Battery fault diagnosis method and system based on clustering and random anomaly selection

Abstract

The invention belongs to the technical field of battery management, and provides a clustering and random anomaly selection algorithm-based battery fault diagnosis method, which comprises the following steps of: processing voltage data of each battery cell in a battery module to obtain a plurality of modal components, and selecting a static component and a dynamic component in the modal components; extracting progressive fault features from the static components, extracting sudden fault features from the dynamic components, and then respectively extracting data points; clustering the two extracted data points, introducing a random anomaly selection algorithm to perform intra-cluster anomaly scoring on each cluster obtained by clustering to obtain two anomaly scores of each battery when the battery module operates normally, and setting a progressive fault threshold value and a sudden fault threshold value; and acquiring real-time data of the battery module, calculating two abnormal scores of all the single batteries in the battery module, comparing the two abnormal scores with corresponding threshold values, and if the two abnormal scores exceed the corresponding threshold values, determining that a corresponding fault occurs. Rapid diagnosis can be realized without training a model.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery management, and in particular relates to a battery fault diagnosis method and system based on clustering and random abnormality selection. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Lithium-ion batteries are widely used in electric vehicles, energy storage systems and other fields due to their long life, high energy density and low self-discharge rate. In the actual application of electric vehicles and energy storage systems, various internal and external faults may occur in the battery during operation, leading to performance problems and potential serious consequences such as thermal runaway, fire or explosion. Therefore, timely diagnosis of battery faults and prevention of their further development are crucial to ensure the safe and reliable operation of the battery system.

[0004] At present, the methods for battery short circuit fault diagnosis can be roughly divided into model-based methods and data-driven methods.

[0005] 1) Model-based method: The model-based short-circuit fault diagnosis method first establishes a battery model by analyzing the physical and chemical principles of the battery. Then the fault is detected by comparing the model parameters or the estimated battery state with the actual value. This method can realize online diagnosis, but it has problems such as high complexity, large amount of calculation and susceptibility to external interference.

[0006] 2) Data-driven method: The data-driven short-circuit diagnosis method learns features from historical fault battery data to form a nonlinear black box mapping model for fault diagnosis. It uses computational intelligence to simulate the inherent nonlinearity of the battery and uses statistical techniques to identify subtle deviations caused by faults. However, this method has the problem of low model diagnostic accuracy and poor robustness due to the lack of high-quality fault data for training. Summary of the invention

[0007] In order to solve the above problems, the present invention proposes a battery fault diagnosis method and system based on clustering and random anomaly selection. The present invention can realize rapid diagnosis of battery short circuit faults with high accuracy and little or no demand for high-quality fault data, thereby ensuring safe and reliable operation of the battery.

[0008] According to some embodiments, the present invention adopts the following technical solutions:

[0009] A battery fault diagnosis method based on clustering and random abnormal selection includes the following steps:

[0010] S1: Obtain historical data of the battery module to be diagnosed when it is operating normally;

[0011] S2: Processing the voltage data of each battery cell in the battery module to obtain multiple modal components, removing the high-frequency components therein, and obtaining static components and dynamic components;

[0012] S3: extracting progressive fault features from the static component, extracting sudden fault features from the dynamic component, and extracting data points from the progressive fault features and the sudden fault features respectively;

[0013] S4: Clustering the two extracted data points, and for each cluster obtained by clustering, introducing a random anomaly selection algorithm to perform intra-cluster anomaly scoring, obtaining two anomaly scores of each battery when the battery module is operating normally, and setting a gradual fault threshold and a sudden fault threshold;

[0014] S5: Obtain real-time data of the battery module, execute steps S2-S4 to calculate two abnormality scores of all single cells in the battery module, and compare them with the gradual failure threshold or the sudden failure threshold respectively. If the corresponding threshold is exceeded, it is determined that the corresponding fault has occurred.

[0015] As an optional implementation, the battery module is connected in series, the number of batteries in the battery module and the cycle conditions are selected according to actual applications, and the cycle conditions of the conditions include the current rate of battery charging and discharging, discharge depth, temperature and cut-off voltage.

[0016] As an optional implementation, the historical data includes voltage and current data of each battery and the corresponding data collection time.

