Battery fault identification method, vehicle and computer program product

Abstract

The invention discloses a battery fault identification method, a vehicle and a computer program product, and relates to the technical field of vehicles. The method comprises the following steps: obtaining battery cell test data, and the battery cell test data is obtained by performing an electrochemical impedance test on a test battery cell with a known fault state; performing feature extraction on the battery cell test data, and determining a feature frequency and an impedance feature value; acquiring real-time impedance data of a to-be-detected battery cell of the vehicle power battery under the characteristic frequency; and carrying out clustering analysis on the impedance characteristic value and the real-time impedance data, and identifying the fault state of the to-be-detected battery cell. According to the invention, the technical problem of poor cell fault identification accuracy of a scheme for identifying faults based on external characteristics of a battery in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a battery fault identification method, a vehicle and a computer program product. Background Art

[0002] With the development of electric vehicle technology, power batteries play a vital role. The stability and health of power batteries are directly related to the safety performance of vehicles. However, during the use of power batteries, the inherent defects and poor balance of individual cells may cause the consistency of power battery cells to be destroyed, which in turn leads to a decrease in battery life, accelerated battery aging, and reduced battery life.

[0003] In this regard, the battery fault identification technology proposed in the related art usually identifies the cell fault based on the external characteristics of the battery (such as voltage, current or temperature parameters), and focuses on passive response after the cell fault occurs. In other words, the battery fault identification solution in the related art has poor real-time identification and low accuracy.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a battery fault identification method, a vehicle and a computer program product to at least solve the technical problem in the related art that the solution for identifying faults based on the external characteristics of the battery has poor accuracy in identifying battery cell faults.

[0006] According to one aspect of an embodiment of the present application, a method is provided, including: obtaining battery cell test data, wherein the battery cell test data is obtained by performing an electrochemical impedance test on a test battery cell with a known fault state; performing feature extraction on the battery cell test data to determine a characteristic frequency and an impedance characteristic value; obtaining real-time impedance data of a battery cell to be tested of a vehicle power battery at a characteristic frequency; and performing cluster analysis on the impedance characteristic value and the real-time impedance data to identify the fault state of the battery cell to be tested.

[0007] Optionally, the test battery cells include normal battery cells and multiple faulty battery cells corresponding to multiple fault types; the battery cell test data include first test data corresponding to the normal battery cells and second test data corresponding to the multiple faulty battery cells, wherein the first test data is obtained by performing an electrochemical impedance test on the normal battery cells based on multiple battery status indicators, and the second test data is obtained by performing an electrochemical impedance test on the multiple faulty battery cells based on multiple fault types and test frequency ranges.

[0008] Optionally, performing feature extraction on the battery cell test data to determine the characteristic frequency and impedance characteristic value includes: performing impedance feature extraction on the battery cell test data to obtain an impedance spectrum; based on the impedance spectrum, selecting multiple characteristic frequencies from multiple preset frequency bands, and determining the test impedance values ​​corresponding to the multiple characteristic frequencies as impedance characteristic values.

[0009] Optionally, clustering analysis is performed on the impedance characteristic values ​​and the real-time impedance data to identify the fault state of the battery cell to be tested, including: clustering the impedance characteristic values ​​and the real-time impedance data based on a target clustering algorithm to obtain clustering results; and performing abnormal data analysis based on the clustering results to identify the fault state.

[0010] Optionally, the target clustering algorithm is a mean clustering algorithm; the impedance characteristic values ​​and the real-time impedance data are clustered based on the target clustering algorithm to obtain clustering results, including: determining the number of clustering centers corresponding to the mean clustering algorithm based on the impedance characteristic values; using the number of clustering centers, performing multiple rounds of iterative clustering on the real-time impedance data to obtain clustering results.

[0011] Optionally, the real-time impedance data is iteratively clustered for multiple rounds using the number of cluster centers to obtain clustering results, including: selecting multiple random data points from the real-time impedance data as multiple cluster centers based on the number of cluster centers; and clustering the impedance data points for multiple rounds based on the distances between the impedance data points in the real-time impedance data and the multiple cluster centers to obtain clustering results.

[0012] Optionally, the battery fault identification method further includes: calculating the sum of squared errors data corresponding to the multiple cluster centers based on the clustering results; and updating the number of cluster centers according to the sum of squared errors data and a preset optimization strategy.

[0013] Optionally, the clustering results include multiple clustering groups corresponding to the battery cells to be tested; abnormal data analysis is performed based on the clustering results, and identifying the fault state includes: based on the normal impedance value corresponding to the normal battery cells in the impedance characteristic value and the multiple abnormal impedance values ​​corresponding to the multiple faulty battery cells, impedance value deviation analysis is performed on the multiple clustering groups to obtain analysis results; based on the analysis results, the fault state of the battery cell to be tested is determined.

