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, and the battery information comprises the voltage of each battery unit at a plurality of sampling points; the plurality of sampling points are divided according to a plurality of pre-obtained sampling point intervals to obtain a plurality of groups, and each group comprises the voltage of each battery unit falling in the corresponding sampling point interval; screening the plurality of groups according to the working condition of the battery to obtain at least one target group, and taking a sampling point in the sampling point interval corresponding to each target group as a target sampling point; according to the voltage difference value of the target sampling point in the at least one target group, the diagnosis result of the battery is determined, the voltage difference value is the difference value between the maximum voltage and the minimum voltage of the multiple battery units at the target sampling point, the actual information of the battery is processed, the diagnosis result is obtained, and therefore the accurate diagnosis result of the battery is obtained. 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] With the rapid development of the economy, the new energy vehicle market has shown explosive growth and has become a key force in promoting the green development of the automotive industry. As the core component of electric vehicles, the safety of power batteries directly determines the safety, power performance and endurance of electric vehicles. Fault detection of battery packs throughout their life cycle is of great practical significance.

[0003] Abnormal self-discharge is one of the more common faults of power batteries. It refers to the fault phenomenon that the battery gradually loses power due to internal chemical reactions when it is not working. At present, the self-discharge rate is obtained by calculating the ratio of the two terminal voltage drops to the time change based on the two terminal voltage drops corresponding to the same state of charge (SOC) range, so as to diagnose the battery fault based on the self-discharge rate.

[0004] However, the above terminal voltage is estimated by the power battery equivalent circuit model, and the obtained self-discharge rate is inaccurate, which 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] Acquire battery information of a vehicle battery, wherein the battery includes a plurality of battery cells, and the battery information includes a voltage of each of the battery cells at a plurality of sampling points;

[0008] Divide the plurality of sampling points according to the plurality of pre-acquired sampling point intervals to obtain a plurality of groups, each of the groups including the voltage of each battery cell falling within the corresponding sampling point interval;

[0009] Screening the plurality of groups according to the working condition of the battery to obtain at least one target group, wherein the sampling points in the sampling point interval corresponding to each target group are target sampling points;

[0010] The diagnosis result of the battery is determined according to the voltage difference value of the target sampling point in the at least one target group, where the voltage difference value is the difference between the maximum voltage and the minimum voltage of the plurality of battery cells at the target sampling point.

[0011] In one embodiment of the present application, the battery information further includes the state of charge SOC of the battery at the plurality of sampling points;

[0012] The step of dividing the plurality of sampling points according to the plurality of pre-acquired sampling point intervals to obtain a plurality of groups includes:

[0013] According to a plurality of preset SOC intervals, determining a sampling point interval corresponding to each of the SOC intervals;

[0014] According to the sampling point interval corresponding to each of the SOC intervals, the plurality of sampling points are divided to obtain a plurality of groups.

[0015] In an embodiment of the present application, the plurality of groups are screened according to the working condition of the battery to obtain at least one target group, including:

[0016] In the case where the operating condition of the battery is a dynamic operating condition, executing for each of the groups: if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to a first preset number, determining the group as the target group;

[0017] When the operating condition of the battery is a static condition, for each of the groups, the following is performed: if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to a second preset number, the group is determined as the target group, and the second preset number is less than the first preset number.

[0018] In an embodiment of the present application, determining the diagnosis result of the battery according to the voltage difference value of the target sampling point in the at least one target group includes:

[0019] Each of the target groups is processed as follows: according to the pressure difference value of each of the target sampling points in the target group, a first characteristic value corresponding to the target group is determined; according to the SOC interval corresponding to the target group, historical target groups in multiple historical time periods are screened to obtain multiple historical target groups, and the SOC interval corresponding to each of the historical target groups is the same as the SOC interval corresponding to the target group; first characteristic values ​​corresponding to the multiple historical target groups are obtained; the first characteristic values ​​corresponding to the multiple historical target groups and the first characteristic value corresponding to the target group are screened to obtain a target characteristic value corresponding to the target group;

[0020] If the target characteristic value with the largest value in any of the target groups is greater than or equal to a preset threshold, it is determined that the battery is faulty.

[0021] In an embodiment of the present application, the first characteristic values ​​corresponding to the plurality of historical target groups and the first characteristic values ​​corresponding to the target group are screened to obtain the target characteristic value corresponding to the target group, including:

[0022] Obtaining the sampling time of the sampling points corresponding to the first characteristic values ​​corresponding to the plurality of historical target groups and the first characteristic values ​​corresponding to the target group;

[0023] According to the sequence of the sampling times, the first characteristic values ​​corresponding to the plurality of historical target groups and the first characteristic values ​​corresponding to the target group are sorted to obtain a characteristic sequence;

[0024] Determining a target residual of a robust regression algorithm based on the total number of first eigenvalues ​​in the characteristic sequence;

[0025] configuring a robust regression algorithm using the target residual;

[0026] The configured robust regression algorithm is used to screen the feature sequence to obtain target information, where the target information includes target feature values ​​corresponding to the target group.

[0027] In one embodiment of the present application, the target information further includes a linear regression slope;

[0028] After determining that the battery is faulty if the target characteristic value with the largest value in any of the target groups is greater than or equal to a preset threshold, the method further includes:

[0029] Determine, according to the total number and the target residual, a slope threshold corresponding to the total number and the target residual;

[0030] If the linear regression slope is greater than the slope threshold, the fault level corresponding to the slope threshold is used as the fault level of the battery.

