Battery fault diagnosis method and device, equipment, storage medium and program product

Abstract

The invention relates to a battery fault diagnosis method and device, equipment, a storage medium and a program product. The method comprises the following steps: firstly, acquiring battery data of a vehicle in a target charging stage, then, selecting a target entropy model according to the battery data, inputting the battery data into the target entropy model to obtain an entropy used for representing uncertainty of a battery system in the vehicle, and finally, according to the entropy and a preset threshold value, determining the uncertainty of the battery system in the vehicle. A fault diagnosis result of the battery in the vehicle is determined. By adopting the method, a complicated electrochemical model does not need to be established to diagnose the fault of the battery, and the fault diagnosis of the battery is easier to realize.

Description

Technical Field

[0001] The present application relates to the technical field of battery fault diagnosis, and in particular to a battery fault diagnosis method, device, equipment, storage medium and program product. Background Art

[0002] With the development of new energy technology, the safety of power batteries has become one of the important issues in the field of new energy vehicles. Therefore, it is necessary to be able to timely identify and screen abnormal power batteries and issue safety risk warnings.

[0003] At present, fault diagnosis of battery systems is generally achieved through electrochemical principles, using the battery system structure and internal chemical reactions. However, this method is difficult to simulate all electrochemical reactions inside the battery, and the fault diagnosis implementation method is complicated. Summary of the invention

[0004] Based on this, it is necessary to provide a battery fault diagnosis method, device, equipment, storage medium and program product to address the above technical problems.

[0005] In a first aspect, the present application provides a battery fault diagnosis method, the method comprising:

[0006] Obtain battery data of the vehicle within the target charging stage;

[0007] Select a target entropy value model according to battery data, and input the battery data into the target entropy value model to obtain an entropy value, which is used to characterize the uncertainty of the battery system in the vehicle;

[0008] Based on the entropy value and the preset threshold, the fault diagnosis result of the battery in the vehicle is determined.

[0009] In one embodiment, selecting a target entropy value model according to battery data includes:

[0010] Extracting a first parameter feature according to the battery data, where the first parameter feature includes at least one of a data sampling frequency, a total battery voltage, and an average cell voltage;

[0011] According to the first parameter feature, a target entropy value model is determined from multiple entropy value models.

[0012] In one embodiment, the multiple entropy value models include at least one of an optimized Shannon entropy model, an improved multi-scale entropy model, a fuzzy entropy model, an approximate entropy model, and a sample entropy model.

[0013] In one embodiment, the preset threshold value includes a first threshold value and a second threshold value, and the fault diagnosis result of the battery is determined according to the entropy value and the preset threshold value, including:

[0014] The entropy value is standardized to obtain the fault score;

[0015] If the fault score is less than the first threshold, it is determined that there is no fault in the battery;

[0016] If the fault score is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that the battery has a potential fault;

[0017] If the fault score is greater than the second threshold, it is determined that the battery has a fault.

[0018] In one embodiment, the process of determining the preset threshold includes:

[0019] Get sample battery data for the vehicle;

[0020] Select a target entropy value model according to the sample battery data, and input the sample battery data into the target entropy value model to obtain a sample entropy value;

[0021] According to the sample entropy value, the preset threshold is determined.

[0022] In one embodiment, the method further comprises:

[0023] Parameters of each entropy value model are determined according to the sample battery data, and the parameters include at least one of a time window and a scale factor.

[0024] In a second aspect, the present application also provides a battery fault diagnosis device, the device comprising:

[0025] An acquisition module, used to acquire battery data of the vehicle in a target charging stage;

[0026] A first determination module is used to select a target entropy value model according to battery data, and input the battery data into the target entropy value model to obtain an entropy value, where the entropy value is used to characterize the uncertainty of the battery system in the vehicle;

[0027] The second determination module is used to determine the fault diagnosis result of the battery in the vehicle according to the entropy value and the preset threshold value.

[0028] 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 battery fault diagnosis method described in any one of the first aspects is implemented.

[0029] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the battery fault diagnosis method described in any one of the first aspects above.

[0030] In a fifth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the battery fault diagnosis method described in any one of the first aspects above.

