Battery cell fault locating method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a method and device for locating faults of an electric core, an electronic device and a storage medium. The method comprises: determining target electric cores corresponding to any production data group from each electric core according to production data of each electric core; determining the correlation degree between the production data group and the target fault according to the number of electric cores with the target fault in each target electric core and the number of electric cores with the target fault in each electric core; and determining at least one target production data group causing the target fault according to the correlation degree between each production data group and the target fault. The method for locating faults of an electric core can improve the accuracy of locating faults of an electric core.

Description

Technical Field

[0001] This application relates to the field of battery technology, specifically to a method, apparatus, electronic device, and storage medium for locating faults in a battery cell. Background Technology

[0002] To improve the yield of battery cells, for a batch of battery cells on the production line, it is necessary to locate the faulty cells to determine the cause of the fault, so as to adjust the battery cell production process according to the cause and improve the yield of battery cells.

[0003] In related technologies, cell fault location is achieved by filtering out corresponding cell parameters as potential causes of battery failure through the linear relationship between cell parameter variables and fault characteristic variables, thereby realizing cell fault location. However, this method can only characterize the correlation between cell parameters and fault characteristics at the linear level, while the relationship between cell parameters and fault characteristics may be non-linear, which affects the accuracy of cell fault location. Summary of the Invention

[0004] In view of the above problems, this application provides a method, apparatus, electronic device and storage medium for fault location of battery cells, which can improve the accuracy of fault location of battery cells.

[0005] In a first aspect, embodiments of this application provide a method for fault location of a battery cell. The method includes: determining target cells corresponding to any production data group from each battery cell based on production data of each battery cell; determining the correlation between the production data group and the target fault based on the number of battery cells with a certain target fault in each target battery cell and the number of battery cells with the target fault in each battery cell; and determining at least one target production data group that causes the target fault based on the correlation between each production data group and the target fault; wherein the production data group includes at least one production data of a certain data category.

[0006] In the technical solution of this application embodiment, by determining each target cell corresponding to any production data group from each cell based on the production data of each cell, and by determining the correlation between the production data group and the target fault based on the number of cells with a certain target fault and the number of cells with the target fault in each cell, at least one target production data group causing the target fault is determined based on the correlation between each production data group and the target fault. Thus, by performing data statistics on a batch of cells, the correlation between production data and a certain fault in the cell is determined, and the correlation between the two is used to locate the production data causing the fault, thereby improving the accuracy of cell fault location.

[0007] In some embodiments, determining target cells corresponding to any production data group from among the cells based on the production data of each cell includes: clustering the production data of the same data category in each of the cells to obtain each production data group; and determining target cells corresponding to any production data group from among the cells. This reduces the number of production data groups that need to be analyzed subsequently, improves fault location efficiency, and ensures a more sufficient number of cells in the same production data group, further improving the accuracy of cell fault location.

[0008] In some embodiments, clustering the production data of the same data category in each of the production data of each of the battery cells to obtain each production data group includes: uniformly dividing the production data of the same data category in each of the production data of each of the battery cells according to the data distribution density of the data category to obtain each production data group.

[0009] In some embodiments, determining the correlation between the production data set and the target fault based on the number of target cells with a specific target fault and the number of cells with the target fault in each target cell includes: obtaining a correlation detection result between the production data set and the target fault based on the number of target cells with the target fault in each target cell; determining that the correlation detection result indicates that the production data set is related to the target fault; and determining the correlation between the production data set and the target fault based on the number of target cells with a specific target fault and the number of cells with the target fault in each target cell. This allows for subsequent fault location detection based on the number of target cells with a specific target fault and the number of cells with the target fault in each target cell, even when the production data set is related to the target fault, thereby reducing invalid detection of cell fault location.

[0010] In some embodiments, obtaining the correlation detection result between the production data set and the target fault based on the number of cells with the target fault in each target cell includes: obtaining the expected frequency corresponding to the production data set based on the number of each target cell, the number of cells with the target fault in each target cell, and the number of each cell; determining the chi-square statistic corresponding to the production data set based on the expected frequency and the number of cells with the target fault in each target cell; performing a chi-square test on the chi-square statistic to obtain the test probability corresponding to the production data set, and determining the correlation detection result between the production data set and the target fault based on the test probability. This allows for a more accurate determination of whether the production data set is correlated with the target fault, improving the reliability of the selected production data set, and consequently improving the accuracy of subsequent cell fault location.