[0031] In an embodiment of the present application, after determining the diagnosis result of the battery according to the voltage difference value of the target sampling point in the at least one target group, the method further includes:

[0032] When the diagnosis result is a battery failure, obtaining the number of times the voltage of each battery cell at each target sampling point is the minimum voltage;

[0033] If the number of times corresponding to the first battery unit is greater than the number threshold, it is determined that the first battery unit has a fault.

[0034] In an embodiment of the present application, after determining that the first battery unit has a fault, the method further includes:

[0035] Obtaining the serial number of the first battery unit having a fault;

[0036] The serial number of the first battery unit is sent to a corresponding terminal.

[0037] In a second aspect, an embodiment of the present application provides a vehicle battery fault diagnosis device, the device comprising:

[0038] An acquisition module, used for acquiring battery information of a vehicle battery, wherein the battery includes a plurality of battery cells, and the battery information includes a voltage of each of the battery cells at a plurality of sampling points;

[0039] A processing module, used for dividing the plurality of sampling points according to the plurality of pre-acquired sampling point intervals to obtain a plurality of groups, each of the groups including the voltage of each battery cell falling within the corresponding sampling point interval;

[0040] The processing module is further used to screen the plurality of groups according to the working condition of the battery to obtain at least one target group, wherein the sampling points in the sampling point interval corresponding to each target group are target sampling points;

[0041] A diagnosis module is used to determine a diagnosis result of the battery according to a voltage difference value of the target sampling point in the at least one target group, wherein the voltage difference value is a difference between a maximum voltage and a minimum voltage of a plurality of the battery cells at the target sampling point.

[0042] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions;

[0043] When the processor executes the computer program instructions, the vehicle battery fault diagnosis method as described in the first aspect is implemented.

[0044] 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.

[0045] 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.

[0046] The vehicle battery fault diagnosis method, device and equipment of the embodiments of the present application obtain battery information of the vehicle, wherein the battery information includes the voltage of each battery cell at multiple sampling points, divides the multiple sampling points according to multiple pre-acquired sampling point intervals to obtain multiple groups, each group includes the voltage of each battery cell falling in the corresponding sampling point interval, and screens each group according to the working condition of the battery to obtain at least one target group, wherein the sampling points in the sampling interval corresponding to the target group are the target sampling points, and determines the diagnosis result according to the voltage difference value of the target sampling point in the target group. Compared with the method of estimating voltage in the prior art, the method of estimating parameters is not used for diagnosis, and the actual battery information is processed to obtain the diagnosis result, thereby obtaining a more accurate battery diagnosis result, which can improve the accuracy of battery diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] 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.

[0048] Figure 1 It is a flow chart of a vehicle battery fault diagnosis method provided by an embodiment of the present application;

[0049] Figure 2 Schematic diagram of the mapping relationship between SOC, sampling point and voltage provided in the embodiment of the present application;

[0050] Figure 3 is another flow chart of the vehicle battery fault diagnosis method provided by an embodiment of the present application;

[0051] Figure 4 is a schematic diagram of the structure of a vehicle battery fault diagnosis device provided in an embodiment of the present application;

[0052] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] 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.

[0054] 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 presence of other identical elements in the process, method, article or device including the elements.

[0055] 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.

[0056] 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:

[0057] Step 101, obtaining battery information of a vehicle battery, where the battery includes a plurality of battery cells, and the battery information includes the voltage of each battery cell at a plurality of sampling points.

[0058] 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.

[0059] 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.

[0060] The battery information includes the voltage of each battery cell at multiple sampling points.

[0061] Step 102 , dividing the plurality of sampling points according to the plurality of pre-acquired sampling point intervals to obtain a plurality of groups, each group including the voltage of each battery cell falling within the corresponding sampling point interval.

[0062] In this embodiment, multiple sampling points are divided according to multiple sampling point intervals obtained in advance to obtain multiple groups, which is actually equivalent to grouping the battery information to facilitate subsequent diagnosis of each group. Each group includes the voltage of each battery cell falling in the corresponding sampling point interval.

[0063] Step 103 , screening multiple groups according to the working conditions of the battery to obtain at least one target group, and the sampling points in the sampling point interval corresponding to each target group are target sampling points.

[0064] In this embodiment, multiple groups are screened according to the operating conditions of the battery, and the operating conditions are divided into dynamic conditions and static conditions, wherein the dynamic conditions include driving conditions and charging conditions, and at least one target group is obtained, and the sampling points in the sampling point interval corresponding to each target group are used as target sampling points.

[0065] Step 104 , determining a diagnosis result of the battery according to a voltage difference value of a target sampling point in at least one target group, where the voltage difference value is a difference between a maximum voltage and a minimum voltage of a plurality of battery cells at the target sampling point.

[0066] In this embodiment, the difference between the maximum voltage and the minimum voltage of multiple battery cells at the target sampling point is calculated as the voltage difference value of the target sampling point, and the battery diagnosis result is determined according to the voltage difference value of the target sampling point in at least one target group.

[0067] In this embodiment, battery information of the vehicle is obtained, and the battery information includes the voltage of each battery cell at multiple sampling points. The multiple sampling points are divided according to the pre-acquired multiple sampling point intervals to obtain multiple groups, each group includes the voltage of each battery cell falling in the corresponding sampling point interval, and each group is screened according to the working condition of the battery to obtain at least one target group. The sampling points in the sampling interval corresponding to the target group are target sampling points. The diagnosis result is determined according to the voltage difference value of the target sampling point in the target group. Compared with the method of estimating voltage in the prior art, the method of estimating parameters is not used for diagnosis, and the actual battery information is processed to obtain the diagnosis result, thereby obtaining a more accurate battery diagnosis result, which can improve the accuracy of battery diagnosis.

