Vehicle battery fault diagnosis method, device and equipment

Abstract

The invention discloses a vehicle battery fault diagnosis method, device and equipment, and the method comprises the steps: obtaining the battery information of a vehicle battery which comprises a plurality of battery units; according to the battery information, voltage characteristic values corresponding to the multiple battery units are determined, the voltage characteristic values are used for representing correlation coefficients between the voltage of each battery unit and the voltages of other battery units, and the other battery units comprise all battery units except the battery unit corresponding to the voltage characteristic value in the multiple battery units; determining a Gini coefficient of the battery according to the voltage characteristic values corresponding to the plurality of battery units; and obtaining a diagnosis result of the battery according to the Gini coefficient of the battery. According to the battery diagnosis method and device, the voltage characteristic values corresponding to the multiple battery units are calculated, the Gini coefficient of the battery is determined according to the voltage characteristic values, and the difference of the battery units is evaluated according to the Gini coefficient, so that a relatively accurate battery diagnosis result is obtained, and the accuracy of battery diagnosis can be improved.

Description

Technical Field

[0001] The present application belongs to the field of battery technology, and in particular, relates to a vehicle battery fault diagnosis method, device and equipment. Background Art

[0002] To meet the power requirements of electric vehicles, battery packs are usually composed of a large number of single cells connected in series and parallel. With the influence of external factors such as charge and discharge cycles and temperature changes, the battery performance decays, resulting in uneven degradation of the performance of the single cells in the battery pack, that is, battery inconsistency. Battery inconsistency indicates that the battery is faulty. The inconsistency problem will gradually worsen with the increase of usage time, affecting the capacity, life and safety of the entire battery system.

[0003] In order to effectively diagnose the health status of the battery, the current monitoring of battery consistency is mainly based on voltage consistency. The voltage difference of the single battery is calculated and compared with the threshold. When the voltage difference exceeds the threshold, it is determined that the battery is inconsistent.

[0004] In the above method, only a simple pressure difference calculation method is used, which cannot well reflect the consistency problem of the battery and affects the accuracy of battery diagnosis. Summary of the invention

[0005] The embodiments of the present application provide a vehicle battery fault diagnosis method, device and equipment, which can improve the accuracy of battery diagnosis.

[0006] In a first aspect, an embodiment of the present application provides a vehicle battery fault diagnosis method, the method comprising:

[0007] Acquiring battery information of a vehicle battery, wherein the battery includes a plurality of battery cells;

[0008] Determine, according to the battery information, voltage characteristic values ​​corresponding to each of the plurality of battery cells, the voltage characteristic values ​​being used to characterize a correlation coefficient between a voltage of each of the battery cells and voltages of remaining battery cells, the remaining battery cells including all other battery cells in the plurality of battery cells except the battery cell corresponding to the voltage characteristic value;

[0009] Determining the Gini coefficient of the battery according to voltage characteristic values ​​corresponding to each of the plurality of battery cells;

[0010] A diagnosis result of the battery is obtained according to the Gini coefficient of the battery.

[0011] In one embodiment of the present application, the battery information includes voltages of a plurality of battery cells corresponding to a plurality of sampling points respectively collected under a charging condition;

[0012] The step of determining voltage characteristic values ​​corresponding to each of the plurality of battery cells according to the battery information includes:

[0013] For each battery cell, the following steps are performed: obtaining a first voltage corresponding to each sampling point of the first battery cell according to a difference between the voltage of the first battery cell at each sampling point and a first mean value, wherein the first mean value is an average value of the voltages of the first battery cell at multiple sampling points; the first battery cell is any one of the multiple battery cells;

[0014] For each first battery cell, perform the following process:

[0015] Obtaining, according to the first voltage of the first battery cell and the first voltage of each second battery cell, respective corresponding correlation coefficients between the voltage of the first battery cell and the voltage of each second battery cell, wherein the second battery cell is a battery cell other than the first battery cell among the plurality of battery cells;

[0016] The voltage characteristic value corresponding to the first battery cell is calculated based on the correlation coefficients respectively corresponding to the voltage of the first battery cell and the voltage of each of the second battery cells.

[0017] In an embodiment of the present application, the voltage characteristic value corresponding to the first battery cell is calculated according to the correlation coefficients respectively corresponding to the voltage of the first battery cell and the voltage of each of the second battery cells, including:

[0018] For each of the first battery cells, the following process is performed:

[0019] Sum the correlation coefficients corresponding to the voltage of the first battery cell and the voltage of each of the second battery cells to obtain a first correlation coefficient corresponding to the first battery cell;

[0020] A voltage characteristic value corresponding to the first battery cell is obtained according to a first correlation coefficient corresponding to the first battery cell and the number of battery cells in the battery.

[0021] In an embodiment of the present application, determining the Gini coefficient of the battery according to the voltage characteristic values ​​corresponding to each of the plurality of battery cells includes:

[0022] If the minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells is greater than a first characteristic value, 0 is used as the Gini coefficient of the battery, wherein the first characteristic value is determined according to a quantile, and the quantile is determined according to a sorting result of the voltage characteristic values ​​of the plurality of battery cells;

[0023] If the minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells is less than or equal to the first characteristic value, the difference between 1 and the first probability value is taken as the Gini coefficient of the battery.

[0024] In an embodiment of the present application, the first probability value is calculated in the following manner:

[0025] Binning the voltage characteristic values ​​of the plurality of battery cells to obtain the number of voltage characteristic values ​​that each bin falls into;

[0026] Obtaining a probability value corresponding to each box according to the number of voltage characteristic values ​​that each box falls into and the number of battery cells in the plurality of batteries;

[0027] The first probability value is calculated according to the probability value corresponding to each box.

[0028] In an embodiment of the present application, obtaining a diagnosis result of the battery according to the Gini coefficient of the battery includes:

[0029] Obtaining a standardized parameter value of the battery, wherein the standardized parameter value is a ratio of a first intermediate value to a second intermediate value, the first intermediate value being a minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells minus a mean of the voltage characteristic values ​​of the plurality of battery cells, and the second intermediate value being a standard deviation of the voltage characteristic values ​​of the plurality of battery cells;

[0030] If the Gini coefficient of the battery is greater than the first fault Gini coefficient and less than the second fault Gini coefficient, and the standardized parameter value is less than the preset first fault value, then the diagnosis result is determined to be a battery fault.

