Storage battery obstacle diagnosis method and device and storage medium
By collecting and splicing the working parameters of vehicles and batteries, pre-processing and clustering analysis, the problems of low efficiency and insufficient accuracy of battery barrier diagnosis are solved, and efficient and accurate fault identification is achieved.
Patent Information
- Application Number
- CN202510583363.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-07
- Publication Date
- 2025-08-22
AI Technical Summary
In the prior art, battery barrier diagnosis efficiency is low and accuracy is limited, especially the problem of low efficiency of expert empirical analysis methods and high requirements for labeled data by preset identification models.
By collecting the working parameters of the vehicle and the battery, forming a continuous time series based on time splicing, performing preprocessing and performing cluster analysis, and determining the number of sequences to be clustered in the cluster cluster to determine the fault type.
Improves the efficiency and accuracy of battery fault diagnosis and enhances the ability to identify new fault categories.
Smart Images
Figure CN120522571A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of vehicle control technology, and in particular to a method, device, and storage medium for diagnosing battery failure. Background Art
[0002] As the core power source for vehicle starting and operation, the health of the battery is crucial to vehicle performance. Battery fault diagnosis can provide early warning of potential problems, ensure stable battery power supply during critical periods, and prevent vehicle starting failure or stalling during driving due to battery failure, thereby ensuring driving safety. In related technologies, methods of identifying fault types are used through expert experience analysis or pre-set models. In related technologies, the method of expert experience analysis has the problems of low efficiency and limited accuracy, and pre-setting the recognition model requires a large amount of labeled data for training, which has certain requirements for the amount of labeled data. Therefore, how to improve the efficiency and accuracy of battery fault diagnosis is a problem that needs to be solved. Summary of the Invention
[0003] The present invention provides a method, device, and storage medium for diagnosing battery failures, which can be used to improve the efficiency and accuracy of battery failure diagnosis. The technical solution is as follows:
[0004] In one aspect, an embodiment of the present application provides a method for diagnosing a battery fault, the method comprising:
[0005] Collecting operating parameters of a vehicle and an operating parameter of a battery of the vehicle, wherein the operating parameters of the vehicle and the operating parameters of the battery include corresponding collection times;
[0006] splicing the operating parameters of the vehicle and the operating parameters of the battery based on the acquisition time to obtain a continuous first time series;
[0007] Preprocessing the first time series to obtain a sequence to be clustered;
[0008] Performing clustering processing on the sequences to be clustered, and determining the number of sequences to be clustered contained in each cluster;
[0009] Obtaining, based on the number of sequences to be clustered contained in each cluster, a fault detection result of a battery corresponding to the sequences to be clustered contained in the cluster, wherein the fault detection result is used to indicate whether the battery has a fault;
[0010] In response to obtaining the fault detection result indicating that the battery has the fault, the fault category of the battery is analyzed based on the sequences to be clustered.
[0011] In another aspect, a device for diagnosing battery failure is provided, the device comprising:
[0012] A collection module, configured to collect operating parameters of a vehicle and an operating parameter of a battery of the vehicle, wherein the operating parameters of the vehicle and the operating parameters of the battery include corresponding collection times;
[0013] a splicing module, configured to splice the operating parameters of the vehicle and the operating parameters of the battery based on the acquisition time to obtain a continuous first time series;
[0014] A preprocessing module, configured to preprocess the first time series to obtain a sequence to be clustered;
[0015] A clustering processing module, configured to perform clustering processing on the sequences to be clustered and determine the number of sequences to be clustered contained in each cluster;
[0016] an acquisition module, configured to acquire, based on the number of sequences to be clustered contained in each cluster, a fault detection result of a battery corresponding to the sequences to be clustered contained in the cluster, wherein the fault detection result is used to indicate whether the battery has a fault;
[0017] An analysis module is configured to, in response to obtaining the fault detection result indicating that the battery has the fault, analyze the fault category of the battery based on the sequence to be clustered.
