deviation score.

[0013] The method for identifying an abnormal battery cell according to an embodiment of the present application or any of the above embodiments, wherein determining a fourth risk value based on the voltage drop data of the battery cells in the plurality of second static periods includes: determining a characteristic deviation score based on the degree of deviation between the voltage drop data of the battery cells in each second static period and the average value of the voltage drop data of the battery cells in the plurality of second static periods; and determining the fourth risk value according to the minimum value of the voltage drop data of the battery cells in the plurality of second static periods and the characteristic deviation score.

[0014] According to a second aspect of the present application, there is provided an apparatus for identifying an abnormal battery cell, the apparatus including: a memory; a processor coupled to the memory; and a computer program stored on the memory, which causes the steps of the method for identifying an abnormal battery cell according to the first aspect of the present application to be executed when the computer program runs on the processor.

[0015] According to a third aspect of the present application, there is provided a non-transitory computer-readable storage medium, characterized in that the non-transitory computer-readable storage medium includes instructions that execute the steps of the method for identifying an abnormal battery cell according to the first aspect of the present application when running.

[0016] According to a fourth aspect of the present application, there is provided a computer program product, the computer program product including instructions that implement the steps of the method for identifying an abnormal battery cell according to the first aspect of the present application when executed by a processor.

[0017] The solution for identifying an abnormal battery cell according to one or more embodiments of the present application can identify an abnormal battery cell by a first risk value determined based on the pressure difference data between battery cells in a plurality of first charging periods, a second risk value determined based on the voltage drop data of battery cells in a plurality of first static periods, a third risk value determined based on the capacity data of battery cells in a plurality of second charging periods, and a fourth risk value determined based on the voltage drop data of battery cells in a plurality of second static periods, thereby making full use of different battery cell data at different times of the vehicle, improving the accuracy of abnormal battery cell identification, facilitating the timely positioning and diagnosis of abnormal battery cells, and improving the safety and reliability of the vehicle. Description of the Drawings

[0018] The above and / or other aspects and advantages of the present application will become clearer and easier to understand through the following description of various aspects in conjunction with the accompanying drawings, where the same or similar units are denoted by the same reference numerals. In the said drawings:

[0019] Figure 1 A flowchart of a method for identifying abnormal battery cells according to one or more embodiments of the present application is shown.

[0020] Figure 2 A schematic diagram of the implementation process for identifying abnormal battery cells according to an embodiment of the present application is shown.

[0021] Figure 3 A schematic block diagram of a device for identifying abnormal battery cells according to one or more embodiments of the present application is shown. Detailed implementation manners

[0022] Exemplary embodiments of the present application are described in detail below, and examples of these embodiments are illustrated in the accompanying drawings. It should be noted that the following description is for explanation and illustration purposes only and should not be construed as a limitation of the present application. Without departing from the principles of the present application, those skilled in the art can make electrical, mechanical, logical, and structural changes to these embodiments according to actual needs without departing from the scope of the present application. In addition, those skilled in the art can understand that one or more features of different embodiments described below can be combined according to any specific application scenario or actual needs.

[0023] Terms such as "including" and "comprising" indicate that in addition to the units and steps directly and explicitly stated in the specification, the technical solutions of the present application do not exclude the situation of having other units and steps that are not directly or explicitly stated. Terms such as "first" and "second" do not indicate the order of the units in terms of time, space, size, etc., but are only used to distinguish the units.

[0024] Hereinafter, various exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0025] Figure 1 A flowchart of a method for identifying abnormal battery cells according to one or more embodiments of the present application is shown.

[0026] As Figure 1 shown, in step S101, differential pressure data between battery cells during multiple first charging periods, voltage drop data of battery cells during multiple first static periods, capacity data of battery cells during multiple second charging periods, and voltage drop data of battery cells during multiple second static periods are acquired.

[0027] Optionally, in step S101, vehicle dynamic data can be obtained and preprocessed to obtain the differential pressure data between cells during multiple first charging periods, the voltage drop data of cells during multiple first static periods, the capacity data of cells during multiple second charging periods, and the voltage drop data of cells during multiple second static periods from the preprocessed vehicle dynamic data.