[0011] In some embodiments, determining the correlation detection result between the production data set and the target fault based on the test probability includes: obtaining the correlation level between the production data set and the target fault based on the comparison result between the test probability and each preset probability; wherein the preset probability is determined based on the correlation level. This enables a more accurate determination of the correlation degree between the production data set and the target fault.

[0012] In some embodiments, determining the correlation between the production data set and the target fault based on the number of target cells containing a specific target fault and the number of cells containing the target fault in each target cell includes: determining an initial correlation value between the production data set and the target fault based on the number of target cells containing a specific target fault and the number of cells containing the target fault in each target cell; and normalizing the initial correlation value to obtain the correlation between the production data set and the target fault. This ensures that the correlation between each production data set and the target fault is on a uniform scale, facilitating subsequent fault location using the correlation between each production data set and the target fault, thereby improving the accuracy of fault location using the correlation between each production data set and the target fault.

[0013] In some embodiments, normalizing the initial correlation value to obtain the correlation degree between the production data set and the target fault includes: mapping the initial correlation value to a target interval to obtain the correlation degree between the production data set and the target fault; wherein the target interval is determined based on the number of normal cells in each target battery cell and the number of normal cells in each battery cell. This allows for a more accurate characterization of the correlation degree between the production data set and the target fault, thereby improving the accuracy of fault location using the correlation degree between each production data set and the target fault.

[0014] Secondly, this application provides a battery cell fault location device, comprising: a battery cell acquisition module, configured to determine each target battery cell corresponding to any production data group from each battery cell based on each production data of each battery cell; an association detection module, configured to determine the correlation degree between the production data group and the target fault based on the number of battery cells with a certain target fault in each target battery cell and the number of battery cells with the target fault in each battery cell; and a fault location module, configured to determine at least one target production data group causing the target fault based on the correlation degree between each production data group and the target fault; wherein the production data group includes at least one production data of a certain data category.

[0015] In the technical solution of this application embodiment, by determining each target cell corresponding to any production data group from each cell based on the production data of each cell, and by determining the correlation between the production data group and the target fault based on the number of cells with a certain target fault and the number of cells with the target fault in each cell, at least one target production data group causing the target fault is determined based on the correlation between each production data group and the target fault. Thus, by performing data statistics on a batch of cells, the correlation between production data and a certain fault in the cell is determined, and the correlation between the two is used to locate the production data causing the fault, thereby improving the accuracy of cell fault location.

[0016] Thirdly, this application provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the method described in the first aspect of the embodiment.

[0017] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the method described in the first aspect of the embodiment.

[0018] Fifthly, this application provides a computer program product that, when run on a computer, causes the computer to perform the method described in the first aspect or any optional implementation thereof. Attached Figure Description

[0019] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a first flowchart of a cell fault location method according to some embodiments of this application; Figure 2 This is a second flowchart of a cell fault location method according to some embodiments of this application; Figure 3 This is a schematic diagram of the structure of a cell fault location device according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of an electronic device according to some embodiments of this application.

[0020] The reference numerals in the detailed embodiments are as follows: 301-Cell acquisition module; 302-Association detection module; 303-Fault location module; 4-Electronic equipment; 401-Processor; 402-Memory; 403-Communication bus. Detailed Implementation

[0021] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0023] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0024] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0025] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0026] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0027] To improve the yield of battery cells, for a batch of battery cells on the production line, it is necessary to locate the faulty cells to determine the cause of the fault, so as to adjust the battery cell production process according to the cause and improve the yield of battery cells.

[0028] In related technologies, cell fault location is achieved by filtering out relevant cell parameters as potential causes of battery failure through the linear relationship between cell parameter variables and fault characteristic variables, thereby realizing cell fault location. However, this method can only characterize the correlation between cell parameters and fault characteristics at the linear relationship level, while the relationship between cell parameters and fault characteristics may be non-linear, making it difficult to determine the correlation between cell parameters and fault characteristics, thus affecting the accuracy of cell fault location.

[0029] To address the aforementioned technical problems, this application embodiment identifies target cells corresponding to any production data group from each cell based on the production data of each cell. Then, based on the number of target cells with a specific target fault and the number of cells with the target fault in each cell, the correlation between the production data group and the target fault is determined. Based on the correlation between each production data group and the target fault, at least one target production data group causing the target fault is identified. Thus, by statistically analyzing data from a batch of cells, the correlation between production data and a specific fault in a cell is determined, and this correlation is used to locate the production data causing the fault, improving the accuracy of cell fault location.

