Battery fault detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a battery fault detection method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining vehicle data of a to-be-detected vehicle; determining a vehicle working condition type according to the vehicle data; and determining fault parameters of the battery according to the vehicle working condition type. According to the embodiment of the invention, the accuracy of battery fault detection can be improved.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery fault detection method, device, electronic device and storage medium. Background Art

[0002] At present, the fault detection of power batteries in vehicles is to send the relevant data of the power batteries to the remote fault diagnosis device through the vehicle terminal, and determine whether there is a fault in the power battery based on the rules and threshold settings.

[0003] Although this fault diagnosis method can diagnose battery faults during the current operation of the vehicle, due to the limitation of signal transmission bandwidth, it cannot diagnose a certain operating condition of the vehicle within a certain period of time, resulting in low accuracy of battery fault detection. Summary of the invention

[0004] The present application provides a battery fault detection method, device, electronic device and storage medium, which can improve the accuracy of battery fault detection.

[0005] In a first aspect, an embodiment of the present application provides a battery fault detection method, the method comprising: acquiring vehicle data of a vehicle to be tested, determining a vehicle operating condition type based on the vehicle data, and determining a battery fault parameter based on the vehicle operating condition type.

[0006] Different from determining the fault parameters of the battery based on the data of the vehicle to be tested, the vehicle's operating condition type is not identified, resulting in fewer valid features and attributes of the vehicle data. Since the vehicle data has different characteristics under different operating conditions, the embodiment of the present application determines the vehicle operating condition type based on the vehicle data, and determines the fault parameters of the battery based on the vehicle operating condition type, taking into account that the valid features and attributes of the vehicle data corresponding to different vehicle operating conditions are different, thereby improving the accuracy of battery fault detection.

[0007] In some possible implementations, the battery fault parameters include the battery fault type and the battery fault severity level.

[0008] In some possible implementations, the vehicle data includes vehicle gear, battery state of charge (SOC), current, voltage, power and speed.

[0009] In some possible implementations, determining the battery fault parameters according to the vehicle operating condition type includes: determining a corresponding battery fault detection model according to the vehicle operating condition type, inputting the vehicle data into the corresponding battery fault detection model, and determining the battery fault parameters.

[0010] In some possible implementations, after obtaining vehicle data of the vehicle to be tested, the method further includes: performing linear interpolation processing on missing values ​​of the vehicle data; and determining the vehicle operating condition type based on the vehicle data includes: inputting the processed vehicle data into a condition identification model to obtain the vehicle operating condition type.

[0011] In the above implementation, unlike the data preprocessing method of the current technology which only has simple data cleaning and data filling, but is limited by some missing data, simple filling cannot well restore the data changes of the actual working conditions. In the data preprocessing stage, this implementation will perform linear interpolation processing on vehicle data such as vehicle gear, battery SOC, current, voltage, power, speed, etc. according to the vehicle's timing change data, to remove the impact of missing data caused by sensor signals and other problems, thereby improving the accuracy of detection.

[0012] In some possible implementations, the method further includes: determining a fault severity level of the battery according to a fault type of the battery.

[0013] In some possible implementations, the battery fault types may include abnormal dynamic pressure difference, abnormal static pressure difference and SOC jump, and the vehicle operating condition types include vehicle driving condition, vehicle static condition and vehicle charging condition.

[0014] In a second aspect, an embodiment of the present application provides a battery fault detection device, the device comprising:

[0015] An acquisition unit, used for acquiring vehicle data of a vehicle to be tested;

[0016] a determination unit, configured to determine a vehicle operating condition type according to the vehicle data;

[0017] The determination unit is further used to determine the fault parameters of the battery according to the vehicle operating condition type.

[0018] In some possible implementations, the battery fault parameters include the battery fault type and the battery fault severity level.

[0019] In some possible implementations, the vehicle data includes vehicle gear, battery SOC, current, voltage, power, and speed.

[0020] In some possible implementations, the determination unit determines the battery fault parameters according to the vehicle operating condition type, and is specifically used to: determine a corresponding battery fault detection model according to the vehicle operating condition type, input the vehicle data into the corresponding battery fault detection model, and determine the battery fault parameters.

[0021] In some possible implementations, the device further includes a processing unit, configured to perform linear interpolation processing on missing values ​​of the vehicle data after the acquisition unit acquires the vehicle data of the vehicle to be tested;

[0022] The determination unit determines the vehicle operating condition type according to the vehicle data, and is specifically used to: input the processed vehicle data into a condition identification model to obtain the vehicle operating condition type.

[0023] In some possible implementations, the processing unit is further configured to determine a fault severity level of the battery according to a fault type of the battery.