[0017] As an optional implementation, in step S2, the variational modal decomposition algorithm is used to adaptively decompose the voltage data of each battery to obtain m modal components: {IMF1, IMF2, ..., IMF m}, m is the preset number of decompositions.

[0018] As a further implementation, only the static component IMF1 for characterizing the battery voltage trend and the IMF2 for reflecting the dynamic fault information are used, and other high-frequency components are regarded as noise and removed. The static components of all batteries are The dynamic component is

[0019] As an optional implementation, the process of extracting the progressive fault feature from the static component includes:

[0020]

[0021] Among them, z i (t) is the standard score of battery i at time t, is the static component of battery i at time t, and T represents the length of the time series involved in the calculation. represents the amplification degree. The larger it is, the more sensitive it is to abnormal data. N is the number of batteries in the battery module, and m is the preset decomposition quantity.

[0022] As an alternative implementation, the process of extracting sudden fault features from the dynamic component includes: using the Pearson correlation coefficient method to process the dynamic component to extract fault features. The specific formula is:

[0023]

[0024] where r i (t) is the correlation coefficient between battery i and the average value of the dynamic components of each battery at time t. is the dynamic component of battery i at time t, Y is the average value sequence of the dynamic components of each battery, is the average value of the dynamic components within the time window.

[0025] As an alternative implementation, the process of extracting data points from the progressive fault features and sudden fault features respectively includes using a sliding window to process the progressive fault features and sudden fault features to obtain static component data points and dynamic component data points, and the widths of the sliding windows in the two data point extraction processes are the same.

[0026] As an alternative implementation, the process in step S4 includes:

[0027] Using the K-means algorithm to cluster the static component data points and dynamic component data points respectively to obtain K clusters: {C1, C2, …, C k}; C i is the i-th cluster, where i = 1, 2, …, K;

[0028] For each point x j ∈ C k , determine its neighborhood: N k (x j ) = {x l ∈ C k : d(x j , x l ) < r}, where r is the neighborhood radius and d(x j , x l ) is the distance metric;

[0029] For each point x j within the cluster, use an unsupervised anomaly detection algorithm to calculate the anomaly score and calculate the local density of point x j ; From the neighborhood N k (x j) randomly select m samples S = {x j1 ,x j2 ,…,x jm}; Calculate its local density: Where σ is the variance of the sample; calculate the anomaly score:

[0030] For the anomaly scores calculated based on the static component data points and the dynamic component data points, the maximum values ​​are set as the gradual failure threshold and the sudden failure threshold respectively.

[0031] As an optional implementation, in step S5, the sudden abnormality score is compared with the sudden failure threshold. If the sudden abnormality score is greater than the sudden failure threshold, it is determined that a sudden failure has occurred; conversely, the gradual abnormality score is compared with the gradual failure threshold. If the gradual abnormality score is greater than the gradual failure threshold, it is determined that a gradual failure has occurred; if both abnormality scores are less than the corresponding thresholds, it is determined that the battery pack is operating normally.

[0032] A battery fault diagnosis system based on clustering and random anomaly selection, comprising:

[0033] A data acquisition module is configured to acquire historical data of the battery module to be diagnosed when it is operating normally, and to acquire real-time data of the battery module;

[0034] The modal decomposition module is configured to process the voltage data of each cell in the battery module to obtain multiple modal components, remove the high-frequency components therein, and obtain static components and dynamic components;

[0035] A fault feature extraction module is configured to extract a progressive fault feature from the static component, extract a sudden fault feature from the dynamic component, and extract data points from the progressive fault feature and the sudden fault feature respectively;

[0036] The anomaly scoring module is configured to cluster the two extracted data points, and introduce a random anomaly selection algorithm to perform intra-cluster anomaly scoring for each cluster obtained by clustering, thereby obtaining two anomaly scores of each battery when the battery module is operating normally, and setting a gradual fault threshold and a sudden fault threshold;

[0037] The fault diagnosis module is configured to call the modal decomposition module, the fault feature extraction module and the anomaly scoring module based on real-time data, calculate the two anomaly scores of all single cells in the battery module, and compare them with the gradual fault threshold or the sudden fault threshold respectively. If the corresponding threshold is exceeded, it is determined that the corresponding fault has occurred.

[0038] An electronic device comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above method are completed.