[0030] The battery cell fault location method, apparatus, electronic device, and storage medium disclosed in this application can be applied to electronic devices to locate the cause of battery cell faults. The terminal device can be a mobile terminal, desktop terminal, vehicle terminal, battery management system, or server. The server can be a standalone server or a server cluster composed of multiple servers, or it can be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence sampling point devices.

[0031] A method for locating battery cell faults is provided according to some embodiments of this application, and this method can be applied to the aforementioned electronic devices. For example... Figure 1 As shown, the fault location method for this battery cell includes: S101, Based on the production data of each cell, determine the target cells corresponding to any production data group from the cells; S102, Based on the number of cells in each target cell that have a certain target fault, and the number of cells in each target cell that have the target fault, determine the correlation between the production data group and the target fault; S103, Based on the correlation between each of the production data groups and the target fault, determine at least one target production data group that caused the target fault; The production data group includes at least one production data from a certain data category.

[0032] In some embodiments, each battery cell can be from the same production batch, and each battery cell has multiple production data sets. The production data of a battery cell refers to MES (Manufacturing Execution System) data collected during the battery cell production process, such as production process data, process data, and battery cell data. For example, the production data can be one of the following: battery cell powder type, winding method, top cover welding station, stirring temperature, charging voltage, charging current, and heating and settling time. That is, the production data for any given battery cell can include its powder type, winding method, top cover welding station, stirring temperature, charging voltage, charging current, and heating and settling time.

[0033] For all production data of each battery cell, production data with the same data category and the same value can be identified as a production data group to obtain multiple production data groups. For example, taking the charging voltage of each battery cell as an example, assuming that the number of each battery cell is n, and the charging voltages of the n battery cells are v1, v2, ... vn, then the same charging voltage can be identified as a production data group. For example, if v1, v3... vi are all 3.1V, then a production data group of 3.1V can be identified.

[0034] After obtaining multiple production data sets based on various production data, for any given production data set, the cells containing production data corresponding to that set can be identified as the target cells for that production data set. For example, if the production data set is a charging voltage of 3.1V, then the cells containing this 3.1V charging voltage can be identified as the target cells for that production data set.

[0035] After obtaining the target cells corresponding to any production data set, the number of cells with different fault types in each target cell within that production data set can be counted. The fault type can be one of the following: poor cell winding or poor cell K-value. For example, assume the data type set of the production data is... That is, any data type Then, the production data sets of any data type, or the average value of the production data sets, can be denoted as: , Indicates data type is The i-th production data set, or the average value of the i-th production data set. Each fault is denoted as... ,in Indicates the fault type. This indicates a normal battery cell, and c-1 indicates the number of fault types. At this point, by analyzing the data, the production data set can be determined. Any fault type in each target cell Number of battery cells At this point, the data type can be obtained as... any production data set With any fault type Cross-contingency tables, such as:

[0036] In this cross contingency table, rows and... , representing any production data group The corresponding number of each target cell, columns and... This indicates the number of cells in each battery cell range that exhibit any fault type or are functioning normally. .

[0037] After obtaining a certain set of production data After determining the corresponding target cell quantities and the quantities of any fault type or normal cells, any fault type within each fault type can be designated as the target fault. Then, for any target fault within each fault type... The production data group can be identified through cross-tabulation tables. The corresponding target cells have target faults. Number of battery cells And the target fault exists in each battery cell. Number of battery cells To determine the target fault present in each target cell Number of battery cells And the target fault exists in each battery cell. Number of battery cells Determine the production data group With target fault The initial association value is To determine the production data group based on this initial association value. With target fault The degree of correlation. For example, if this initial correlation value is determined as the production data group... With target fault The correlation degree can be determined using the above method. That is, the correlation degree between each production data group, i.e., all data types of production data groups, and the target fault can be determined.

[0038] After obtaining the correlation between each production data set and the target fault, the correlation between any production data set and the target fault can be compared with a preset correlation. The preset correlation can be set according to actual conditions. If the correlation between the production data set and the target fault is greater than the preset correlation, it indicates that the production data set is a significant cause of the target cell's fault. In this case, the production data set can be identified as the target production data set causing the target fault, thus enabling the localization of the production data causing the target fault.

[0039] Alternatively, the correlation between each production data group and the target fault can be compared to identify the production data group with the highest correlation as the target production data group causing the target fault, thereby locating the production data causing the target fault.