[0031] The above-mentioned battery fault diagnosis method, device, equipment, storage medium and program product first obtain the battery data of the vehicle in the target charging stage, then select the target entropy value model according to the battery data, and input the battery data into the target entropy value model to obtain the entropy value used to characterize the uncertainty of the battery system in the vehicle, and finally, determine the fault diagnosis result of the battery in the vehicle according to the entropy value and the preset threshold. In this way, the target entropy value model is selected according to the battery data of the vehicle, and the entropy value is calculated. The entropy value can characterize the uncertainty of the battery system, so that the fault diagnosis result of the battery can be determined according to the entropy value. There is no need to establish a complex electrochemical model to diagnose the battery fault, and the battery fault diagnosis is easier to achieve. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 is a flowchart of a battery fault diagnosis method in one embodiment;

[0034] Figure 2 A schematic diagram of a process for determining a target entropy value model in one embodiment;

[0035] Figure 3 is a flowchart of a battery fault diagnosis method in another embodiment;

[0036] Figure 4 A schematic diagram of target entropy value model output results in another embodiment;

[0037] Figure 5 is a flowchart of a battery fault diagnosis method in another embodiment;

[0038] Figure 6 is a flowchart of a battery fault diagnosis method in another embodiment;

[0039] Figure 7 is a structural block diagram of a battery fault diagnosis device in one embodiment;

[0040] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0041] 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.

[0042] In an exemplary embodiment, Figure 1 As shown, a battery fault diagnosis method is provided, and the method is applied to a terminal as an example for explanation. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server, and includes the following steps:

[0043] Step 101, obtaining battery data of a vehicle in a target charging phase.

[0044] Among them, the battery data may include the battery voltage data and battery current data of the vehicle in the target charging stage. Optionally, the target charging stage may be a charging stage selected according to user needs. The battery data of the vehicle can be obtained through the vehicle cloud big data platform, or the battery data of the vehicle can be obtained from the vehicle local terminal. The battery data may be data within a period of time, such as time series data. After the battery data is obtained, the battery data may be processed, and the data processing may include cleaning the data, removing null values ​​and outliers, etc. Furthermore, the obtained battery data may be analyzed, such as performing a quantitative distribution analysis on the battery data, determining the distribution of the battery data, performing a skewness analysis and a peak analysis on the battery data, and performing a correlation analysis between different features of the battery data.

[0045] Step 102 , selecting a target entropy value model according to the battery data, and inputting the battery data into the target entropy value model to obtain an entropy value.

[0046] Among them, the entropy value is used to characterize the uncertainty of the battery system in the vehicle. The target entropy value model can be one of multiple entropy value models. Optionally, the multiple entropy value models can include Shannon entropy model, multi-scale entropy model, fuzzy entropy model, approximate entropy model and sample entropy model. Since different entropy value models are applicable to different scenarios, a matching entropy value model can be selected as the target entropy value model according to the characteristics of the battery data, and then the target entropy value model is input according to the battery data for calculation to obtain the entropy value corresponding to the battery data.

[0047] Step 103, determining a fault diagnosis result of the battery in the vehicle according to the entropy value and a preset threshold value.

[0048] Among them, the preset threshold value can be a warning threshold value, and the preset threshold value can be determined after fault diagnosis of battery data with historical faults through a target entropy value model. According to the entropy value calculated based on the battery data and the preset threshold value, the vehicle fault can be diagnosed and predicted. Optionally, the above-mentioned target entropy value model and preset threshold value can be set in the battery management system of the vehicle, and the battery data of the vehicle can be collected in real time during the operation of the vehicle to realize fault diagnosis and prediction of the vehicle.

[0049] In the above embodiment, first, the battery data of the vehicle in the target charging stage is obtained, then the target entropy value model is selected according to the battery data, and the battery data is input into the target entropy value model to obtain an entropy value used to characterize the uncertainty of the battery system in the vehicle, and finally, the fault diagnosis result of the battery in the vehicle is determined according to the entropy value and the preset threshold. In this way, the target entropy value model is selected according to the battery data of the vehicle, and the entropy value is calculated. The entropy value can characterize the uncertainty of the battery system, so that the fault diagnosis result of the battery can be determined according to the entropy value, and there is no need to establish a complex electrochemical model to diagnose the battery fault, and the fault diagnosis of the battery is easier to achieve.

