Battery fault detection method and device, electronic equipment and storage medium

Abstract

This application provides a battery fault detection method, apparatus, electronic device, and storage medium. The method includes: acquiring voltage data of individual battery cells; determining a voltage curve and a median voltage curve for each battery cell based on the voltage data; determining the deviation between the voltage curve and the median voltage curve of each battery cell based on the voltage curve and the median voltage curve; for any given battery cell, acquiring the average normalized value of the deviation and the mean of the standard scores of the deviation as characteristic data of the battery cell; determining the local outlier factor of the battery cell based on the characteristic data; and determining that the battery cell has not failed if the local outlier factor is less than a preset value. This application achieves battery fault detection by combining standard scores and average normalized values ​​related to battery voltage, which fully utilizes information related to battery voltage and thus improves the accuracy of battery fault detection.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a battery fault detection method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the widespread application of batteries in numerous fields, especially in electric vehicles, battery fault detection has become crucial. Battery failures can lead to decreased equipment performance, shortened lifespan, and even endanger the safety of passengers in electric vehicles. For example, battery failures may cause a sudden reduction in the driving range or a sudden loss of power in an electric vehicle. Moreover, due to the complexity of battery systems, faults may be hidden under various operating parameters and conditions. If not detected in time, they may cause more serious problems. Therefore, battery fault detection is a necessary means to ensure the normal use of batteries and the safe and stable operation of related equipment.

[0003] Existing battery fault detection methods typically rely solely on standard scores related to battery voltage for fault detection. However, this method fails to effectively utilize complete information related to battery voltage, leading to low accuracy in battery fault detection. Summary of the Invention

[0004] This application provides a battery fault detection method, apparatus, electronic device, and storage medium to solve the problem of low accuracy in battery fault detection caused by relying solely on standard scores related to battery voltage for fault detection in related technologies.

[0005] In a first aspect, embodiments of this application provide a battery fault detection method, applied to a battery, wherein the battery comprises a plurality of battery cells, and the method includes:

[0006] Obtain the voltage data of the individual battery cells;

[0007] The voltage curve and median voltage curve of the battery cell are determined based on the voltage data of the battery cell.

[0008] Based on the voltage curve of the individual battery cell and the median voltage curve, determine the deviation between the voltage curve of the individual battery cell and the median voltage curve;

[0009] For any of the aforementioned battery cells, the average normalized value of the deviation value and the mean of the standard scores of the deviation value of the battery cell are obtained, and used as the feature data of the battery cell;

[0010] The local outlier factor of the battery cell is determined based on the characteristic data of the battery cell.

[0011] If the local outlier factor of the battery cell is less than a preset value, it is determined that the battery cell has not malfunctioned.

[0012] Optionally, determining the deviation between the voltage curve of the battery cell and the median voltage curve based on the voltage curve of the battery cell includes:

[0013] Obtain the distance between the voltage data in the voltage curve and the median voltage data in the median voltage curve;

[0014] Determine the minimum distance based on the distance between the voltage data and the median voltage data;

[0015] The minimum distance is used as the deviation value between the voltage curve and the median voltage curve.

[0016] Optionally, obtaining the average normalized value of the deviation value of the battery cell includes:

[0017] Based on all the aforementioned deviation values, determine the maximum, minimum, and average values ​​of the deviation values ​​respectively;

[0018] The average normalized value of the deviation value is determined based on the deviation value, the maximum value of the deviation value, the minimum value of the deviation value, and the average value of the deviation value.

[0019] Optionally, the average of the standard scores for obtaining the deviation values ​​of the individual battery cells includes:

[0020] Obtain the standard score of the deviation value;

[0021] The mean of the standard scores is determined based on the standard scores of all the aforementioned deviation values.

[0022] Optionally, the average of the standard scores for obtaining the deviation values ​​of the individual battery cells includes:

[0023] Obtain the number of the deviation values;

[0024] The standard deviation of the deviation values ​​is determined based on the average value of the deviation values, the deviation values ​​themselves, and the number of deviation values.

[0025] The standard score of the deviation value is determined based on the deviation value, the average value of the deviation values, and the standard deviation of the deviation values.

[0026] The mean of the standard scores is determined based on the standard scores of all the aforementioned deviation values.

[0027] Optionally, determining the local outlier factor of the battery cell based on its characteristic data includes:

[0028] Obtain the local reachability density of the feature data and the preset distance neighborhood of the feature data, wherein the preset distance neighborhood of the feature data is the set of all the feature data within a preset distance of the feature data;

[0029] The local outlier factor is determined based on the local reachability density of the feature data, the local reachability density of other feature data besides the feature data, and the preset distance neighborhood of the feature data.