[0024] In some possible implementations, the battery fault types may include abnormal dynamic pressure difference, abnormal static pressure difference and SOC jump, and the vehicle operating condition types include vehicle driving condition, vehicle static condition and vehicle charging condition.

[0025] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the method in the above-mentioned first aspect and any possible implementation manner thereof when executing the computer program.

[0026] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method in the above-mentioned first aspect and any possible implementation manner thereof is implemented.

[0027] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method in the above-mentioned first aspect and any possible implementation manner thereof.

[0028] The beneficial effects brought about by the second to fifth aspects mentioned above can be referred to the description of the beneficial effects in the first aspect, and will not be repeated here.

[0029] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0031] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0032] Figure 1 It is a flowchart of a battery fault detection method provided in an embodiment of the present application;

[0033] Figure 2 is a calculation flow chart of a working condition identification model of an embodiment of the present application;

[0034] Figure 3 It is a schematic diagram of a training process of a battery fault detection model in an embodiment of the present application;

[0035] Figure 4 It is a schematic diagram of the overall flow of data processing in an embodiment of the present application;

[0036] Figure 5 is a structural schematic diagram of a battery fault detection device provided in an embodiment of the present application;

[0037] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] The terms "first", "second", etc. in the embodiments of the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0040] It should be understood that in the present application, "at least one (item)" means one or more, "more than one" means two or more, and "at least two (items)" means two or three and more than three. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " can indicate that the previous and next associated objects are in an "or" relationship, which refers to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one item (item) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0041] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0042] The execution subject of the battery fault detection method may be a battery fault detection device. For example, the battery fault detection method may be executed by a terminal device or a server or other processing device, wherein the terminal device may be, but is not limited to, various personal computers, laptops, tablet computers, smart phones, and portable wearable devices, and the server may be implemented as an independent server or a server cluster composed of multiple servers. In some possible implementations, the battery fault detection method may be implemented by a processor calling a computer-readable instruction stored in a memory.

[0043] See also Figure 1 , Figure 1 It is a flowchart of a battery fault detection method provided in an embodiment of the present application. The battery fault detection method includes the following steps S101 to S102.

[0044] S101, obtaining vehicle data of a vehicle to be tested.

[0045] Vehicle data may include vehicle gear, battery SOC, current, voltage, power and speed, etc.

[0046] The vehicle data of the vehicle to be tested can be obtained in real time, or the vehicle data can be obtained first, stored in a distributed database, and then the vehicle data of the vehicle to be tested is obtained from the distributed database. Due to the resource limitation of a single database, this embodiment stores the vehicle data in a distributed database, which can solve the problem of resource shortage of a single database for massive vehicle data.

[0047] S102, determining a vehicle operating condition type according to vehicle data.

[0048] After obtaining the vehicle data of the vehicle to be tested, the vehicle operating condition type can be determined according to the vehicle data. In one possible implementation, the vehicle operating condition type can be determined according to the time series change of the vehicle data. For example, for SOC, if it gradually decreases with time, it can be determined that the vehicle operating condition is a vehicle static operating condition. If the SOC gradually increases with time, it can be determined that the vehicle operating condition is a vehicle charging operating condition. It can be understood that the vehicle operating condition can also be determined based on the judgment of SOC in combination with signals such as the gear position of the vehicle and the plug-in status of the charging gun, which is not limited in this embodiment. In another possible implementation, the vehicle data can be input into the operating condition recognition model, and the input operating condition recognition model can output a label corresponding to the vehicle operating condition, and the vehicle operating condition type can be obtained from the label. The vehicle operating condition type may include vehicle driving conditions, vehicle static conditions, vehicle charging conditions, etc. In other words, the vehicle operating condition can be divided according to vehicle data such as the vehicle gear position, power on and off conditions, SOC and other signals through the operating condition recognition model, and the vehicle data can be divided into multiple groups according to different operating conditions. For example, the vehicle driving, static, and charging operating condition labels can be marked. For example, see Figure 2 , Figure 2 is a calculation flow chart of a working condition identification model in an embodiment of the present application. Figure 2 As shown, the vehicle data of the vehicle to be tested can be divided into different operating condition data such as driving condition data 1, driving condition data 2, driving condition data 3, charging condition data 1, static condition data 1... according to pre-set conditions 1, condition 2, condition 3, ..., condition n, and each operating condition characteristic data set can be obtained based on these different operating condition data.

[0049] In a possible implementation, corresponding to the vehicle data acquired in real time in the above steps, the vehicle data can be input into the operating condition identification model in real time to obtain the vehicle operating condition type.