[0050] In one embodiment, different entropy value calculation methods are different, and have different effects when diagnosing different data types. The target entropy value model is selected according to the battery data, such as Figure 2 As shown, including:

[0051] Step 201: extracting a first parameter feature according to battery data.

[0052] The first parameter feature includes at least one of a data sampling frequency, a total battery voltage, and an average cell voltage. The power battery may include multiple cells, and the average cell voltage includes the average voltage of each of the multiple cells. Optionally, based on the acquired battery data, the first parameter feature in the battery data is extracted. For example, the total battery voltage and the average cell voltage can be calculated from the battery voltage in the battery data.

[0053] Step 202: Determine a target entropy value model from a plurality of entropy value models according to the first parameter feature.

[0054] Optionally, for different parameter features, different entropy value models can be selected according to the parameter characteristics of the parameter features for entropy value calculation, that is, the target entropy value model is determined according to the first parameter feature. Optionally, a preset correspondence table can be set, and the preset correspondence table includes the correspondence between the first parameter feature of the battery data and the entropy value model. The preset correspondence table can be queried through the first parameter feature to determine the target entropy value model.

[0055] In one embodiment, the multiple entropy value models include at least one of an optimized Shannon entropy model, an improved multi-scale entropy model, a fuzzy entropy model, an approximate entropy model, and a sample entropy model.

[0056] The traditional Shannon entropy model needs to repeatedly calculate past data, which will increase the computational cost in fault diagnosis. Optionally, the optimized Shannon entropy model is optimized for electric vehicles based on the traditional Shannon entropy model, and battery fault diagnosis is performed by quantifying the degree of data confusion of data segments. The entropy value model can be made more suitable for real-time battery fault diagnosis by improving the sliding method of the time window, thereby reducing the computational cost by optimizing the calculation process. Optionally, the calculation of the optimized Shannon entropy can be as follows.

[0057] X min =min{x(i, j)|i=1, 2, 3...k; j=1, 2, 3...n}

[0058] X max =max{x(i,j)|i=0,1,2,3...k;j=0,1,2,3...n}Define the function:

[0059]

[0060] in,

[0061]

[0062] The optimized Shannon entropy is defined as:

[0063]

[0064] Among them, X min , X max is the extreme value of the matrix x(i,j), x(i,j) is the battery data to be diagnosed, C i,j , P i,j are the elements that define functions C and P respectively.

[0065] Optionally, the improved multiscale entropy model has better consistency than the multiscale sample entropy model, so it is more suitable for consistency evaluation of input data. When battery data needs to be evaluated for consistency, the multiscale entropy model can be used. The improved multiscale entropy combines the information of all granularity sequences under different scale factors and has better consistency than the standard multiscale entropy model. The calculation of the improved multiscale entropy model is shown below.

[0066] Assume the battery data is:

[0067] x i=x1,x2,x3,…,x n

[0068] The improved multi-scale entropy uses different scale factors τ to divide the battery data into non-overlapping windows, and the coarse-grained sequence is established as follows:

[0069]

[0070] When the scale factor increases, the length of the coarse-grained sequence becomes shorter, and the entropy deviation and estimation error will also increase. The coarse-grained sequence is defined as: For each scale factor, calculate the sample entropy of each coarse-grained sequence

[0071]

[0072] Among them, m is the dimension of battery data vector, and r is the set threshold. It can be seen that the improved multi-scale entropy combines the information of all granularity sequences under different scale factors, and has better consistency than the standard multi-scale entropy.

[0073] Optionally, the fuzzy entropy model is an entropy algorithm improved on the basis of the sample entropy model. Compared with the sample entropy model, the fuzzy entropy model divides the processed data into two parts: greater than a threshold and less than a threshold. The fuzzy entropy model determines whether the input data is abnormal by calculating the fuzzy membership of the data above the threshold. The fuzzy entropy model has good potential in data processing, and the calculation method of the fuzzy entropy is shown in the following formula.

[0074]

[0075] Optionally, the approximate entropy model is a nonlinear dynamic parameter used to quantify the regularity and unpredictability of time series fluctuations, reflecting the possibility of new information in the time series. The more complex the time series, the greater the corresponding approximate entropy. The time series is also the input battery data sequence. Compared with the Shannon entropy model, the approximate entropy is more robust. The calculation method of the approximate entropy is shown in the following formula.