[0031] In an embodiment of the present application, after obtaining a diagnosis result of the battery according to the Gini coefficient of the battery, the method further includes:

[0032] In the case where the diagnosis result is a battery failure, if the minimum voltage characteristic value is located in a first fault interval among a plurality of preset fault intervals, the fault level corresponding to the first fault interval is used as the level of the battery failure, wherein a fault level is set corresponding to each of the plurality of fault intervals.

[0033] In an embodiment of the present application, after obtaining a diagnosis result of the battery according to the Gini coefficient of the battery, the method further includes:

[0034] In the case where the diagnosis result is a battery failure, a second fault interval is determined, the upper boundary of the second fault interval is a first boundary value, the lower boundary of the second fault interval is a minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells, and the first boundary value is determined according to the quantile of the binning process;

[0035] A battery cell whose corresponding voltage characteristic value among the plurality of battery cells falls within the second fault interval is determined as a faulty battery cell.

[0036] In a second aspect, an embodiment of the present application provides a vehicle battery fault diagnosis device, the device comprising:

[0037] An acquisition module, used to acquire battery information of a vehicle battery, wherein the battery includes a plurality of battery cells;

[0038] A first determination module is used to determine, according to the battery information, voltage characteristic values ​​corresponding to each of the plurality of battery cells, wherein the voltage characteristic values ​​are used to characterize a correlation coefficient between a voltage of each of the battery cells and voltages of remaining battery cells, wherein the remaining battery cells include all other battery cells in the plurality of battery cells except the battery cells corresponding to the voltage characteristic values;

[0039] A second determination module, used to determine the Gini coefficient of the battery according to the voltage characteristic values ​​corresponding to each of the plurality of battery cells;

[0040] The diagnosis module is used to obtain a diagnosis result of the battery according to the Gini coefficient of the battery.

[0041] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions;

[0042] When the processor executes the computer program instructions, the vehicle battery fault diagnosis method as described in the first aspect is implemented.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the vehicle battery fault diagnosis method as described in the first aspect is implemented.

[0044] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the vehicle battery fault diagnosis method as described in the first aspect.

[0045] The vehicle battery fault diagnosis method, device and equipment of the embodiments of the present application calculate the voltage characteristic values ​​corresponding to each of the multiple battery cells, determine the Gini coefficient of the battery based on the voltage characteristic values, and evaluate the differences between the battery cells based on the Gini coefficient, so as to obtain a more accurate battery diagnosis result, which can improve the accuracy of battery diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 It is a flow chart of a vehicle battery fault diagnosis method provided by an embodiment of the present application;

[0048] Figure 2 is another flow chart of the vehicle battery fault diagnosis method provided by an embodiment of the present application;

[0049] Figure 3 is a schematic diagram of the structure of a vehicle battery fault diagnosis device provided in an embodiment of the present application;

[0050] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0052] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0053] In order to solve the problems in the prior art, the embodiments of the present application provide a vehicle battery fault diagnosis method, device and equipment. The vehicle battery fault diagnosis method provided by the embodiments of the present application is first introduced below.

[0054] Figure 1 FIG. 1 is a flow chart of a vehicle battery fault diagnosis method provided by an embodiment of the present application. Figure 1 As shown, the vehicle battery fault diagnosis method provided in the embodiment of the present application is applied to an electronic device, such as a server, and includes the following steps 101 to 104, wherein:

[0055] Step 101, obtaining battery information of a vehicle battery, where the battery includes a plurality of battery cells.

[0056] In this embodiment, the electronic device may be a cloud server (hereinafter referred to as the cloud). The cloud is used as an example for explanation below. The cloud is connected to multiple vehicles for communication. The cloud receives battery information reported by the vehicles. The battery includes multiple battery cells, which may also be referred to as single cells. The cloud performs fault diagnosis on the battery information reported by each vehicle.

[0057] Among them, the vehicle reports battery information after power-on, so that the cloud can obtain the vehicle's battery information in time for real-time diagnosis, or report according to a pre-set reporting time, such as reporting battery information at 24:00 every day; or, the cloud sends a diagnostic command, and the vehicle reports the battery information after receiving the diagnostic command.

[0058] Step 102, based on the battery information, determine the voltage characteristic values ​​corresponding to each of the multiple battery cells, where the voltage characteristic values ​​are used to characterize the correlation coefficient between the voltage of each battery cell and the voltages of the remaining battery cells, where the remaining battery cells include all other battery cells in the multiple battery cells except the battery cells corresponding to the voltage characteristic values.

[0059] In this embodiment, the battery information includes voltage. According to the battery information, voltage characteristic values ​​corresponding to each of the multiple battery cells are determined, and the voltage characteristic value represents the correlation coefficient between the voltage of each battery cell and the voltages of the remaining battery cells. For example, the battery includes multiple battery cells, such as battery cell a, battery cell b, and battery cell c. The voltage characteristic value corresponding to battery cell a, the voltage characteristic value corresponding to battery cell b, and the voltage characteristic value corresponding to battery cell c are determined respectively. For example, the voltage characteristic value corresponding to battery cell a is determined to represent the correlation coefficient between the voltage of battery cell a and the voltages of the remaining batteries, namely, battery cell b and battery cell c, that is, the remaining battery cells include all other battery cells in the multiple battery cells except the battery cells corresponding to the voltage characteristic values.

[0060] The correlation coefficient is a statistical indicator that measures the degree of correlation between two variables, and its value range is between -1 and 1. When the correlation coefficient is close to 1, it indicates that there is a strong positive linear correlation between the two variables, that is, the voltage of the battery cell a has a strong positive linear correlation with the voltages of the other battery cells; when the correlation coefficient is close to -1, it indicates that there is a strong negative linear correlation between the two variables, that is, the voltage of the battery cell a has a strong negative linear correlation with the voltages of the other battery cells; when the correlation coefficient is 0, it indicates that there is no linear correlation between the two variables.

[0061] Step 103, determining the Gini coefficient of the battery according to the voltage characteristic values ​​corresponding to each of the plurality of battery cells.

[0062] In this embodiment, the Gini coefficient of the battery is determined based on the voltage characteristic values ​​corresponding to each of the multiple battery cells. Specifically, the Gini coefficient of the battery is determined based on the minimum voltage characteristic value among the voltage characteristic values ​​of the multiple battery cells. When the Gini coefficient is 0, it indicates that there is no abnormality in the battery.