[0039] The electronic device may be a battery controller or a battery management system.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention uses a variational mode decomposition algorithm to decompose the battery voltage sequence, and extracts a static component reflecting the characteristics of progressive faults and a dynamic component reflecting the characteristics of sudden faults. Then, different fault feature extraction methods are used to process the components according to the characteristics of the two components to extract fault features. Finally, the two extracted fault features are respectively input into a diagnostic algorithm combining K-means clustering and random anomaly selection algorithm to complete the rapid and accurate diagnosis of short-circuit faults.

[0042] The fault diagnosis method proposed in the present invention can realize rapid diagnosis of short-circuit faults without training models, and gets rid of the problem that traditional machine learning methods cannot effectively train models due to lack of high-quality fault data.

[0043] The present invention extracts static components and dynamic components from the decomposed modal components, and processes them using different feature extraction methods respectively, thereby avoiding mutual interference between the two components and realizing the diagnosis of progressive faults and sudden faults.

[0044] The present invention can effectively cope with battery fault diagnosis scenarios with complex distribution or multimodal data by combining the global clustering results of K-means and the local anomaly scoring of the random anomaly selection algorithm, thereby effectively improving the diagnosis speed and ensuring high diagnostic accuracy.

[0045] The method developed by the present invention has data-driven characteristics, does not involve complex battery electrochemical mechanisms, and can be conveniently used for fault diagnosis of various types of batteries without the need to construct different battery models under different circumstances like model-based methods.

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0048] Figure 1 A flowchart of a battery short circuit fault diagnosis method provided by an embodiment;

[0049] Figure 2 A flowchart for performing fault diagnosis provided by an embodiment;

[0050] Figure 3 A schematic diagram of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0052] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0053] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0054] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0055] Embodiment 1

[0056] A battery fault diagnosis method based on clustering and random anomaly selection, such as Figure 1 As shown, the following steps are included:

[0057] S1: Obtain historical data of the battery module to be diagnosed when it is operating normally.

[0058] In this embodiment, the battery module is connected in series, the number of batteries N in the module and the cycle conditions are selected according to the actual application, and the cycle conditions of the operating conditions include the current rate of battery charging and discharging, discharge depth, temperature and cut-off voltage; the collected battery module historical data includes but is not limited to each battery voltage, current data and the corresponding data collection time.

[0059] S2: Use the variational modal decomposition algorithm to process the voltage data of each cell in the battery module to obtain m modal components, and take the low-frequency components.

[0060] Specifically, the variational mode decomposition algorithm is used to adaptively decompose the voltage data of each battery to obtain m modal components: {IMF1,IMF2,…,IMF m}, m is the preset number of decompositions. Only the static component IMF1 that best represents the battery voltage trend and IMF2 that best reflects dynamic fault information are used, and other high-frequency components are treated as noise and removed. The static components of all batteries are The dynamic component is

[0061] S3: The obtained static components of each battery are processed to extract the progressive fault features, and then the sudden fault features are extracted from the dynamic components using the Pearson correlation coefficient. Finally, the sliding window is used to extract data points from the two fault features respectively.

[0062] The specific steps are:

[0063] S31: Process the static component to extract the progressive fault characteristics. The specific formula is:

[0064]

[0065] Where z i (t) is the standard score of battery i at time t, is the static component of battery i at time t, T represents the length of the time series involved in the calculation, Indicates the degree of amplification. The larger it is, the more sensitive it is to abnormal data.

[0066] S32: Use the Pearson correlation coefficient method to process the dynamic component to extract fault characteristics. The specific formula is:

[0067]

[0068] Where r i (t) is the correlation coefficient of battery i at time t with the average value of the dynamic components of each battery, is the dynamic component of battery i at time t, Y is the average value sequence of the dynamic components of each battery, is the average value of the dynamic component within the time window.

[0069] S33: Processing z using sliding windows i (t) and r i (t) Get the static component data point x i ={z i (t-W+1), z i (t-W+2),…,z i (t)}; i = 1, 2, ..., N, and the dynamic component data point n i = {r i (t-W+1), r i (t-W+2),…,r i(t)}; i = 1, 2, ..., N. Where W represents the sliding window width, all battery data points x i and n i They constitute static component input and dynamic component input respectively.

[0070] S4: Input the two extracted data points into the diagnostic algorithm to obtain two abnormal scores of each battery when the battery module is operating normally, and take the maximum value as the gradual failure threshold J1 and the sudden failure threshold J2.