[0014] According to another aspect of an embodiment of the present application, a vehicle is also provided, including an on-board memory and an on-board processor, wherein a computer program is stored in the on-board memory, and the on-board processor is configured to run the computer program to execute any one of the above-mentioned methods.

[0015] According to another aspect of the embodiments of the present application, a computer program product and a method are also provided.

[0016] In an embodiment of the present application, cell test data is obtained, wherein the cell test data is obtained by performing an electrochemical impedance test on a test cell with a known fault state; feature extraction is performed on the cell test data to determine a characteristic frequency and an impedance characteristic value; real-time impedance data of the cell to be tested of the vehicle power battery at the characteristic frequency is obtained; and cluster analysis is performed on the impedance characteristic value and the real-time impedance data to identify the fault state of the cell to be tested. The cell test data obtained by the above electrochemical impedance test can characterize the internal characteristics of the cell, and it is more efficient to obtain the real-time impedance data of the cell to be tested at the characteristic frequency from the vehicle end after determining the characteristic frequency based on the cell test data. Therefore, the embodiment of the present application achieves the purpose of identifying the fault state of the cell of the vehicle power battery based on the electrochemical impedance test data and the real-time impedance data of the vehicle end, thereby achieving the technical effect of improving the accuracy of cell fault identification, and further solving the technical problem of poor accuracy of cell fault identification in the solution of identifying faults based on external characteristics of the battery in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and the related descriptions of the embodiments are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a hardware structure block diagram of an optional computing terminal for implementing another method according to an embodiment of the present application;

[0019] Figure 2 is a flow chart of another method according to an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of an optional impedance spectrum according to an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of an optional battery cell fault identification process according to an embodiment of the present application;

[0022] Figure 5 It is a structural block diagram of a specific device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] 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 only include a part of the embodiments of the present application, rather than 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 should fall within the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. 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 comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to an embodiment of the present application, a method embodiment of a different method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] First, the operating environment of the above method embodiment is exemplarily described. Figure 1 is a hardware structure block diagram of a computing terminal for implementing another method according to an optional embodiment of the present application, such as Figure 1 As shown, a computing terminal 10 (for example, a computer terminal, a mobile smart terminal, a vehicle terminal, or a cloud computing virtual terminal, etc.) may include: one or more processors 102, a memory 104 for storing data, and a transmission device 106 for implementing a communication function, wherein each processor 102 may include but is not limited to a processing component such as a microprocessor (Microcontroller Unit, referred to as MCU) or a programmable logic device (Field Programmable Gate Array, referred to as FPGA).

[0027] The computing terminal 10 may further include: a display device 110, an input / output device 108, a Universal Serial Bus (USB) port (the USB port may be used as one of the ports of a computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure) and a camera (not shown in the figure). A person skilled in the art may understand that Figure 1 The structure of the computing terminal 10 shown is only for illustration and does not impose a strict limitation on the structure of the computing terminal 10. For example, the computing terminal 10 may also include Figure 1 More or fewer components than those shown in FIG. 1 , or computing terminal 10 may have the same components as those shown in FIG. Figure 1Different categories of components are shown.

[0028] It should be noted that the one or more processors 102 and / or other data processing circuits in the computing terminal 10 may be embodied in whole or in part as software, hardware, firmware or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the vehicle terminal 10 (or mobile device).

[0029] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the other methods in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned other methods. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the vehicle terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the vehicle terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0031] Under the above operating environment, the embodiment of the present application provides the following Figure 2 Other methods shown, Figure 2 is a flowchart of another method according to an embodiment of the present application, such as Figure 2 As shown, the method includes the following implementation steps:

[0032] Step S201, obtaining battery cell test data, wherein the battery cell test data is obtained by performing an electrochemical impedance test on a test battery cell in a known fault state;

[0033] Step S202, extracting features from the battery cell test data to determine characteristic frequencies and impedance characteristic values;

[0034] Step S203, obtaining real-time impedance data of the battery cell to be tested of the vehicle power battery at a characteristic frequency;

[0035] Step S204, performing cluster analysis on the impedance characteristic value and the real-time impedance data to identify the fault state of the battery cell to be tested.