[0040] By analyzing production data from each battery cell, target cells corresponding to any given production data set are identified. The correlation between production data sets and target faults is determined based on the number of target cells with a specific fault and the total number of target cells within each set. This correlation allows for the identification of at least one target production data set causing the fault. By statistically analyzing data from a batch of battery cells, the correlation between production data and a particular fault within a cell can be determined, enabling the identification of the production data causing the fault and improving the accuracy of cell fault location.

[0041] Considering that the amount of production data obtained for battery cells may be large, and that there are many different values ​​for production data such as stirring temperature, charging voltage, and heating and settling time, the approximate values ​​have a basically the same impact on the battery cells. Therefore, in order to improve the efficiency of battery cell fault location, in some embodiments, based on the production data of each battery cell, the target battery cells corresponding to any production data group are determined from the battery cells. This includes: clustering the production data of the same data category in the production data of each battery cell to obtain each production data group; and determining the target battery cells corresponding to any production data group from the battery cells.

[0042] For example, K-means clustering or hierarchical clustering can be used to cluster the production data of any data category within each production data set to obtain the production data groups under that data category. Taking charging voltage as an example, assuming the charging voltages of the n battery cells are v1, v2, ..., vn, a clustering algorithm can be applied to the charging voltage of each battery cell to obtain multiple production data groups with charging voltage as the data category, such as {v1, v2}, ..., {vi, ..., vn}. This allows us to obtain the production data groups under any given data category.

[0043] For production data categorized as powder type, winding method, and top cover welding station, due to significant differences between different powder types, winding methods, and top cover welding stations, and given that the parameters for these parameters are fixed, clustering these data categories still results in individual production data groups. For example, if the top cover welding stations for each battery cell include station A, station B, and station C, then the resulting clustered production data groups would be station A, station B, and station C, respectively.

[0044] After obtaining each production data set, for any given production data set, the cells containing production data corresponding to that production data set can be identified from the individual cells and designated as the target cells for that production data set. For example, if the production data set is a charging voltage {V1, V2}, then the cells containing either charging voltage V1 or V2 can be identified as the target cells for that production data set.

[0045] By clustering production data of the same category in each cell's production data, production data groups are obtained. From each cell, the target cells corresponding to any production data group can be identified, thereby reducing the number of production data groups that need to be analyzed subsequently, improving fault location efficiency, and ensuring that the number of cells in the same production data group is more sufficient, further improving the accuracy of cell fault location.

[0046] In some embodiments, clustering the production data of the same data category in each of the production data of each of the battery cells to obtain each production data group includes: uniformly dividing the production data of the same data category in each of the production data of each of the battery cells according to the data distribution density of the data category to obtain each production data group.

[0047] For example, taking charging voltage as the data category, the set of charging voltages for each battery cell can be obtained as V={v1,v2,……vn}. This set is then uniformly divided into k continuous intervals according to the data distribution density. The i-th interval can be denoted as... The intervals obtained at this point can then be identified as production data groups.

[0048] After determining each production data group, target cells corresponding to any production data group can be identified from each battery cell. The correlation between the production data group and the target fault can be determined based on the number of target cells containing a specific target fault and the number of cells containing the target fault in each battery cell. To reduce invalid detections for battery cell fault location, in some embodiments, determining the correlation between the production data group and the target fault based on the number of target cells containing a specific target fault and the number of cells containing the target fault in each battery cell includes: obtaining a correlation detection result between the production data group and the target fault based on the number of target cells containing the target fault; determining that the correlation detection result indicates the production data group is related to the target fault; and determining the correlation between the production data group and the target fault based on the number of target cells containing a specific target fault and the number of cells containing the target fault in each battery cell.

[0049] In some embodiments, after determining each target cell corresponding to the production data group, the number of cells with target faults in each target cell can be detected first. For example, the number of cells with target faults in each target cell can be compared with a preset number to determine whether there is a correlation between the production data group and the target fault.

[0050] If the number of target cells with the target fault in each target cell is greater than a preset value, such as greater than zero, it indicates that the production data set may be related to the target fault. In this case, the correlation detection result between the production data set and the target fault can be determined to be that the production data set is related to the target fault. If the number of target cells with the target fault in each target cell is less than or equal to the preset value, such as the number of target cells with the target fault in each target cell is 0, it indicates that the production data set is not related to the target fault. In this case, the correlation detection result between the production data set and the target fault can be determined to be that the production data set is not related to the target fault.