[0028] In one embodiment, the vehicle dynamic data in the vehicle database can be extracted according to the vehicle VIN number, and information such as the vehicle charging state, vehicle driving mileage, battery SOC, vehicle speed, cell voltage list, cell temperature list, etc. can be extracted from the vehicle dynamic data, and the extracted information can be subjected to format conversion and data cleaning. Exemplarily, the timestamp in the format of year, month, and day can be converted to absolute seconds to facilitate the processing of time in the algorithm; the charging state data can be converted to numerical representation, for example, converting "parking charging" to "1"; for numerical information, the unit can be removed and only the numerical value is retained; for the cell voltage list, each list can contain the voltage values of all cells in the battery pack, separate the voltage values of each cell according to the delimiter, and put the voltage values of each cell into each column, and the column names are named "CELL1", "CELL2", etc., and the voltage values of each cell can be multiplied by 1000 for unit conversion; for the cell temperature list, each list can contain the detection values of all probes, separate the temperatures according to the delimiter, and put the values of each probe into each column after separation, and the column names are named "TEMP1", "TEMP2", etc. Exemplarily, during the data cleaning process, abnormal fields such as "ERR", "NULL", "NAN", "NONE", etc. in the data can be deleted. For example, when the above abnormal fields appear in the data table, the entire row can be deleted. After deleting the abnormal fields, the data can be sorted in ascending order according to the timestamp, calculate the interval of the upload time of adjacent rows, and use the upload time interval as the screening condition to select the rows with an appropriate upload time interval. For example, if the upload time interval is greater than the calibrated number of seconds, the subsequent data row that meets the condition is deleted; if the upload time interval is zero seconds, a data row is randomly deleted.

[0029] Optionally, in step S101, a plurality of first charging periods may be determined based on the charging start time and the charging end time, the voltage of each battery cell within the plurality of first charging periods may be determined, and the differential pressure data between the battery cells for the plurality of first charging periods may be obtained based on the voltage of each battery cell. In one embodiment, a plurality of candidate first charging periods may be determined based on the charging start time and the charging end time, the charging duration of each candidate first charging period may be determined based on the charging start time and the charging end time of each candidate first charging period, and the candidate first charging periods with a charging duration less than a preset duration (e.g., 10 minutes) may be deleted from the plurality of candidate first charging periods to obtain a plurality of first charging periods. In one embodiment, within each first charging period, the absolute value of the difference between the voltage of each battery cell and the voltage of other battery cells may be calculated to obtain the differential pressure data between the battery cells.

[0030] Optionally, in step S101, a plurality of candidate first static periods may be determined based on the current of the battery cell, a plurality of first static periods may be determined according to the time interval length between the plurality of candidate first static periods, and the voltage drop data of the battery cell for the plurality of first static periods may be obtained based on the difference between the voltage of the battery cell at the start time of each first static period and the voltage of the battery cell at the end time of each first static period. In one embodiment, the periods when the current of the battery cell is lower than a current threshold (e.g., 1 mA) may be selected as the plurality of candidate first static periods, and the candidate first static periods with a time interval length between the plurality of candidate first static periods greater than a preset duration (e.g., 1 s) may be used as the first static periods.

[0031] Optionally, in step S101, a plurality of candidate second charging periods may be determined based on the charging start time and the charging end time, a plurality of second charging periods may be determined according to the voltage range of the battery cell for each candidate second charging period, and the capacity data of the battery cell for the plurality of second charging periods may be obtained based on the current of the battery cell within each second charging period. In one embodiment, a voltage range of the battery cell may be preset (e.g., preset between 4V and 4.2V), and the candidate second charging periods whose voltage range of the battery cell covers the preset voltage range of the battery cell may be selected from the plurality of candidate second charging periods as the second charging periods, and the capacity data of the battery cell may be obtained based on the integration of the current of the battery cell within each second charging period.

[0032] Optionally, in step S101, multiple candidate second static periods can be determined based on the charging termination moment and a predetermined duration. Multiple second static periods can be determined according to the current of the battery cell and the vehicle speed within each candidate second static period, and the voltage drop data of the battery cell for multiple second static periods can be obtained based on the difference between the voltage of the battery cell at the start moment of each second static period and the voltage of the battery cell at the end moment of each second static period. In one embodiment, the charging termination moment plus the predetermined duration can be used as multiple candidate second static periods, and the candidate second static periods in which the current of the battery cell is less than the current threshold (e.g., 1 mA) and the vehicle speed is less than the vehicle speed threshold (e.g., 1 km / h) can be selected from the multiple candidate second static periods as the second static periods.

[0033] In step S103, a first risk value is determined based on the differential pressure data between battery cells for multiple first charging periods, a second risk value is determined based on the voltage drop data of the battery cell for multiple first static periods, a third risk value is determined based on the capacity data of the battery cell for multiple second charging periods, and a fourth risk value is determined based on the voltage drop data of the battery cell for multiple second static periods.