[0036] The above method steps provided in the embodiment of the present application can be run on a cloud server. After the cloud server obtains the battery cell test data obtained by the pre-test, it performs feature extraction on the battery cell test data to determine the characteristic frequency and impedance characteristic value. The cloud server sends the characteristic frequency to the vehicle and regularly obtains the real-time impedance data of the battery cell to be tested at the characteristic frequency from the vehicle. Furthermore, the cloud server performs cluster analysis on the impedance characteristic value and the real-time impedance data to identify the fault status of the battery cell to be tested.

[0037] The above method steps provided in the embodiment of the present application can be applied to provide power battery cell fault identification services for preset application scenarios. The above preset application scenarios may include but are not limited to intelligent driving scenarios, artificial intelligence driving scenarios, power battery repair and maintenance scenarios, etc.

[0038] The electrochemical impedance test is a test method for power batteries based on electrochemical impedance spectroscopy (EIS). Specifically, the impedance of the battery cell is calculated by applying small-amplitude AC signals of different frequencies to the battery cell and measuring the voltage response of the battery cell. The change in the impedance of the battery cell is related to the internal structure and chemical reaction of the battery cell, and can be used as an important indicator to judge the health of the battery cell.

[0039] The above cell test data is obtained by performing electrochemical impedance tests on the test cells. The fault status of these test cells is known. For example, the test cells may include cells that have not failed (i.e., normal cells) or faulty cells that have failed (including multiple types of faults).

[0040] The electrochemical impedance test is performed on the above-mentioned test cell, and the obtained test data of the above-mentioned cell can reflect the impedance characteristics of the test cell under different operating conditions (such as cell AC signal frequency, different temperatures, different charge states, different health states, etc.). The impedance characteristics are internal characteristics of the cell and can more accurately reflect the health status and potential faults of the cell.

[0041] Furthermore, the cloud server performs feature analysis on the battery cell test data to extract characteristic frequencies and impedance characteristic values. Specifically, in the process of feature analysis on the battery cell test data, the frequency and impedance value most relevant to the battery cell charge and discharge state are determined. The characteristic frequency refers to the frequency point in the battery cell test data that is particularly sensitive to identifying the battery cell charge and discharge state. The impedance characteristic value is the battery cell impedance value corresponding to these characteristic frequencies. By extracting the features of the battery cell test data, the computational complexity of the subsequent process can be reduced, and the accuracy of fault identification can be improved.

[0042] The above real-time impedance data refers to the impedance data obtained when the power battery cell (i.e. the cell to be tested) is monitored in real time during the operation of the vehicle. The cloud server can periodically obtain the real-time impedance data from the vehicle. The above real-time impedance data can reflect the current health status of the cell to be tested.

[0043] It should be noted that a sensor may be installed on the battery cell to be tested of the above-mentioned vehicle power battery, so that the vehicle can collect impedance data of the battery cell to be tested in real time.

[0044] It should be noted that in addition to uploading the real-time impedance data of the battery cell to the cloud server, other status data of the battery cell can also be uploaded to the cloud server. For example, other status data may include voltage, current, temperature, battery charge, battery health, etc. In particular, after collecting the above-mentioned real-time impedance data and other status data, the vehicle side can also perform data cleaning on the real-time impedance data and other status data to remove invalid data and blank data, and upload the cleaned data to the cloud server.

[0045] Furthermore, cluster analysis is performed on the impedance characteristic values ​​and the real-time impedance data, so that data points with similar impedance characteristics can be clustered into a group. In one embodiment, the data points targeted by the cluster analysis may include the impedance characteristic values ​​and the impedance data points in the real-time impedance data; in another embodiment, the data points targeted by the cluster analysis may only include the impedance data points in the real-time impedance data.

[0046] Through the above cluster analysis, in the embodiment of the present application, the cloud server can compare the real-time impedance data with the previously extracted impedance characteristic values, identify which battery cells to be tested have impedance data that deviates from the normal range, and thus determine whether each battery cell to be tested has a fault.

[0047] From the above, the embodiments of the present application combine electrochemical impedance testing, feature extraction, real-time monitoring and cluster analysis to monitor the health status of power battery cells in real time during vehicle operation and identify faulty cells in a timely manner, thereby achieving active management of the battery system.