[0030] Optionally, obtaining the local reachability density of the feature data includes:

[0031] Obtain the distance between the feature data and other feature data besides the feature data, as well as the preset distance of the feature data, wherein the preset distance of the feature data is the distance from the feature data to a preset sorting position;

[0032] Based on the distance between the feature data and other feature data besides the feature data and the preset distance of the feature data, the preset reachable distance of the feature data is determined;

[0033] The local reachability density of the feature data is determined based on the preset reachability distance and the preset distance neighborhood of the feature data.

[0034] Secondly, embodiments of this application provide a battery fault detection device, the device comprising:

[0035] A voltage data acquisition module is used to acquire the voltage data of the battery cell;

[0036] The voltage curve determination module is used to determine the voltage curve and median voltage curve of the battery cell based on the voltage data of the battery cell.

[0037] The deviation data determination module is used to determine the deviation value between the voltage curve of the battery cell and the median voltage curve based on the voltage curve of the battery cell and the median voltage curve.

[0038] The battery cell feature data acquisition module is used to acquire, for any given battery cell, the average normalized value of the deviation value and the mean of the standard scores of the deviation value of the battery cell, as feature data of the battery cell.

[0039] A local outlier determination module is used to determine the local outlier factor of the battery cell based on the characteristic data of the battery cell.

[0040] The battery fault detection module is used to determine that the battery cell has not failed when the local outlier factor of the battery cell is less than a preset value.

[0041] Optionally, the deviation data determination module includes:

[0042] The distance data acquisition submodule is used to acquire the distance between the voltage data in the voltage curve and the median voltage data in the median voltage curve;

[0043] The minimum distance determination submodule is used to determine the minimum distance based on the distance between the voltage data and the median voltage data;

[0044] The deviation data determination submodule is used to determine the minimum distance as the deviation value between the voltage curve and the median voltage curve.

[0045] Optionally, the battery cell feature data acquisition module includes:

[0046] The deviation value calculation submodule is used to determine the maximum value, minimum value and average value of the deviation values ​​based on all the deviation values;

[0047] The average normalization operation submodule is used to determine the average normalized value of the deviation value based on the deviation value, the maximum value of the deviation value, the minimum value of the deviation value, and the average value of the deviation value.

[0048] Optionally, the battery cell feature data acquisition module includes:

[0049] The standard score acquisition submodule is used to acquire the standard score of the deviation value;

[0050] The first standard score mean determination submodule is used to determine the mean of the standard scores based on the standard scores of all the deviation values.

[0051] Optionally, the battery cell feature data acquisition module includes:

[0052] The deviation value quantity acquisition submodule is used to acquire the quantity of the deviation values;

[0053] The deviation standard deviation determination submodule is used to determine the standard deviation of the deviation value based on the average value of the deviation value, the deviation value, and the number of the deviation values.

[0054] The deviation value standard score determination submodule is used to determine the standard score of the deviation value based on the deviation value, the average value of the deviation values, and the standard deviation of the deviation values.

[0055] The second standard score mean determination submodule is used to determine the mean of the standard scores based on the standard scores of all the deviation values.

[0056] Optionally, the local outlier determination module includes:

[0057] The local reachability density acquisition submodule is used to acquire the local reachability density of the feature data and the preset distance neighborhood of the feature data, wherein the preset distance neighborhood of the feature data is the set of all the feature data within the preset distance of the feature data;

[0058] The local outlier factor determination submodule is used to determine the local outlier factor based on the local reachability density of the feature data, the local reachability density of other feature data besides the feature data, and the preset distance neighborhood of the feature data.

[0059] Optionally, the locally reachable density acquisition submodule includes:

[0060] A distance acquisition unit is used to acquire the distance between the feature data and other feature data besides the feature data, as well as a preset distance of the feature data, wherein the preset distance of the feature data is the distance from the feature data to a preset sorting position;

[0061] The reachability distance acquisition unit is used to determine the preset reachability distance of the feature data based on the distance between the feature data and other feature data besides the feature data and the preset distance of the feature data;

[0062] The local reachability density determination unit is used to determine the local reachability density of the feature data based on the preset reachability distance of the feature data and the preset distance neighborhood of the feature data.

[0063] Thirdly, embodiments of this application also provide an electronic device, including: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute the instructions to implement the battery fault detection method as described above.

[0064] Fourthly, embodiments of this application also provide a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform any of the battery fault detection methods described above.