[0051] If the correlation detection result between the production data set and the target fault indicates that the production data set is unrelated to the target fault, then the production data set can be ignored to reduce invalid fault location detection. If the correlation detection result indicates that the production data set is related to the target fault, then the correlation between the production data set and the target fault is determined based on the number of cells with the target fault in each target cell and the number of cells with the target fault in each target cell. Therefore, even if the production data set is related to the target fault, subsequent fault location detection can be performed based on the number of cells with the target fault in each target cell and the number of cells with the target fault in each target cell, reducing invalid fault location detection for the cells.

[0052] To more accurately determine whether a production data set is related to a target fault, in some embodiments, the correlation detection result between the production data set and the target fault is obtained based on the number of cells with the target fault in each target cell. This includes: obtaining the expected frequency corresponding to the production data set based on the number of each target cell, the number of cells with the target fault in each target cell, and the total number of cells; determining the chi-square statistic corresponding to the production data set based on the expected frequency and the number of cells with the target fault in each target cell; performing a chi-square test on the chi-square statistic to obtain the test probability corresponding to the production data set, and determining the correlation detection result between the production data set and the target fault based on the test probability.

[0053] In some embodiments, the number of target cells corresponding to a production data group and the number of cells with target faults within each group can be counted first. For example, this can be done by recording a certain production data group. With target fault The cross-tabulation table identifies the production data group. The corresponding number of target battery cells And the presence of target faults in each battery cell. Number of battery cells According to production data groups The corresponding number of target battery cells Target faults exist in each battery cell. Number of battery cells And the number n of each battery cell, to obtain this production data set. Corresponding expected frequency .

[0054] After obtaining the production data set Corresponding expected frequency Then, based on the expected frequency And the number of target cells with target faults in each target cell Perform chi-square statistics. The difference between the actual frequency and the expected frequency in the chi-square statistics is represented by the chi-square statistic. The characterization is based on a chi-square distribution with df degrees of freedom, therefore, according to the expected frequency... And the number of target cells with target faults in each target cell By performing chi-square statistics, this production data set can be obtained. Corresponding chi-square statistic for:

[0055] in, ,

[0056] In some embodiments, a chi-square test can be designed using the principles of statistical hypothesis testing. Specifically, the chi-square test assumes the null hypothesis H0: the production data set is unrelated to the target fault; and the alternative hypothesis H1: the production data set is related to the target fault. After obtaining the production data set... Corresponding chi-square statistic Then, the error probability of rejecting the null hypothesis H0 can be found through the chi-square distribution table, which is the test probability corresponding to this production data set. , where F(x) is The probability distribution function.

[0057] After obtaining the test probability corresponding to the production data set Then, the test probability can be... The significance level is the pre-set probability of the chi-square test. A comparison was performed. Among them, .when When the null hypothesis H0 is rejected and the alternative hypothesis H1 is accepted, the probability of statistically failing to conclude that "the production data set is related to the target failure" is no more than [missing information]. . The actual value can be set according to the actual situation, such as 0.10~0.40.

[0058] If the test probability Less than or equal to this significance level If the correlation is positive, it indicates that the production data set is related to the target fault. In this case, the correlation detection result can be determined as a correlation between the production data set and the target fault. If the test probability... Greater than the significance level The correlation detection results indicate that the production data set is unrelated to the target fault.

[0059] By using the number of target cells, the number of cells with target faults in each cell, the total number of cells, and the number of cells with target faults in each target cell, a chi-square test is performed to assess the correlation between the production data set and the target fault. This allows for a more accurate determination of whether the production data set is related to the target fault, improving the reliability of the selected production data set and consequently enhancing the accuracy of subsequent cell fault location.

[0060] To more accurately determine the correlation between the production data set and the target fault, in some embodiments, the correlation detection result between the production data set and the target fault is determined based on the test probability, including: obtaining the correlation level between the production data set and the target fault based on the comparison result between the test probability and each preset probability; wherein the preset probability is determined based on the correlation level.

[0061] In some embodiments, multiple preset probabilities, i.e. multiple significance levels, can be preset. In order to pass the test probability With different significance levels The comparison results are used to determine the specific correlation between the production data set and the target fault. If the correlation is greater than or equal to the significance level of the test probability... The smaller the value, the higher the correlation between the production data set and the target fault; that is, the higher the correlation level between the production data set and the target fault. The correlation levels, from highest to lowest, are: significant correlation, strong correlation, correlation, weak correlation, and no correlation. The correlation level is negatively correlated with the preset probability; that is, the higher the correlation level, the lower the corresponding preset probability.