[0050] Another possible implementation method corresponds to obtaining vehicle data from a distributed database in the above step. After obtaining the vehicle data of the vehicle to be tested from the distributed database, the vehicle operating condition type can be determined based on the spark data processing engine. In this embodiment, spark can be used as a data processing engine. The computing framework of spark is a memory computing framework, which can improve the computing speed when facing a large amount of data. Secondly, compared with real-time computing, Spark offline computing has the following advantages: more economical and efficient computing, offline computing can be run in batch form, making full use of cluster resources and avoiding resource waste; faster computing speed and lower cost; more flexible computing, pre-computation can be performed during off-peak hours, and repeated computing can be performed, supporting multiple computing engines and allowing error retry; more complete data, offline computing uses complete historical data, the analysis results are more comprehensive and accurate, and real-time computing may have data loss or incompleteness; it can perform complex calculations that require long-term operation, such as iterative algorithms and graph computing, without delay restrictions; no risk of data loss, offline computing allows repeated computing, and can be retried after failure, without the risk of data loss; more flexible development, multiple programming languages ​​can be used to develop analysis tasks, reducing development difficulty; resources can be reused, offline computing resources can be released after completing the task, with high reuse rate and resource cost saving. In general, offline big data computing has low cost, high calculation accuracy, strong development flexibility, and is suitable for scenarios that require comprehensive analysis and efficient computing (such as vehicle battery fault detection).

[0051] Optionally, before determining the vehicle operating condition type based on the vehicle data, the vehicle data may be preprocessed. Preprocessing may include cleaning, filling, normalizing, and whitening the vehicle data. Among them, filling may be linear interpolation of missing values ​​of the vehicle data. Different from the data preprocessing method of the current technology, which only has simple data cleaning and data filling, it is limited by some missing data, and simple filling cannot well restore the data changes of the real working conditions. Therefore, in the data preprocessing stage, this embodiment can perform linear interpolation on the vehicle data according to the timing changes of the vehicle to remove the impact of missing data caused by problems such as sensor signals, thereby improving the accuracy of detection.

[0052] S103, determining the fault parameters of the battery according to the vehicle operating condition type.

[0053] After determining the vehicle operating condition type according to the vehicle data, the battery fault parameters can be determined according to the vehicle operating condition type. Specifically, a corresponding battery fault detection model is determined according to the vehicle operating condition type, and the vehicle data is input into the corresponding battery fault detection model to determine the battery fault parameters.

[0054] Among them, the fault parameters of the battery may include the fault type of the battery and the fault severity level of the battery. The fault types of the battery may include abnormal dynamic pressure difference, abnormal static pressure difference and SOC jump, among which the pressure difference may refer to the difference between the maximum voltage of a single cell of the battery pack and the minimum voltage of a single cell of the battery pack, the dynamic pressure difference may refer to the pressure difference when the vehicle is in driving or charging, the static pressure difference may refer to the pressure difference when the vehicle is in a stationary state, and the SOC jump may refer to the SOC changing more than the threshold value within a specified time during the discharge or charging process.

[0055] The severity level of the battery fault can be determined based on the type of battery fault. Specifically, the values ​​corresponding to the types of battery faults in the vehicle can be weighted to obtain a numerical value, and the corresponding battery fault severity level can be determined based on the numerical value. For example, the battery fault severity levels are divided into A, B, and C, with the corresponding values ​​for A being 0-10, B being 11-20, and C being 21-30. For the detected vehicle, the label of the fault type of the battery of the vehicle output by the battery fault detection model is a dynamic pressure difference abnormality (assuming the corresponding value is 5) and an SOC jump (assuming the corresponding value is 10), then the battery fault severity level = 5 + 2 * 10 = 25, so it can be obtained that the battery fault severity level is C.

[0056] Among them, the specific implementation of the battery fault detection model can be as follows:

[0057] See also Figure 3 , Figure 3 FIG. 1 is a schematic diagram of a training process of a battery fault detection model according to an embodiment of the present application. Figure 3 As shown, first, the original data set can be obtained, and the working condition features of the original data set can be extracted to obtain each working condition feature data set. Each working condition feature data set can be bootstrap resampled to obtain k bootstrap subsample sets. K decision trees are constructed through the CART algorithm and combined to obtain a random forest algorithm classifier. The random forest algorithm classifier is distributedly calculated to obtain the vehicle fault results for each working condition. The specific implementation can be as follows:

[0058] Obtain vehicle data of different working conditions of multiple faulty vehicles to obtain original data sets corresponding to different working conditions. For example, a list of faulty vehicles can be obtained from an application layer database, and vehicle data of different working conditions of multiple faulty vehicles can be obtained according to the VIN numbers of the faulty vehicles to obtain original data sets corresponding to different working conditions.