[0065] In this embodiment, the voltage data of individual battery cells is acquired; the voltage curve and median voltage curve of each battery cell are determined based on the voltage data; the deviation between the voltage curve and the median voltage curve of each battery cell is determined based on the voltage curve and the median voltage curve; for any battery cell, the average normalized value of the deviation value and the mean of the standard scores of the deviation value are obtained as characteristic data of the battery cell; the local outlier factor of the battery cell is determined based on the characteristic data; if the local outlier factor of the battery cell is less than a preset value, it is determined that the battery cell has not failed. This application achieves battery fault detection by combining standard scores and average normalized values ​​related to battery voltage. Compared with the prior art, which only uses standard scores related to battery voltage to detect battery faults, this method makes fuller use of complete information related to battery voltage, thereby improving the accuracy of battery fault detection. In addition, this application uses the local outlier factor algorithm to obtain the local outlier factor of the feature data of the battery cell, and determines whether the battery cell has failed based on the local outlier factor of the feature data of the battery cell. By combining the local outlier factor algorithm, the battery cell can be quickly detected for faults, thereby improving the efficiency of battery fault detection.

[0066] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0067] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. 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:

[0068] Figure 1 This is one of the flowcharts of a battery fault detection method provided in this application embodiment;

[0069] Figure 2 This is the second step in the flowchart of a battery fault detection method provided in the embodiments of this application;

[0070] Figure 3 This is the third step in the flowchart of a battery fault detection method provided in the embodiments of this application;

[0071] Figure 4 This is the fourth step in the flowchart of a battery fault detection method provided in the embodiments of this application;

[0072] Figure 5 This is the fifth step in the flowchart of a battery fault detection method provided in the embodiments of this application;

[0073] Figure 6 This is the sixth step in the flowchart of a battery fault detection method provided in the embodiments of this application;

[0074] Figure 7 This is the seventh step in the flowchart of a battery fault detection method provided in the embodiments of this application;

[0075] Figure 8 This is a device block diagram of a battery fault detection device provided in an embodiment of this application;

[0076] Figure 9 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0077] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0078] The terms "first," "second," etc., used in the specification and claims of this invention are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0079] The following detailed description, in conjunction with the accompanying drawings, of a battery fault detection method, apparatus, storage medium, and vehicle provided in this application, through specific embodiments and application scenarios, will be provided in detail.

[0080] Figure 1 This is a flowchart illustrating the steps of a battery fault detection method provided in an embodiment of this application, as follows: Figure 1 As shown, the method includes:

[0081] Step 101: Obtain the voltage data of the individual battery cells.

[0082] It should be noted that, in this embodiment of the application, the battery on the vehicle is composed of several battery cells. In order to accurately locate the faulty battery cell, it is first necessary to obtain the voltage data of each battery cell in the battery.

[0083] Optionally, after obtaining the voltage data of all battery cells, the obtained voltage data of all battery cells can be cleaned, including outlier handling, missing value handling, and outlier handling.

[0084] Step 102: Determine the voltage curve and median voltage curve of each battery cell based on the voltage data of the individual cells.

[0085] It should be noted that, in the embodiments of this application, the moving window is a data processing technique that allows a fixed-size window to slide through the data. Each time the window moves, the data within the window is processed, and the size of the moving window determines the amount of data processed each time.

[0086] After obtaining the voltage data of all individual battery cells, the total number of voltage data points can be counted. Then, the size of the moving window can be determined based on the total number of voltage data points. The determined size of the moving window should ensure that there is enough data within the moving window for effective calculation and analysis, while also avoiding excessively large moving windows that could lead to computational delays or excessive resource consumption.

[0087] Based on the determined size of the moving window, the voltage curve of the battery cell is determined according to the voltage data of the battery cell in the current moving window, and the median voltage curve of the battery cell is determined according to the voltage data of the battery cell in the current moving window.

[0088] Specifically, the voltage curve of a battery cell is determined based on the voltage data of the battery cell in the current moving window. Specifically, for the voltage data of any battery cell, the voltage data of the battery cell is plotted as a voltage curve to represent the voltage change of the battery cell within the current moving window.

[0089] The median voltage curve of a battery cell is determined based on the voltage data of the battery cells in the current moving window. Specifically, for any given battery cell, the median voltage data of that battery cell is determined from all the voltage data of that battery cell; and the median voltage data of all battery cells are plotted as a median voltage curve.

[0090] Step 103: Determine the deviation between the voltage curve of a single battery cell and the median voltage curve based on the voltage curve of the individual battery cell and the median voltage curve.