[0062] For example, multiple preset probabilities can be set according to the correlation levels of significant correlation, strong correlation, correlation, weak correlation, and no correlation. For instance, the preset probability for significant correlation is 0.10, for strong correlation it is 0.20, for correlation it is 0.30, and for weak correlation and no correlation it is 0.40. After determining each preset probability, the test probability will be... Compare with each preset probability. If If , it indicates that the corresponding production data set is significantly related to the target fault, and in this case, the correlation level between the production data set and the target fault can be determined to be significant; if If so, it indicates that the corresponding production data group is a production data group strongly correlated with the target fault, and at this time, the correlation level between the production data group and the target fault can be determined to be strong; if If the corresponding production data group is related to the target fault, then the correlation level between the production data group and the target fault can be determined to be "correlation". If , it indicates that the corresponding production data group is weakly correlated with the target fault, and in this case, the correlation level between the production data group and the target fault can be determined to be weak; if If the value is 0, it means that the corresponding production data group is a production data group that is not related to the target fault. In this case, it can be determined that the correlation level between the production data group and the target fault is not related.

[0063] By comparing the test probability with multiple preset probabilities, the correlation level between the production data set and the target fault can be obtained, thereby more accurately determining the degree of correlation between the production data set and the target fault.

[0064] After obtaining the correlation level between the production data set and the target fault, if the correlation level between the production data set and the target fault is weak or above, it indicates that the production data set is related to the target fault. In this case, the correlation degree between the production data set and the target fault can be determined based on the number of target cells with the target fault in each target cell corresponding to the production data set, and the number of cells with the target fault in each cell. To further improve the accuracy of fault location using correlation degree, in some embodiments, the correlation degree between the production data set and the target fault is determined based on the number of cells with a certain target fault in each target cell, and the number of cells with the target fault in each cell. This includes: determining an initial correlation value between the production data set and the target fault based on the number of cells with a certain target fault in each target cell, and the number of cells with the target fault in each cell; and normalizing the initial correlation value to obtain the correlation degree between the production data set and the target fault.

[0065] In some embodiments, production data groups can be determined using cross-tabulation tables. The corresponding target cells have target faults. Number of battery cells And the presence of target faults in each battery cell. Number of battery cells To determine the target fault present in each target cell Number of battery cells And the target fault exists in each battery cell. Number of battery cells Determine the production data group With target fault The initial association value is .

[0066] After obtaining the production data set With target fault After obtaining the initial correlation value, the initial correlation value can be normalized to obtain the correlation degree between the production data group and the target fault.

[0067] To further improve the accuracy and sensitivity of fault location by utilizing the correlation between each production data set and the target fault, in some embodiments, the initial correlation value is normalized to obtain the correlation between the production data set and the target fault. This includes mapping the initial correlation value to a target interval to obtain the correlation between the production data set and the target fault; wherein the target interval is determined based on the number of normal cells in each target cell and the number of normal cells in each cell.

[0068] For example, the number of normal cells in each target cell corresponding to a production data set can be obtained by looking up a cross-reference table that records production data sets and target faults. And the number of normal cells in each cell. To determine the target interval as .

[0069] After determining the target range, the initial correlation values ​​can be set. Mapping to the target interval yields the correlation between the production data set and the target fault, i.e., the correlation between the production data set and the target fault. The correlation between each production data set and the target fault obtained at this time can characterize the concentration of cells in each production data set at the target fault location, thereby enabling a more accurate characterization of the correlation between the production data set and the target fault, and thus improving the accuracy of fault location using the correlation between each production data set and the target fault.

[0070] In some embodiments, after determining the correlation between each production data group and the target fault, the correlation between any production data group and the target fault can be compared with a preset correlation to determine whether the production data group is the target production data group causing the target fault. For example, suppose the correlation between a certain production data group and the target fault is... The preset correlation degree is 2. If If the value is greater than 2, then the production data group can be identified as the target production data group that caused the target fault, so as to locate the production data that caused the target fault.

[0071] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below. In some embodiments, such as Figure 2 As shown, the fault location method for this battery cell includes: S201, cluster the production data of the same data category in each production data of each battery cell to obtain each production data group. For example, the production data of the same data category in each production data of each battery cell can be evenly divided according to the data distribution density of the data category to obtain each production data group.

[0072] S202, based on the number of each target cell, the number of cells with target faults in each cell, and the number of each cell, obtain the expected frequency corresponding to the production data group.

[0073] S203, based on the expected frequency and the number of cells with target faults in each target cell, determine the chi-square statistic corresponding to the production data group.

[0074] S204, perform a chi-square test on the chi-square statistic to obtain the test probability corresponding to the production data set.