[0018] On the other hand, a non-temporary computer-readable storage medium is also provided, characterized in that a computer program is stored in the computer-readable storage medium, and the computer program is loaded and executed by a processor to implement any of the above-mentioned battery fault diagnosis methods.
[0019] On the other hand, a computer program product is provided, which includes computer instructions, and when the computer instructions are executed by a processor, the steps of any of the above-mentioned battery fault diagnosis methods are implemented.
[0020] The technical solution provided by this application brings at least the following beneficial effects:
[0021] The present application collects the operating parameters of the vehicle and the battery, and splices the operating parameters of the vehicle and the battery based on the collection time to obtain a continuous first time series; then preprocesses the first time series to obtain a sequence to be clustered; clusters the sequences to be clustered to determine the number of sequences to be clustered contained in each cluster; then determines whether the battery corresponding to the cluster exists based on the number of sequences to be clustered contained in the cluster; if the battery exists a fault, analyzes the fault category of the battery based on the sequence to be clustered, thereby improving the efficiency and accuracy of battery fault diagnosis and at the same time improving the ability to identify newly added categories of faults. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. 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 any creative work.
[0023] Figure 1 This is a schematic diagram of an implementation environment provided by an embodiment of the present application;
[0024] Figure 2 This is a flow chart of a method for diagnosing battery failure provided by an embodiment of the present application;
[0025] Figure 3 It is a structural diagram of a battery fault diagnosis device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0026] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.
[0027] This application embodiment provides a method for diagnosing battery failure, please refer to Figure 1 , which shows a schematic diagram of the implementation environment of the method provided in the embodiments of the present application. This implementation environment may include: vehicle cloud 11, TBOX (Telematics Box, vehicle-mounted intelligent terminal) 12, BCM (Body Control Module, body control module) 13, FLZCU (Front Left Zone Control Unit, left front zone controller) 14, DCU (Domain Control Unit, domain controller) 15, and BMS (Battery Management System, battery management system) 16.
[0028] Optionally, the BCM 13 collects the ignition key's power-on status and sends it to the TBOX 12; the FLZCU 14 collects the power mode and sends it to the TBOX 12; the DCU 15 collects the DC-DC (Direct Current to Direct Current) converter status and sends it to the TBOX 12; and the BMS 16 collects the battery's voltage, current, temperature, SOH (State of Health), and SOC (State of Charge) and sends them to the TBOX 12. The TBOX 12 aggregates the collected information and uploads it to the Car Cloud 11, which uses it to determine whether the battery is faulty.
[0029] Among them, the car cloud 11, TBOX12, BCM13, FLZCU14, DCU15 and BMS16 establish communication connections through wired or wireless networks.
[0030] Based on the above Figure 1 The embodiment of the present application provides a method for diagnosing battery failure. Figure 2 As shown, taking the method applied to the car cloud as an example, the method includes steps 201 to 206.
[0031] In step 201 , the vehicle cloud collects the operating parameters of the vehicle and the operating parameters of the battery of the vehicle, and the operating parameters of the vehicle and the battery include the corresponding collection time.
[0032] In one possible implementation, the vehicle's operating parameters include, but are not limited to, the ignition key's power-on state, the power mode, and the DC-DC converter's state. The battery's operating parameters include, but are not limited to, the battery's voltage, current, temperature, SOH, and SOC.
[0033] Exemplarily, the vehicle cloud collects the operating parameters of the vehicle and the operating parameters of the vehicle's battery, including: the vehicle cloud collects the power-on status of the ignition key from the BCM through the TBOX; collects the power mode from the FLZCU; collects the status of the DC-DC converter from the DCU; and collects the battery's voltage, current, temperature, SOH, and SOC from the BMS.
[0034] Optionally, the power-on state of the ignition key includes power on and power off, the clerk mode includes complete power-off mode, accessory power mode, ignition mode, start mode, drivable mode and low-power sleep mode, and the vehicle's operating parameters and the battery's operating parameters include corresponding collection time.