[0048] Through the technical solutions provided by the above steps S201 to S204, in the embodiment of the present application, the battery cell test data is obtained, wherein the battery cell test data is obtained by performing an electrochemical impedance test on a test battery cell with a known fault state; feature extraction is performed on the battery cell test data to determine the characteristic frequency and the impedance characteristic value; real-time impedance data of the battery cell to be tested of the vehicle power battery at the characteristic frequency is obtained; cluster analysis is performed on the impedance characteristic value and the real-time impedance data to identify the fault state of the battery cell to be tested. The battery cell test data obtained by the above electrochemical impedance test can characterize the internal characteristics of the battery cell, and it is more efficient to obtain the real-time impedance data of the battery cell to be tested at the characteristic frequency from the vehicle end after determining the characteristic frequency based on the battery cell test data. Therefore, the embodiment of the present application achieves the purpose of identifying the fault state of the battery cell of the vehicle power battery based on the electrochemical impedance test data and the real-time impedance data of the vehicle end, thereby achieving the technical effect of improving the accuracy of battery cell fault identification, and then solving the technical problem of poor accuracy of battery cell fault identification in the solution based on battery external characteristics in the related art.

[0049] As an optional implementation, in the above-mentioned method, the test battery cells include normal battery cells and multiple faulty battery cells corresponding to multiple fault types; the battery cell test data include first test data corresponding to the normal battery cells and second test data corresponding to the multiple faulty battery cells, wherein the first test data is obtained by performing an electrochemical impedance test on the normal battery cells based on multiple battery status indicators, and the second test data is obtained by performing an electrochemical impedance test on the multiple faulty battery cells based on multiple fault types and test frequency ranges.

[0050] The normal cells are known test cells that have not experienced any failure. The faulty cells are known test cells that have experienced any failure. Each faulty cell may correspond to a fault type, and each faulty cell may include multiple cells with different fault levels (such as different abnormal manifestations).

[0051] For example, the above-mentioned various fault types may include but are not limited to: leakage fault, swelling fault, internal short circuit fault, capacity attenuation fault, lithium deposition fault, overcharge fault, over-discharge fault, etc.

[0052] The electrochemical impedance test (also known as EIS test) is a technology used to study and diagnose battery faults. It measures the impedance response of the battery cell by applying a small AC voltage or current to the battery cell, thereby analyzing the characteristics of the electrochemical process inside the battery.

[0053] The above-mentioned multiple battery status indicators may include: battery temperature state (State of Temperature, referred to as SOT) indicator, battery power state (State of Charge, referred to as SOC) indicator and battery health state (State of Health, referred to as SOH) indicator. Based on this, in the test phase, EIS test is performed on normal cells under different SOT, different SOC and different SOH to obtain the above-mentioned first test data. The first test data can reflect the impedance characteristics of normal cells under various states.

[0054] The above-mentioned test frequency range refers to the frequency range used in the EIS test, which usually ranges from low frequency to high frequency, covering impedance measurements at different frequencies, so as to fully understand the impedance characteristics of the battery cell at different frequencies. Based on this, during the test phase, an EIS test is performed on each of the multiple faulty battery cells based on the test frequency range (0.1Hz to 1kHz in this case) to obtain the above-mentioned second test data. The second test data can be used to establish an impedance model corresponding to different fault categories, so that in subsequent fault identification, the impedance of the battery cell to be tested and the faulty battery cell can be positively compared, thereby identifying the fault type of the battery cell to be tested.

[0055] Through optional implementation methods, the embodiments of the present application can perform comprehensive EIS testing on the test cells during the testing phase, and upload more comprehensive and detailed cell test data to the cloud server for fault identification of the vehicle's test cells, thereby improving the accuracy of cell fault identification.

[0056] As an optional implementation, in the above step S202, feature extraction is performed on the battery cell test data to determine the characteristic frequency and the impedance characteristic value, and the following execution steps may also be included:

[0057] Step S221, extracting impedance characteristics of the battery cell test data to obtain an impedance spectrum;

[0058] Step S222: Based on the impedance spectrum, multiple characteristic frequencies are selected from multiple preset frequency bands, and the test impedance values ​​corresponding to the multiple characteristic frequencies are determined as impedance characteristic values.

[0059] In the process of extracting impedance features from the cell test data, attention is paid to the impedance features that are closely related to the cell state. For example, in an exemplary application scenario, in the process of extracting impedance features from the cell test data, attention may be paid to the changes in the reactance, resistance, capacitance, inductance and other parameters of the test cell at different frequencies.

[0060] The above impedance spectrum is a graphical representation of the correlation between the impedance characteristic value obtained by extracting the impedance characteristics of the battery test data and the EIS test frequency. The above impedance spectrum can be a Nyquist diagram, where the horizontal axis of the impedance spectrum represents the real part of the impedance (or resistance), and the vertical axis of the impedance spectrum represents the imaginary part of the impedance (or reactance), thereby drawing a curve of the battery cell impedance changing with frequency.