[0076]

[0077] Optionally, the sample entropy model measures the complexity of the time series, that is, the battery data series, by measuring the probability of generating a new pattern in the input signal. Compared with the approximate entropy model, the calculation of the sample entropy model does not depend on the length of the input data and has better consistency. Compared with nonlinear dynamic methods such as the sample entropy model, the sample entropy model requires less data length and is more resistant to noise. Therefore, when the amount of battery data series is small, the sample entropy model can be selected, but the sample entropy model is often only used to process a single time scale. The calculation method of the sample entropy is shown in the following formula.

[0078]

[0079] In the above embodiments, different entropy models have different characteristics, so different entropy models can be selected according to different input data in battery fault diagnosis. For example, the optimized Shannon entropy model is suitable for real-time battery fault diagnosis. The improved multi-scale entropy is suitable for consistency detection of battery data, such as cell voltage consistency, temperature consistency, etc. The fuzzy entropy model is suitable for battery fault diagnosis through thresholds, and is not suitable for scenarios with many faults. The approximate entropy model has good robustness, but the calculation process is highly dependent on the length of the input battery data, so it can be applied to scenarios when the optimized Shannon entropy is not applicable. The sample entropy model is suitable for situations where the battery data length is short and there is more noise in the battery data. Therefore, according to the characteristics of the battery data, by establishing a preset correspondence table, the target entropy model can be determined from multiple entropy models to perform fault diagnosis on the battery data, and the accuracy and efficiency of fault diagnosis are higher. At the same time, by selecting a suitable target entropy model, the robustness of the fault diagnosis process is further improved and the calculation cost is reduced.

[0080] In one embodiment, the preset threshold value includes a first threshold value and a second threshold value, and the step of determining the fault diagnosis result of the battery according to the entropy value and the preset threshold value is as follows: Figure 3 As shown, including:

[0081] Step 301: normalize the entropy value to obtain a fault score.

[0082] After the entropy value is calculated according to the target entropy value model, the entropy value is standardized, that is, the standardized score of the entropy value of each data point in the battery data sequence is calculated. Optionally, the mean and standard deviation of the entropy value of each data point are calculated, and then the standardized score of the entropy value of each data point is obtained according to the mean and standard deviation, that is, the fault score. The calculation method is shown in the following formula.

[0083]

[0084] Among them, X i is the entropy value of each data point, Z i Fault score, is the mean and s is the standard deviation.

[0085] Step 302: If the fault score is less than the first threshold, it is determined that there is no fault in the battery.

[0086] If the fault score of the data point is less than the first threshold, the data point is considered to be normal data, and it is determined that the battery cell corresponding to the data point does not have a fault, and the battery does not have a fault.

[0087] Step 303: If the fault score is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that there is a potential fault in the battery.

[0088] If the fault score is greater than the first threshold and less than or equal to the second threshold, it is determined that the battery cell corresponding to the data point has a potential fault, and the battery has a potential fault.

[0089] Step 304: If the fault score is greater than the second threshold, it is determined that the battery has a fault.

[0090] If the fault score is greater than the second threshold, it is determined that the cell corresponding to the data point has a fault, and the battery has a fault. Figure 4 As shown, it is a result diagram of the fault scores of 95 battery cells included in the battery, wherein the first threshold value can be 1, and the second threshold value can be 3. If the fault score is less than 1, the data point is considered to be normal data. If the fault score is between 1 and 3, it is considered that the battery cell has a potential fault. If the fault score is greater than 3, it is considered that the battery cell has a fault and needs to be checked.

[0091] In one embodiment, the process of determining the preset threshold is as follows: Figure 5 As shown, including:

[0092] Step 501, obtaining sample battery data of a vehicle.

[0093] The sample battery data may be battery data with historical battery failures, and the sample battery data may be battery data sequences of multiple charging stages of multiple vehicles.

[0094] Step 502 , selecting a target entropy value model according to the sample battery data, and inputting the sample battery data into the target entropy value model to obtain a sample entropy value.