[0035] In step 202 , the vehicle cloud splices the operating parameters of the vehicle and the operating parameters of the battery based on the collection time to obtain a continuous first time series.
[0036] In one possible implementation, before the vehicle and battery operating parameters are combined, the vehicle and battery operating parameters are cleaned to remove abnormal parameters and noise signals. Exemplary methods for cleaning the vehicle and battery operating parameters include, but are not limited to, Kalman filtering or median filtering.
[0037] Optionally, after the cleaning of the vehicle operating parameters and the battery operating parameters is completed, the vehicle cloud splices the vehicle operating parameters and the battery operating parameters based on the collection time to obtain a continuous first time series, wherein the first time series can be as follows:
[0038]
[0039] Among them, V1-V n is the battery voltage, I1-I n is the battery current, T1-T n is the battery temperature, SOH1-SOH n is the battery's SOH, SOC1-SOC n is the SOC of the battery, K1-K n P1-P is the power-on state of the ignition key. n For power mode, D1-D n The status of the DC-DC converter.
[0040] In step 203, the car cloud preprocesses the first time series to obtain a sequence to be clustered.
[0041] Exemplarily, after obtaining the first time series, Cheyun preprocesses the first time series to obtain a sequence to be clustered, including: performing median filtering, smoothing, and root mean square normalization on the first time series to obtain a sequence to be clustered.
[0042] In one possible implementation, the formula for the car cloud to perform median filtering on the first time series is as follows:
[0043] s ′ (t)=median{s(ti)∣i∈neighborhood}
[0044] Among them, s(ti) is the value of the first time series at time point t, s ′ (t) is the value of the second time series after median filtering at time point t, neighborhood is a predefined neighborhood, and i represents the offset relative to time point t within the neighborhood of time point t.
[0045] Optionally, after obtaining the second time series, a formula for smoothing the second time series is as follows:
[0046]
[0047] Among them, x j is the second time series, l means to calculate the sliding average at the lth data point in the signal sequence, MA l Indicates that from x l-k+1 to x l The average value of the k series is the third time series after smoothing, where k is a positive integer representing the number of data points covered by the sliding window.
[0048] For example, after obtaining the third time series, the formula for the first step of performing RMS normalization on the third time series is as follows:
[0049]
[0050] Where RMS is the root mean square value of the third time series, N is the number of series, and x m represents the mth sequence in the third time series.
[0051] The formula for the second step is as follows:
[0052]
[0053] Among them, x(n) is the nth sequence in the third time series, x RMS标准化 (n) is the third time series after RMS normalization, i.e., the series to be clustered.
[0054] In step 204 , the car cloud performs clustering processing on the sequences to be clustered, and determines the number of sequences to be clustered contained in each cluster.
[0055] In one possible implementation, after obtaining the sequences to be clustered, Cheyun clusters the sequences to be clustered and determines the number of sequences to be clustered contained in each clustering cluster, including: establishing a shared projection axis based on the sequences to be clustered, and the shared projection axis is used to maximize the variance of the sequences to be clustered; projecting the sequences to be clustered onto the shared projection axis to obtain the low-dimensional projection corresponding to the sequences to be clustered; obtaining the clustering clusters corresponding to the sequences to be clustered; and counting the number of sequences to be clustered contained in each clustering cluster.
[0056] Optionally, a shared projection axis is established based on the sequence to be clustered, including: randomly assigning each sequence to be clustered to a cluster, calculating the variance of each cluster, and generating a variance matrix for the cluster; performing SVD (singular value decomposition) on the variance matrix to determine the shared projection axis for each cluster, wherein the shared projection axis is used to maximize the variance of the sequence to be clustered. After determining the shared projection axis, the sequence to be clustered is projected onto the shared projection axis to obtain a low-dimensional projection corresponding to the sequence to be clustered. The calculation formula for the low-dimensional projection is as follows:
[0057] P i =X i S
[0058] Among them, P i is the low-dimensional projection of the sequence to be clustered on the corresponding shared projection axis, X i is the sequence to be clustered, and S is the shared projection axis.