[0061] The preset frequency bands mentioned above may be a plurality of frequency bands preset based on the impedance spectrum, such as an ultra-high frequency band, a high frequency band, a medium frequency band and a low frequency band.

[0062] In an exemplary application scenario, the EIS spectrum (i.e., impedance spectrum) obtained by feature extraction of EIS test data is as follows: Figure 3 As shown, the preset ultra-high frequency band is in the fourth quadrant, which represents the inductive reactance of the cell connection and is not analyzed in this example; for the high frequency band, the intercept of the horizontal axis (also called the real axis) is used to represent the ohmic impedance of the cell, and the first capacitive reactance arc of the high frequency band is used to represent the double-layer impedance of the cell; for the medium frequency band, the second capacitive reactance arc is used to represent the charge transfer impedance of the cell; for the low frequency band, the oblique line is used to represent the solid diffusion impedance of the cell. Based on this, a characteristic frequency is selected from the high frequency band, the medium frequency band, and the low frequency band, and the EIS impedance corresponding to each characteristic frequency is used as the impedance characteristic value. The impedance characteristic data set is constructed based on the impedance characteristic value.

[0063] Through the technical solutions provided by the above-mentioned steps S221 to S222, the embodiments of the present application can make full use of the battery cell test data obtained in the testing phase through impedance feature extraction, which helps to improve the accuracy of the battery cell fault identification scheme based on the battery cell test data; in addition, by determining the characteristic frequencies corresponding to different frequency bands, the coverage of subsequent battery cell fault identification schemes can also be improved.

[0064] As an optional implementation, in the above step S204, cluster analysis is performed on the impedance characteristic value and the real-time impedance data to identify the fault state of the battery cell to be tested, and the following execution steps may also be included:

[0065] Step S241, clustering the impedance characteristic value and the real-time impedance data based on the target clustering algorithm to obtain a clustering result;

[0066] Step S242: perform abnormal data analysis based on the clustering results to identify the fault status.

[0067] The target clustering algorithm may be a pre-set clustering algorithm for clustering impedance characteristic values ​​and real-time impedance data. For example, the target clustering algorithm may include but is not limited to: mean clustering algorithm, hierarchical clustering algorithm, Gaussian mixture clustering algorithm, fuzzy clustering algorithm, density-based spatial clustering of applications with noise (DBSCAN) algorithm, etc.

[0068] Through the clustering algorithm, the real-time impedance data can be grouped according to data similarity. The similarity between the impedance data points in each cluster group is high, while the similarity between the impedance data points in different cluster groups is low, thereby obtaining a clustering result. The clustering result is used to determine multiple clustering groups corresponding to the real-time impedance data.

[0069] By performing abnormal data analysis on the clustering results, data points significantly different from the normal state can be identified from the clustering results, and these data points can be used as abnormal data points. Based on these abnormal data points, the fault state (such as normal or faulty) of the corresponding battery cell to be tested can be determined.

[0070] In addition, the above step S204 may also include: performing data cleaning on the real-time impedance data to obtain a cleaning result; performing cluster analysis on the impedance characteristic value and the cleaning result to identify the fault state.

[0071] Through the technical solutions provided by the above steps S241 to S242, the embodiment of the present application can perform cluster analysis on the real-time impedance data obtained from the vehicle side in real time, dynamically and accurately identify the fault status of the vehicle's power battery cells, so as to promptly discover the abnormal performance of the cells, thereby providing early warning, reducing the safety hazards caused by battery failures, and improving the safety and reliability of vehicle operation.

[0072] As an optional implementation, the target clustering algorithm is a mean clustering algorithm; in the above step S241, the impedance characteristic value and the real-time impedance data are clustered based on the target clustering algorithm to obtain a clustering result, and the following execution steps may also be included:

[0073] Step S2411, determining the number of cluster centers corresponding to the mean value clustering algorithm based on the impedance characteristic value;

[0074] Step S2412, using the number of cluster centers, perform multiple rounds of iterative clustering on the real-time impedance data to obtain clustering results.

[0075] The above mean clustering algorithm is the K-means clustering algorithm. The K-means clustering algorithm is an unsupervised learning method used for clustering analysis of data points, classifying similar data points into the same category. In battery cell fault identification, the K-means clustering algorithm can be used to classify the real-time impedance data of the battery cell to identify the health or fault status of the battery cell.

[0076] Specifically, the K value corresponding to the K-means clustering algorithm is determined based on the impedance characteristic value, and the K value is used to determine the number of cluster centers, that is, clustering the real-time impedance data into K cluster groups. Based on the K value, multiple rounds of iterative clustering are performed on the real-time impedance data to obtain the above clustering results.