[0075] S205. Based on the comparison between the test probability and each preset probability, the correlation level between the production data set and the target fault is obtained. The preset probability is negatively correlated with the correlation level.

[0076] S206, determine the correlation level between the production data group and the target fault, indicating that the production data group is related to the target fault. Based on the number of cells with a certain target fault in each target cell and the number of cells with the target fault in each cell, determine the initial correlation value between the production data group and the target fault.

[0077] S207, map the initial correlation value to the target interval to obtain the correlation degree between the production data group and the target fault; wherein, the target interval is determined based on the number of normal cells in each target cell and the number of normal cells in each cell.

[0078] S208, Based on the correlation between each production data group and the target fault, determine at least one target production data group that caused the target fault.

[0079] Figure 3 The diagram shows a schematic structural block diagram of a battery cell fault location device according to an embodiment of this application. It should be understood that this device is related to... Figure 1 as well as Figure 2 The method implementation described above corresponds to the method embodiment and is capable of performing the steps involved in the aforementioned method. The specific functions of this device can be found in the description above; to avoid repetition, detailed descriptions are omitted here. This device includes at least one software function module that can be stored in a memory or embedded in the device's operating system (OS) in the form of software or firmware. Specifically, the device includes a cell acquisition module 301, used to determine each target cell corresponding to any production data group from each cell based on each cell's production data; an association detection module 302, used to determine the correlation between the production data group and the target fault based on the number of cells with a certain target fault in each target cell and the number of cells with the target fault in each cell; and a fault location module 303, used to determine at least one target production data group causing the target fault based on the correlation between each production data group and the target fault; wherein, the production data group includes at least one production data of a certain data category.

[0080] In the technical solution of this application embodiment, by determining each target cell corresponding to any production data group from each cell based on the production data of each cell, and by determining the correlation between the production data group and the target fault based on the number of cells with a certain target fault and the number of cells with the target fault in each cell, at least one target production data group causing the target fault is determined based on the correlation between each production data group and the target fault. Thus, by performing data statistics on a batch of cells, the correlation between production data and a certain fault in the cell is determined, and the correlation between the two is used to locate the production data causing the fault, thereby improving the accuracy of cell fault location.

[0081] According to some embodiments of this application, the cell acquisition module 301 is specifically used to: cluster the production data of the same data category in each of the production data of each of the cells to obtain each production data group; and determine each target cell corresponding to any production data group from each of the cells.

[0082] According to some embodiments of this application, the cell acquisition module 301 is specifically used to: uniformly divide the production data of the same data category in each of the production data of each of the cells according to the data distribution density of the data category, so as to obtain each production data group.

[0083] According to some embodiments of this application, the correlation detection module 302 is specifically used to: obtain the correlation detection result between the production data group and the target fault based on the number of cells with the target fault in each target cell; determine that the correlation detection result indicates that the production data group is related to the target fault; and determine the correlation degree between the production data group and the target fault based on the number of cells with a certain target fault in each target cell and the number of cells with the target fault in each target cell.

[0084] According to some embodiments of this application, the correlation detection module 302 is specifically used to: obtain the expected frequency corresponding to the production data group based on the number of each target cell, the number of cells in each target cell containing the target fault, and the total number of cells; determine the chi-square statistic corresponding to the production data group based on the expected frequency and the number of cells in each target cell containing the target fault; perform a chi-square test on the chi-square statistic to obtain the test probability corresponding to the production data group, so as to determine the correlation detection result between the production data group and the target fault based on the test probability.

[0085] According to some embodiments of this application, the correlation detection module 302 is specifically used to: obtain the correlation level between the production data group and the target fault based on the comparison results of the inspection probability and each preset probability; wherein, the preset probability is negatively correlated with the correlation level.

[0086] According to some embodiments of this application, the association detection module 302 is specifically used to: determine the initial association value between the production data group and the target fault based on the number of cells with a certain target fault in each target cell and the number of cells with the target fault in each of the target cells; and normalize the initial association value to obtain the association degree between the production data group and the target fault.

[0087] According to some embodiments of this application, the correlation detection module 302 is specifically used to: map the initial correlation value to a target interval to obtain the correlation degree between the production data group and the target fault; wherein, the target interval is determined based on the number of normal cells in each of the target cells and the number of normal cells in each of the cells.

