Electric vehicle battery fault early warning method and device, storage medium and program product

Abstract

The invention relates to an electric vehicle battery fault early warning method and device, a storage medium and a program product. The method comprises the following steps: acquiring target index data of a target electric vehicle under a key battery index in a current time period; wherein the key battery indexes are indexes related to vehicle battery faults and screened out from all the candidate battery indexes according to a cross entropy loss function and an original data set; each piece of sample data in the original data set comprises sample index data of the sample electric vehicle under each candidate battery index and a sample category label of the sample electric vehicle; determining a battery aging factor of the target electric vehicle according to the initial battery capacity and the current battery capacity of the target electric vehicle; and based on a Bayesian network model, according to the target index data and the battery aging factor, carrying out vehicle battery fault early warning on the target electric vehicle. By adopting the method, accurate early warning of the vehicle battery fault can be realized.

Description

Technical Field

[0001] The present application relates to the field of vehicle diagnosis technology, and in particular to an electric vehicle battery fault early warning method, device, storage medium and program product. Background Art

[0002] As new energy vehicles are becoming more and more popular, promoting the development of new energy vehicles is also an important means to promote "carbon neutrality" and "carbon peak". Lithium-ion batteries are widely used in various fields such as new energy vehicles due to their high energy density and long life. However, lithium-ion batteries also have some potential safety risks, such as internal short circuit, thermal runaway, and lithium precipitation.

[0003] In the existing technology, most lithium-ion battery safety warning technologies collect battery voltage, current and other data and use machine learning algorithms to issue safety warnings for the battery. However, this method is not comprehensive, such as not considering factors such as vehicle historical behavior data and battery aging, and therefore cannot achieve accurate prediction of faults. Summary of the invention

[0004] Based on this, it is necessary to provide an electric vehicle battery failure warning method, device, storage medium and program product to address the above technical problems, which can achieve accurate warning of vehicle battery failure.

[0005] In a first aspect, the present application provides an electric vehicle battery failure early warning method, the method comprising:

[0006] Obtain target indicator data of the target electric vehicle under key battery indicators in the current period; wherein the key battery indicator is an indicator related to vehicle battery failure screened from each candidate battery indicator according to the cross entropy loss function and the original data set; each sample data in the original data set includes sample indicator data of the sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle;

[0007] Determining a battery aging factor of the target electric vehicle based on the initial battery capacity and the current battery capacity of the target electric vehicle;

[0008] Based on the Bayesian network model, vehicle battery failure warning is issued for the target electric vehicle according to the target indicator data and battery aging factor.

[0009] In one embodiment, the key battery indicator is determined by:

[0010] According to the cross entropy loss function and the original data set, the correlation between each candidate battery indicator and the vehicle battery failure is determined; according to the correlation between each candidate battery indicator and the vehicle battery failure, the key battery indicators are screened out from the candidate battery indicators.

[0011] In one embodiment, determining the correlation between each candidate battery indicator and the vehicle battery failure according to the cross entropy loss function and the original data set includes:

[0012] The original data set is divided into multiple original sample subsets with the same number of samples; each original sample subset is processed using the cross entropy loss function to obtain an initial prediction accuracy; for each candidate battery indicator, the sample indicator data corresponding to the candidate battery indicator is removed from the sample data of each original sample subset to obtain each new sample subset corresponding to the candidate battery indicator; based on the cross entropy loss function, the initial prediction accuracy and each new sample subset, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0013] In one embodiment, a cross entropy loss function is used to process each original sample subset to obtain an initial prediction accuracy, including:

[0014] For each original sample subset, the cross entropy loss function is used to process the original sample subset to obtain the first prediction accuracy of the original sample subset; the average of the first prediction accuracy of each original sample subset is used as the initial prediction accuracy.

[0015] In one embodiment, determining the correlation between the candidate battery indicator and the vehicle battery failure according to the cross entropy loss function, the initial prediction accuracy and each new sample subset includes:

[0016] For each new sample subset, the cross entropy loss function is used to process the new sample subset to obtain the second prediction accuracy of the new sample subset, and the difference between the second prediction accuracy of the new sample subset and the initial prediction accuracy is used as the accuracy deviation of the original sample subset corresponding to the new sample subset for the candidate battery indicator; according to the accuracy deviation of the original sample subset corresponding to each new sample subset for the candidate battery indicator, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0017] In one embodiment, based on the Bayesian network model, according to the target indicator data and the battery aging factor, a vehicle battery failure warning is performed on the target electric vehicle, including:

[0018] The target indicator data and battery aging factor are input into the Bayesian network model to obtain the target failure probability of the target electric vehicle; based on the corresponding relationship between the failure probability and the failure level, the target failure level corresponding to the target failure probability is determined; according to the target failure level, a vehicle battery failure warning is issued for the target electric vehicle.