[0059] For example, after the projection of the sequence to be clustered is completed, the back-projection sequence of the low-dimensional projection of the sequence to be clustered in the high-dimensional space is calculated to convert the low-dimensional projection P i Re-projecting to the original high-dimensional space of the sequence to be clustered, the calculation formula of the back-projection sequence is as follows:
[0060] Y i =P i S T =X i SS T
[0061] Among them, Y i is the back-projection sequence, S T is the transposed matrix of S.
[0062] In one possible implementation, after obtaining the back-projection sequence, obtaining the cluster corresponding to the sequence to be clustered includes: calculating the projection error of the sequence to be clustered based on the sequence to be clustered and the back-projection sequence, and then adjusting the cluster to which the sequence to be clustered belongs based on the projection error. The same calculation and adjustment are performed for each sequence to be clustered in the same manner, minimizing the projection error of the sequence to be clustered in each cluster, thereby obtaining the final cluster. Optionally, after obtaining the final cluster, the vehicle cloud counts the number of sequences to be clustered contained in each cluster.
[0063] Optionally, the car cloud can also calculate the average sequence of the sequence to be clustered in each cluster, and project the average sequence onto the common projection axis of the cluster as the position of the center point of the cluster, which is used to determine which cluster the data sequence of the battery of the newly added vehicle on the road belongs to, thereby determining whether the battery of the newly added vehicle has a fault.
[0064] In step 205 , the vehicle cloud obtains the fault detection result of the battery corresponding to the sequence to be clustered contained in the cluster based on the number of sequences to be clustered contained in each cluster. The fault detection result is used to indicate whether the battery has a fault.
[0065] Exemplarily, after obtaining the number of sequences to be clustered contained in each cluster, Cheyun obtains the fault detection result of the battery corresponding to the sequence to be clustered contained in the cluster based on the number of sequences to be clustered contained in each cluster, wherein the fault detection result is used to indicate whether the battery has a fault.
[0066] Optionally, based on the number of sequences to be clustered contained in each clustering cluster, the fault detection results of the batteries corresponding to the sequences to be clustered contained in the clustering cluster are obtained, including: when the number of sequences to be clustered contained in the response cluster is the largest, a fault detection result of no fault is obtained for the battery, and fault detection results of faults are obtained for the remaining batteries.
[0067] In one possible implementation, based on the number of sequences to be clustered contained in each cluster, if any cluster contains the largest number of sequences to be clustered, the vehicle cloud obtains a fault detection result that the battery of the vehicle corresponding to the cluster is not faulty, and regards the batteries of the vehicles corresponding to other clusters except the cluster as having faults.
[0068] In step 206 , in response to obtaining a fault detection result indicating that a battery fault exists, the vehicle cloud analyzes the fault category of the battery based on the sequence to be clustered.
[0069] For example, after obtaining a battery fault detection result, if a battery fault is detected, the vehicle cloud analyzes the battery fault category based on the sequence to be clustered. This includes: based on the sequence to be clustered contained in the cluster with the fault, the vehicle cloud determines the battery fault category corresponding to the cluster according to the correspondence between the data sequence and the fault category. The correspondence between the data sequence and the fault category can be determined in advance through experiments.
[0070] The embodiment of the present application collects the operating parameters of the vehicle and the battery, and splices the operating parameters of the vehicle and the battery based on the collection time to obtain a continuous first time series; then preprocesses the first time series to obtain a sequence to be clustered; clusters the sequences to be clustered to determine the number of sequences to be clustered contained in each cluster; then, based on the number of sequences to be clustered contained in the cluster, determines whether the battery corresponding to the cluster has a fault; if the battery has a fault, analyzes the fault category of the battery based on the sequence to be clustered, thereby improving the efficiency and accuracy of battery fault diagnosis and at the same time improving the ability to identify newly added categories of faults.