[0095] According to the type of sample battery data, a suitable target entropy value model is determined from multiple entropy value models, and the sample battery data is input into the target entropy value model to obtain the corresponding sample entropy value.

[0096] Step 503: Determine a preset threshold value according to the sample entropy value.

[0097] According to the sample entropy value, an anomaly detection algorithm based on Gaussian distribution is used to identify anomalies in the entropy value and determine a preset threshold. The preset threshold may include a first threshold and a second threshold. Further, the obtained preset threshold may be verified by testing battery data, and the test battery data may include battery data with faults, battery data with potential faults, and battery data without faults, so as to confirm the accuracy of the preset threshold.

[0098] Optionally, parameters of each entropy value model are determined based on sample battery data, and the parameters include at least one of a time window and a scale factor.

[0099] Among them, the time window is used to characterize the number of data sets that need to be calculated at each step in the actual operation of the vehicle. Under different time windows, the diagnostic results of the entropy algorithm are different. For example, when the time window is 200, each calculation takes 200 adjacent data to calculate its disorder. Therefore, when the time window is set to a large size, the calculation cost will be high due to the large amount of data. When the time window is set to a small size, the calculation accuracy cannot be guaranteed due to the small amount of data, and thus the accuracy of fault diagnosis cannot be guaranteed. Therefore, in each entropy value model, it is necessary to select a suitable time window.

[0100] At the same time, the scale factor is also very important for reducing the amount of calculation and improving the fault diagnosis effect. The basic principle of multi-scale entropy includes coarse-graining the time series. Coarse-grained data refers to taking the average of different numbers of continuous points to create signals of different scales or resolutions. By adjusting the size of the scale factor, the diagnostic effect of the entropy value model can be optimized. Therefore, choosing an appropriate scale factor can reduce the computational cost and improve the diagnostic effect of the model.

[0101] Tests are performed based on sample battery data and multiple groups of time windows and scale factors, and the diagnostic results of each entropy model under each group of time windows and scale factors are recorded. The optimal time window and scale factor parameter combination of each entropy model is determined based on the diagnostic results and saved in each entropy model.

[0102] In the above embodiment, the preset threshold value, time window and scale factor parameters are determined by sample battery data, thereby improving the accuracy and sensitivity of diagnosis of each entropy value model.

[0103] In an embodiment of the present application, a battery fault diagnosis method is provided, such as Figure 6 As shown, including:

[0104] Step 601, obtaining battery data of the vehicle in the target charging phase.

[0105] Step 602: extracting a first parameter feature according to the battery data.

[0106] Step 603: Determine a target entropy value model from multiple entropy value models according to the first parameter feature.

[0107] Step 604: Input the battery data into the target entropy value model to obtain the entropy value.

[0108] Step 605: normalize the entropy value to obtain a fault score.

[0109] Step 606: If the fault score is less than the first threshold, it is determined that the battery has no fault.

[0110] Step 607: If the fault score is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that there is a potential fault in the battery.

[0111] Step 608: If the fault score is greater than the second threshold, it is determined that the battery is faulty.

[0112] 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 is not strictly limited in order, 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 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.

[0113] Based on the same inventive concept, the embodiment of the present application also provides a battery fault diagnosis device for implementing the battery fault diagnosis 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 battery fault diagnosis device embodiments provided below can refer to the limitations of the battery fault diagnosis method above, and will not be repeated here.

[0114] In an exemplary embodiment, Figure 7 As shown, a battery fault diagnosis device is provided, comprising: an acquisition module, a first determination module and a second determination module, wherein:

[0115] An acquisition module, used to acquire battery data of the vehicle in a target charging stage;

[0116] A first determination module is used to select a target entropy value model according to battery data, and input the battery data into the target entropy value model to obtain an entropy value, where the entropy value is used to characterize the uncertainty of the battery system in the vehicle;

[0117] The second determination module is used to determine the fault diagnosis result of the battery in the vehicle according to the entropy value and the preset threshold value.

[0118] In one embodiment, the first determination module is specifically used to extract a first parameter feature based on battery data, where the first parameter feature includes at least one of a data sampling frequency, a total battery voltage, and an average cell voltage; and based on the first parameter feature, determine a target entropy value model from multiple entropy value models.