[0068] In one embodiment of the present application, the battery information also includes the state of charge (SOC) of the battery at multiple sampling points. Accordingly, in step 102, the multiple sampling points are divided according to the pre-acquired multiple sampling point intervals to obtain multiple groups, including:

[0069] According to a plurality of preset SOC intervals, determining a sampling point interval corresponding to each SOC interval;

[0070] According to the sampling point interval corresponding to each SOC interval, multiple sampling points are divided to obtain multiple groups.

[0071] SOC is a key parameter to measure the remaining power of the battery. The value range of SOC is usually from 0% to 100%, where 0% means that the battery is fully discharged and 100% means that the battery is fully charged. SOC not only reflects the remaining power of the battery, but is also directly related to the endurance of the electric vehicle. In the above steps, multiple SOC intervals are pre-set, and the sampling point interval corresponding to each SOC interval is determined according to the preset multiple SOC intervals, wherein the preset multiple SOC intervals can be set according to the type of battery. For example, due to different characteristics of ternary lithium batteries and lithium iron phosphate batteries, multiple SOC intervals corresponding to different types of batteries are pre-set. Furthermore, according to the sampling point interval corresponding to each SOC interval, the multiple sampling points are divided to obtain multiple groups.

[0072] Different SOC intervals are set for ternary lithium batteries and lithium iron phosphate batteries, as shown in Table 1:

[0073] Table 1

[0074] Ternary lithium battery [0,15) [15,50) [50,85) [85,95) [95,100] Lithium iron phosphate battery [0,30) [30,50) [50,70) [70,90) [90,95]

[0075] Taking ternary lithium battery as an example, the multiple SOC intervals of ternary lithium battery include: [30,50), see Figure 2 , Figure 2 : It is a schematic diagram of the mapping relationship between SOC, sampling points and voltage provided in an embodiment of the present application, the value of SOC at each sampling point, and the voltage of each battery cell at each sampling point. Taking SOC[30,50) as an example, the sampling point interval corresponding to SOC[30,50) is determined according to SOC[30,50), and the sampling point interval includes [t1,t2] and [t3,t4], wherein t1, t2, t3, and t4 are sampling points, that is, sampling moments. According to [t1,t2] and [t3,t4], multiple sampling points are divided to obtain multiple groups, wherein multiple sampling points included in [t1,t2] are target sampling points, and multiple sampling points included in [t3,t4] are target sampling points.

[0076] It should be noted that the setting of the SOC interval is not limited to the above-mentioned partitions and can be set according to actual conditions.

[0077] By setting multiple SOC intervals to group the sampling points, multiple groups are obtained. Each group includes the voltage of each battery cell that falls in the corresponding sampling point interval. In different SOC intervals, the consistency of each battery cell in the power battery system is different, and the deviation of battery parameters reflected in different SOC intervals is different. Grouping processing can better analyze the differences between battery cells.

[0078] In one embodiment of the present application, specifically, step 103, screening multiple groups according to the working conditions of the battery to obtain at least one target group, includes:

[0079] When the working condition of the battery is a dynamic working condition, executing for each group: if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to a first preset number, determining the group as a target group;

[0080] When the battery is in a static condition, for each group, if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to a second preset number, the group is determined as a target group, and the second preset number is less than the first preset number.

[0081] In this embodiment, the working condition is divided into a dynamic working condition and a static working condition. Different working conditions correspond to different screening conditions. When the working condition of the battery is a dynamic working condition, for each group, if the number of sampling points in the sampling point interval corresponding to the group can meet the demand, that is, the number of sampling points is greater than or equal to the first preset number, indicating that the data volume demand can be met, the group is determined as a target group; if the number of sampling points in the sampling point interval corresponding to the group cannot meet the demand, that is, the number of sampling points is less than the first preset number, indicating that the data volume demand cannot be met, the group is determined as a non-target group. For example, the first preset number can be set to 50. If the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to 50, the group is determined as a target group.

[0082] When the battery is in a static condition, for each group, if the number of sampling points in the sampling point interval corresponding to the group can meet the demand, that is, the number of sampling points is greater than or equal to the second preset number, indicating that the data volume demand can be met, the group is determined as a target group; if the number of sampling points in the sampling point interval corresponding to the group cannot meet the demand, that is, the number of sampling points is less than the second preset number, indicating that the data volume demand cannot be met, the group is determined as a non-target group. For example, the first preset number can be set to 3, and if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to 3, the group is determined as a target group. It should be noted that the above-mentioned first preset number is not limited to the above-mentioned value, and can also be other suitable values.

[0083] By setting dynamic and static working conditions, the voltage data under different working conditions can be processed. Compared with the strict requirements of traditional solutions on working conditions, it has a wider applicability.

[0084] In one embodiment of the present application, specifically, step 104, determining a diagnosis result of the battery according to a voltage difference value of a target sampling point in at least one target group, includes:

[0085] Each target group is processed as follows: according to the pressure difference value of each target sampling point in the target group, a first characteristic value corresponding to the target group is determined; according to the SOC interval corresponding to the target group, historical target groups in multiple historical time periods are screened to obtain multiple historical target groups, and the SOC interval corresponding to each historical target group is the same as the SOC interval corresponding to the target group; first characteristic values ​​corresponding to the multiple historical target groups are obtained; the first characteristic values ​​corresponding to the multiple historical target groups and the first characteristic value corresponding to the target group are screened to obtain a target characteristic value corresponding to the target group;

[0086] If the target characteristic value with the largest value in any target group is greater than or equal to a preset threshold, it is determined that the battery is faulty.