[0071] See also Figure 3 , an embodiment of the present application provides a battery fault diagnosis device, the device comprising:
[0072] The acquisition module 301 is used to acquire the operating parameters of the vehicle and the operating parameters of the battery of the vehicle, wherein the operating parameters of the vehicle and the operating parameters of the battery include corresponding acquisition times;
[0073] A splicing module 302 is configured to splice the operating parameters of the vehicle and the operating parameters of the battery based on the acquisition time to obtain a continuous first time series;
[0074] A preprocessing module 303 is used to preprocess the first time series to obtain a sequence to be clustered;
[0075] The clustering processing module 304 is used to perform clustering processing on the sequences to be clustered and determine the number of sequences to be clustered contained in each cluster;
[0076] An acquisition module 305 is configured to acquire, based on the number of sequences to be clustered contained in each cluster, a fault detection result of the battery corresponding to the sequences to be clustered contained in the cluster, wherein the fault detection result is used to indicate whether the battery has a fault;
[0077] The analysis module 306 is configured to analyze the fault category of the battery based on the sequence to be clustered in response to obtaining the fault detection result indicating that the battery has a fault.
[0078] In a possible implementation, the splicing module 302 is further configured to clean the operating parameters of the vehicle and the battery, and remove abnormal parameters and noise signals.
[0079] In a possible implementation, the preprocessing module 303 is configured to perform median filtering, smoothing, and root mean square normalization on the first time series to obtain a sequence to be clustered.
[0080] In one possible implementation, the clustering processing module 304 is used to establish a shared projection axis based on the sequence to be clustered, where the shared projection axis is used to maximize the variance of the sequence to be clustered; project the sequence to be clustered onto the shared projection axis to obtain a low-dimensional projection corresponding to the sequence to be clustered; obtain clustering clusters corresponding to the sequence to be clustered; and count the number of sequences to be clustered contained in each clustering cluster.
[0081] In a possible implementation, the clustering processing module 304 is further configured to calculate a back-projection of the low-dimensional projection of the sequence to be clustered in the high-dimensional space.
[0082] In a possible implementation, the acquisition module 305 is configured to acquire a fault detection result indicating that the battery has no faults in response to the cluster containing the largest number of sequences to be clustered, and acquire fault detection results indicating that the remaining batteries have faults.
[0083] The device collects the operating parameters of the vehicle and the battery, and splices the operating parameters of the vehicle and the battery based on the collection time to obtain a continuous first time series; then preprocesses the first time series to obtain a sequence to be clustered; clusters the sequences to be clustered to determine the number of sequences to be clustered contained in each cluster; then, based on the number of sequences to be clustered contained in the cluster, it is determined whether the battery corresponding to the cluster has a fault; if the battery has a fault, the fault category of the battery is analyzed based on the sequence to be clustered, thereby improving the efficiency and accuracy of battery fault diagnosis and at the same time improving the ability to identify newly added categories of faults.
[0084] It should be noted that the apparatus provided in the above embodiments is merely illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.
[0085] In an exemplary embodiment, a computer-readable storage medium is also provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor of a computer device to enable the computer to implement any of the above-mentioned battery fault diagnosis methods.
[0086] In one possible implementation, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
[0087] In an exemplary embodiment, a computer program product or computer program is also provided. The computer program product or computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the above-described battery fault diagnosis methods.
[0088] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the vehicle operating parameters, battery operating parameters, battery fault detection results, and battery fault categories involved in this application are all obtained with full authorization.
[0089] It should be understood that the term "plurality" used herein refers to two or more. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates an "or" relationship between the associated objects.
[0090] It should be noted that the terms "first," "second," etc. (if any) in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the numbers used in this way are interchangeable where appropriate so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the application as detailed in the appended claims.
[0091] The above description is merely an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.