[0071] The diagnostic algorithm combines K-means clustering with random anomaly selection algorithm. The specific steps of the algorithm and the method of setting the threshold are as follows:

[0072] S41: First, the input data points are clustered using the K-means algorithm to obtain K clusters: {C1, C2, …, C k}.

[0073] S42: Calculate the abnormal score within each cluster, specifically for each cluster C k , perform the following steps:

[0074] S421: For each point x j ∈C k , determine its neighborhood:

[0075] N k (x j )={x l ∈C k :d(x j ,x l ) <r}

[0076] Where r is the neighborhood radius, d(x j ,x l ) is the distance metric.

[0077] S432: For each point x in the cluster j , execute the SOS algorithm to calculate the anomaly score:

[0078] (1) Calculate point x j The local density

[0079]

[0080] (2) From the neighborhood N k (x j ) randomly select m samples S = {x j1 ,x j2 ,…,x jm};

[0081] (3) Calculate its local density:

[0082]

[0083] Where σ is the sample variance.

[0084] (4) Calculate the anomaly score:

[0085]

[0086] S44: The static component input and the dynamic component input extracted by the sliding window are respectively input into the diagnostic algorithm to obtain the gradual abnormality score and the sudden abnormality score of each battery when the battery module is operating normally, and the maximum value is set as the gradual fault threshold J1 and the sudden fault threshold J2 respectively.

[0087] S5: Obtain real-time data of the battery module, calculate the two abnormality scores of all single cells in the battery module using the same calculation method, and compare them with thresholds J1 and J2 respectively. If the threshold is exceeded, it is determined that a fault has occurred and the fault is classified.

[0088] The battery module is the same as the battery module in step S1. The specific detection method is: Figure 2 As shown, the real-time data of the battery module is obtained, and the two abnormality scores of all the single cells in the battery module are calculated in the same way. First, the sudden abnormality score is compared with the sudden fault threshold J2. If the sudden abnormality score is greater than J2, it is determined that a sudden fault has occurred. Conversely, the gradual abnormality score is compared with the gradual fault threshold J1. If the gradual abnormality score is greater than J1, it is determined that a gradual fault has occurred. If both abnormality scores are less than the threshold, it is determined that the battery pack is working normally.

[0089] Embodiment 2

[0090] A battery fault diagnosis system based on clustering and random anomaly selection, comprising:

[0091] A data acquisition module is configured to acquire historical data of the battery module to be diagnosed when it is operating normally, and to acquire real-time data of the battery module;

[0092] The execution process of this module can be specifically referred to the process of obtaining data in steps S1 and S4 of the first embodiment, which will not be repeated here.

[0093] The modal decomposition module is configured to process the voltage data of each cell in the battery module to obtain multiple modal components, remove the high-frequency components therein, and obtain static components and dynamic components;

[0094] The execution process of this module may be specifically referred to the process of step S2 of the first embodiment, which will not be repeated here.

[0095] A fault feature extraction module is configured to extract a progressive fault feature from the static component, extract a sudden fault feature from the dynamic component, and extract data points from the progressive fault feature and the sudden fault feature respectively;

[0096] The execution process of this module may refer to the process of step S3 of the first embodiment for details, which will not be repeated here.

[0097] The anomaly scoring module is configured to cluster the two extracted data points, and introduce a random anomaly selection algorithm to perform intra-cluster anomaly scoring for each cluster obtained by clustering, thereby obtaining two anomaly scores of each battery when the battery module is operating normally, and setting a gradual fault threshold and a sudden fault threshold;

[0098] The execution process of this module may be specifically referred to the process of step S4 of the first embodiment, which will not be repeated here.

[0099] The fault diagnosis module is configured to call the modal decomposition module, the fault feature extraction module and the anomaly scoring module based on real-time data, calculate the two anomaly scores of all single cells in the battery module, and compare them with the gradual fault threshold or the sudden fault threshold respectively. If the corresponding threshold is exceeded, it is determined that the corresponding fault has occurred.

[0100] The execution process of this module may be specifically referred to the process of step S5 of the first embodiment, which will not be described in detail here.

[0101] It can be understood that the above-mentioned units / modules can be separately or completely combined into one or several other units / modules, or one (some) of the units can be further divided into multiple functionally smaller units, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application.