[0091] It should be noted that, in the embodiments of this application, for the voltage curve of any battery cell, the deviation value between the voltage curve and the median voltage curve of the battery cell is determined based on the voltage curve and the median voltage curve of the battery cell.

[0092] Step 104: For any given battery cell, obtain the average normalized value of the deviation value and the mean of the standard scores of the deviation value, as the characteristic data of the battery cell.

[0093] It should be noted that, in this embodiment of the application, for any single battery cell, based on the deviation between the voltage curve and the median voltage curve of the battery cell, the average normalized value of the deviation value and the mean of the standard scores of the deviation value are obtained, and the average normalized value of the deviation value and the mean of the standard scores of the deviation value are used as the feature data of the battery cell. That is, each battery cell corresponds to a set of feature data, wherein the set of feature data includes the average normalized value of the deviation value of the battery cell and the mean of the standard scores of the deviation value of the battery cell.

[0094] Step 105: Determine the local outlier factor of the battery cell based on the characteristic data of the battery cell.

[0095] It should be noted that, in the embodiments of this application, for any battery cell, the LOF (Local Outlier Factor) algorithm is used to perform a series of operations on the feature data of the battery cell to obtain the local outlier factor of the battery cell.

[0096] Step 106: If the local outlier factor of a battery cell is less than a preset value, it is determined that the battery cell has not failed.

[0097] It should be noted that, in this embodiment, the preset value can be 1. For any single battery cell, after obtaining its local outlier factor, it is determined whether the local outlier factor is less than 1. If the local outlier factor is less than 1, it indicates that the density of the battery cell is higher, and the battery cell is a normal battery cell, thus determining that the battery cell has not failed. If the local outlier factor is greater than 1, it indicates that the density of the battery cell is lower, and the battery cell is an abnormal battery cell, thus determining that the battery cell has failed.

[0098] This application achieves battery fault detection by combining standard scores and average normalized values ​​related to battery voltage. Compared to existing technologies that only rely on standard scores related to battery voltage for fault detection, this approach more fully utilizes complete information related to battery voltage, thereby improving the accuracy of battery fault detection. Furthermore, this application employs a local outlier factor algorithm to obtain local outlier factors from the feature data of individual battery cells. Based on these local outlier factors, it determines whether a battery cell has experienced a fault. By combining this algorithm with the local outlier factor algorithm, fault detection of individual battery cells can be performed quickly, thus improving the efficiency of battery fault detection.

[0099] Furthermore, in the embodiments of this application, such as Figure 2 As shown, step 103 may also include the following steps:

[0100] Step 201: Obtain the distance between the voltage data in the voltage curve and the median voltage data in the median voltage curve.

[0101] It should be noted that, in the embodiments of this application, for the voltage curve of any battery cell, the distance between the voltage data in the voltage curve and the median voltage data in the median voltage curve can be obtained according to formula (1).

[0102]

[0103] Where d(x) i ,y i (x) represents the voltage data in the voltage curve. i Median voltage data y in the median voltage curve i The distance between them, x i For voltage data in the voltage curve, y i This refers to the median voltage data in the median voltage curve.

[0104] Step 202: Determine the minimum distance based on the distance between the voltage data and the median voltage data.

[0105] Step 203: The minimum distance is taken as the deviation value between the voltage curve and the median voltage curve.

[0106] After obtaining the distance between the voltage data in the voltage curve and the median voltage data in the median voltage curve, the minimum distance between the voltage curve and the median voltage curve can be determined according to formula (2).

[0107] S(i,j)=d(x i ,y i )+min(S(i-1,j),S(i,j-1),S(i-1,j-1)) Formula (2)

[0108] Where S(i,j) is the distance between the i-th voltage data point of the voltage curve and the j-th median voltage data point of the median voltage curve, which is also the minimum distance between the voltage curve and the median voltage curve, d(x i ,y i (x) represents the voltage data in the voltage curve. i Median voltage data y in the median voltage curve i The distance between the (i-1)th voltage data point of the voltage curve and the jth median voltage data point of the median voltage curve, S(i,j-1) is the distance between the ith voltage data point of the voltage curve and the (j-1)th median voltage data point of the median voltage curve, and S(i-1,j-1) is the distance between the (i-1)th voltage data point of the voltage curve and the (j-1)th median voltage data point of the median voltage curve.

[0109] For any single battery cell voltage curve, after determining the minimum distance between the voltage curve and the median voltage curve, the minimum distance can be used as the deviation value between the voltage curve and the median voltage curve. The smaller the deviation value, the higher the similarity between the voltage curve and the median voltage curve; the larger the deviation value, the lower the similarity between the voltage curve and the median voltage curve.