[0077] It is easy to notice that the number of cluster centers (K value) is determined based on the impedance characteristic value, which involves a preprocessing stage. In the preprocessing stage, the impedance characteristic values ​​of normal cells and faulty cells are analyzed to determine a reasonable number of clusters K. For example, in the intelligent driving scenario, the approximate number of cluster groups can be determined by analyzing the normal cell test data and faulty cell test data that have been collected. For example, the faulty cell test data mainly corresponds to 3 common fault types, and the number of cluster groups (K value) can be determined as 4 (including 1 normal cell category and 3 faulty cell categories).

[0078] Through the technical solutions provided by the above steps S2411 to S2412, the embodiment of the present application can automatically identify and classify the fault status of the battery cell by using the mean clustering algorithm without manual intervention. This not only improves the efficiency of fault identification, but also enhances the accuracy and reliability of the system. In the application scenario, the above method steps can timely and accurately identify battery cell failures to avoid potential safety risks and ensure the reliable operation of the vehicle. At the same time, it can also help with the maintenance and management of the battery cell, extend battery life, and reduce operating costs.

[0079] As an optional implementation, in the above step S2412, the number of cluster centers is used to perform multiple rounds of iterative clustering on the real-time impedance data to obtain clustering results, and the following execution steps may also be included:

[0080] Step S2413, selecting multiple random data points from the real-time impedance data as multiple cluster centers according to the number of cluster centers;

[0081] Step S2414, performing multiple rounds of clustering assignments on the impedance data points according to the distances between the impedance data points and multiple cluster centers in the real-time impedance data to obtain clustering results.

[0082] The specific clustering process based on the mean value clustering algorithm may include the following iterative steps.

[0083] In the first step, K random data points are selected from the real-time impedance data as the initial cluster centers, which are denoted as .

[0084] The second step is to calculate the impedance data points in the real-time impedance data. The distance between each cluster center , and assign the impedance data point to the target cluster center that is closest to it.

[0085] The third step is to recalculate the cluster centers of the K cluster groups.

[0086] In the fourth step, if the distance between the recalculated cluster center and the original cluster center is greater than the preset threshold, the next round of iterative clustering is performed based on the recalculated cluster center (that is, repeating the second and third steps); if the distance between the recalculated cluster center and the original cluster center is less than or equal to the preset threshold, it is determined that the iterative clustering is completed and the clustering result is obtained.

[0087] It should be noted that the above distance can be the Euclidean distance between two data points (an impedance data point and a cluster center), Manhattan distance, etc. The smaller the above distance, the more similar the impedance data point and the cluster center are.

[0088] Through the technical solutions provided by the above steps S2413 to S2414, the embodiment of the present application analyzes the real-time impedance data through the mean clustering algorithm, and can automatically identify and classify the status of the battery cells. In the application scenario, the embodiment of the present application can monitor the health of the vehicle's power battery in real time, promptly detect potential faulty cells, avoid vehicle safety problems caused by battery failures, and improve the reliability and efficiency of the battery management system. In addition, through multiple rounds of iterations, the accuracy of the clustering results can be ensured, the risk of false alarms and missed alarms can be reduced, and more accurate guidance can be provided for battery maintenance and replacement.

[0089] As an optional implementation, the above method may further include the following execution steps:

[0090] Step S251, based on the clustering results, calculating the sum of squared error data corresponding to multiple cluster centers;

[0091] Step S252, updating the number of cluster centers according to the error square sum data and the preset optimization strategy.

[0092] In the application scenario, the maximum value of the number of cluster centers (K value) can be the number of impedance characteristic values. The larger the K value, the higher the clustering degree of the cluster group. However, if the K value is too large, the significance of the clustering result for the battery cell fault identification task will be reduced. In the embodiment of the present application, a prediction optimization strategy is used to optimize and update the number of cluster centers.

[0093] The above-mentioned preset optimization strategy can be a K-value optimization strategy that minimizes the sum of squared errors, also known as the Elbow Method. The core indicator of the Elbow Method is the sum of squared errors (SSE for short). For example, the calculation method of the sum of squared errors can be shown in the following formula (1).

[0094] Formula (1)

[0095] In the above formula (1), represents the i-th cluster group, x represents The impedance data points in express The corresponding cluster center.

[0096] It should be noted that SSE can characterize the sum of squares of distances between an impedance data point and the cluster center corresponding to the cluster group to which the impedance data point belongs. The smaller the SSE, the better the quality of the clustering result. Generally, when the number of cluster centers (K value) increases, the SSE value decreases accordingly. However, as the number of cluster centers increases, the decrease in SSE gradually slows down. Based on this, an optimal k value can be found so that the increase in the number of cluster centers no longer significantly reduces the SSE value. At this time, the optimal K value is used to update the number of cluster centers.