[0087] In the above steps, for each target group, according to the pressure difference value of each target sampling point in the target group, the first eigenvalue corresponding to the target group is calculated. Specifically, for each target group, the pressure difference value of each target sampling point in the target group is sorted from small to large to obtain the eigenvalue sorting result corresponding to the target group. The 75th percentile is determined from the eigenvalue sorting result, that is, the 75th percentile is obtained. The 25th percentile is determined from the eigenvalue sorting result, that is, the 25th percentile is obtained. The first eigenvalue corresponding to the target group is calculated according to the two quantiles. Specifically, the first eigenvalue corresponding to the target group is calculated using formula (1), and formula (1) is as follows:

[0088] Bl=Q25-A×(Q75-Q25) (1)

[0089] Among them, Bl is the first eigenvalue corresponding to the target group, Q25 is the 25th percentile, Q75 is the 75th percentile, and A is set according to actual needs, such as 1.5.

[0090] In the above steps, according to the SOC interval corresponding to the target group, the historical target groups within multiple historical time periods are screened to obtain multiple historical target groups, wherein the SOC interval corresponding to each historical target group is the same as the SOC interval corresponding to the target group, that is, the first characteristic value is aligned using the SOC interval. Further, the first characteristic values ​​corresponding to the multiple historical target groups are obtained, the first characteristic values ​​corresponding to the multiple historical target groups and the first characteristic value corresponding to the target group are screened to obtain the target characteristic value corresponding to the target group, and whether the battery is faulty is determined according to the target characteristic value.

[0091] Specifically, if the largest target characteristic value in any target group is greater than or equal to the preset threshold, it is determined that the battery is faulty, indicating that the battery has abnormal discharge; if the largest target characteristic value in each target group is less than the preset threshold, it means that the battery currently does not have abnormal discharge and there is no fault.

[0092] In this embodiment, by screening and reducing the effect of non-target characteristic values, the target characteristic values ​​can be analyzed in a targeted manner, so as to more accurately determine whether the battery has a fault.

[0093] In one embodiment of the present application, first feature values ​​corresponding to multiple historical target groups and first feature values ​​corresponding to a target group are screened to obtain a target feature value corresponding to the target group, including:

[0094] Obtain the sampling time of the sampling points corresponding to the first eigenvalues ​​of multiple historical target groups and the first eigenvalues ​​of the target groups; sort the first eigenvalues ​​of multiple historical target groups and the first eigenvalues ​​of the target groups according to the sequence of sampling time to obtain a feature sequence; determine the target residual of the robust regression algorithm according to the total number of first eigenvalues ​​in the feature sequence; configure the robust regression algorithm using the target residual; use the configured robust regression algorithm to screen the feature sequence to obtain target information, wherein the target information includes the target eigenvalues ​​corresponding to the target groups.

[0095] In the above steps, the sampling times of the sampling points corresponding to the first eigenvalues ​​corresponding to the multiple historical target groups and the first eigenvalues ​​corresponding to the target group are obtained, and the above eigenvalues ​​are sorted according to the sampling time to obtain a feature sequence sorted by time. Specifically, according to the order of the sampling time, the first eigenvalues ​​corresponding to the multiple historical target groups and the first eigenvalues ​​corresponding to the target group are sorted to obtain the feature sequence {Bli},i=1.2....N.

[0096] Configure the robust regression algorithm: According to the total number N of the first eigenvalues ​​in the feature sequence, determine the target residual of the robust regression algorithm. See Table 2, which shows the mapping relationship between the number, residual, slope, and fault level:

[0097] Table 2

[0098]

[0099] According to the total number of the first eigenvalues ​​in the feature sequence and the number in the mapping relationship, the residual corresponding to the matched number is found, and the residual is the target residual. For example, the total number N is N1, and the target residual is residual_threshold1. The above mapping relationship can be configured according to the needs, and the number, residual, slope and fault level correspond one to one.

[0100] The target residual is used to configure the robust regression algorithm. In addition, the hyperparameters of the robust regression algorithm need to be configured. The hyperparameters include: the minimum number of samples randomly selected from the original data (Min_samples) and the threshold number of inliers for stopping iteration (stop_n_inliers). Specifically, according to the total number of first eigenvalues ​​corresponding to multiple historical target groups and the first eigenvalues ​​corresponding to the target group, the minimum number of samples randomly selected from the original data and the threshold number of inliers for stopping iteration are calculated, as follows: Min_samples = A1×N, stop_n_inliers = A2×N, where N is the total number, and A1 and A2 can be set according to actual needs. For example, A1 can be set to 80% and A2 can be set to 60%.

[0101] The robust regression algorithm also needs to pre-set the maximum number of iterations (max_trails) of random sample selection, for example, to 50 times. Based on the above parameters, the configured robust regression algorithm is used to screen the feature sequence to obtain target information, which includes the target feature values ​​corresponding to the target grouping.

[0102] In this embodiment, a robust regression algorithm is used to calculate the self-discharge trend of the continuous characteristic parameters of a single battery cell over a period of time. The algorithm has strong robustness, is insensitive to abnormal values ​​in the data, and can obtain the target characteristic value.

[0103] In one embodiment of the present application, the target information further includes a linear regression slope; if the target characteristic value with the largest value in any target group is greater than or equal to a preset threshold, then it is determined that the battery is faulty, the method further includes:

[0104] After determining that the battery is faulty if the target characteristic value with the largest value in any target group is greater than or equal to a preset threshold, the method further includes:

[0105] According to the total number and the target residual, the slope threshold corresponding to the total number and the target residual is determined; if the linear regression slope is greater than the slope threshold, the fault level corresponding to the slope threshold is used as the fault level of the battery.