[0034] Optionally, in step S103, the operating condition characteristic scores for multiple first charging periods can be determined based on the degree of deviation between the differential pressure data between battery cells for each first charging period and the average value of the differential pressure data between battery cells for multiple first charging periods, and the first risk value can be determined according to the operating condition characteristic scores for multiple first charging periods. In one embodiment, for each first charging period, the difference between the differential pressure data between battery cells for each first charging period and the average value of the differential pressure data between battery cells for multiple first charging periods can be determined, and the operating condition characteristic score for this first charging period can be determined based on the ratio of this difference to this average value. In one embodiment, the corresponding relationship between the operating condition characteristic score and the first risk value can be preset to determine the first risk value based on this corresponding relationship from the operating condition characteristic score.

[0035] Optionally, in step S103, the characteristic deviation score and the operating condition characteristic separation ratio may be determined based on the deviation degree between the voltage drop data of the battery cells in each first static period and the average value of the voltage drop data of the battery cells in multiple first static periods, and the second risk value may be determined according to the maximum value, the characteristic deviation score, and the operating condition characteristic separation ratio of the voltage drop data of the battery cells in multiple first static periods. In one embodiment, the maximum value and the minimum value may be removed from the voltage drop data of the battery cells in multiple first static periods, then the average value of the voltage drop data of the battery cells in multiple first static periods after removing the maximum value and the minimum value may be calculated, the difference between the voltage drop data of the battery cells in each first static period and the average value may be determined, and the characteristic deviation score may be determined based on the ratio of the difference to the average value. In one embodiment, the operating condition characteristic separation ratio may be determined based on the ratio of the extreme values (e.g., maximum value, minimum value) in the voltage drop data of the battery cells in multiple first static periods to the average value of the voltage drop data of the battery cells in multiple first static periods. In one embodiment, the maximum value, the characteristic deviation score, and the operating condition characteristic separation ratio of the voltage drop data of the battery cells in the first static period may be subjected to standardized measurement, and the second risk value may be determined based on the product of the three after standardized measurement.

[0036] Optionally, in step S103, the characteristic deviation score may be determined based on the deviation degree between the capacity data of the battery cells in each second charging period and the average value of the capacity data of the battery cells in multiple second charging periods, and the third risk value may be determined according to the minimum value and the characteristic deviation score of the capacity data of the battery cells in multiple second charging periods. In one embodiment, the maximum value and the minimum value may be removed from the capacity data of the battery cells in multiple second charging periods, then the average value of the capacity data of the battery cells in multiple second charging periods after removing the maximum value and the minimum value may be calculated, the difference between the capacity data of the battery cells in each second charging period and the average value may be determined, and the characteristic deviation score may be determined based on the ratio of the difference to the average value. In one embodiment, the minimum value and the characteristic deviation score of the capacity data of the battery cells in multiple second charging periods may be subjected to standardized measurement, and the third risk value may be determined based on the product of the two after standardized measurement.

[0037] Optionally, in step S103, the characteristic deviation score may be determined based on the deviation degree between the voltage drop data of the battery cells in each second static period and the average value of the voltage drop data of the battery cells in multiple second static periods, and the fourth risk value may be determined according to the minimum value of the voltage drop data of the battery cells in multiple second static periods and the characteristic deviation score. In one embodiment, the maximum value and the minimum value may be removed from the voltage drop data of the battery cells in multiple second static periods, then the average value of the voltage drop data of the battery cells in multiple second static periods after removing the maximum value and the minimum value may be calculated, the difference between the voltage drop data of the battery cells in each second static period and the average value may be determined, and the characteristic deviation score may be determined based on the ratio of the difference to the average value. In one embodiment, the minimum value of the voltage drop data of the battery cells in multiple second static periods and the characteristic deviation score may be subjected to standardized measurement, and the fourth risk value may be determined based on the product of the two after standardized measurement.

[0038] In one embodiment, the differential pressure data between the battery cells in multiple first charging periods, the voltage drop data of the battery cells in multiple first static periods, the capacity data of the battery cells in multiple second charging periods, and the voltage drop data of the battery cells in multiple second static periods obtained above may be respectively input into a pre-trained neural network model to respectively determine the first risk value, the second risk value, the third risk value, and the fourth risk value.

[0039] In step S105, the abnormal battery cells are identified based on the first risk value, the second risk value, the third risk value, and the fourth risk value.