[0019] In a second aspect, the present application also provides an electric vehicle battery failure warning device, the device comprising:

[0020] An acquisition module is used to obtain target indicator data of a target electric vehicle under a key battery indicator in a current period; wherein the key battery indicator is an indicator related to vehicle battery failure selected from each candidate battery indicator according to a cross entropy loss function and an original data set; each sample data in the original data set includes sample indicator data of a sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle;

[0021] A factor determination module, used to determine a battery aging factor of a target electric vehicle according to an initial battery capacity and a current battery capacity of the target electric vehicle;

[0022] The early warning module is used to provide vehicle battery failure early warning for the target electric vehicle based on the Bayesian network model, according to the target indicator data and the battery aging factor.

[0023] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0024] Obtain target indicator data of the target electric vehicle under key battery indicators in the current period; wherein the key battery indicator is an indicator related to vehicle battery failure screened from each candidate battery indicator according to the cross entropy loss function and the original data set; each sample data in the original data set includes sample indicator data of the sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle;

[0025] Determining a battery aging factor of the target electric vehicle based on the initial battery capacity and the current battery capacity of the target electric vehicle;

[0026] Based on the Bayesian network model, vehicle battery failure warning is issued for the target electric vehicle according to the target indicator data and battery aging factor.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0028] Obtain target indicator data of the target electric vehicle under key battery indicators in the current period; wherein the key battery indicator is an indicator related to vehicle battery failure screened from each candidate battery indicator according to the cross entropy loss function and the original data set; each sample data in the original data set includes sample indicator data of the sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle;

[0029] Determining a battery aging factor of the target electric vehicle based on the initial battery capacity and the current battery capacity of the target electric vehicle;

[0030] Based on the Bayesian network model, vehicle battery failure warning is issued for the target electric vehicle according to the target indicator data and battery aging factor.

[0031] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0032] Obtain target indicator data of the target electric vehicle under key battery indicators in the current period; wherein the key battery indicator is an indicator related to vehicle battery failure screened from each candidate battery indicator according to the cross entropy loss function and the original data set; each sample data in the original data set includes sample indicator data of the sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle;

[0033] Determining a battery aging factor of the target electric vehicle based on the initial battery capacity and the current battery capacity of the target electric vehicle;

[0034] Based on the Bayesian network model, vehicle battery failure warning is issued for the target electric vehicle according to the target indicator data and battery aging factor.

[0035] The above-mentioned electric vehicle battery failure warning method, device, storage medium and program product obtain the target indicator data of the target electric vehicle under the key battery indicators in the current period, and determine the battery aging factor of the target electric vehicle according to the initial battery capacity and current battery capacity of the target electric vehicle; wherein the key battery indicator is an indicator related to vehicle battery failure selected from each candidate battery indicator according to the cross entropy loss function and the original data set; further, based on the Bayesian network model, the target indicator data and the battery aging factor, the target electric vehicle is given a vehicle battery failure warning. This scheme provides a basis for selecting key battery indicators from each candidate battery indicator by introducing the cross entropy loss function; further, by combining the target indicator data and the battery aging factor, a comprehensive consideration of the vehicle battery condition is achieved, and ultimately an accurate warning of the vehicle battery failure is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] FIG1 is an application environment diagram of an electric vehicle battery failure warning method provided in an embodiment of the present application;

[0038] FIG2 is a schematic diagram of a process flow of an electric vehicle battery failure warning provided in an embodiment of the present application;

[0039] FIG3 is a schematic diagram of a process for determining key battery indicators provided in an embodiment of the present application;

[0040] FIG4 is a schematic diagram of a process for determining relevance provided in an embodiment of the present application;

[0041] FIG5 is a schematic diagram of a flow chart of another electric vehicle battery failure warning method provided in an embodiment of the present application;

[0042] FIG6 is a structural block diagram of an electric vehicle battery failure warning device provided in an embodiment of the present application;

[0043] FIG. 7 is an internal structure diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] The electric vehicle battery failure warning method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 is installed on the target electric vehicle to monitor various indicators of the target electric vehicle, and send the monitored indicator data to the server 104; then, the server 104 can perform vehicle battery failure warning on the target electric vehicle based on the battery aging factor and indicator data of the target electric vehicle. Among them, the terminal 102 can be but is not limited to various monitoring devices and sensors. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0046] In an exemplary embodiment, as shown in FIG2 , a method for early warning of battery failure of an electric vehicle is provided. The method is described by taking the application of the method to the server 104 in FIG1 as an example, and the method may include the following steps:

[0047] S201, obtaining target indicator data of a target electric vehicle under key battery indicators in a current period.

[0048] Among them, the key battery indicators can be selected from the candidate battery indicators and the indicators related to vehicle battery failure according to the cross entropy loss function and the original data set; each sample data in the original data set includes the sample indicator data of the sample electric vehicle under each candidate battery indicator and the sample category label of the sample electric vehicle. Optionally, the current period can represent the latest charge-discharge period.