[0063] Step 104, obtaining a diagnosis result of the battery according to the Gini coefficient of the battery.

[0064] In this embodiment, the Gini coefficient of the battery is compared with the fault Gini coefficient, and the diagnosis result of the battery is obtained according to the comparison result. For example, if the Gini coefficient of the battery is greater than the first fault Gini coefficient and less than the second fault Gini coefficient, the diagnosis result of the battery is that the battery is faulty. It should be noted that after obtaining the battery information of the vehicle battery, the solution of determining the voltage characteristic values ​​corresponding to each of the multiple battery cells according to the battery information is continued to be executed, so as to determine again whether the battery is faulty.

[0065] In this embodiment, battery information of the vehicle battery is obtained, and voltage characteristic values ​​corresponding to each of the multiple battery cells are determined based on the battery information. The voltage characteristic values ​​are used to characterize the correlation coefficient between the voltage of each battery cell and the voltages of the remaining battery cells. The Gini coefficient of the battery is further determined based on the voltage characteristic values ​​corresponding to each of the multiple battery cells. The differences between the battery cells are evaluated based on the Gini coefficient, thereby obtaining a more accurate battery diagnosis result, which can improve the accuracy of battery diagnosis.

[0066] In one embodiment of the present application, the battery information includes voltages of multiple battery cells corresponding to multiple sampling points respectively collected under charging conditions. Specifically, step 102, based on the battery information, determines voltage characteristic values ​​corresponding to the multiple battery cells respectively, including:

[0067] For each battery cell, the following steps are performed: obtaining a first voltage corresponding to the first battery cell at each sampling point according to a difference between a voltage of the first battery cell at each sampling point and a first average value, wherein the first average value is an average value of voltages of the first battery cell at multiple sampling points; the first battery cell is any one of the multiple battery cells;

[0068] For each first battery cell, perform the following process:

[0069] Obtaining corresponding correlation coefficients between the voltage of the first battery cell and the voltage of each second battery cell respectively according to the first voltage of the first battery cell and the first voltage of each second battery cell, wherein the second battery cell is a battery cell other than the first battery cell among the plurality of battery cells;

[0070] The voltage characteristic value corresponding to the first battery cell is calculated based on the corresponding correlation coefficients between the voltage of the first battery cell and the voltage of each second battery cell.

[0071] In this embodiment, the above-mentioned battery information includes the voltages of multiple battery cells corresponding to multiple sampling points collected under charging conditions, and the following steps are performed for each battery cell: based on the difference between the voltage of the battery cell at each sampling point and the first mean, the first voltage corresponding to the first battery cell at each sampling point is calculated, wherein the first battery cell is any one of the multiple battery cells, and wherein the first mean is the average value of the voltages of the battery cell at multiple sampling points.

[0072] For each first battery cell, the corresponding correlation coefficients between the voltage of the first battery cell and the voltage of each second battery cell are calculated based on the first voltage of the first battery cell and the first voltage of each second battery cell, and the second battery cell is any one of the multiple battery cells except the first battery cell.

[0073] Furthermore, the voltage characteristic value corresponding to the first battery cell is calculated based on the corresponding correlation coefficients between the voltage of the first battery and the voltage of each second battery cell, and the number of battery cells in the battery.

[0074] By calculating the voltage characteristic value, the correlation between the voltage of each battery cell and the voltage of the remaining battery cells can be reflected. The correlation between the battery cell and the remaining battery cells can be reflected according to the correlation degree. The voltage characteristic value is used as a preliminary fault characteristic parameter of consistency abnormality, so as to further evaluate the battery performance and improve the accuracy of diagnosis.

[0075] In one embodiment of the present application, the correlation coefficients corresponding to the voltage of the first battery cell and the voltage of each second battery cell are obtained according to the first voltage of the first battery cell and the first voltage of each second battery cell, respectively, including:

[0076] For the first battery cell and each second battery cell, the following process is performed:

[0077] For each sampling point, multiply the first voltage corresponding to the first battery unit at each sampling point by the first voltage corresponding to the second battery unit at each sampling point to obtain a first value corresponding to the first battery unit at each sampling point;

[0078] Adding the first value corresponding to the first battery cell at each sampling point to obtain a second value corresponding to the first battery cell;

[0079] Performing a square operation on the first voltage corresponding to the first battery unit at each sampling point to obtain a third value corresponding to the first battery at each sampling point;

[0080] Adding the third value corresponding to each sampling point of the first battery to obtain a fourth value;

[0081] Performing a square operation on the first voltage corresponding to the second battery unit at each sampling point to obtain a fifth value corresponding to the second battery at each sampling point;

[0082] Add the fifth value corresponding to each sampling point of the second battery to obtain a sixth value;

[0083] Calculate the square roots of the fourth value and the sixth value respectively to obtain the seventh value and the eighth value;

[0084] The second value is used as a numerator and the product of the seventh value and the eighth value is used as a denominator to obtain a correlation coefficient corresponding to the voltage of the first battery unit and the voltage of the second battery unit.

[0085] In the above, for each sampling point, the first voltage corresponding to the first battery cell at each sampling point is multiplied by the first voltage corresponding to the second battery cell at each sampling point to obtain the first value corresponding to the first battery cell at each sampling point, and the first values ​​corresponding to the first battery cell at each sampling point are added to obtain the second value corresponding to the first battery cell.

[0086] A square operation is performed on the first voltage corresponding to the first battery unit at each sampling point to obtain a third value corresponding to the first battery at each sampling point, and the third values ​​corresponding to the first battery at each sampling point are added to obtain a fourth value.

[0087] A square operation is performed on the first voltage corresponding to the second battery unit at each sampling point to obtain a fifth value corresponding to the second battery at each sampling point, and the fifth values ​​corresponding to the second battery at each sampling point are added to obtain a sixth value.

[0088] In the above, after respectively calculating the square roots of the fourth value and the sixth value to obtain the seventh value and the eighth value, the second value can be used as the numerator and the product of the seventh value and the eighth value as the denominator to obtain the correlation coefficient corresponding to the voltage of the first battery cell and the voltage of the second battery cell.