[0106] In this embodiment, a configured robust regression algorithm is used to screen the feature sequence to obtain target information, including target feature values ​​and linear regression slopes corresponding to the target groups.

[0107] When it is determined that the battery has a fault, the slope threshold corresponding to the target residual is determined according to the total number of the first eigenvalues ​​in the feature sequence and the target residual, see Table 2, if the total number N is N1, the target residual is residual_threshold1, and the slope threshold is throld_k1, further, the slope threshold is compared with the linear regression slope, if the linear regression slope is greater than the slope threshold, then the fault level corresponding to the slope threshold is used as the fault level of the battery, for example, the fault level corresponding to throld_k1: level 1 is used as the fault level of the battery.

[0108] The fault level of the second level fault is greater than the fault level of the first level fault and less than the fault level of the third level fault. It should be noted that the configuration of the above parameters can be set according to actual conditions.

[0109] In this embodiment, by setting relevant fault levels, faults of different levels can be classified, thereby providing more refined management and timely discovering faulty batteries.

[0110] In one embodiment of the present application, after determining the diagnosis result of the battery according to the voltage difference value of the target sampling point in at least one target group, the method further includes:

[0111] When the diagnosis result is a battery failure, the number of times the voltage of each battery cell at each target sampling point is the minimum voltage is obtained; if the number of times corresponding to the first battery cell is greater than the number threshold, it is determined that the first battery cell has a fault.

[0112] When it is determined that the diagnosis result is a battery failure, it is necessary to locate the problematic faulty battery cell and count the number of times the voltage of each battery cell is the minimum voltage at each target sampling point. If the number of times corresponding to the first battery cell is greater than the number threshold, it means that the battery cell frequently has a low voltage, and it is determined that the first battery cell is faulty.

[0113] In one embodiment of the present application, after determining that the first battery unit has a fault, the method further includes:

[0114] Obtaining the serial number of the first battery unit having a fault;

[0115] The serial number of the first battery unit is sent to a corresponding terminal.

[0116] In this embodiment, the number of the faulty first battery unit is obtained, and the cloud sends the number of the first battery unit to a corresponding terminal, such as a maintenance terminal or a user terminal, so that the battery can be replaced or repaired in time.

[0117] The following is an example of the vehicle battery fault diagnosis method provided in the embodiment of the present application. Figure 3 Another flow chart of an embodiment of the vehicle battery fault diagnosis method provided by the present application is shown as follows: Figure 3 As shown, the vehicle battery fault diagnosis method includes:

[0118] Step 301, operating condition data screening: screening out voltage monitoring data of single cells in dynamic or static operating conditions that meet the conditions.

[0119] In this embodiment, the execution subject is a cloud big data platform, and 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 cells). 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 data format conversion, to obtain a data set A, such as a daily data set A. Then, according to the vehicle status, speed, and current data, the data set A is screened to screen out the static working condition data set A1 (that is, the battery information of the vehicle obtained in the above text) and the dynamic working condition data set A2 (that is, the battery information of the vehicle obtained in the above text). Among them, the static working condition A1 refers to the data under the working condition that the vehicle is completely powered off and the static time is greater than a certain threshold, and the current after powering on is less than a certain threshold; the dynamic working condition is the data set after the static working condition data is removed from the data set A, and each data set includes the voltage of each single cell at multiple sampling points (that is, the battery information in the above text includes the voltage of each battery cell at multiple sampling points).

[0120] Step 302, data set binning: binning the data set.

[0121] In this embodiment, the multiple sampling points are divided according to the pre-acquired multiple sampling point intervals to obtain multiple sets, each set includes the voltage of each single battery cell falling in the corresponding sampling point interval (that is, the multiple sampling points are divided according to the pre-acquired multiple sampling point intervals above to obtain multiple groups, each group includes the voltage of each battery cell falling in the corresponding sampling point interval).

[0122] Specifically, the data set also includes: the SOC of the battery pack at multiple sampling points (that is, the battery information in the above text also includes the SOC of the battery at multiple sampling points), and the multiple sampling points are divided according to the pre-acquired multiple sampling point intervals to obtain multiple sets including:

[0123] According to the preset multiple SOC intervals, the sampling point interval corresponding to each SOC interval is determined; according to the sampling point interval corresponding to each SOC interval, the multiple sampling points are divided to obtain multiple sets.

[0124] In this embodiment, the SOC can be obtained by uploading data from the vehicle-side BMS or calculating based on a model. It is the real SOC. Different SOC intervals are set for ternary lithium batteries and lithium iron phosphate batteries. See Table 1 for multiple preset SOC intervals. The sampling point interval corresponding to each SOC interval is determined; according to the sampling point interval corresponding to each SOC interval, multiple sampling points are divided to obtain multiple sets.

[0125] Step 303, set data screening: screening out target sets that meet the conditions.

[0126] In this embodiment, the above-mentioned multiple sets are screened according to the operating conditions of the battery to screen out target sets that meet the conditions, and the sampling points corresponding to the sampling point interval corresponding to each target set are target sampling points (that is, the multiple groups are screened according to the operating conditions of the battery above to obtain at least one target group, and the sampling points in the sampling point interval corresponding to each target group are target sampling points).

[0127] Specifically, different screening conditions are pre-set according to different working conditions. For dynamic working conditions, the following is executed for each set: if the number of sampling points in the sampling point interval corresponding to the set is greater than or equal to a first preset number, the set is determined as a target set; for static working conditions: the following is executed for each set: if the number of sampling points in the sampling point interval corresponding to the set is greater than or equal to a second preset number, the set is determined as a target set, and the second preset number is less than the first preset number.