[0049] For example, key battery indicators may include battery indicators, cell indicators and vehicle indicators; wherein the battery in the target electric vehicle includes multiple cells, and the battery indicators may include discharge capacity, maximum / minimum current, slow charge times, fast charge times, low temperature high current charge times, high temperature high current charge times, slow charge ampere-hours, fast charge ampere-hours, charge and discharge period greater than 20% / 40% (SOC (State of Charge and Discharge Period) The number of times the battery's state of charge (SOC) changes within a range greater than 20% / 40%, the maximum / minimum voltage at the start / end of charging, the number of times the battery is charged within different SOC ranges during the charge-discharge period, the number of times the SOC is terminated (the number of times the battery is charged within different SOC ranges, the number of times the average charging current falls within different current ranges, the number of times the maximum charging current falls within different current ranges, the number of times the maximum temperature of the charging process falls within different temperature ranges, the number of times the maximum temperature difference of the charging process falls within different temperature ranges, the number of times the minimum temperature of the charging process falls within different temperature ranges, the number of times the maximum charging current and the corresponding maximum temperature of the maximum charging current fall within different current and temperature range combinations, the number of times the maximum charging current and the corresponding minimum temperature of the maximum charging current fall within different current and temperature range combinations, the number of times the maximum single cell voltage falls within different voltage ranges at the end of charging, the number of times the voltage difference between the maximum single cell voltage and the minimum single cell voltage falls within different voltage ranges at the end of charging, and the average value of the battery when charging passes through different SOC ranges (10% range). The battery cell indicators may include the number of charging times when the charging current and temperature combinations fall in different charging current ranges and temperature ranges; the battery cell indicators may include the number of charging times when the charging cut-off voltage of the single battery cell falls in different voltage ranges, the number of charging times when the pressure difference at the charging cut-off of the single battery cell (single battery cell voltage-average voltage) falls in different voltage ranges, the change in the difference between the single battery voltage and the average voltage in the whole life cycle of the battery in different SOC ranges (initial pressure difference-current pressure difference), the difference between the single battery voltage and the average voltage in different voltage ranges in the current period, the difference between the capacity (dQ / dV) of the single battery in different voltage ranges and the average battery capacity in the current period, the change in the difference between the single battery voltage and the average voltage in different SOC ranges in the whole life cycle of the battery (initial pressure difference-current pressure difference), the difference between the single battery voltage and the average voltage in different voltage ranges in the current period, and the difference between the capacity (dQ / dV) of the single battery in different voltage ranges and the average battery capacity in the current period; the vehicle indicators may include the total vehicle mileage, the average daily mileage of the vehicle, the presence or absence of collision, the maximum continuous running time of the vehicle, and the average running temperature of the vehicle.

[0050] Exemplarily, terminal 102 monitors the indicators of the target electric vehicle in real time, and sends the monitored indicator data to server 104 through the communication module; then, server 104 can receive the monitoring data of the target electric vehicle, and can directly obtain the target indicator data of the target electric vehicle under the key battery indicators in the current time period.

[0051] S202 : Determine a battery aging factor of the target electric vehicle according to the initial battery capacity and the current battery capacity of the target electric vehicle.

[0052] Among them, the initial battery capacity can represent the standard battery capacity of the target electric vehicle when it leaves the factory, that is, the rated capacity of the battery in a brand new state; the current battery capacity can represent the battery capacity of the target electric vehicle in the current period; the battery aging factor can represent the parameters of the degree of battery aging during use.

[0053] For example, the battery aging factor λ of the target electric vehicle may be calculated according to the initial battery capacity c0 and the current battery capacity c1 of the target electric vehicle, which may be specifically expressed as:

[0054]

[0055] S203, based on the Bayesian network model, according to the target indicator data and the battery aging factor, a vehicle battery failure warning is issued to the target electric vehicle.

[0056] Among them, the Bayesian network model is a model that evaluates vehicle battery failure based on the Bayesian total probability formula according to target indicator data and battery aging factors; fault warning can include fault level, expected fault time and fault-related location, etc.

[0057] For example, the battery aging factor λ can be integrated into the Bayesian total probability formula of the key battery indicator for failure, which can be expressed as:

[0058]

[0059] Where n can represent the number of key battery indicators; x i It can represent the i-th key battery indicator; Y can represent the vehicle label corresponding to the i-th key battery indicator, including normal and faulty categories; is the prior probability of Y, Is considered The prior probability of Y.

[0060] The above-mentioned electric vehicle battery failure warning method obtains the target indicator data of the target electric vehicle under the key battery indicators in the current period, and determines the battery aging factor of the target electric vehicle according to the initial battery capacity and the current battery capacity of the target electric vehicle; wherein the key battery indicator is an indicator related to vehicle battery failure selected from each candidate battery indicator according to the cross entropy loss function and the original data set; further, based on the Bayesian network model, the target indicator data and the battery aging factor, the target electric vehicle is given a vehicle battery failure warning. This scheme provides a basis for selecting key battery indicators from each candidate battery indicator by introducing the cross entropy loss function; furthermore, by combining the target indicator data and the battery aging factor, a comprehensive consideration of the vehicle battery condition is achieved, and finally an accurate warning of the vehicle battery failure is achieved.