[0089] Specifically, the correlation coefficient can be calculated according to formula (1), which is as follows:

[0090]

[0091] Among them, R ij represents the correlation coefficient between the voltage of the first battery cell i and the voltage of the second battery cell j, U i(t) represents the voltage of the first battery cell i at sampling point t, represents the average value of the voltage of the first battery cell i at multiple sampling points, that is, the first mean value, represents the first voltage of the first battery cell at sampling point t, U j(t) represents the voltage of the second battery cell at the sampling point t, represents the average value of the voltage of the second battery unit at multiple sampling points, represents the first voltage of the second battery cell at the sampling point t, represents the first value, represents the second value, represents the third value, represents the fourth value, represents the fifth value, represents the sixth value, represents the seventh value, Indicates the eighth value.

[0092] The correlation coefficient is used to measure the correlation between the voltage of a battery cell and the voltages of other battery cells. The inconsistent battery cells can be accurately located through the correlation coefficient.

[0093] In one embodiment of the present application, the voltage characteristic value corresponding to the first battery cell is calculated based on the correlation coefficients respectively corresponding to the voltage of the first battery cell and the voltage of each second battery cell, including:

[0094] For each first battery cell, perform the following process:

[0095] Sum the correlation coefficients corresponding to the voltage of the first battery unit and the voltage of each second battery unit to obtain a first correlation coefficient corresponding to the first battery unit;

[0096] A voltage characteristic value corresponding to the first battery cell is obtained according to a first correlation coefficient corresponding to the first battery cell and the number of battery cells in the battery.

[0097] In this embodiment, for each first battery cell, the correlation coefficients corresponding to the voltage of the first battery cell and the voltage of each second battery cell are summed to obtain the first correlation coefficient corresponding to the first battery cell, and the voltage characteristic value corresponding to the first battery cell is calculated using formula (2), which is as follows:

[0098]

[0099] Among them, R i represents the voltage characteristic value corresponding to the first battery cell, n represents the number of battery cells in the battery, represents the first correlation coefficient.

[0100] Optionally, the voltage characteristic value corresponding to the first battery unit may also be calculated using formula (3), which is as follows:

[0101]

[0102] Among them, R i represents the voltage characteristic value corresponding to the first battery cell, n represents the number of battery cells in the battery, represents the first correlation coefficient corresponding to the first battery cell, and 1 represents the correlation coefficient of Rii, that is, the correlation coefficient of the first battery cell itself, R i It represents the average value of the correlation coefficient between the voltage of the first battery cell and the voltages of the other battery cells and its own voltage.

[0103] The correlation coefficient is used to measure the correlation between the voltage of a battery cell and the voltages of other battery cells. The inconsistent battery cells can be accurately located through the correlation coefficient.

[0104] In one embodiment of the present application, specifically, step 103, determining the Gini coefficient of the battery according to the voltage characteristic values ​​corresponding to each of the plurality of battery cells, includes:

[0105] If the minimum voltage characteristic value among the voltage characteristic values ​​of the multiple battery cells is greater than the first characteristic value, 0 is used as the Gini coefficient of the battery, the first characteristic value is determined according to the quantile, and the quantile is determined according to the sorting result of the voltage characteristic values ​​of the multiple battery cells;

[0106] If the minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells is less than or equal to the first characteristic value, the difference between 1 and the first probability value is taken as the Gini coefficient of the battery.

[0107] In the above steps, the minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells is compared with the first characteristic value, and the Gini coefficient is determined according to the comparison result. Specifically, if the minimum voltage characteristic value is greater than the first characteristic value, 0 is taken as the Gini coefficient of the battery, which is expressed as: min(R i )>X, Gini=0, where min(R i ) is the minimum voltage eigenvalue, X is the first eigenvalue, and the Gini coefficient is 0.

[0108] If the minimum voltage characteristic value is less than or equal to the first characteristic value, the difference between 1 and the first probability value is taken as the Gini coefficient of the battery, expressed as: min(R i )≤X, Gini=1-Y, where min(R i ) is the minimum voltage eigenvalue, X is the first eigenvalue, and the Gini coefficient is the difference between 1 and the first probability value Y.

[0109] Specifically, the first eigenvalue is determined in the following manner: sort the voltage eigenvalues ​​of multiple battery cells from small to large to obtain a sorting result, determine the 75th% value from the sorting result, that is, obtain the 75th quantile, determine the 25th% value from the sorting result, that is, obtain the 25th quantile, and further determine the first eigenvalue based on the two quantiles.

[0110] Furthermore, the first eigenvalue is expressed as: X = Q25-1.5×(Q75-Q25), and the above Gini coefficient is expressed as: min(R i )>Q25-1.5×(Q75-Q25), Gini=0, where Q25 is the 25th percentile, Q75 is the 75th percentile, min(R i ) is the minimum voltage characteristic value, and Gini is the Gini coefficient.

[0111] In this embodiment, the Gini coefficient is determined by comparing the minimum voltage characteristic value with the first characteristic value, and the Gini coefficient is used as one of the abnormality evaluation indicators, so that the battery can be diagnosed accurately.

[0112] In one embodiment of the present application, the first probability value is calculated in the following manner:

[0113] The voltage characteristic values ​​of the plurality of battery cells are binned to obtain the number of voltage characteristic values ​​that each bin falls into;

[0114] According to the number of voltage characteristic values ​​that each box falls into and the number of battery cells in the multiple batteries, a probability value corresponding to each box is obtained;

[0115] The first probability value is calculated according to the probability value corresponding to each box.

[0116] Specifically, the first probability value is obtained by binning, and the binning is set as follows: bin = [min(R i ), Blll], [Blll, max(R i )],min(R i ) is the minimum voltage characteristic value among the voltage characteristic values ​​of the multiple battery cells, Blll is the first boundary value, max(R i ) is the maximum voltage characteristic value among the voltage characteristic values ​​of multiple battery cells.

[0117] Specifically, the first boundary value can also be calculated based on the above two quantiles, and the first boundary value is expressed as: Blll=Q25-4.5×(Q75-Q25), wherein Q25 is the 25th quantile and Q75 is the 75th quantile.

[0118] The voltage characteristic values ​​of multiple battery cells are divided into boxes by using a box plot to obtain the number of voltage characteristic values ​​that each box falls into. According to the number of voltage characteristic values ​​that each box falls into and the number of battery cells in multiple batteries, the probability value corresponding to each box is obtained, which can be calculated by formula (4):

[0119]

[0120] Among them, P k is the probability value corresponding to the box, n k is the number of voltage characteristic values ​​that fall into bin k, and n represents the number of battery cells in the battery.