[0059] According to the original data sets corresponding to the different working conditions, a multi-classification model based on random forest is built. That is to say, a feature multi-classifier training model can be established using random forest to obtain battery fault detection models corresponding to different working conditions. For example, data can be divided according to the working conditions, and battery fault detection models corresponding to the three working conditions of driving, charging, and stationary can be built respectively.

[0060] The random forest algorithm is an algorithm based on a feature set. Assume that the random forest algorithm consists of k classifiers h1(T), h2(T), …, h k (T), expressed as: H = {h1(T), h2(T), …, h k (T)}. Where: T is the input feature set, h q (T), q = 1, 2, ..., k is the base classifier, each classifier is a decision tree generated by the CART algorithm, and the classification results of the k decision trees are voted according to the principle of minority obeys majority, and the voting result is the classification result of the random forest.

[0061] The bootstrap resampling method is used to perform k random samplings with replacement from the original data set corresponding to the first working condition containing n samples to form k bootstrap sub-sample sets, each of which includes n samples. The first working condition is any working condition among multiple working conditions, and n and k are positive integers. For each bootstrap sub-sample set, the CART algorithm is used to construct a decision tree. The algorithm can use the "Gini index" as an indicator for dividing the optimal feature and the optimal split value. Assume that the currently selected feature t i There are C categories in it, and its Gini value can be as follows:

[0062]

[0063] Use k bootstrap subsample sets to generate k decision trees to form a random forest. When each decision tree grows, it randomly extracts from a set T containing k features. The features are taken as a feature subset, and the feature subset is used as the partition attribute in the decision tree growth process. The decision tree is grown according to the principle of minimum Gini value. The constructed k decision trees are used as the base classifier group of random forest to divide the feature data into fault categories. In other words, the classification results of k decision trees can be combined, and the classification results of random forest can be obtained by voting based on the principle of minority obeys majority, so as to realize fault diagnosis.

[0064] After the battery fault detection model is trained, the vehicle data can be input into the battery fault detection model corresponding to the working condition according to the vehicle working condition type, so that the fault detection result of the battery under the corresponding working condition can be obtained. First, the vehicle working condition type of the vehicle data of the vehicle to be tested is determined, and the fault parameters of the battery are determined according to the vehicle working condition type. This can not only effectively reduce the amount of data input into the model, but also improve the calculation speed of the battery fault detection model, thereby improving the efficiency of battery fault detection. Secondly, unlike determining the fault parameters of the battery according to the vehicle data to be tested, the working condition type of the vehicle is not identified, resulting in fewer valid features and attributes of the vehicle data, and the features generated by unsupervised classification have certain errors. Since the vehicle data has different characteristics under different working conditions, the embodiment of the present application determines the vehicle working condition type according to the vehicle data, and determines the battery fault parameters according to the vehicle working condition type, taking into account the different valid features and attributes of the vehicle data corresponding to different vehicle working conditions, thereby improving the accuracy of battery fault detection.

[0065] Optionally, the fault parameters of the battery output by the battery fault detection model may also be further stored in the original data set used to train the battery fault detection model, so as to continuously update the trained battery fault detection model and continuously improve the accuracy of the model.

[0066] In combination with the above method embodiment, in a specific embodiment, please refer to Figure 4 , Figure 4 This is a schematic diagram of the overall process of data processing in an embodiment of the present application. Figure 4 As shown, first obtain the statistical data of the working conditions of the faulty vehicle list stored in the distributed system from the application layer database, input the segmented data of the working conditions of the faulty vehicle into the model for training the model to obtain the battery fault detection model. Obtain the vehicle data of the vehicle to be tested from the distributed system, first input the working condition recognition model to determine the working condition type of the vehicle data, and then input the vehicle data into the corresponding battery fault detection model according to the working condition type, so that the fault parameters of the vehicle battery can be detected on the battery fault detection system platform.

[0067] Unlike the current practice of extracting data from the big data platform to the local computer for calculation, the calculation speed and efficiency will also be greatly affected due to the limitation of single machine resources. This application is based on a distributed machine learning framework to perform distributed computing and training on massive big data to achieve a balance between training speed and training accuracy. Because distributed computing can quickly process massive amounts of data, the training model also requires a data set with a large enough sample size to achieve better results. Therefore, the use of a distributed computing framework can not only improve the calculation speed of the model, but also improve the model accuracy, and obtain a high hit rate to achieve the purpose of detecting battery failures in an actual production environment.