[0061] Based on the above embodiment, the present application embodiment explains the above embodiment S201 in detail. Specifically, the process of determining key battery indicators in the present application embodiment, as shown in FIG3, specifically includes the following steps:

[0062] S301, determining the correlation between each candidate battery indicator and the vehicle battery failure according to the cross entropy loss function and the original data set.

[0063] It should be noted that the original data set can be obtained by screening the total data of each electric vehicle throughout its life cycle; for example, the SOC variation range within each charge-discharge period can be judged, and the charge-discharge periods in which the SOC variation range is less than 20% can be eliminated to obtain the original data set.

[0064] Exemplarily, the original data set can be input into a cross-entropy loss function, which analyzes each candidate battery indicator in the original data set to determine the cross-entropy loss corresponding to each candidate battery indicator. Furthermore, based on the cross-entropy loss corresponding to each candidate battery indicator, the correlation between each candidate battery indicator and the vehicle battery failure can be determined.

[0065] S302 , selecting key battery indicators from the candidate battery indicators according to the correlation between the candidate battery indicators and the vehicle battery failure.

[0066] For example, the correlation between each candidate battery indicator and the vehicle battery fault can be ranked, and the indicator with high correlation can be selected as the key battery indicator. For example, each candidate battery indicator can be screened according to a preset ratio, such as 60% of the candidate battery indicators can be determined as key battery indicators; indicators with correlation exceeding a relevant threshold can also be determined as key battery indicators. The embodiment of the present application does not specifically limit the method of screening key battery indicators.

[0067] In an embodiment of the present application, by introducing the cross entropy loss function, a tool is provided for determining the correlation between each candidate battery indicator and the vehicle battery failure, thereby laying the foundation for accurately determining the key battery indicators.

[0068] Based on the above embodiment, the embodiment of the present application explains the above embodiment S301 in detail. Specifically, the embodiment of the present application involves a process of determining the correlation between each candidate battery indicator and the vehicle battery fault, as shown in FIG4 , which specifically includes the following steps:

[0069] S401, dividing the original data set into a plurality of original sample subsets with the same number of samples.

[0070] Exemplarily, the original data set may be divided into M original sample subsets with the same number of samples; wherein each sample in each original sample subset includes all candidate battery indicators and vehicle labels.

[0071] S402, using a cross entropy loss function to process each original sample subset to obtain an initial prediction accuracy.

[0072] Among them, the initial prediction accuracy can represent the loss value of fault prediction based on all candidate battery indicators.

[0073] One feasible method is to process each original sample subset using a cross entropy loss function to obtain a first prediction accuracy of the original sample subset; and use the average of the first prediction accuracies of each original sample subset as the initial prediction accuracy.

[0074] Exemplarily, for each original sample subset, the original sample subset can be input into the cross entropy loss function, and the cross entropy loss function performs loss calculation on the original sample subset to obtain the first prediction accuracy of the original sample subset. Then, based on the first prediction accuracy of each original sample subset, the mean calculation is performed, and the result of the mean calculation is determined as the initial prediction accuracy.

[0075] Another possible implementation method is to directly input each original sample subset into the cross entropy model, which analyzes and processes each original sample subset, such as averaging, removing the maximum value, and removing the minimum value, and finally obtains the initial prediction accuracy.

[0076] S403 , for each candidate battery indicator, remove the sample indicator data corresponding to the candidate battery indicator from the sample data of each original sample subset to obtain each new sample subset corresponding to the candidate battery indicator.

[0077] Exemplarily, the candidate battery index includes three indexes, namely z1, z2 and z3; the original sample subset includes three subsets, namely T1={z1, z2, z3}, T2={z1, z2, z3} and T3={z1, z2, z3}; further, for the candidate battery index z1, the sample index data corresponding to the candidate battery index z1 is removed from the sample data of each original sample subset (T1, T2 and T3), and each new sample subset corresponding to the candidate battery index z1 is obtained, namely T 1_1 ={z2,z3}、T 1_2 ={z2,z3} and T 1_3 ={z2, z3}; for the candidate battery index z2, the sample index data corresponding to the candidate battery index z2 is removed from the sample data of each original sample subset (T1, T2 and T3), and each new sample subset corresponding to the candidate battery index z2 is obtained, that is, T 2_1 ={z1,z3}、T 2_2 ={z1,z3} and T 2_3 ={z1, z3}; for the candidate battery index z3, the sample index data corresponding to the candidate battery index z3 is removed from the sample data of each original sample subset (T1, T2 and T3), and each new sample subset corresponding to the candidate battery index z3 is obtained, that is, T 3_1 ={z1,z2}、T 3_2 ={z1,z2} and T 3_3 ={z1,z2}.

[0078] S404, determining the correlation between the candidate battery indicator and the vehicle battery failure according to the cross entropy loss function, the initial prediction accuracy and each new sample subset.

[0079] An implementation method is to use a cross entropy loss function to process each new sample subset to obtain a second prediction accuracy of the new sample subset, and use the difference between the second prediction accuracy of the new sample subset and the initial prediction accuracy as the accuracy deviation of the original sample subset corresponding to the new sample subset for the candidate battery indicator; determine the correlation between the candidate battery indicator and the vehicle battery fault based on the accuracy deviation of the original sample subset corresponding to each new sample subset for the candidate battery indicator.