[0121] Furthermore, the first probability value is calculated according to the probability value corresponding to each box, and is calculated using formula (5):

[0122]

[0123] Where Y is the first probability value, then the above Gini coefficient is expressed as: min(R i )≤X,

[0124] In one embodiment of the present application, specifically, step 104, obtaining a diagnosis result of the battery according to the Gini coefficient of the battery, includes:

[0125] Obtaining a standardized parameter value of the battery, wherein the standardized parameter value is a ratio of a first intermediate value to a second intermediate value, the first intermediate value is a minimum voltage characteristic value among voltage characteristic values ​​of a plurality of battery cells minus an average of voltage characteristic values ​​of a plurality of battery cells, and the second intermediate value is a standard deviation of the voltage characteristic values ​​of a plurality of battery cells;

[0126] If the Gini coefficient of the battery is greater than the first fault Gini coefficient and less than the second fault Gini coefficient, and the standardized parameter value is less than the preset first fault value, the diagnosis result is determined to be a battery fault.

[0127] In this embodiment, the standardized parameter of the battery and the Gini coefficient are combined as an indicator for battery consistency evaluation. Specifically, the standardized parameter value of the battery is calculated according to the first intermediate value and the second intermediate value, and the standardized parameter value is calculated using formula (6), which is as follows:

[0128]

[0129] Among them, Zscore min Indicates the standardized parameter value of the battery, min(R i ) is the minimum voltage characteristic value, mean(R i ) is the mean value of the voltage characteristic values ​​of multiple battery cells, min(R i )-mean(R i ) represents the first intermediate value, std(R i ) represents the second median value, which is also the standard deviation.

[0130] Furthermore, if the Gini coefficient of the battery is greater than the first fault Gini coefficient and less than the second fault Gini coefficient, and the standardized parameter value is less than the preset first fault value, the diagnosis result is determined to be a battery fault, wherein the first fault Gini coefficient can be set to 0, expressed as: 0<Gini<throldgini, and Zscore min <throldz, Gini is the Gini coefficient of the battery, throldgini is the second fault Gini coefficient, Zscore min is the standardized parameter value of the battery, throldz is the first fault value, then the diagnosis result is determined to be a battery failure, that is, the battery is inconsistent.

[0131] By using standardized parameters and the Gini coefficient as indicators for battery consistency assessment, battery inconsistency can be accurately determined and the accuracy of battery diagnosis can be improved.

[0132] In one embodiment of the present application, after step 104, the following steps are further included:

[0133] When the diagnosis result is a battery fault, if the minimum voltage characteristic value is located in the first fault interval among multiple preset fault intervals, the fault level corresponding to the first fault interval is used as the level of the battery fault, wherein each fault interval in the multiple fault intervals is correspondingly set with a fault level.

[0134] In this embodiment, multiple fault intervals are pre-set. When the diagnosis result is a battery fault, it is determined in which of the multiple fault intervals the minimum voltage characteristic value is located, and the fault interval in which the minimum voltage characteristic value is located is determined as the first fault interval. The fault level corresponding to the first fault interval is used as the level of the battery fault, wherein a fault level is set corresponding to each of the multiple fault intervals.

[0135] Optionally, the fault intervals set for different batteries may be different. For example, for a ternary lithium battery, three fault intervals are set, namely: (1, throld Rmin-ncm1 ],(throld Rmin-ncm1 ,throld Rmin-ncm2 ],(throld Rmin-ncm2 ,0],throld Rmin-ncm1 is the first threshold corresponding to the ternary lithium battery, throld Rmin-ncm2 is the second threshold corresponding to the ternary lithium battery, and the first threshold is greater than the second threshold. Rmin-ncm1 ] The corresponding fault level is level one fault, (throld Rmin-ncm1 ,throld Rmin-ncm2 ] The corresponding fault level is a secondary fault, (throld Rmin-ncm2 ,0] corresponds to a level 3 fault, and the level of a level 2 fault is greater than that of a level 1 fault and less than that of a level 3 fault. Early warning is given according to the level of the fault. For example, if the minimum voltage characteristic value is located at (throld Rmin-ncm2 , 0], the corresponding fault level is taken as the level of battery fault, that is, the third level fault is taken as the level of battery fault.

[0136] For example, for lithium iron phosphate batteries, three fault intervals are set: (1, throld Rmin-lfp1 ],(throld Rmin-lfp1 ,throld Rmin-lfp2 ],(throldRmin-lfp2 ,0],throld Rmin-lfp1 is the first threshold corresponding to the lithium iron phosphate battery, throld Rmin-lfp1 is the second threshold corresponding to the lithium iron phosphate battery, and the first threshold is greater than the second threshold. Rmin-ncm1 ] The corresponding fault level is level one fault, (throld Rmin-lfp1 ,throld Rmin-lfp2 ] The corresponding fault level is a secondary fault, (throld Rmin-lfp2 ,0] corresponds to a level 3 fault, and the level of a level 2 fault is greater than that of a level 1 fault and less than that of a level 3 fault. Early warning is given according to the level of the fault. For example, if the minimum voltage characteristic value is located at (throld Rmin-lfp2 , 0], the corresponding fault level is taken as the level of battery fault, that is, the third level fault is taken as the level of battery fault.

[0137] By setting the fault interval, it is possible to accurately determine whether the battery has a fault. Moreover, different fault intervals can be set for different types of batteries, which can be applicable to ternary lithium batteries and lithium iron phosphate batteries.

[0138] In one embodiment of the present application, after step 104, the following steps are further included:

[0139] When the diagnosis result is a battery failure, a second fault interval is determined, the upper boundary of the second fault interval is the first boundary value, the lower boundary of the second fault interval is the minimum voltage characteristic value among the voltage characteristic values ​​of multiple battery cells, and the first boundary value is determined according to the quantile of the binning processing; the battery cells whose corresponding voltage characteristic values ​​among the multiple battery cells fall into the second fault interval are judged as faulty battery cells.

[0140] In this embodiment, when the diagnosis result is a battery fault, the second fault interval is determined, and the upper boundary of the second fault interval is the first boundary value, which is calculated according to the two quantiles above. The first boundary value is expressed as: Blll = Q25-4.5×(Q75-Q25), where Q25 is the 25th quantile and Q75 is the 75th quantile. The lower boundary value of the second fault is the minimum voltage characteristic value. The second fault interval is expressed as: [min(R i ), Blll], min(R i ) is the minimum voltage characteristic value among the voltage characteristic values ​​of the multiple battery cells, the battery cells whose corresponding voltage characteristic values ​​among the multiple battery cells fall into the second fault interval are determined to be faulty battery cells, the number of the faulty battery cell is obtained, and the cloud sends the number of the faulty battery cell to a corresponding terminal, such as a maintenance terminal,

[0141] Or user terminal, so that the battery can be replaced or repaired in time.