[0088] According to some embodiments of this application, such as Figure 4 As shown, this application embodiment provides an electronic device 4, including: a processor 401 and a memory 402. The processor 401 and the memory 402 are interconnected and communicate with each other through a communication bus 403 and / or other forms of connection mechanism (not shown). The memory 402 stores a computer program executable by the processor 401. When the computing device is running, the processor 401 executes the computer program to execute the method executed by the external terminal in any optional implementation, for example: determining each target cell corresponding to any production data group from each cell based on each production data of each cell; determining the correlation between the production data group and the target fault based on the number of cells with a certain target fault in each target cell and the number of cells with the target fault in each cell; determining at least one target production data group causing the target fault based on the correlation between each production data group and the target fault; wherein, the production data group includes at least one production data of a certain data category.

[0089] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the method in any of the aforementioned optional implementations.

[0090] The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0091] This application provides a computer program product that, when run on a computer, causes the computer to perform a method in any of the optional implementations.

[0092] This application provides a battery management system having a computer program stored thereon, which, when executed by a processor, implements a method in any of the optional implementation methods.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes those falling within the scope of the claims. All technical solutions within the scope.

Claims

1. A method for fault location of a battery cell, characterized in that, The method includes: Based on the production data of each cell, determine the target cells corresponding to any production data set from each cell. The correlation between the production data set and the target fault is determined based on the number of target cells with a certain target fault and the number of cells with the target fault in each target cell. Based on the correlation between each of the production data groups and the target fault, at least one target production data group causing the target fault is determined; The production data group includes at least one production data from a certain data category.

2. The method according to claim 1, characterized in that, Based on the production data of each battery cell, determine the target battery cells corresponding to any production data set from the battery cells, including: Cluster the production data of the same data category in each of the battery cells to obtain each production data group; From each of the stated cells, determine the target cells corresponding to any of the stated production data sets.

3. The method according to claim 2, characterized in that, Clustering the production data of the same data category in each of the aforementioned battery cells yields various production data groups, including: For each of the production data of each of the battery cells, the production data of the same data category are evenly divided according to the data distribution density of the data category to obtain each production data group.

4. The method according to claim 1, characterized in that, Based on the number of target cells containing a specific target fault and the number of cells containing the target fault within each target cell, the correlation between the production data set and the target fault is determined, including: Based on the number of target cells containing the target fault, the correlation detection result between the production data set and the target fault is obtained; The correlation detection result indicates that the production data set is related to the target fault. Based on the number of cells with a certain target fault in each target cell and the number of cells with the target fault in each target cell, the correlation degree between the production data set and the target fault is determined.

5. The method according to claim 4, characterized in that, Based on the number of target cells containing the target fault, the correlation detection results between the production data set and the target fault are obtained, including: Based on the number of each target cell, the number of cells with the target fault in each cell, and the number of each cell, the expected frequency corresponding to the production data group is obtained; Based on the expected frequency and the number of cells with the target fault in each target cell, determine the chi-square statistic corresponding to the production data group; A chi-square test is performed on the chi-square statistic to obtain the test probability corresponding to the production data set, and the correlation detection result between the production data set and the target fault is determined based on the test probability.

6. The method according to claim 5, characterized in that, Based on the test probability, the correlation detection result between the production data set and the target fault is determined, including: Based on the comparison results between the test probability and each preset probability, the correlation level between the production data set and the target fault is obtained; The preset probability is negatively correlated with the relevant level.

7. The method according to any one of claims 1, 4-6, characterized in that, Based on the number of target cells containing a specific target fault and the number of cells containing the target fault within each target cell, the correlation between the production data set and the target fault is determined, including: Based on the number of target cells with a certain target fault and the number of cells with the target fault in each target cell, the initial correlation value between the production data group and the target fault is determined. The initial correlation value is normalized to obtain the correlation degree between the production data group and the target fault.

8. The method according to claim 7, characterized in that, The initial correlation values ​​are normalized to obtain the correlation degree between the production data set and the target fault, including: The initial correlation value is mapped to the target interval to obtain the correlation degree between the production data group and the target fault; The target range is determined based on the number of normal cells in each target cell and the number of normal cells in each cell.

9. A fault location device for a battery cell, characterized in that, The device includes: The cell acquisition module is used to determine the target cells corresponding to any production data group from the cells based on the production data of each cell. The correlation detection module is used to determine the correlation between the production data group and the target fault based on the number of cells with a certain target fault in each target cell and the number of cells with the target fault in each of the target cells. The fault location module is used to determine at least one target production data group that causes the target fault based on the correlation between each production data group and the target fault. The production data group includes at least one of the production data of a certain data category.

10. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 8.

Images