[0080] As in the above example, based on the candidate battery indicator z1, each new sample subset corresponding to the candidate battery indicator z1 is determined, that is, T 1_1 ={z2,z3}、T 1_2 ={z2,z3} and T 1_3 ={z2, z3}; further, T 1_1 ={z2,z3}、T 1_2 ={z2,z3} and T 1_3= {z2, z3} each new sample subset is input into the cross entropy loss function, and the cross entropy loss function is used to calculate the new sample subset (T 1_1 , T 1_2 and T 1_3 ) to calculate the loss and obtain each new sample subset (T 1_1 , T 1_2 and T 1_3 ) of the second prediction accuracy; further, for each new sample subset (T 1_1 , T 1_2 and T 1_3 ), the new sample subset T 1_i The second prediction accuracy of (i=1, 2, 3) is calculated by difference with the initial prediction accuracy, and the new sample subset T 1_i The difference operation result is determined as the new sample subset T 1_i The corresponding original sample subset T i The accuracy deviation P1={w 1_1 、w 1_2 and w 1_3}.

[0081] Based on the candidate battery index z2, determine each new sample subset corresponding to the candidate battery index z2, that is, T 2_1 ={z1,z3}、T 2_2 ={z1,z3} and T 2_3 ={z1,z3}; further, T 2_1 ={z1,z3}、T 2_2 ={z1,z3} and T 2_3 = {z1, z3} each new sample subset is input into the cross entropy loss function, and the cross entropy loss function is used to calculate the new sample subset (T 2_1 , T 2_2 and T 2_3 ) to calculate the loss and obtain each new sample subset (T 2_1 , T 2_2 and T 2_3 ) of the second prediction accuracy; further, for each new sample subset (T 2_1 , T 2_2 and T 2_3 ), the new sample subset T 2_i The second prediction accuracy of (i=1, 2, 3) is calculated by difference with the initial prediction accuracy, and the new sample subset T 2_i The difference operation result is determined as the new sample subset T 2_i The corresponding original sample subset T i The accuracy deviation P2={w 2_1 、w 2_2and w 2_3}.

[0082] Based on the candidate battery index z3, each new sample subset corresponding to the candidate battery index z3 is determined, that is, T 3_1 ={z1,z2}、T 3_2 ={z1,z2} and T 3_3 ={z1,z2}; further, T 3_1 ={z1,z2}、T 3_2 ={z1,z2} and T 3_3 = {z1, z2} each new sample subset is input to the cross entropy loss function, and the cross entropy loss function is used to calculate the new sample subset (T 3_1 , T 3_2 and T 3_3 ) to calculate the loss and obtain each new sample subset (T 3_1 , T 3_2 and T 3_3 ) of the second prediction accuracy; further, for each new sample subset (T 3_1 , T 3_2 and T 3_3 ), the new sample subset T 3_i The second prediction accuracy of (i=1, 2, 3) is calculated by difference with the initial prediction accuracy, and the new sample subset T 3_i The difference operation result is determined as the new sample subset T 3_i The corresponding original sample subset T i The accuracy deviation P3 of the candidate battery indicator z3 = {w 3_1 、w 3_2 and w 3_3}.

[0083] Furthermore, for the candidate battery indicator z1, w in the accuracy deviation P1 can be 1_1 、w 1_2 and w 1_3 Perform mean processing. If the mean processing value is greater than 0, it can be determined that the correlation between the candidate battery indicator z1 and the vehicle battery failure is 0; if the mean processing value is less than 0, the result of the mean processing can be determined as the correlation between the candidate battery indicator z1 and the vehicle battery failure; for the candidate battery indicator z2, w in the accuracy deviation P2 can be 2_1 、w 2_2 and w 2_3 Perform mean processing and determine the correlation between the candidate battery index z2 and the vehicle battery failure; for the candidate battery index z3, w in the accuracy deviation P3 can be 3_1 、w 3_2 and w 3_3Perform mean processing and determine the correlation between the candidate battery index z3 and the vehicle battery failure.

[0084] Another possible implementation method is to directly input the cross entropy loss function, the initial prediction accuracy and each new sample subset into the correlation determination model; the correlation determination model analyzes them and determines the correlation between the candidate battery indicators and the vehicle battery failure based on the analysis results.

[0085] In the embodiment of the present application, by constructing each new sample subset corresponding to each candidate battery indicator, a foundation is laid for determining the correlation between each candidate battery indicator and the vehicle battery fault.

[0086] Based on the above-mentioned embodiments, the embodiments of the present application explain the above-mentioned embodiment S203 in detail. Specifically, the embodiments of the present application involve a process of providing a vehicle battery failure warning for a target electric vehicle, which specifically includes the following steps: inputting the target indicator data and the battery aging factor into the Bayesian network model to obtain a target failure probability for the target electric vehicle; based on the corresponding relationship between the failure probability and the failure level, determining a target failure level corresponding to the target failure probability; and providing a vehicle battery failure warning for the target electric vehicle according to the target failure level.