[0128] Alternatively, for dynamic working conditions: if the number of data frames of the pressure difference value of the sampling point corresponding to the set is greater than or equal to 50 frames, and one frame can correspond to one sampling point, then the set is determined as the target set, and the pressure difference value is the difference between the maximum voltage and the minimum voltage of multiple single cells at the sampling point; for static working conditions: if the number of data frames of the pressure difference value of the sampling point corresponding to the set is greater than or equal to 3 frames, then the set is determined as the target set.

[0129] Step 304, feature calculation: calculate the individual pressure difference of the target sampling point in each target set, and calculate the first feature value based on the individual pressure difference using a box plot.

[0130] In this embodiment, the single cell voltage difference of the target sampling point in each target set is calculated (ie, the voltage difference value of the target sampling point in the target group mentioned above, the voltage difference value is the difference between the maximum voltage and the minimum voltage of multiple battery cells at the target sampling point).

[0131] The monomer pressure difference is calculated using formula (2), which is as follows:

[0132] ΔU(t)=U max (t)-U min (t) (2)

[0133] Among them, △U(t) is the single cell pressure difference at the target sampling point t, U max (t) is the maximum voltage of a single core at the target sampling point t, U min (t) is the minimum voltage of a single cell at the target sampling point t.

[0134] The corresponding features are calculated based on the single pressure difference using a box plot. Specifically, according to the pressure difference value of each sampling point in the target set, the first eigenvalue corresponding to the target set is determined. The first eigenvalue Bl is the lower edge eigenvalue, which is calculated based on the 75th quantile and the 25th quantile. The 75th quantile and the 25th quantile are obtained using a box plot. The first eigenvalue is calculated based on formula (1) above.

[0135] Step 305, robust regression algorithm call: the robust regression algorithm is used to calculate the regression slope and the interior point sequence for the first eigenvalue within a past period of time.

[0136] In this embodiment, historical target sets within multiple historical time periods are screened according to the SOC interval corresponding to the target set to obtain multiple historical target sets within the historical time period, and the SOC interval corresponding to each historical target set is the same as the SOC interval corresponding to the target set; first characteristic values ​​corresponding to multiple historical target sets are obtained; the first characteristic values ​​corresponding to multiple historical target sets and the first characteristic value corresponding to the target set are screened to obtain target characteristic values ​​corresponding to the target set (that is, according to the SOC interval corresponding to the target grouping in the above, historical target groups within multiple historical time periods are screened to obtain multiple historical target groups, and the SOC interval corresponding to each historical target group is the same as the SOC interval corresponding to the target group; the first characteristic values ​​corresponding to multiple historical target groups are obtained; the first characteristic values ​​corresponding to multiple historical target groups and the first characteristic value corresponding to the target group are screened to obtain target characteristic values ​​corresponding to the target group).

[0137] Specifically, the first eigenvalues ​​corresponding to multiple historical target sets and the sampling times of the sampling points corresponding to the first eigenvalues ​​corresponding to the target set are obtained; the first eigenvalues ​​corresponding to multiple historical target sets and the first eigenvalues ​​corresponding to the target set are sorted according to the sequence of sampling times to obtain a feature sequence; the target residual of the robust regression algorithm is determined according to the total number of first eigenvalues ​​in the feature sequence; the robust regression algorithm is configured using the target residual; the feature sequence is screened using the configured robust regression algorithm to obtain target information, wherein the target information includes the target eigenvalues ​​corresponding to the target set.

[0138] In the above steps, the above eigenvalues ​​are sorted according to the sampling time to obtain a feature sequence sorted by time. Specifically, the first eigenvalues ​​corresponding to multiple historical target sets and the first eigenvalues ​​corresponding to the target set are sorted according to the order of sampling time to obtain a feature sequence {Bli},i=1.2....N. The configured robust regression algorithm (see the aforementioned configuration method for the configuration method) is used to screen the feature sequence {Bli},i=1.2....N to obtain target information. The target information includes an inlier sequence {Bli_inlieri} corresponding to the target set, which includes the target eigenvalues. The target information also includes a linear regression slope.

[0139] Step 306, self-discharge abnormality identification: abnormality identification and warning are performed according to the interior point sequence, linear regression slope, and warning threshold.

[0140] Different parameter settings are performed for different risk levels, as shown in Table 2.

[0141] The largest target eigenvalue in the interior point sequence is compared with the safety threshold. If the largest target eigenvalue in the interior point sequence is less than the safety threshold, it means that there is no self-discharge abnormality, and no warning is triggered; if the largest target eigenvalue in the interior point sequence is greater than or equal to the safety threshold, it means that there is a self-discharge abnormality (that is, if the target eigenvalue with the largest value in any target group is greater than or equal to the preset threshold in the above text, it is determined that the battery is faulty), then a warning is triggered, and the warning level of the battery pack is determined according to the target residual of the robust regression and the total number of the first eigenvalues ​​in the feature sequence and the linear regression slope. Specifically, the slope threshold corresponding to the total number and the target residual is determined according to the total number and the target residual; if the linear regression slope is greater than the slope threshold, the warning level corresponding to the slope threshold is used as the warning level of the battery (that is, according to the total number and the target residual, the slope threshold corresponding to the total number and the target residual is determined according to the above text; if the linear regression slope is greater than the slope threshold, the fault level corresponding to the slope threshold is used as the fault level of the battery).

[0142] Step 307, fault location: locating the abnormal single cell.