[0097] Through the technical solutions provided by the above steps S251 to S252, the embodiment of the present application dynamically adjusts the number of cluster centers according to the SSE value and the optimization strategy, which can ensure that the cluster analysis is neither over-segmented (causing each cluster to contain only a few data points, making it difficult to form a pattern) nor over-simplified (causing data points of different patterns to be incorrectly grouped together). By dynamically optimizing the number of cluster centers, the mean clustering algorithm can more accurately distinguish between normal battery cells and different types of faulty battery cells, thereby timely discovering potential battery cell failures during vehicle operation, thereby ensuring vehicle safety and battery life.

[0098] As an optional implementation, the clustering result includes multiple clustering groups corresponding to the battery cells to be tested; in the above step S242, abnormal data analysis is performed based on the clustering result to identify the fault state, and the following execution steps may also be included:

[0099] Step S2421, based on the normal impedance value corresponding to the normal battery cell and the multiple abnormal impedance values ​​corresponding to the multiple faulty battery cells in the impedance characteristic value, impedance value deviation analysis is performed on the multiple cluster groups to obtain analysis results;

[0100] Step S2422: Determine the fault status of the battery cell to be tested according to the analysis result.

[0101] According to the embodiments of the present application, for all the battery cells to be tested in the same battery pack, although they are continuously in a similar working environment (including temperature, SOC and SOH, etc.), they should theoretically maintain consistency. However, in actual use, due to the inherent defects of the battery cells or the failure of the balancing mechanism, the battery pack may fail or have performance differences, thereby affecting the service life of the entire battery pack.

[0102] According to the embodiment of the present application, a battery fault identification method is proposed, which uses a target clustering algorithm (i.e., a mean clustering algorithm) to perform cluster analysis on the real-time impedance data of all cells at the same time. Specifically, when the clustering result indicates that there is a single cluster group, it can be inferred that the battery pack is either composed entirely of normal cells or all of them are faulty cells; and when the clustering result indicates that there are two or more cluster groups, it can be determined that there is at least one type of normal cell, and the rest may be faulty cells.

[0103] In order to further clarify the state of the battery cells in the cluster group, that is, to distinguish between normal and abnormal states, the embodiment of the present application uses the impedance characteristic value extracted from the battery cell test data as a reference to perform deviation analysis on the impedance under different fault characteristics. By comparing the difference between the normal impedance value and the abnormal impedance value in the real-time impedance data and the impedance characteristic value, accurate identification of normal and abnormal battery cells is achieved.

[0104] Once an abnormal cell is identified, the embodiment of the present application further integrates the synergy of EIS (electrochemical impedance spectroscopy) data and the cloud big data platform, which can not only accurately locate the abnormal cell, but also automatically send key information such as the vehicle identification code, vehicle model, and number of the abnormal cell to the background management system to trigger the intelligent reminder mechanism. After receiving the reminder, the background system will conduct in-depth analysis and confirmation of the reported abnormal situation to provide data support for subsequent fault handling.

[0105] In an exemplary application scenario, according to the above method steps, a method is provided as follows: Figure 4 The cell fault detection process is shown in Figure 1. Figure 4As shown, first, EIS tests are performed on normal cells in the test cells at different temperatures, different SOCs and different SOHs; EIS tests are performed on faulty cells in the test cells at different frequencies to obtain EIS test spectra; feature extraction is performed on the EIS test spectra to obtain characteristic frequencies and impedance characteristic values; further, real-time impedance data of all cells of the power battery at characteristic frequencies are regularly obtained from the actual vehicle; based on the K-means clustering algorithm, cluster analysis is performed on the real-time impedance data to obtain clustering results; based on the clustering results, it is determined whether the cell to be tested has a fault; if a fault occurs, an intelligent reminder is given in the background according to the cell number of the faulty cell; if no fault occurs, the next detection cycle is entered, and the real-time impedance data of all cells of the power battery at the characteristic frequency are obtained from the actual vehicle again to perform cell fault detection.

[0106] It can be seen from the above that the embodiment of the present application effectively realizes the intelligent identification and positioning of the fault status of the battery cells in the battery pack by combining the characteristic frequency and impedance characteristic value of the battery cells for cluster analysis, providing a powerful technical means for the health management of the vehicle power battery.