[0087] Among them, the target failure probability can represent the probability of a target electric vehicle failure predicted based on the target indicator data in the current time period; the target failure level can represent the level of battery failure predicted for the target electric vehicle based on the target indicator data in the current time period.

[0088] Exemplarily, the target indicator data and the battery aging factor can be input into the Bayesian network model, which analyzes the target indicator data and the battery aging factor, and predicts the failure probability corresponding to the target indicator data battery aging factor to obtain the target failure probability of the target electric vehicle; further, the target failure level corresponding to the target failure probability can be determined based on the corresponding relationship between the preset failure probability and the failure level; and based on the target failure level, a failure warning of the vehicle battery can be performed.

[0089] Optionally, the corresponding relationship between the failure probability and the failure level may be as shown in Table 1.

[0090]

[0091] Table 1 Correspondence

[0092] In the embodiment of the present application, a Bayesian network model is introduced to determine the target failure probability of the target electric vehicle, laying the foundation for accurately making fault warnings for the vehicle battery.

[0093] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0094] Based on the same inventive concept, the embodiment of the present application also provides an electric vehicle battery failure warning device for implementing the electric vehicle battery failure warning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more electric vehicle battery failure warning device embodiments provided below can refer to the limitations of the electric vehicle battery failure warning method above, and will not be repeated here.

[0095] In an exemplary embodiment, as shown in FIG5 , an electric vehicle battery failure warning device 1 is provided, comprising: an acquisition module 10, a factor determination module 20 and a warning module 30, wherein:

[0096] The acquisition module 10 is used to obtain the target indicator data of the target electric vehicle under the key battery indicator in the current time period; wherein the key battery indicator is an indicator related to vehicle battery failure screened out from each candidate battery indicator based on the cross entropy loss function and the original data set; each sample data in the original data set includes the sample indicator data of the sample electric vehicle under each candidate battery indicator and the sample category label of the sample electric vehicle.

[0097] The factor determination module 20 is used to determine the battery aging factor of the target electric vehicle according to the initial battery capacity and the current battery capacity of the target electric vehicle.

[0098] The early warning module 30 is used to provide a vehicle battery failure early warning for the target electric vehicle based on the Bayesian network model according to the target indicator data and the battery aging factor.

[0099] In one embodiment, as shown in FIG6 , the acquisition module 10 specifically further includes:

[0100] The correlation determination unit 11 is used to determine the correlation between each candidate battery indicator and the vehicle battery fault according to the cross entropy loss function and the original data set.

[0101] The indicator screening unit 12 is used to screen out key battery indicators from each candidate battery indicator according to the correlation between each candidate battery indicator and the vehicle battery failure.

[0102] In one embodiment, the relevance determination unit 11 is further configured to:

[0103] The original data set is divided into multiple original sample subsets with the same number of samples; each original sample subset is processed using the cross entropy loss function to obtain an initial prediction accuracy; for each candidate battery indicator, the sample indicator data corresponding to the candidate battery indicator is removed from the sample data of each original sample subset to obtain each new sample subset corresponding to the candidate battery indicator; based on the cross entropy loss function, the initial prediction accuracy and each new sample subset, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0104] In one embodiment, the relevance determination unit 11 is further configured to:

[0105] For each original sample subset, the cross entropy loss function is used to process the original sample subset to obtain the first prediction accuracy of the original sample subset; the average of the first prediction accuracy of each original sample subset is used as the initial prediction accuracy.

[0106] In one embodiment, the relevance determination unit 11 is further configured to:

[0107] For each new sample subset, the cross entropy loss function is used to process the new sample subset to obtain the second prediction accuracy of the new sample subset, and the difference between the second prediction accuracy of the new sample subset and the initial prediction accuracy is used as the accuracy deviation of the original sample subset corresponding to the new sample subset for the candidate battery indicator; according to the accuracy deviation of the original sample subset corresponding to each new sample subset for the candidate battery indicator, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0108] In one embodiment, the early warning module 30 is specifically used for:

[0109] The target indicator data and battery aging factor are input into the Bayesian network model to obtain the target failure probability of the target electric vehicle; based on the corresponding relationship between the failure probability and the failure level, the target failure level corresponding to the target failure probability is determined; according to the target failure level, a vehicle battery failure warning is issued for the target electric vehicle.

[0110] Each module in the above-mentioned electric vehicle battery fault warning device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0111] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG7. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store indicator data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an electric vehicle battery fault warning method is implemented.

[0112] Those skilled in the art will understand that the structure shown in FIG. 7 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0113] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0114] Obtain target indicator data of the target electric vehicle under key battery indicators in the current period; wherein the key battery indicator is an indicator related to vehicle battery failure screened from each candidate battery indicator according to the cross entropy loss function and the original data set; each sample data in the original data set includes sample indicator data of the sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle;

[0115] Determining a battery aging factor of the target electric vehicle based on the initial battery capacity and the current battery capacity of the target electric vehicle;

[0116] Based on the Bayesian network model, vehicle battery failure warning is issued for the target electric vehicle according to the target indicator data and battery aging factor.