[0110] This application calculates the minimum distance between the voltage curve and the median voltage curve and uses it as the deviation value between the voltage curve and the median voltage curve. This not only enables a more comprehensive assessment of the health status of individual battery cells, but also allows for real-time fault detection during battery operation, timely discovery of potential problems, and ensures normal battery use and the safe and stable operation of related equipment.

[0111] Furthermore, in the embodiments of this application, such as Figure 3 As shown, step 104 may also include the following steps:

[0112] Step 301: Based on all deviation values, determine the maximum, minimum, and average values ​​of the deviation values ​​respectively.

[0113] Step 302: Determine the average normalized value of the deviation value based on the deviation value, the maximum value of the deviation value, the minimum value of the deviation value, and the average value of the deviation value.

[0114] It should be noted that, in this embodiment, the deviations between the voltage curves of all individual cells and the median voltage curve are sorted in descending order to obtain a sorting result. The deviation with the largest value in the sorting result is taken as the maximum value, and the deviation with the smallest value in the sorting result is taken as the minimum value.

[0115] The average value of the deviation is determined according to formula (3).

[0116]

[0117] in, S is the average of the deviation values, N is the number of deviation values, and S is the average of the deviation values. i This represents the deviation between the voltage curve of the i-th cell and the median voltage curve.

[0118] Furthermore, the average normalized value of the deviation value is determined according to formula (4).

[0119]

[0120] Wherein, S is the average normalized value of the X” deviation value. i Let be the deviation between the voltage curve of the i-th cell and the median voltage curve. S is the average of the deviation values. max S represents the maximum value of the deviation. min This represents the minimum value of the deviation.

[0121] This application determines the average normalized value of the deviation value based on the deviation value, the maximum value of the deviation value, the minimum value of the deviation value, and the average value of the deviation value, providing a more comprehensive data foundation for subsequent battery fault detection, thereby improving the accuracy of battery fault detection.

[0122] Furthermore, in the embodiments of this application, such as Figure 4 As shown, step 104 may also include the following steps:

[0123] Step 401: Obtain the standard score of the deviation value.

[0124] Step 402: Determine the mean of the standard scores based on the standard scores of all deviation values.

[0125] It should be noted that, in this embodiment of the application, for the deviation value between the voltage curve and the median voltage curve of any battery cell, a standard score of the deviation value is obtained according to steps 501-503. After obtaining the standard scores of the deviation values ​​of all battery cells, an average value is calculated based on the standard scores of all battery cells and the number of standard scores of the deviation values. The resulting average value is the mean of the standard scores.

[0126] This application obtains standard scores for deviation values ​​and determines the mean of the standard scores based on all deviation values, providing a more comprehensive data foundation for subsequent battery fault detection and thus improving the accuracy of battery fault detection.

[0127] Furthermore, in the embodiments of this application, such as Figure 5As shown, step 104 may also include the following steps:

[0128] Step 501: Obtain the number of deviation values.

[0129] Step 502: Determine the standard deviation of the deviation values ​​based on the average value, the deviation values, and the number of deviation values.

[0130] Step 503: Determine the standard score of the deviation value based on the deviation value, the average value of the deviation value, and the standard deviation of the deviation value.

[0131] Step 504: Determine the mean of the standard scores based on the standard scores of all deviation values.

[0132] It should be noted that, in the embodiments of this application, the specific implementation process for obtaining the standard score of the deviation value is as follows: obtain the number of deviation values ​​based on all deviation values; determine the standard deviation of the deviation value according to the following formula (5); and determine the standard score of the deviation value according to the following formula (6).

[0133]

[0134] Where σ is the standard score of the deviation value, N is the number of deviation values, and S i Let be the deviation between the voltage curve of the i-th cell and the median voltage curve. This represents the average of the deviation values.

[0135]

[0136] Where X' is the standard score of the deviation value, S i Let be the deviation between the voltage curve of the i-th cell and the median voltage curve. Let σ be the average of the deviation values, and σ be the standard score of the deviation values.

[0137] After obtaining the standard scores of the deviation values ​​of all battery cells, the average value is calculated based on the standard scores of all battery cells and the number of standard scores of the deviation values. The resulting average value is the mean of the standard scores.

[0138] This application determines the standard score of the deviation value based on the deviation value, the average value of the deviation value, and the standard deviation of the deviation value, and then determines the mean of the standard score based on the standard score, thereby enabling a more comprehensive detection of the fault status of individual battery cells.