[0102] The above modules of the system are divided based on logical functions. In practical applications, the function of one module can also be implemented by multiple modules, or the functions of multiple modules can be implemented by one module. For example, the modal decomposition module of this embodiment may include:

[0103] The decomposition module is used to adaptively decompose the voltage data of each battery using the variational mode decomposition algorithm to obtain m modal components: {IMF1,IMF2,…,IMF m}, m is the preset number of decompositions;

[0104] The selection module is used to select the static component IMF1 used to characterize the battery voltage trend and IMF2 used to reflect the dynamic fault information. Other high-frequency components are treated as noise and removed. The static components of all batteries are The dynamic component is

[0105] Similarly, in other embodiments of the present application, the system may also include other units / modules. In actual applications, these functions may also be implemented with the assistance of other units, and may be implemented by collaboration of multiple units.

[0106] According to another embodiment of the present application, the system described in this embodiment can be constructed and the method of Embodiment 1 can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Embodiment 1 on a general computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0107] Embodiment 3

[0108] This implementation provides an electronic device, such as Figure 3 As shown, the electronic device includes a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer-readable storage medium 1003 may be connected via a bus or other means.

[0109] Among them, the communication interface 1002 is used to receive and send data, the computer-readable storage medium 1003 can be stored in the memory of the electronic device, the computer-readable storage medium 1003 is used to store a computer program, the computer program includes program instructions, and the processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0110] Processor 1001 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions.

[0111] The processor 1001 is configured to execute the following process:

[0112] S1: Obtain historical data of the battery module to be diagnosed when it is operating normally;

[0113] S2: Processing the voltage data of each battery cell in the battery module to obtain multiple modal components, removing the high-frequency components therein, and obtaining static components and dynamic components;

[0114] S3: extracting progressive fault features from the static component, extracting sudden fault features from the dynamic component, and extracting data points from the progressive fault features and the sudden fault features respectively;

[0115] S4: Clustering the two extracted data points, and for each cluster obtained by clustering, introducing a random anomaly selection algorithm to perform intra-cluster anomaly scoring, obtaining two anomaly scores of each battery when the battery module is operating normally, and setting a gradual fault threshold and a sudden fault threshold;

[0116] S5: Obtain real-time data of the battery module, execute steps S2-S4 to calculate two abnormality scores of all single cells in the battery module, and compare them with the gradual failure threshold or the sudden failure threshold respectively. If the corresponding threshold is exceeded, it is determined that the corresponding fault has occurred.

[0117] Or the process of steps S1-S5 in embodiment 1 is not repeated here.

[0118] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.

Claims

1. A battery fault diagnosis method based on clustering and random anomaly selection, characterized in that: The following steps are involved: S1: Obtain historical data of the battery module to be diagnosed when it is operating normally; S2: Processing the voltage data of each battery cell in the battery module to obtain multiple modal components, removing the high-frequency components therein, and obtaining static components and dynamic components; S3: extracting progressive fault features from the static component, extracting sudden fault features from the dynamic component, and extracting data points from the progressive fault features and the sudden fault features respectively; S4: Clustering the two extracted data points, and for each cluster obtained by clustering, introducing a random anomaly selection algorithm to perform intra-cluster anomaly scoring, obtaining two anomaly scores of each battery when the battery module is operating normally, and setting a gradual fault threshold and a sudden fault threshold; S5: Obtain real-time data of the battery module, execute steps S2-S4 to calculate two abnormality scores of all single cells in the battery module, and compare them with the gradual failure threshold or the sudden failure threshold respectively. If the corresponding threshold is exceeded, it is determined that the corresponding fault has occurred.

2. A battery fault diagnosis method based on clustering and random abnormal selection as claimed in claim 1, characterized in that: The battery module is connected in series, the number of batteries in the battery module and the cycle conditions are selected according to the actual application, and the cycle conditions of the working conditions include the current rate, discharge depth, temperature and cut-off voltage of the battery charge and discharge; The historical data includes the voltage and current data of each battery and the corresponding data collection time.