[0117] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0118] According to the cross entropy loss function and the original data set, the correlation between each candidate battery indicator and the vehicle battery failure is determined; according to the correlation between each candidate battery indicator and the vehicle battery failure, the key battery indicators are screened out from the candidate battery indicators.

[0119] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0120] The original data set is divided into multiple original sample subsets with the same number of samples; each original sample subset is processed using the cross entropy loss function to obtain an initial prediction accuracy; for each candidate battery indicator, the sample indicator data corresponding to the candidate battery indicator is removed from the sample data of each original sample subset to obtain each new sample subset corresponding to the candidate battery indicator; based on the cross entropy loss function, the initial prediction accuracy and each new sample subset, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0121] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0122] For each original sample subset, the cross entropy loss function is used to process the original sample subset to obtain the first prediction accuracy of the original sample subset; the average of the first prediction accuracy of each original sample subset is used as the initial prediction accuracy.

[0123] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0124] For each new sample subset, the cross entropy loss function is used to process the new sample subset to obtain the second prediction accuracy of the new sample subset, and the difference between the second prediction accuracy of the new sample subset and the initial prediction accuracy is used as the accuracy deviation of the original sample subset corresponding to the new sample subset for the candidate battery indicator; according to the accuracy deviation of the original sample subset corresponding to each new sample subset for the candidate battery indicator, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0125] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0126] The target indicator data and battery aging factor are input into the Bayesian network model to obtain the target failure probability of the target electric vehicle; based on the corresponding relationship between the failure probability and the failure level, the target failure level corresponding to the target failure probability is determined; according to the target failure level, a vehicle battery failure warning is issued for the target electric vehicle.

[0127] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0128] Obtain target indicator data of the target electric vehicle under key battery indicators in the current period; wherein the key battery indicator is an indicator related to vehicle battery failure screened from each candidate battery indicator according to the cross entropy loss function and the original data set; each sample data in the original data set includes sample indicator data of the sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle;

[0129] Determining a battery aging factor of the target electric vehicle based on the initial battery capacity and the current battery capacity of the target electric vehicle;

[0130] Based on the Bayesian network model, vehicle battery failure warning is issued for the target electric vehicle according to the target indicator data and battery aging factor.

[0131] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0132] According to the cross entropy loss function and the original data set, the correlation between each candidate battery indicator and the vehicle battery failure is determined; according to the correlation between each candidate battery indicator and the vehicle battery failure, the key battery indicators are screened out from the candidate battery indicators.

[0133] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0134] The original data set is divided into multiple original sample subsets with the same number of samples; each original sample subset is processed using the cross entropy loss function to obtain an initial prediction accuracy; for each candidate battery indicator, the sample indicator data corresponding to the candidate battery indicator is removed from the sample data of each original sample subset to obtain each new sample subset corresponding to the candidate battery indicator; based on the cross entropy loss function, the initial prediction accuracy and each new sample subset, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0135] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0136] For each original sample subset, the cross entropy loss function is used to process the original sample subset to obtain the first prediction accuracy of the original sample subset; the average of the first prediction accuracy of each original sample subset is used as the initial prediction accuracy.

[0137] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0138] For each new sample subset, the cross entropy loss function is used to process the new sample subset to obtain the second prediction accuracy of the new sample subset, and the difference between the second prediction accuracy of the new sample subset and the initial prediction accuracy is used as the accuracy deviation of the original sample subset corresponding to the new sample subset for the candidate battery indicator; according to the accuracy deviation of the original sample subset corresponding to each new sample subset for the candidate battery indicator, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0139] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0140] The target indicator data and battery aging factor are input into the Bayesian network model to obtain the target failure probability of the target electric vehicle; based on the corresponding relationship between the failure probability and the failure level, the target failure level corresponding to the target failure probability is determined; according to the target failure level, a vehicle battery failure warning is issued for the target electric vehicle.

[0141] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0142] Obtain target indicator data of the target electric vehicle under key battery indicators in the current period; wherein the key battery indicator is an indicator related to vehicle battery failure screened from each candidate battery indicator according to the cross entropy loss function and the original data set; each sample data in the original data set includes sample indicator data of the sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle;

[0143] Determining a battery aging factor of the target electric vehicle based on the initial battery capacity and the current battery capacity of the target electric vehicle;

[0144] Based on the Bayesian network model, vehicle battery failure warning is issued for the target electric vehicle according to the target indicator data and battery aging factor.

[0145] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0146] According to the cross entropy loss function and the original data set, the correlation between each candidate battery indicator and the vehicle battery failure is determined; according to the correlation between each candidate battery indicator and the vehicle battery failure, the key battery indicators are screened out from the candidate battery indicators.