[0139] Furthermore, in the embodiments of this application, such as Figure 6 As shown, step 105 may also include the following steps:

[0140] Step 601: Obtain the local reachability density of the feature data and the preset distance neighborhood of the feature data, wherein the preset distance neighborhood of the feature data is the set of all feature data within the preset distance of the feature data.

[0141] It should be noted that in the embodiments of this application, a preset distance neighborhood, also known as the k-th distance neighborhood, is defined as the set of all feature data within the k-th distance of the feature data, including the feature data at the k-th distance.

[0142] For any given battery cell's feature data, obtain the local reachability density of the battery cell's feature data, the k-th distance neighborhood of the battery cell's feature data, and the local reachability density of the feature data of other battery cells besides the battery cell's feature data.

[0143] Step 602: Determine the local outlier factor based on the local reachability density of the feature data, the local reachability density of other feature data besides the feature data, and the preset distance neighborhood of the feature data.

[0144] It should be noted that, in the embodiments of this application, after obtaining the local reachability density of the feature data of the battery cell, the k-th distance neighborhood of the feature data of the battery cell, and the local reachability density of the feature data of other battery cells besides the feature data of the battery cell, the local outlier factor of the feature data of the battery cell can be determined according to formula (7).

[0145]

[0146] Among them, LOF k (p) represents the local outlier factor of the characteristic data of a single battery cell, N k (p) represents the k-th distance neighborhood of the feature data of a single battery cell, lrd k (o) represents the local reachability density of feature data for battery cells other than the feature data of individual battery cells, lrd k (p) represents the local reachability density of the characteristic data of a single battery cell.

[0147] This application determines the local outlier factor based on the local reachability density of the feature data, the local reachability density of other feature data besides the feature data, and the preset distance neighborhood of the feature data. In other words, it uses the local outlier factor algorithm to obtain the local outlier factor of the feature data of a battery cell, thereby realizing the determination of whether a battery cell has failed based on the local outlier factor of the feature data of the battery cell. By combining the local outlier factor algorithm, fault detection of battery cells can be performed quickly, thereby improving the efficiency of battery fault detection.

[0148] Furthermore, in the embodiments of this application, such as Figure 7As shown, step 601 may further include the following steps:

[0149] Step 701: Obtain the distance between the feature data and other feature data besides the feature data, as well as the preset distance of the feature data, wherein the preset distance of the feature data is the distance from the feature data at the preset sorting position.

[0150] It should be noted that, in the embodiments of this application, the preset distance, that is, the Kth distance, refers to the distance value that is farthest from the feature data of the battery cell, that is, the distance of the feature data of the battery cell from the kth neighbor.

[0151] For any single battery cell's feature data, if the feature data of the battery cell is represented by p, and other feature data besides the feature data of the battery cell is represented by o, then calculate the Euclidean distance between the feature data of the battery cell and other feature data besides the feature data of the battery cell, i.e., the distance, denoted by dist(p,o).

[0152] Simultaneously, the Kth distance of the characteristic data of the battery cell is also required. The Kth distance of the characteristic data of the battery cell can be represented by dist. k (p) indicates.

[0153] Step 702: Determine the preset reachable distance of the feature data based on the distance between the feature data and other feature data besides the feature data and the preset distance of the feature data.

[0154] It should be noted that, in the embodiments of this application, the preset reachable distance, that is, the Kth reachable distance, is defined as the larger of the kth distance of the feature data of the battery cell and the distance between the feature data of the battery cell and other feature data besides the feature data of the battery cell.

[0155] After obtaining the distance between the feature data of the battery cell and other feature data besides the feature data of the battery cell, and the Kth distance of the feature data of the battery cell, the preset reachable distance of the feature data can be determined according to formula (8).

[0156] reach_dist k (p,,o)=max{dist k Formula (8) = (p),dist(p,o)}

[0157] Among them, reach_dist k (p,o) represents the Kth reachable distance of the characteristic data of a single battery cell, dist k(p) represents the Kth distance of the feature data of a single battery cell, and dist(p,o) represents the distance between the feature data of a single battery cell and other feature data besides the feature data of the single battery cell.

[0158] Step 703: Determine the local reachability density of the feature data based on the preset reachability distance and the preset distance neighborhood of the feature data.

[0159] It should be noted that, in the embodiments of this application, specifically, the local reachability density of the characteristic data of the battery cell can be determined according to formula (9).

[0160]

[0161] Among them, lrd k (p) represents the local reachability density of the characteristic data of a single battery cell, N k (p) represents the k-th distance neighborhood of the feature data of a single battery cell, reach_dist k (p,o) represents the Kth reachable distance of the characteristic data of a single battery cell.