[0119] In one embodiment, the multiple entropy value models include at least one of an optimized Shannon entropy model, an improved multi-scale entropy model, a fuzzy entropy model, an approximate entropy model, and a sample entropy model.

[0120] In one of the embodiments, the preset threshold includes a first threshold and a second threshold, and the second determination module is specifically used to standardize the entropy value to obtain a fault score; if the fault score is less than the first threshold, it is determined that the battery has no fault; if the fault score is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that the battery has a potential fault; if the fault score is greater than the second threshold, it is determined that the battery has a fault.

[0121] In one of the embodiments, a third determination module is also included, which is used to obtain sample battery data of the vehicle; select a target entropy value model based on the sample battery data, and input the sample battery data into the target entropy value model to obtain a sample entropy value; and determine a preset threshold value based on the sample entropy value.

[0122] In one of the embodiments, a fourth determination module is further included, which is used to determine parameters of each entropy value model according to the sample battery data, and the parameters include at least one of a time window and a scale factor.

[0123] Each module in the above battery fault diagnosis device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0124] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. 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 in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a battery fault diagnosis method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0125] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0126] 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 the processor implements the following steps when executing the computer program: obtaining battery data of a vehicle in a target charging stage; selecting a target entropy value model based on the battery data, and inputting the battery data into the target entropy value model to obtain an entropy value, wherein the entropy value is used to characterize the uncertainty of a battery system in the vehicle; and determining a fault diagnosis result of the battery in the vehicle based on the entropy value and a preset threshold.

[0127] In one embodiment, when the processor executes the computer program, the following steps are also implemented: extracting a first parameter feature based on the battery data, the first parameter feature including at least one of the data sampling frequency, the total battery voltage, and the average cell voltage; and determining a target entropy value model from multiple entropy value models based on the first parameter feature.

[0128] In one embodiment, the multiple entropy value models include at least one of an optimized Shannon entropy model, an improved multi-scale entropy model, a fuzzy entropy model, an approximate entropy model, and a sample entropy model.

[0129] In one embodiment, the preset threshold includes a first threshold and a second threshold, and the processor further implements the following steps when executing the computer program: normalizing the entropy value to obtain a fault score; if the fault score is less than the first threshold, determining that the battery has no fault; if the fault score is greater than or equal to the first threshold and less than or equal to the second threshold, determining that the battery has a potential fault; if the fault score is greater than the second threshold, determining that the battery has a fault.

[0130] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining sample battery data of the vehicle; selecting a target entropy value model based on the sample battery data, and inputting the sample battery data into the target entropy value model to obtain a sample entropy value; and determining a preset threshold value based on the sample entropy value.

[0131] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determining parameters of each entropy value model according to the sample battery data, the parameters including at least one of a time window and a scale factor.

[0132] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining battery data of a vehicle in a target charging stage; selecting a target entropy value model based on the battery data, and inputting the battery data into the target entropy value model to obtain an entropy value, which is used to characterize the uncertainty of the battery system in the vehicle; and determining a fault diagnosis result of the battery in the vehicle based on the entropy value and a preset threshold.

[0133] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the battery data, a first parameter feature is extracted, the first parameter feature includes at least one of the data sampling frequency, the total battery voltage, and the average cell voltage; based on the first parameter feature, a target entropy value model is determined from multiple entropy value models.

[0134] In one embodiment, the multiple entropy value models include at least one of an optimized Shannon entropy model, an improved multi-scale entropy model, a fuzzy entropy model, an approximate entropy model, and a sample entropy model.

[0135] In one embodiment, the preset threshold includes a first threshold and a second threshold, and the computer program, when executed by the processor, also implements the following steps: normalizing the entropy value to obtain a fault score; if the fault score is less than the first threshold, determining that the battery has no fault; if the fault score is greater than or equal to the first threshold and less than or equal to the second threshold, determining that the battery has a potential fault; if the fault score is greater than the second threshold, determining that the battery has a fault.

[0136] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining sample battery data of the vehicle; selecting a target entropy value model based on the sample battery data, and inputting the sample battery data into the target entropy value model to obtain a sample entropy value; and determining a preset threshold value based on the sample entropy value.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining parameters of each entropy value model according to the sample battery data, the parameters including at least one of a time window and a scale factor.