[0143] In this embodiment, for the vehicle that triggers the early warning, that is, the vehicle including the battery pack that triggers the early warning as mentioned above, the number of times the voltage of each single battery at each target sampling point is the minimum voltage is obtained; if the number of times corresponding to the first single battery is greater than the number threshold, it means that the battery frequently has a small voltage value, and it is determined that the first single battery has a fault (that is, in the above text, when the diagnosis result is a battery fault, the number of times the voltage of each battery unit at each target sampling point is the minimum voltage is obtained; if the number of times corresponding to the first battery unit is greater than the number threshold, it is determined that the first battery unit has a fault).

[0144] The advantage of the big data of the cloud monitoring platform of this application is that the key influencing parameters are designed by binning, and then the characteristic parameters of the battery cell are extracted by the statistical box plot method. The machine learning robust regression algorithm is used to calculate the self-discharge trend of the continuous characteristic parameters of a single battery cell over a period of time, and the model hyperparameters are graded according to the risk level to achieve refined classification of risks and early detection of risks. The vehicle monitoring data of the cloud monitoring platform is used, and cloud service calculation and analysis are performed in a daily batch processing manner. Compatibility design is carried out for both static and dynamic working conditions. Compared with the strict requirements of traditional solutions for working conditions, a wider range of calculation coverage is achieved and the risk of underreporting is reduced. The machine learning robust regression algorithm is used, which has strong robustness, is insensitive to abnormal disturbances of the data, and can find abnormal points, that is, target characteristic values. By setting relevant parameters, risks of different levels can be graded and classified for monitoring, thereby providing more refined and effective risk management and achieving early detection of risks.

[0145] Figure 4 FIG. 1 shows a structural diagram of a vehicle battery fault diagnosis device provided by an embodiment of the present application. Figure 4 As shown, the vehicle battery fault diagnosis device 400 includes:

[0146] An acquisition module 401 is used to acquire battery information of a vehicle battery, where the battery includes a plurality of battery cells, and the battery information includes the voltage of each battery cell at a plurality of sampling points;

[0147] The processing module 402 is used to divide the multiple sampling points according to the multiple sampling point intervals obtained in advance to obtain multiple groups, each group including the voltage of each battery cell falling in the corresponding sampling point interval;

[0148] The processing module 402 is further used to screen the multiple groups according to the working condition of the battery to obtain at least one target group, and the sampling points in the sampling point interval corresponding to each target group are target sampling points;

[0149] The diagnosis module 403 is used to determine the diagnosis result of the battery according to the voltage difference value of the target sampling point in at least one target group, where the voltage difference value is the difference between the maximum voltage and the minimum voltage of multiple battery cells at the target sampling point.

[0150] In one embodiment of the present application, the processing module 402 is further used to determine the sampling point interval corresponding to each SOC interval according to the preset multiple SOC intervals; and divide the multiple sampling points according to the sampling point interval corresponding to each SOC interval to obtain multiple groups.

[0151] In one embodiment of the present application, the processing module 402 is also used to, when the operating condition of the battery is a dynamic condition, execute for each group: if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to a first preset number, then the group is determined as a target group; when the operating condition of the battery is a static condition, execute for each group: if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to a second preset number, then the group is determined as a target group, and the second preset number is less than the first preset number.

[0152] In one embodiment of the present application, the diagnostic module 403 is also used to perform the following processing on each target group: determine the first characteristic value corresponding to the target group according to the pressure difference value of each target sampling point in the target group; filter the historical target groups in multiple historical time periods according to the SOC interval corresponding to the target group to obtain multiple historical target groups, and the SOC interval corresponding to each historical target group is the same as the SOC interval corresponding to the target group; obtain the first characteristic values ​​corresponding to the multiple historical target groups; filter the first characteristic values ​​corresponding to the multiple historical target groups and the first characteristic value corresponding to the target group to obtain the target characteristic value corresponding to the target group; if the target characteristic value with the largest value in any target group is greater than or equal to the preset threshold, it is determined that the battery is faulty.

[0153] In one embodiment of the present application, the diagnostic module 403 is also used to obtain the sampling time of the sampling points corresponding to the first eigenvalues ​​corresponding to multiple historical target groups and the first eigenvalues ​​corresponding to the target group; sort the first eigenvalues ​​corresponding to the multiple historical target groups and the first eigenvalues ​​corresponding to the target group according to the sequence of sampling time to obtain a feature sequence; determine the target residual of the robust regression algorithm according to the total number of first eigenvalues ​​in the feature sequence; configure the robust regression algorithm using the target residual; use the configured robust regression algorithm to screen the feature sequence to obtain target information, the target information including the target eigenvalues ​​corresponding to the target group.

[0154] In one embodiment of the present application, the diagnostic module 403 is also used to determine the slope threshold corresponding to the total number and the target residual based on the total number and the target residual; if the linear regression slope is greater than the slope threshold, the fault level corresponding to the slope threshold is used as the fault level of the battery.

[0155] In one embodiment of the present application, the diagnostic module 403 is also used to obtain the number of times that the voltage of each battery cell is the minimum voltage at each target sampling point when the diagnosis result is a battery failure; if the number of times corresponding to the first battery cell is greater than the number threshold, it is determined that the first battery cell has a fault.

[0156] In one embodiment of the present application, the vehicle battery fault diagnosis device further includes a transceiver module;

[0157] The acquisition module 401 is further used to acquire the serial number of the first battery unit having a fault;

[0158] The transceiver module is used to send the serial number of the first battery unit to the corresponding terminal.

[0159] The vehicle battery fault diagnosis device 400 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.

[0160] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0161] The electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0162] Specifically, the processor 501 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.

[0163] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 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, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0164] 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.

[0165] The processor 501 implements any one of the information auditing methods in the above embodiments by reading and executing computer program instructions stored in the memory 502 .