[0162] This application determines the local reachability density of feature data based on the preset reachability distance and the preset distance neighborhood of feature data, providing a data foundation for subsequent acquisition of local outlier factors. Furthermore, it can combine local outlier factors to determine whether a battery cell has failed, thereby improving the efficiency of battery fault detection.

[0163] Corresponding to the method provided in the above-described embodiments of the battery fault detection method of this application, see [link to relevant documentation]. Figure 8 This application also provides a device block diagram of a battery fault detection device. In this embodiment, the device includes:

[0164] Voltage data acquisition module 801 is used to acquire voltage data of individual battery cells;

[0165] The voltage curve determination module 802 is used to determine the voltage curve and median voltage curve of a battery cell based on the voltage data of the battery cell.

[0166] The deviation data determination module 803 is used to determine the deviation value between the voltage curve and the median voltage curve of a battery cell based on the voltage curve and the median voltage curve of the battery cell.

[0167] The battery cell feature data acquisition module 804 is used to acquire, for any given battery cell, the average normalized value of the deviation value and the mean of the standard scores of the deviation value, as the feature data of the battery cell.

[0168] The local outlier determination module 805 is used to determine the local outlier factor of a battery cell based on the characteristic data of the battery cell.

[0169] The battery fault detection module 806 is used to determine that the battery cell has not failed when the local outlier factor of the battery cell is less than a preset value.

[0170] Optionally, the deviation data determination module includes:

[0171] The distance data acquisition submodule is used to acquire the distance between the voltage data in the voltage curve and the median voltage data in the median voltage curve;

[0172] The minimum distance determination submodule is used to determine the minimum distance based on the distance between the voltage data and the median voltage data;

[0173] The deviation data determination submodule is used to determine the minimum distance as the deviation value between the voltage curve and the median voltage curve.

[0174] Optionally, the battery cell feature data acquisition module includes:

[0175] The deviation value calculation submodule is used to determine the maximum, minimum and average values ​​of the deviation values ​​based on all deviation values.

[0176] The average normalization calculation submodule is used to determine the average normalized value of the deviation value based on the deviation value, the maximum value of the deviation value, the minimum value of the deviation value, and the average value of the deviation value.

[0177] Optionally, the battery cell feature data acquisition module includes:

[0178] The standard score acquisition submodule is used to obtain the standard score of the deviation value;

[0179] The first standard score mean determination submodule is used to determine the mean of the standard scores based on the standard scores of all deviation values.

[0180] Optionally, the battery cell feature data acquisition module includes:

[0181] The deviation value quantity acquisition submodule is used to obtain the quantity of deviation values;

[0182] The standard deviation determination submodule is used to determine the standard deviation of the deviation values ​​based on the average value, the deviation values, and the number of deviation values.

[0183] The standard score determination submodule is used to determine the standard score of the deviation value based on the deviation value, the average deviation value, and the standard deviation of the deviation value.

[0184] The second standard score mean determination submodule is used to determine the mean of the standard scores based on the standard scores of all the deviation values.

[0185] Optionally, the local outlier determination module includes:

[0186] The local reachability density acquisition submodule is used to acquire the local reachability density of feature data and the preset distance neighborhood of feature data, wherein the preset distance neighborhood of feature data is the set of all feature data within the preset distance of feature data;

[0187] The local outlier factor determination submodule is used to determine the local outlier factor based on the local reachability density of the feature data, the local reachability density of other feature data besides the feature data, and the preset distance neighborhood of the feature data.

[0188] Optionally, the locally reachable density acquisition submodule includes:

[0189] The distance acquisition unit is used to acquire the distance between the feature data and other feature data besides the feature data, as well as the preset distance of the feature data. The preset distance of the feature data is the distance from the feature data to the preset sorting position.

[0190] The reachability distance acquisition unit is used to determine the preset reachability distance of the feature data based on the distance between the feature data and other feature data besides the feature data and the preset distance of the feature data;

[0191] The local reachability density determination unit is used to determine the local reachability density of the feature data based on the preset reachability distance of the feature data and the preset distance neighborhood of the feature data.

[0192] Figure 9 This is a structural diagram of an electronic device M00 provided in an embodiment of this application. In the diagram, the electronic device M00 includes a processor M01 and a memory M02. The memory M02 stores a program or instructions that can run on the processor M01. When the program or instructions are executed by the processor M01, they implement the various steps of the above-described battery fault detection method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0193] In embodiments of this application, the memory M02 can be used to store software programs and various data. The memory M02 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, applications or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory M02 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory M02 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0194] The processor M01 may include one or more processing units; optionally, the processor M01 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor M01.