[0142] The following is an example of the vehicle battery fault diagnosis method provided in the embodiment of the present application. Figure 2 Another flow chart of an embodiment of the vehicle battery fault diagnosis method provided by the present application is shown as follows: Figure 2 As shown, the vehicle battery fault diagnosis method includes:

[0143] Step 201, operating condition data screening: screening out voltage monitoring data of single cells of charging operating conditions that meet the conditions.

[0144] In this embodiment, the execution subject is the cloud big data platform. The vehicle reports the original monitoring data of the battery pack to the cloud big data platform. The battery pack includes multiple single cells (that is, the battery in the above text includes multiple battery units). The cloud big data platform cleans the original monitoring data of the battery pack reported by the vehicle, including but not limited to the cleaning steps such as removing abnormal values ​​and converting data formats, to obtain data set A, such as daily data set A. Then, according to the vehicle status, speed, and current data, the data set A is screened to obtain the charging condition data set B. The charging condition data set B includes: the voltages of multiple single cells corresponding to multiple sampling points collected under the charging condition (that is, the battery information in the above text includes the voltages of multiple battery units corresponding to multiple sampling points collected under the charging condition).

[0145] Step 202, primary feature calculation: calculate the Pearson correlation coefficient matrix of the voltage of each single cell, and perform averaging to calculate the primary features.

[0146] In this embodiment, the Pearson correlation coefficient matrix R of the voltage of each single cell is calculated based on the charging condition data set B. ij (i.e. the correlation coefficient mentioned above), the average value of the correlation coefficients between all other single cells is calculated for the single cell to obtain a primary characteristic (i.e. the voltage characteristic value mentioned above), specifically:

[0147] For each single cell i: calculate the average value of the voltage of the single cell i (i.e., the first battery unit mentioned above) at multiple sampling points as the first mean value, and obtain the first voltage corresponding to the single cell i at each sampling point according to the difference between the voltage of the single cell i at each sampling point and the first mean value, where the single cell i is any single cell among the multiple single cells.

[0148] For each single cell i: according to the first voltage of single cell i and the first voltage of each single cell j, obtain the corresponding correlation coefficients between the voltage of single cell i and the voltage of each single cell j (that is, each second battery unit in the above text), single cell j is a single cell in the multiple battery units except single cell i; according to the corresponding correlation coefficients between the voltage of single cell i and the voltage of each single cell j, calculate the primary characteristic of single cell i (that is, the voltage characteristic value in the above text, and the voltage characteristic value will be used for explanation below).

[0149] The corresponding correlation coefficients between the voltage of the single battery cell i and the voltage of each single battery cell j (ie, each second battery unit in the above text) can be calculated using formula (1).

[0150] The voltage characteristic value of the single cell i can be calculated using formula (2) or (3).

[0151] Step 203, feature binning: perform box plot calculation on the correlation coefficient feature and extract statistical features.

[0152] In this embodiment, a box plot is used to divide the voltage characteristic values ​​of a single cell into boxes, and the probability value P in each box is counted. k , and record the binning results of each monomer, where bins is the binning setting, as shown below:

[0153] bin=[min(R i ), Blll], [Blll, max(R i )];

[0154] Blll = Q75 + 4.5 * (Q75 - Q25);

[0155]

[0156] Among them, P k is the probability value corresponding to the box, n k is the number of voltage characteristic values ​​that fall into bin k, and n represents the number of battery cells in the battery.

[0157] Step 204, secondary feature calculation: calculate the Gini coefficient based on the feature binning results.

[0158] If the minimum voltage characteristic value among the voltage characteristic values ​​of multiple single cells is greater than the first characteristic value, 0 is used as the Gini coefficient of the battery. The first characteristic value is calculated based on the 75th percentile and the 25th percentile, and is expressed as:

[0159] If min(R i )>Q25-1.5×(Q75-Q25), then Gini=0.

[0160] If the minimum voltage eigenvalue is less than or equal to the first eigenvalue, the difference between 1 and the first probability value is taken as the Gini coefficient of the battery. The first probability value is obtained according to the above binning process (see the calculation process of the first probability value), and is expressed as:

[0161] If min(R i )≤Q25-1.5×(Q75-Q25), then

[0162] Step 205, consistency anomaly identification: consistency anomaly identification is performed in combination with multi-dimensional features.

[0163] In this embodiment, according to R i Calculate the minimum value Rmin and the standardized parameter Zscore min As consistency assessment indicators:

[0164] In this embodiment, the minimum voltage characteristic value is selected from the voltage characteristic values ​​corresponding to the plurality of single cells, and the standardized parameter value of the battery pack is calculated according to the minimum voltage characteristic value. The standardized parameter value can be calculated using formula (6).

[0165] According to Zscore min With Gini, combined with different warning threshold settings, risk warnings are issued when the following conditions are met:

[0166] 0<Gini<throldgini, and Zscore min <throldz, the diagnosis result is battery failure, and the minimum voltage characteristic value R min Throld at different warning levels Rmin Within the scope, for ternary cells and lithium iron phosphate cells (i.e. ternary lithium batteries and lithium iron phosphate batteries mentioned above), different levels of throld Rmin Carry out risk level warning, and Table 1 shows the warning level classification, as shown in Table 1:

[0167] Table 1

[0168] Level 1 warning Second level warning Level 3 warning Ternary battery cell <![CDATA[(1,throld Rmin-ncm1 ]]]> <![CDATA[(throld Rmin-ncm1 ,throld Rmin-ncm2 ]]]> <![CDATA[(throld Rmin-ncm2 ,0]]]> Lithium iron phosphate battery <![CDATA[(1,throld Rmin-lfp1 ]]]> <![CDATA[(throld Rmin-lfp1 ,throld Rmin-lfp2 ]]]> <![CDATA[(throld Rmin-lfp2 ,0]]]>

[0169] The multiple intervals corresponding to the three levels of the first-level warning, the second-level warning and the third-level warning are warning intervals (i.e., the fault intervals mentioned above). If the minimum voltage characteristic value is located in the first warning interval among the multiple warning intervals (i.e., the first fault interval mentioned above), the warning level corresponding to the first warning interval is used as the battery warning level (i.e., the battery fault level mentioned above), wherein each warning interval among the multiple warning intervals is correspondingly set with a warning level (i.e., the fault level mentioned above).