[0138] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the following steps: obtaining battery data of a vehicle in a target charging phase; selecting a target entropy value model based on the battery data, and inputting the battery data into the target entropy value model to obtain an entropy value, wherein the entropy value is used to characterize the uncertainty of a battery system in the vehicle; and determining a fault diagnosis result of the battery in the vehicle based on the entropy value and a preset threshold.

[0139] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the battery data, a first parameter feature is extracted, the first parameter feature includes at least one of the data sampling frequency, the total battery voltage, and the average cell voltage; based on the first parameter feature, a target entropy value model is determined from multiple entropy value models.

[0140] In one embodiment, the multiple entropy value models include at least one of an optimized Shannon entropy model, an improved multi-scale entropy model, a fuzzy entropy model, an approximate entropy model, and a sample entropy model.

[0141] In one embodiment, the preset threshold includes a first threshold and a second threshold, and the computer program, when executed by the processor, also implements the following steps: normalizing the entropy value to obtain a fault score; if the fault score is less than the first threshold, determining that the battery has no fault; if the fault score is greater than or equal to the first threshold and less than or equal to the second threshold, determining that the battery has a potential fault; if the fault score is greater than the second threshold, determining that the battery has a fault.

[0142] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining sample battery data of the vehicle; selecting a target entropy value model based on the sample battery data, and inputting the sample battery data into the target entropy value model to obtain a sample entropy value; and determining a preset threshold value based on the sample entropy value.

[0143] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determining parameters of each entropy value model according to the sample battery data, the parameters including at least one of a time window and a scale factor.

[0144] It should be noted that the user information (including but not limited to user device information, user personal 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 authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0145] Those of ordinary skill 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 the present application can include at least one of non-volatile memory 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), magnetic 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 thereto. 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, an artificial intelligence (AI) processor, etc., but are not limited thereto.

[0146] 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 application.

[0147] 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 battery fault diagnosis method, characterized in that: The method comprises: Obtain battery data of the vehicle within the target charging stage; Selecting a target entropy value model according to the battery data, and inputting the battery data into the target entropy value model to obtain an entropy value, wherein the entropy value is used to characterize the uncertainty of the battery system in the vehicle; A fault diagnosis result of a battery in the vehicle is determined based on the entropy value and a preset threshold.

2. The method according to claim 1, characterized in that The selecting a target entropy value model according to the battery data includes: Extracting a first parameter feature according to the battery data, where the first parameter feature includes at least one of a data sampling frequency, a total battery voltage, and an average cell voltage; According to the first parameter feature, the target entropy value model is determined from multiple entropy value models.

3. The method according to claim 2, characterized in that The multiple entropy value models include at least one of an optimized Shannon entropy model, an improved multi-scale entropy model, a fuzzy entropy model, an approximate entropy model and a sample entropy model.

4. The method according to claim 1, characterized in that: The preset threshold value includes a first threshold value and a second threshold value, and determining the fault diagnosis result of the battery according to the entropy value and the preset threshold value includes: Standardizing the entropy value to obtain a fault score; If the fault score is less than the first threshold, it is determined that the battery has no fault; If the fault score is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that the battery has a potential fault; If the fault score is greater than the second threshold, it is determined that the battery has a fault.

5. The method according to claim 1, characterized in that The process of determining the preset threshold includes: obtaining sample battery data of the vehicle; Selecting the target entropy value model according to the sample battery data, and inputting the sample battery data into the target entropy value model to obtain a sample entropy value; The preset threshold is determined according to the sample entropy value.

6. The method according to claim 5, characterized in that The method further comprises: Parameters of each of the entropy value models are determined according to the sample battery data, and the parameters include at least one of a time window and a scale factor.

7. A battery fault diagnosis device, characterized in that: The device comprises: An acquisition module, used to acquire battery data of the vehicle in a target charging stage; A first determination module, configured to select a target entropy value model according to the battery data, and input the battery data into the target entropy value model to obtain an entropy value, wherein the entropy value is used to characterize the uncertainty of the battery system in the vehicle; The second determination module is used to determine the fault diagnosis result of the battery in the vehicle according to the entropy value and a preset threshold.

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