[0195] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described battery fault detection method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0196] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0197] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described battery fault detection method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0198] It should be understood that the chip involved in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0199] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the battery fault detection method embodiment described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0200] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A battery fault detection method, characterized in that, Applied to a battery, wherein the battery comprises a plurality of battery cells, the method includes: Obtain the voltage data of the individual battery cells; The voltage curve and median voltage curve of the battery cell are determined based on the voltage data of the battery cell. Based on the voltage curve of the individual battery cell and the median voltage curve, determine the deviation between the voltage curve of the individual battery cell and the median voltage curve; For any of the battery cells, the average normalized value of the deviation value and the mean of the standard scores of the deviation value of the battery cell are obtained as the feature data of the battery cell. The local outlier factor of the battery cell is determined based on the characteristic data of the battery cell. If the local outlier factor of the battery cell is less than a preset value, it is determined that the battery cell has not failed. The step of determining the deviation between the voltage curve of the battery cell and the median voltage curve based on the voltage curve of the battery cell includes: Obtain the distance between the voltage data in the voltage curve and the median voltage data in the median voltage curve; Determine the minimum distance based on the distance between the voltage data and the median voltage data; The minimum distance is used as the deviation value between the voltage curve and the median voltage curve.

2. The method according to claim 1, characterized in that, The average normalized value of the deviation value of the battery cell is obtained as follows: Based on all the aforementioned deviation values, determine the maximum, minimum, and average values ​​of the deviation values ​​respectively; The average normalized value of the deviation value is determined based on the deviation value, the maximum value of the deviation value, the minimum value of the deviation value, and the average value of the deviation value.

3. The method according to claim 1, characterized in that, The mean of the standard scores for obtaining the deviation values ​​of the individual battery cells includes: Obtain the standard score of the deviation value; The mean of the standard scores is determined based on the standard scores of all the aforementioned deviation values.

4. The method according to claim 2, characterized in that, The mean of the standard scores for obtaining the deviation values ​​of the individual battery cells includes: Obtain the number of the deviation values; The standard deviation of the deviation values ​​is determined based on the average value of the deviation values, the deviation values ​​themselves, and the number of deviation values. The standard score of the deviation value is determined based on the deviation value, the average value of the deviation values, and the standard deviation of the deviation values. The mean of the standard scores is determined based on the standard scores of all the aforementioned deviation values.

5. The method according to claim 1, characterized in that, The step of determining the local outlier factor of the battery cell based on the characteristic data of the battery cell includes: Obtain the local reachability density of the feature data and the preset distance neighborhood of the feature data, wherein the preset distance neighborhood of the feature data is the set of all the feature data within a preset distance of the feature data; The local outlier factor is determined based on the local reachability density of the feature data, the local reachability density of other feature data besides the feature data, and the preset distance neighborhood of the feature data.

6. The method according to claim 5, characterized in that, The local reachability density of the feature data includes: Obtain the distance between the feature data and other feature data besides the feature data, as well as the preset distance of the feature data, wherein the preset distance of the feature data is the distance from the feature data to a preset sorting position; Based on the distance between the feature data and other feature data besides the feature data and the preset distance of the feature data, the preset reachable distance of the feature data is determined; The local reachability density of the feature data is determined based on the preset reachability distance and the preset distance neighborhood of the feature data.

7. A battery fault detection device, characterized in that, The device includes: Voltage data acquisition module, used to acquire voltage data of individual battery cells; The voltage curve determination module is used to determine the voltage curve and median voltage curve of the battery cell based on the voltage data of the battery cell. The deviation data determination module is used to determine the deviation value between the voltage curve of the battery cell and the median voltage curve based on the voltage curve of the battery cell and the median voltage curve. The battery cell feature data acquisition module is used to acquire, for any given battery cell, the average normalized value of the deviation value and the mean of the standard scores of the deviation value of the battery cell, as feature data of the battery cell. A local outlier determination module is used to determine the local outlier factor of the battery cell based on the characteristic data of the battery cell. The battery fault detection module is used to determine that the battery cell has not failed when the local outlier factor of the battery cell is less than a preset value. The deviation data determination module includes: The distance data acquisition submodule is used to acquire the distance between the voltage data in the voltage curve and the median voltage data in the median voltage curve; The minimum distance determination submodule is used to determine the minimum distance based on the distance between the voltage data and the median voltage data; The deviation data determination submodule is used to take the minimum distance as the deviation value between the voltage curve and the median voltage curve.

8. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the battery fault detection method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the battery fault detection method as described in any one of claims 1 to 6.

Images