3. The battery fault diagnosis method based on clustering and random abnormal selection according to claim 1, characterized in that: In step S2, the variational modal decomposition algorithm is used to adaptively decompose the voltage data of each battery to obtain m modal components: {IMF1, IMF2, ..., IMF m }, m is the preset number of decompositions; Only the static component IMF1 used to characterize the battery voltage trend and IMF2 used to reflect the dynamic fault information are used, and other high-frequency components are treated as noise and removed. The static components of all batteries are The dynamic component is 4. The battery fault diagnosis method based on clustering and random abnormal selection according to claim 1, characterized in that: The process of extracting the progressive fault characteristics from the static component includes: Among them, z i (t) is the standard score of battery i at time t, is the static component of battery i at time t, T represents the length of the time series involved in the calculation, Indicates the degree of amplification. The larger the amplification, the more sensitive it is to abnormal data. N is the number of batteries in the battery module, and m is the preset number of decompositions.

5. The battery fault diagnosis method based on clustering and random abnormal selection according to claim 1, characterized in that: The process of extracting sudden fault features from dynamic components includes: using the Pearson correlation coefficient method to process the dynamic components to extract fault features. The specific formula is: Among them, r i (t) is the correlation coefficient of battery i at time t with the average value of the dynamic components of each battery, is the dynamic component of battery i at time t, Y is the average value sequence of the dynamic components of each battery, is the average value of the dynamic component within the time window.

6. A battery fault diagnosis method based on clustering and random abnormal selection as claimed in claim 1, characterized in that: The process of extracting data points from progressive fault features and sudden fault features respectively includes using a sliding window to process progressive fault features and sudden fault features to obtain static component data points and dynamic component data points, and the width of the sliding window in the two data point extraction processes is the same.

7. The battery fault diagnosis method based on clustering and random abnormal selection according to claim 1, characterized in that: The process in step S4 includes: The static component data points and dynamic component data points are clustered using the K-means algorithm to obtain K clusters: {C1, C2, …, C k }, C i is the i-th cluster, i=1,2,…,K; For each point x j ∈ C k , determine its neighborhood: N k (x j ) = {x l ∈ C k : d(x j , x l ) < r}, where r is the neighborhood radius and d(x j , x l ) is the distance metric; For each point x in the cluster j , use the unsupervised anomaly detection algorithm to calculate the anomaly score and calculate the point x j The local density From the neighborhood N k (x j ) randomly select m samples S = {x j1 ,x j2 ,…,x jm }; Calculate its local density: Where σ is the variance of the sample; calculate the anomaly score: For the anomaly scores calculated based on the static component data points and the dynamic component data points, the maximum values ​​are set as the gradual failure threshold and the sudden failure threshold respectively.

8. The battery fault diagnosis method based on clustering and random abnormal selection according to claim 1, characterized in that: In the step S5, the sudden abnormality score is compared with the sudden failure threshold. If the sudden abnormality score is greater than the sudden failure threshold, it is determined that a sudden failure has occurred; conversely, the gradual abnormality score is compared with the gradual failure threshold. If the gradual abnormality score is greater than the gradual failure threshold, it is determined that a gradual failure has occurred; if both abnormality scores are less than the corresponding thresholds, it is determined that the battery pack is operating normally.

9. A battery fault diagnosis system based on clustering and random anomaly selection, characterized in that: include: A data acquisition module is configured to acquire historical data of the battery module to be diagnosed when it is operating normally, and to acquire real-time data of the battery module; The modal decomposition module is configured to process the voltage data of each cell in the battery module to obtain multiple modal components, remove the high-frequency components therein, and obtain static components and dynamic components; A fault feature extraction module is configured to extract a progressive fault feature from the static component, extract a sudden fault feature from the dynamic component, and extract data points from the progressive fault feature and the sudden fault feature respectively; The anomaly scoring module is configured to cluster the two extracted data points, and introduce a random anomaly selection algorithm to perform intra-cluster anomaly scoring for each cluster obtained by clustering, thereby obtaining two anomaly scores of each battery when the battery module is operating normally, and setting a gradual fault threshold and a sudden fault threshold; The fault diagnosis module is configured to call the modal decomposition module, the fault feature extraction module and the anomaly scoring module based on real-time data, calculate the two anomaly scores of all single cells in the battery module, and compare them with the gradual fault threshold or the sudden fault threshold respectively. If the corresponding threshold is exceeded, it is determined that the corresponding fault has occurred.

10. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps in the method according to any one of claims 1 to 8 are completed.

Images