[0068] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0069] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0070] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a battery fault detection device provided in an embodiment of the present application. The battery fault detection device 500 includes:

[0071] An acquisition unit 501 is used to acquire vehicle data of a vehicle to be tested;

[0072] A determination unit 502, configured to determine a vehicle operating condition type according to the vehicle data;

[0073] The determination unit 502 is further configured to determine a fault parameter of the battery according to the vehicle operating condition type.

[0074] In some possible implementations, the battery fault parameters include the battery fault type and the battery fault severity level.

[0075] In some possible implementations, the vehicle data includes vehicle gear, battery SOC, current, voltage, power, and speed.

[0076] In some possible implementations, the determination unit 502 determines the battery fault parameters according to the vehicle operating condition type, and is specifically used to: determine the corresponding battery fault detection model according to the vehicle operating condition type, input the vehicle data into the corresponding battery fault detection model, and determine the battery fault parameters.

[0077] In some possible implementations, the device further includes a processing unit 503, configured to perform linear interpolation processing on missing values ​​of the vehicle data after the acquisition unit acquires the vehicle data of the vehicle to be tested;

[0078] The determination unit 502 determines the vehicle operating condition type according to the vehicle data, and is specifically used to: input the processed vehicle data into a operating condition identification model to obtain the vehicle operating condition type.

[0079] In some possible implementations, the processing unit 503 is further configured to determine a fault severity level of the battery according to the fault type of the battery.

[0080] In some possible implementations, the battery fault types may include abnormal dynamic pressure difference, abnormal static pressure difference and SOC jump, and the vehicle operating condition types include vehicle driving condition, vehicle static condition and vehicle charging condition.

[0081] For the specific definition of the battery fault detection device, please refer to the definition of the battery fault detection method above, which will not be repeated here. Each unit in the above-mentioned battery fault detection device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned units 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 operations corresponding to the above-mentioned units.

[0082] See also Figure 6 , Figure 6 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 600 includes a memory 601 and a processor 602. Optionally, the electronic device 600 also includes a communication interface 603 and a bus 604. The memory 601, the processor 602 and the communication interface 603 are connected to each other through the bus 604. The memory 601 stores a computer program, and the processor 602 is used to execute the computer program stored in the memory 601 to implement the methods in the above-mentioned method embodiments.

[0083] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the methods in the above-mentioned method embodiments are implemented.

[0084] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in the above-mentioned method embodiments is implemented.

[0085] It should be understood that the memory / readable storage medium in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory may be a hard disk drive (HDD), a solid-state drive (SSD), a read-only memory (ROM) or a flash memory, etc. The volatile memory may be a random access memory (RAM) or an external cache memory. As an illustration and not limitation, RAM may be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0086] The processor in the embodiments of the present application may be a combination of one or more processing modules such as a central processing unit (CPU), a graphics processing unit (GPU) or a microprocessor (MPU), and may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0087] 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.

[0088] The above-mentioned 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 invention patent. It should be pointed out that, for ordinary technicians in this field, 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.

Claims

1. A battery failure detection method, characterized in that: The method comprises: Obtain vehicle data of the vehicle to be tested; determining a vehicle operating condition type according to the vehicle data; A fault parameter of the battery is determined according to the vehicle operating condition type.

2. The method according to claim 1, characterized in that The battery fault parameters include the battery fault type and the battery fault severity level.

3. The method according to claim 2, characterized in that The vehicle data includes vehicle gear, battery state of charge SOC, current, voltage, power and speed.

4. The method according to any one of claims 1 to 3, characterized in that: The determining of the fault parameters of the battery according to the vehicle operating condition type includes: A corresponding battery fault detection model is determined according to the working condition type of the vehicle, the vehicle data is input into the corresponding battery fault detection model, and the fault parameters of the battery are determined.

5. The method according to claim 4, characterized in that After obtaining the vehicle data of the vehicle to be tested, the method further includes: Performing linear interpolation processing on the missing values ​​of the vehicle data; The determining the vehicle operating condition type according to the vehicle data includes: The processed vehicle data is input into the operating condition identification model to obtain the vehicle operating condition type.

6. The method according to claim 5, characterized in that The method further comprises: A fault severity level of the battery is determined according to a fault type of the battery.

7. The method according to claim 2, characterized in that: The battery failure types include abnormal dynamic pressure difference, abnormal static pressure difference and SOC jump, and the vehicle operating condition types include vehicle driving condition, vehicle static condition and vehicle charging condition.

8. A battery fault detection device, characterized in that: The method comprises a unit for executing the battery failure detection method as claimed in claims 1-7.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images