[0147] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0148] The original data set is divided into multiple original sample subsets with the same number of samples; each original sample subset is processed using the cross entropy loss function to obtain an initial prediction accuracy; for each candidate battery indicator, the sample indicator data corresponding to the candidate battery indicator is removed from the sample data of each original sample subset to obtain each new sample subset corresponding to the candidate battery indicator; based on the cross entropy loss function, the initial prediction accuracy and each new sample subset, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0149] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0150] For each original sample subset, the cross entropy loss function is used to process the original sample subset to obtain the first prediction accuracy of the original sample subset; the average of the first prediction accuracy of each original sample subset is used as the initial prediction accuracy.

[0151] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0152] For each new sample subset, the cross entropy loss function is used to process the new sample subset to obtain the second prediction accuracy of the new sample subset, and the difference between the second prediction accuracy of the new sample subset and the initial prediction accuracy is used as the accuracy deviation of the original sample subset corresponding to the new sample subset for the candidate battery indicator; according to the accuracy deviation of the original sample subset corresponding to each new sample subset for the candidate battery indicator, the correlation between the candidate battery indicator and the vehicle battery failure is determined.

[0153] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0154] The target indicator data and battery aging factor are input into the Bayesian network model to obtain the target failure probability of the target electric vehicle; based on the corresponding relationship between the failure probability and the failure level, the target failure level corresponding to the target failure probability is determined; according to the target failure level, a vehicle battery failure warning is issued for the target electric vehicle.

[0155] It should be noted that the information (including but not limited to vehicle information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0156] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0157] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle fault warning method, characterized in that: The method comprises: Obtain target indicator data of the target electric vehicle under key battery indicators in the current period; wherein the key battery indicator is an indicator related to vehicle failure screened from each candidate battery indicator according to the cross entropy loss function and the original data set; each sample data in the original data set includes sample indicator data of the sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle; Determining a battery aging factor of the target electric vehicle according to an initial battery capacity and a current battery capacity of the target electric vehicle; Based on the Bayesian network model, fault warning is performed on the target electric vehicle according to the target indicator data and the battery aging factor.

2. The method according to claim 1, characterized in that The key battery indicators are determined in the following way: Determine the correlation between each candidate battery indicator and vehicle fault based on the cross entropy loss function and the original data set; The key battery indicator is selected from the candidate battery indicators according to the correlation between the candidate battery indicators and the vehicle fault.

3. The method according to claim 2, characterized in that Determining the correlation between each candidate battery indicator and the vehicle fault according to the cross entropy loss function and the original data set includes: Dividing the original data set into a plurality of original sample subsets with the same number of samples; The cross entropy loss function is used to process each original sample subset to obtain the initial prediction accuracy; For each candidate battery indicator, sample indicator data corresponding to the candidate battery indicator is removed from sample data of each original sample subset to obtain each new sample subset corresponding to the candidate battery indicator; The correlation between the candidate battery indicator and the vehicle fault is determined according to the cross entropy loss function, the initial prediction accuracy and each new sample subset.

4. The method according to claim 3, characterized in that The cross entropy loss function is used to process each original sample subset to obtain the initial prediction accuracy, including: For each original sample subset, a cross entropy loss function is used to process the original sample subset to obtain a first prediction accuracy of the original sample subset; The first prediction accuracy mean of each original sample subset is taken as the initial prediction accuracy.

5. The method according to claim 3, characterized in that: The determining, according to the cross entropy loss function, the initial prediction accuracy and each new sample subset, the correlation between the candidate battery indicator and the vehicle fault includes: For each new sample subset, a cross entropy loss function is used to process the new sample subset to obtain a second prediction accuracy of the new sample subset, and a difference between the second prediction accuracy of the new sample subset and the initial prediction accuracy is used as the accuracy deviation of the original sample subset corresponding to the new sample subset for the candidate battery indicator; The correlation between the candidate battery indicator and the vehicle fault is determined according to the accuracy deviation of the original sample subset corresponding to each new sample subset for the candidate battery indicator.

6. The method according to claim 1, characterized in that The method of providing a fault warning to the target electric vehicle based on the Bayesian network model according to the target indicator data and the battery aging factor includes: Inputting the target indicator data and the battery aging factor into a Bayesian network model to obtain a target failure probability of the target electric vehicle; Based on the corresponding relationship between the failure probability and the failure level, determining a target failure level corresponding to the target failure probability; According to the target fault level, a fault warning is provided to the target electric vehicle.

7. A vehicle fault warning device, characterized in that: The device comprises: An acquisition module is used to acquire target indicator data of a target electric vehicle under a key battery indicator in a current period; wherein the key battery indicator is an indicator related to vehicle failure screened from each candidate battery indicator according to a cross entropy loss function and an original data set; each sample data in the original data set includes sample indicator data of a sample electric vehicle under each candidate battery indicator and a sample category label of the sample electric vehicle; A factor determination module, used to determine a battery aging factor of the target electric vehicle according to an initial battery capacity and a current battery capacity of the target electric vehicle; The early warning module is used to provide fault early warning for the target electric vehicle based on the Bayesian network model according to the target indicator data and the battery aging factor.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images