[0166] In one example, the electronic device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0167] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0168] Bus 510 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 510 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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: Acquire battery information of a vehicle battery, wherein the battery includes a plurality of battery cells, and the battery information includes a voltage of each of the battery cells at a plurality of sampling points; Divide the plurality of sampling points according to the plurality of pre-acquired sampling point intervals to obtain a plurality of groups, each of the groups including the voltage of each battery cell falling within the corresponding sampling point interval; Screening the plurality of groups according to the working condition of the battery to obtain at least one target group, wherein the sampling points in the sampling point interval corresponding to each target group are target sampling points; The diagnosis result of the battery is determined according to the voltage difference value of the target sampling point in the at least one target group, where the voltage difference value is the difference between the maximum voltage and the minimum voltage of the plurality of battery cells at the target sampling point.

2. The vehicle battery fault diagnosis method according to claim 1, characterized in that: The battery information also includes the state of charge (SOC) of the battery at the plurality of sampling points; The step of dividing the plurality of sampling points according to the plurality of pre-acquired sampling point intervals to obtain a plurality of groups includes: According to a plurality of preset SOC intervals, determining a sampling point interval corresponding to each of the SOC intervals; According to the sampling point interval corresponding to each of the SOC intervals, the plurality of sampling points are divided to obtain a plurality of groups.

3. The vehicle battery fault diagnosis method according to claim 1, characterized in that: The screening of the plurality of groups according to the working condition of the battery to obtain at least one target group includes: In the case where the operating condition of the battery is a dynamic operating condition, executing for each of the groups: if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to a first preset number, determining the group as the target group; When the operating condition of the battery is a static condition, for each of the groups, the following is performed: if the number of sampling points in the sampling point interval corresponding to the group is greater than or equal to a second preset number, the group is determined as the target group, and the second preset number is less than the first preset number.

4. The vehicle battery fault diagnosis method according to claim 1, characterized in that: The step of determining the diagnosis result of the battery according to the voltage difference value of the target sampling point in the at least one target group includes: Each of the target groups is processed as follows: according to the pressure difference value of each of the target sampling points in the target group, a first characteristic value corresponding to the target group is determined; according to the SOC interval corresponding to the target group, historical target groups in multiple historical time periods are screened to obtain multiple historical target groups, and the SOC interval corresponding to each of the historical target groups is the same as the SOC interval corresponding to the target group; first characteristic values ​​corresponding to the multiple historical target groups are obtained; the first characteristic values ​​corresponding to the multiple historical target groups and the first characteristic value corresponding to the target group are screened to obtain a target characteristic value corresponding to the target group; If the target characteristic value with the largest value in any of the target groups is greater than or equal to a preset threshold, it is determined that the battery is faulty.

5. The vehicle battery fault diagnosis method according to claim 4, characterized in that: The first characteristic values ​​corresponding to the plurality of historical target groups and the first characteristic values ​​corresponding to the target group are screened to obtain the target characteristic value corresponding to the target group, including: Obtaining the sampling time of the sampling points corresponding to the first characteristic values ​​corresponding to the plurality of historical target groups and the first characteristic values ​​corresponding to the target group; According to the sequence of the sampling times, the first characteristic values ​​corresponding to the plurality of historical target groups and the first characteristic values ​​corresponding to the target group are sorted to obtain a characteristic sequence; Determining a target residual of a robust regression algorithm based on the total number of first eigenvalues ​​in the characteristic sequence; configuring a robust regression algorithm using the target residual; The configured robust regression algorithm is used to screen the feature sequence to obtain target information, where the target information includes target feature values ​​corresponding to the target group.

6. The vehicle battery fault diagnosis method according to claim 5, characterized in that: The target information also includes a linear regression slope; After determining that the battery is faulty if the target characteristic value with the largest value in any of the target groups is greater than or equal to a preset threshold, the method further includes: Determine, according to the total number and the target residual, a slope threshold corresponding to the total number and the target residual; If the linear regression slope is greater than the slope threshold, the fault level corresponding to the slope threshold is used as the fault level of the battery.

7. The vehicle battery fault diagnosis method according to any one of claims 1 to 6, characterized in that: After determining the diagnosis result of the battery according to the voltage difference value of the target sampling point in the at least one target group, the method further includes: When the diagnosis result is a battery failure, obtaining the number of times the voltage of each battery cell at each target sampling point is the minimum voltage; If the number of times corresponding to the first battery unit is greater than the number threshold, it is determined that the first battery unit has a fault.

8. The vehicle battery fault diagnosis method according to claim 7, characterized in that: After determining that the first battery unit has a fault, the method further includes: Obtaining the serial number of the first battery unit having a fault; The serial number of the first battery unit is sent to a corresponding terminal.

9. A vehicle battery fault diagnosis device, characterized in that: The device comprises: An acquisition module, used for acquiring battery information of a vehicle battery, wherein the battery includes a plurality of battery cells, and the battery information includes a voltage of each of the battery cells at a plurality of sampling points; A processing module, used for dividing the plurality of sampling points according to the plurality of pre-acquired sampling point intervals to obtain a plurality of groups, each of the groups including the voltage of each battery cell falling within the corresponding sampling point interval; The processing module is further used to screen the plurality of groups according to the working condition of the battery to obtain at least one target group, wherein the sampling points in the sampling point interval corresponding to each target group are target sampling points; A diagnosis module is used to determine a diagnosis result of the battery according to a voltage difference value of the target sampling point in the at least one target group, wherein the voltage difference value is a difference between a maximum voltage and a minimum voltage of a plurality of the battery cells at the target sampling point.

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