Claims
1. A method for diagnosing battery failure, characterized in that: The method comprises: Collecting operating parameters of a vehicle and an operating parameter of a battery of the vehicle, wherein the operating parameters of the vehicle and the operating parameters of the battery include corresponding collection times; splicing the operating parameters of the vehicle and the operating parameters of the battery based on the acquisition time to obtain a continuous first time series; Preprocessing the first time series to obtain a sequence to be clustered; Performing clustering processing on the sequences to be clustered, and determining the number of sequences to be clustered contained in each cluster; Obtaining, based on the number of sequences to be clustered contained in each cluster, a fault detection result of a battery corresponding to the sequences to be clustered contained in the cluster, wherein the fault detection result is used to indicate whether the battery has a fault; In response to obtaining the fault detection result indicating that the battery has the fault, the fault category of the battery is analyzed based on the sequences to be clustered.
2. The method according to claim 1, characterized in that Before the step of splicing the operating parameters of the vehicle and the operating parameters of the battery based on the acquisition time to obtain a continuous first time series, the method further includes: The operating parameters of the vehicle and the battery are cleaned to remove abnormal parameters and noise signals.
3. The method according to claim 1, characterized in that The preprocessing of the first time series to obtain a sequence to be clustered includes: Perform median filtering, smoothing, and root mean square normalization on the first time series to obtain the sequence to be clustered.
4. The method according to claim 1, wherein The clustering process is performed on the sequences to be clustered to determine the number of sequences to be clustered contained in each cluster, including: Establishing a shared projection axis based on the sequence to be clustered, wherein the shared projection axis is used to maximize the variance of the sequence to be clustered; Projecting the sequence to be clustered onto the shared projection axis to obtain a low-latitude projection corresponding to the sequence to be clustered; Obtaining a cluster corresponding to the sequence to be clustered; The number of sequences to be clustered contained in each cluster is counted.
5. The method according to claim 4, characterized in that Before obtaining the cluster corresponding to the sequence to be clustered, the method further includes: Calculate the back projection of the low-dimensional projection of the sequence to be clustered in the high-dimensional space.
6. The method according to claim 1, characterized in that The obtaining, based on the number of sequences to be clustered contained in each cluster, the fault detection results of the batteries corresponding to the sequences to be clustered contained in the clusters, includes: In response to the cluster containing the largest number of sequences to be clustered, the fault detection result of the battery not having the fault is obtained, and the fault detection results of the remaining batteries having the fault are obtained.
7. A battery fault diagnosis device, characterized in that: The device comprises: A collection module, configured to collect operating parameters of a vehicle and an operating parameter of a battery of the vehicle, wherein the operating parameters of the vehicle and the operating parameters of the battery include corresponding collection times; a splicing module, configured to splice the operating parameters of the vehicle and the operating parameters of the battery based on the acquisition time to obtain a continuous first time series; A preprocessing module, configured to preprocess the first time series to obtain a sequence to be clustered; A clustering processing module, configured to perform clustering processing on the sequences to be clustered and determine the number of sequences to be clustered contained in each cluster; an acquisition module, configured to acquire, based on the number of sequences to be clustered contained in each cluster, a fault detection result of a battery corresponding to the sequences to be clustered contained in the cluster, wherein the fault detection result is used to indicate whether the battery has a fault; An analysis module is configured to, in response to obtaining the fault detection result indicating that the battery has the fault, analyze the fault category of the battery based on the sequence to be clustered.
8. The device according to claim 7, characterized in that The splicing module is also used to clean the operating parameters of the vehicle and the battery, and remove abnormal parameters and noise signals.
9. A computer program product, comprising computer instructions, wherein when the computer instructions are executed by a processor, the steps of the battery fault diagnosis method according to any one of claims 1 to 6 are implemented.
10. A non-transitory computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which is loaded and executed by a processor to implement the battery fault diagnosis method according to any one of claims 1 to 6.