[0040] Optionally, in step S105, the abnormal battery cells may be identified based on the weighted sum of the first risk value, the second risk value, the third risk value, and the fourth risk value. Exemplarily, the weights of the first risk value, the second risk value, the third risk value, and the fourth risk value may be adjusted according to the degree of attention to different battery cell data in different periods. Exemplarily, when the weighted sum of the first risk value, the second risk value, the third risk value, and the fourth risk value is greater than the risk threshold, the corresponding battery cell may be identified as an abnormal battery cell.

[0041] The method for identifying abnormal battery cells according to one or more embodiments of the present application can identify abnormal battery cells by the first risk value determined based on the differential pressure data between the battery cells in multiple first charging periods, the second risk value determined based on the voltage drop data of the battery cells in multiple first static periods, the third risk value determined based on the capacity data of the battery cells in multiple second charging periods, and the fourth risk value determined based on the voltage drop data of the battery cells in multiple second static periods, thereby making full use of different battery cell data in different periods of the vehicle, improving the accuracy of abnormal battery cell identification, facilitating the timely positioning and diagnosis of abnormal battery cells, and improving the safety and reliability of the vehicle.

[0042] The following will be combined with Figure 2Further describe the specific implementation manner of identifying abnormal battery cells according to one or more embodiments of the present application.

[0043] Figure 2 The schematic diagram of the implementation process of identifying abnormal battery cells according to an embodiment of the present application is shown.

[0044] As Figure 2 shown, the vehicle 210 uploads real-time vehicle dynamic data to the cloud 220 for storage. The local computer 230 obtains the vehicle dynamic data from the cloud 220 and executes the method of identifying abnormal battery cells according to one or more embodiments of the present application based on the vehicle dynamic data. For example, refer to the method shown above Figure 1 When an abnormal battery cell is identified, the local computer 230 can generate an alarm message about the abnormal battery cell and send the alarm message to the vehicle 210, so as to take troubleshooting and repair measures for the abnormal battery cell.

[0045] Figure 3 The schematic block diagram of the device for identifying abnormal battery cells according to one or more embodiments of the present application is shown.

[0046] As Figure 3 shown, the device 300 for identifying abnormal battery cells includes a memory 310, a processor 320, and a computer program 330 stored on the memory 310 and executable on the processor 320. The processor 320 runs the computer program 330 to implement the method of identifying abnormal battery cells according to one aspect of the present application.

[0047] In addition, the present application can also be implemented as a non-transitory computer-readable storage medium, in which a program for causing a computer to execute the method of identifying abnormal battery cells according to one aspect of the present application is stored.

[0048] Here, as the non-transitory computer-readable storage medium, various non-transitory computer-readable storage media such as disk types (for example, magnetic disks, optical disks, etc.), card types (for example, memory cards, optical cards, etc.), semiconductor memory types (for example, ROM, non-volatile memories, etc.), tape types (for example, magnetic tapes, cassette tapes, etc.) can be adopted.

[0049] In applicable cases, various embodiments provided by this application can be implemented using hardware, software, or a combination of hardware and software. Moreover, in applicable cases, without departing from the scope of this application, various hardware components and / or software components described herein can be combined into composite components including software, hardware, and / or both. In applicable cases, without departing from the scope of this application, various hardware components and / or software components described herein can be divided into sub-components including software, hardware, or both. Additionally, in applicable cases, it is contemplated that software components can be implemented as hardware components, and vice versa.

[0050] Software according to this application (such as program code and / or data) can be stored on one or more non-transitory computer-readable storage media. It is also contemplated that one or more general-purpose or special-purpose computers and / or computer systems, whether networked and / or otherwise, can be used to implement the software identified herein. In applicable cases, the order of the various steps described herein can be changed, combined into composite steps, and / or divided into sub-steps to provide the features described herein.

[0051] The embodiments and examples provided herein are intended to best illustrate the embodiments in accordance with this application and its specific applications, and thereby enable those skilled in the art to implement and use this application. However, those skilled in the art will know that the above description and examples are provided for ease of illustration and exemplification only. The proposed description is not intended to cover all aspects of this application or to limit this application to the precise forms disclosed.