[0170] Step 206, fault location: locate the faulty cell according to the correlation coefficient characteristics.

[0171] In this embodiment, for the risk battery pack that triggers the early warning, the voltage characteristic value R corresponding to the single cell is i Falling into [min(R i ), Blll] is used as the faulty battery cell (i.e., the battery cell whose corresponding voltage characteristic value among the multiple battery cells falls into the second fault interval is determined to be the faulty battery cell).

[0172] The vehicle battery fault diagnosis method provided in the embodiment of the present application performs cloud service calculation and analysis in a daily batch processing manner based on the vehicle monitoring data of the cloud monitoring platform, and uses charging condition data. Compared with the strict requirements of traditional solutions on working conditions, it achieves a wider calculation coverage and reduces the risk of missed reports. It is suitable for both ternary batteries and lithium iron phosphate batteries, and the algorithm has strong versatility; by setting relevant parameters, it can monitor risks of different levels in a graded and classified manner, thereby providing more refined and effective risk management and realizing early risk detection.

[0173] Figure 3 FIG. 1 shows a structural diagram of a vehicle battery fault diagnosis device provided by an embodiment of the present application. Figure 3 As shown, the vehicle battery fault diagnosis device 300 includes:

[0174] An acquisition module 301 is used to acquire battery information of a vehicle battery, where the battery includes a plurality of battery cells;

[0175] A first determination module 302 is used to determine voltage characteristic values ​​corresponding to each of the plurality of battery cells according to the battery information, where the voltage characteristic values ​​are used to characterize the correlation coefficient between the voltage of each battery cell and the voltages of the remaining battery cells, where the remaining battery cells include all other battery cells in the plurality of battery cells except the battery cell corresponding to the voltage characteristic value;

[0176] A second determination module 303 is used to determine the Gini coefficient of the battery according to the voltage characteristic values ​​corresponding to each of the plurality of battery cells;

[0177] The diagnosis module 304 is used to obtain a diagnosis result of the battery according to the Gini coefficient of the battery.

[0178] In an embodiment of the present application, the first determination module 302 is further used to execute, for each battery cell: obtaining, according to the difference between the voltage of the first battery cell at each sampling point and the first mean, a first voltage corresponding to the first battery cell at each sampling point, where the first mean is an average value of the voltages of the first battery cell at multiple sampling points; the first battery cell is any one of the multiple battery cells;

[0179] For each first battery cell, perform the following process:

[0180] Based on the first voltage of the first battery cell and the first voltage of each second battery cell, respectively, the corresponding correlation coefficients between the voltage of the first battery cell and the voltage of each second battery cell are obtained, and the second battery cell is a battery cell other than the first battery cell among the multiple battery cells; based on the corresponding correlation coefficients between the voltage of the first battery cell and the voltage of each second battery cell, the voltage characteristic value corresponding to the first battery cell is calculated.

[0181] In one embodiment of the present application, the first determination module 302 is also used to sum the corresponding correlation coefficients between the voltage of the first battery cell and the voltage of each second battery cell to obtain a first correlation coefficient corresponding to the first battery cell; and obtain a voltage characteristic value corresponding to the first battery cell based on the first correlation coefficient corresponding to the first battery cell and the number of battery cells in the battery.

[0182] In one embodiment of the present application, the second determination module 303 is further configured to use 0 as the Gini coefficient of the battery if the minimum voltage characteristic value among the voltage characteristic values ​​of the multiple battery cells is greater than the first characteristic value, the first characteristic value is determined according to the quantile, and the quantile is determined according to the sorting result of the voltage characteristic values ​​of the multiple battery cells;

[0183] If the minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells is less than or equal to the first characteristic value, the difference between 1 and the first probability value is taken as the Gini coefficient of the battery.

[0184] In one embodiment of the present application, the second determination module includes a box division module and a determination submodule;

[0185] A binning module, used for binning the voltage characteristic values ​​of the plurality of battery cells to obtain the number of voltage characteristic values ​​that each bin falls into;

[0186] The determination submodule is used to obtain the probability value corresponding to each box according to the number of voltage characteristic values ​​falling into each box and the number of battery cells in the multiple batteries; and calculate the first probability value according to the probability value corresponding to each box.

[0187] In one embodiment of the present application, the diagnostic module 304 is also used to obtain a standardized parameter value of the battery, wherein the standardized parameter value is a ratio of a first intermediate value to a second intermediate value, the first intermediate value is a minimum voltage characteristic value among the voltage characteristic values ​​of multiple battery cells minus a mean of the voltage characteristic values ​​of multiple battery cells, and the second intermediate value is a standard deviation of the voltage characteristic values ​​of multiple battery cells; if the Gini coefficient of the battery is greater than the first fault Gini coefficient and less than the second fault Gini coefficient, and the standardized parameter value is less than the preset first fault value, then the diagnostic result is determined to be a battery fault.

[0188] In one embodiment of the present application, the diagnostic module 304 is also used to, when the diagnosis result is a battery fault, if the minimum voltage characteristic value is located in the first fault interval among multiple preset fault intervals, then the fault level corresponding to the first fault interval is used as the level of the battery fault, wherein each fault interval in the multiple fault intervals is correspondingly set with a fault level.

[0189] In one embodiment of the present application, the diagnostic module 304 is also used to determine a second fault interval when the diagnosis result is a battery fault, the upper boundary of the second fault interval is the first boundary value, the lower boundary of the second fault interval is the minimum voltage characteristic value among the voltage characteristic values ​​of multiple battery cells, and the first boundary value is determined according to the quantile of the binning processing; the battery cells whose corresponding voltage characteristic values ​​among the multiple battery cells fall into the second fault interval are determined as faulty battery cells.

[0190] The vehicle battery fault diagnosis device 300 provided in the embodiment of the present application can implement the various processes implemented in the aforementioned vehicle battery fault diagnosis method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0191] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0192] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0193] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0194] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an integrated gateway disaster recovery device. In a specific embodiment, memory 402 is a non-volatile solid-state memory.

[0195] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect or the second aspect of the present disclosure.

[0196] The processor 401 implements any one of the information auditing methods in the above embodiments by reading and executing computer program instructions stored in the memory 402 .