Claims

1. A method for identifying abnormal battery cells, characterized in that: The method comprises the following steps: Acquire a plurality of voltage difference data between battery cells in a first charging period, a plurality of voltage drop data of battery cells in a first static period, a plurality of capacity data of battery cells in a second charging period, and a plurality of voltage drop data of battery cells in a second static period; Determine a first risk value based on the voltage difference data between the battery cells in the first charging periods, determine a second risk value based on the voltage drop data of the battery cells in the first resting periods, determine a third risk value based on the capacity data of the battery cells in the second charging periods, and determine a fourth risk value based on the voltage drop data of the battery cells in the second resting periods; as well as Abnormal cells are identified based on the first risk value, the second risk value, the third risk value, and the fourth risk value.

2. The method according to claim 1, wherein obtaining the voltage difference data between the battery cells in the first charging period comprises: Determine the plurality of first charging time periods based on the charging start time and the charging end time; Determining the voltage of each battery cell in the plurality of first charging time periods; as well as The voltage difference data between the battery cells in the plurality of first charging periods are obtained based on the voltage of each battery cell.

3. The method according to claim 1, wherein obtaining the voltage drop data of the battery cells in the first static period comprises: determining a plurality of candidate first rest time periods based on the current of the battery cell; Determine the plurality of first quiet periods according to the lengths of the time intervals between the plurality of candidate first quiet periods; as well as The voltage drop data of the battery cells in the first rest periods are acquired based on the difference between the voltage of the battery cells at the start time of each first rest period and the voltage of the battery cells at the end time of each first rest period.

4. The method according to claim 1, wherein obtaining the capacity data of the battery cells in the second charging period comprises: determining a plurality of candidate second charging time periods based on the charging start time and the charging end time; Determine the plurality of second charging time periods according to the voltage range of the battery cell in each candidate second charging time period; as well as Capacity data of the battery cells in the plurality of second charging periods are acquired based on the current of the battery cells in each second charging period.

5. The method according to claim 1, wherein obtaining the voltage drop data of the battery cells in a plurality of second static periods comprises: determining a plurality of candidate second rest time periods based on the charging termination time and the predetermined duration; Determining the plurality of second static time periods according to the current of the battery cell and the vehicle speed in each candidate second static time period; as well as The voltage drop data of the battery cells in the plurality of second rest periods are acquired based on the difference between the voltage of the battery cells at the start time of each second rest period and the voltage of the battery cells at the end time of each second rest period.

6. The method according to claim 1, wherein determining the first risk value based on the voltage difference data between the battery cells in the plurality of first charging periods comprises: Determine the operating condition characteristic scores of the plurality of first charging periods based on the degree of deviation between the voltage difference data between the battery cells in each first charging period and the average of the voltage difference data between the battery cells in the plurality of first charging periods; as well as The first risk value is determined according to the operating condition characteristics of the plurality of first charging time periods.

7. The method according to claim 1, wherein determining the second risk value based on the voltage drop data of the battery cells during the plurality of first rest periods comprises: Determining a characteristic bias score and an operating condition characteristic separation ratio based on a degree of deviation between the voltage drop data of the battery cell in each first static period and an average of the voltage drop data of the battery cells in the plurality of first static periods; as well as The second risk value is determined according to a maximum value of the voltage drop data of the battery cells in the plurality of first static time periods, the characteristic bias score, and the operating condition characteristic separation ratio.

8. The method according to claim 1, wherein determining the third risk value based on the capacity data of the battery cells in the plurality of second charging periods comprises: determining a characteristic bias score based on a degree of deviation between the capacity data of the battery cell in each second charging period and an average value of the capacity data of the battery cells in the plurality of second charging periods; as well as The third risk value is determined according to a minimum value of the capacity data of the battery cells in the plurality of second charging time periods and the characteristic bias score.

9. The method according to claim 1, wherein determining the fourth risk value based on the voltage drop data of the battery cells in the plurality of second rest periods comprises: determining a characteristic deviation score based on a degree of deviation between the voltage drop data of the battery cell in each second static period and an average of the voltage drop data of the battery cells in the plurality of second static periods; as well as The fourth risk value is determined according to a minimum value of the voltage drop data of the battery cells in the plurality of second rest periods and the characteristic bias score.

10. A device for identifying abnormal battery cells, characterized in that: The device comprises: Memory; a processor coupled to the memory; and A computer program stored on the memory and running on the processor, wherein the running of the computer program leads to the execution of the method for identifying abnormal cells according to any one of claims 1 to 9.

11. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium includes instructions, which, when executed, execute the method for identifying abnormal battery cells according to any one of claims 1 to 9.

12. A computer program product, characterized in that The computer program product comprises instructions, and when the instructions are executed by a processor, the method for identifying abnormal battery cells according to any one of claims 1 to 9 is implemented.

Images