[0197] In one example, the electronic device may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0198] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0199] Bus 410 includes hardware, software or both, and the parts of information audit method or verification equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0200] In addition, in combination with the vehicle battery fault diagnosis method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any vehicle battery fault diagnosis method in the above embodiment is implemented.

[0201] In addition, the embodiments of the present application may be implemented by providing a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device implements any one of the vehicle battery fault diagnosis methods in the above embodiments.

[0202] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiment, several specific steps are described as examples. However, the method process of the present application is not limited to the specific steps described, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0203] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0204] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0205] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0206] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A vehicle battery fault diagnosis method, characterized in that: The method comprises: Acquiring battery information of a vehicle battery, wherein the battery includes a plurality of battery cells; Determine, according to the battery information, voltage characteristic values ​​corresponding to each of the plurality of battery cells, the voltage characteristic values ​​being used to characterize a correlation coefficient between a voltage of each of the battery cells and voltages of remaining battery cells, the remaining battery cells including all other battery cells in the plurality of battery cells except the battery cell corresponding to the voltage characteristic value; Determining the Gini coefficient of the battery according to voltage characteristic values ​​corresponding to each of the plurality of battery cells; A diagnosis result of the battery is obtained according to the Gini coefficient of the battery.

2. The method according to claim 1, characterized in that The battery information includes voltages of a plurality of battery cells corresponding to a plurality of sampling points respectively collected under a charging condition; The step of determining voltage characteristic values ​​corresponding to each of the plurality of battery cells according to the battery information includes: For each battery cell, the following steps are performed: obtaining a first voltage corresponding to each sampling point of the first battery cell according to a difference between the voltage of the first battery cell at each sampling point and a first mean value, wherein the first mean value is an average value of the voltages of the first battery cell at multiple sampling points; the first battery cell is any one of the multiple battery cells; For each first battery cell, perform the following process: Obtaining, according to the first voltage of the first battery cell and the first voltage of each second battery cell, respective corresponding correlation coefficients between the voltage of the first battery cell and the voltage of each second battery cell, wherein the second battery cell is a battery cell other than the first battery cell among the plurality of battery cells; The voltage characteristic value corresponding to the first battery cell is calculated based on the correlation coefficients respectively corresponding to the voltage of the first battery cell and the voltage of each of the second battery cells.

3. The method according to claim 2, characterized in that The step of calculating the voltage characteristic value corresponding to the first battery cell according to the correlation coefficients respectively corresponding to the voltage of the first battery cell and the voltage of each of the second battery cells comprises: For each of the first battery cells, the following process is performed: Sum the correlation coefficients corresponding to the voltage of the first battery cell and the voltage of each of the second battery cells to obtain a first correlation coefficient corresponding to the first battery cell; A voltage characteristic value corresponding to the first battery cell is obtained according to a first correlation coefficient corresponding to the first battery cell and the number of battery cells in the battery.

4. The method according to claim 1, characterized in that: The determining the Gini coefficient of the battery according to the voltage characteristic values ​​corresponding to each of the plurality of battery cells comprises: If the minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells is greater than a first characteristic value, 0 is used as the Gini coefficient of the battery, wherein the first characteristic value is determined according to a quantile, and the quantile is determined according to a sorting result of the voltage characteristic values ​​of the plurality of battery cells; If the minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells is less than or equal to the first characteristic value, the difference between 1 and the first probability value is taken as the Gini coefficient of the battery.

5. The method according to claim 4, characterized in that The first probability value is calculated in the following way: Binning the voltage characteristic values ​​of the plurality of battery cells to obtain the number of voltage characteristic values ​​that each bin falls into; Obtaining a probability value corresponding to each box according to the number of voltage characteristic values ​​that each box falls into and the number of battery cells in the plurality of batteries; The first probability value is calculated according to the probability value corresponding to each box.

6. The method according to claim 1, characterized in that The step of obtaining a diagnosis result of the battery according to the Gini coefficient of the battery includes: Obtaining a standardized parameter value of the battery, wherein the standardized parameter value is a ratio of a first intermediate value to a second intermediate value, the first intermediate value being a minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells minus a mean of the voltage characteristic values ​​of the plurality of battery cells, and the second intermediate value being a standard deviation of the voltage characteristic values ​​of the plurality of battery cells; If the Gini coefficient of the battery is greater than the first fault Gini coefficient and less than the second fault Gini coefficient, and the standardized parameter value is less than the preset first fault value, then the diagnosis result is determined to be a battery fault.

7. The method according to any one of claims 1 to 6, characterized in that After obtaining a diagnosis result of the battery according to the Gini coefficient of the battery, the method further includes: In the case where the diagnosis result is a battery failure, if the minimum voltage characteristic value is located in a first fault interval among a plurality of preset fault intervals, the fault level corresponding to the first fault interval is used as the level of the battery failure, wherein a fault level is set corresponding to each of the plurality of fault intervals.

8. The method according to any one of claims 1 to 6, characterized in that After obtaining a diagnosis result of the battery according to the Gini coefficient of the battery, the method further includes: In the case where the diagnosis result is a battery failure, a second fault interval is determined, the upper boundary of the second fault interval is a first boundary value, the lower boundary of the second fault interval is a minimum voltage characteristic value among the voltage characteristic values ​​of the plurality of battery cells, and the first boundary value is determined according to the quantile of the binning process; A battery cell whose corresponding voltage characteristic value among the plurality of battery cells falls within the second fault interval is determined as a faulty battery cell.

9. A vehicle battery fault diagnosis device, characterized in that: The device comprises: An acquisition module, used to acquire battery information of a vehicle battery, wherein the battery includes a plurality of battery cells; A first determination module is used to determine, according to the battery information, voltage characteristic values ​​corresponding to each of the plurality of battery cells, wherein the voltage characteristic values ​​are used to characterize a correlation coefficient between a voltage of each of the battery cells and voltages of remaining battery cells, wherein the remaining battery cells include all other battery cells in the plurality of battery cells except the battery cells corresponding to the voltage characteristic values; A second determination module, used to determine the Gini coefficient of the battery according to the voltage characteristic values ​​corresponding to each of the plurality of battery cells; The diagnosis module is used to obtain a diagnosis result of the battery according to the Gini coefficient of the battery.

10. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the vehicle battery fault diagnosis method according to any one of claims 1 to 8 is implemented.

Images