[0107] In summary, by implementing the battery fault identification method of the present application, the time for EIS measurement on the actual vehicle can be effectively shortened, the energy consumption and cost of battery status monitoring can be reduced, and the timeliness and accuracy of fault detection can be ensured. The optimized k-means clustering algorithm can automatically adjust the number of cluster centers, avoiding the deficiency of the traditional k-means algorithm that requires manual setting of the number of clusters, and improving the intelligent level of fault identification. In addition, with the help of cloud computing resources, the present method can process large-scale battery cell data, realize comprehensive fault identification of vehicle power batteries, ensure the safety of vehicle operation, reduce the computing pressure of vehicle-mounted equipment, and extend its service life. In summary, the method of the present application greatly improves the efficiency and practicality of the system while ensuring the accuracy of fault identification, and provides an efficient and intelligent solution for battery status monitoring and fault diagnosis.

[0108] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0109] It should be noted that, for the above method embodiments, for the sake of simplicity, the technical solutions in the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of actions in the described action combinations, because according to the present application, some of the above steps can be performed in other orders or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification of this application belong to preferred embodiments, and the actions and modules involved are not necessarily necessary to implement the technical solutions of the present application.

[0110] According to an embodiment of the present invention, a device embodiment of a different device is also provided, and the different device is used to implement the above method embodiment and various optional implementations of the method embodiment. The technical content described above is not repeated in the device embodiment. It should be noted that in the following related descriptions of the device embodiment, a "module" can be software, hardware, or a combination of software and hardware for implementing a specified function.

[0111] Figure 5 is a structural block diagram of a device according to an embodiment of the present application, such as Figure 5 As shown, the above-mentioned device includes: a first acquisition module 501, used to acquire battery cell test data, wherein the battery cell test data is obtained by performing an electrochemical impedance test on a test battery cell with a known fault state; an extraction module 502, used to perform feature extraction on the battery cell test data, and determine a characteristic frequency and an impedance characteristic value; a second acquisition module 503, used to acquire real-time impedance data of a battery cell to be tested of a vehicle power battery at a characteristic frequency; and an analysis module 504, used to perform cluster analysis on the impedance characteristic value and the real-time impedance data, and identify the fault state of the battery cell to be tested.

[0112] Optionally, in the above-mentioned device, the test battery cells include normal battery cells and multiple faulty battery cells corresponding to multiple fault types; the battery cell test data include first test data corresponding to the normal battery cells and second test data corresponding to the multiple faulty battery cells, wherein the first test data is obtained by performing an electrochemical impedance test on the normal battery cells based on multiple battery status indicators, and the second test data is obtained by performing an electrochemical impedance test on the multiple faulty battery cells based on multiple fault types and test frequency ranges.

[0113] Optionally, the extraction module 502 is further used to: extract impedance features from the cell test data to obtain an impedance spectrum; based on the impedance spectrum, select multiple characteristic frequencies from multiple preset frequency bands, and determine the test impedance values ​​corresponding to the multiple characteristic frequencies as impedance characteristic values.

[0114] Optionally, the above analysis module 504 is further used to: perform clustering processing on the impedance characteristic value and the real-time impedance data based on the target clustering algorithm to obtain a clustering result; perform abnormal data analysis based on the clustering result to identify the fault state.

[0115] Optionally, the target clustering algorithm is a mean clustering algorithm; the above analysis module 504 is also used to: determine the number of clustering centers corresponding to the mean clustering algorithm based on the impedance characteristic value; use the number of clustering centers to perform multiple rounds of iterative clustering on the real-time impedance data to obtain clustering results.

[0116] Optionally, the above-mentioned analysis module 504 is also used to: select multiple random data points from the real-time impedance data as multiple cluster centers according to the number of cluster centers; perform multiple rounds of clustering assignments on the impedance data points according to the distances between the impedance data points in the real-time impedance data and the multiple cluster centers to obtain clustering results.

[0117] Optionally, in addition to the above-mentioned multiple modules, the above-mentioned device also includes an update module (not shown in the figure), which is used to calculate the error sum of squares data corresponding to multiple cluster centers based on the clustering results; and update the number of cluster centers according to the error sum of squares data and a preset optimization strategy.

[0118] Optionally, the clustering results include multiple clustering groups corresponding to the battery cells to be tested; the above-mentioned analysis module 504 is also used to: based on the normal impedance values ​​corresponding to the normal battery cells in the impedance characteristic values ​​and the multiple abnormal impedance values ​​corresponding to the multiple faulty battery cells, perform impedance value deviation analysis on the multiple clustering groups to obtain analysis results; determine the fault state of the battery cells to be tested according to the analysis results.

[0119] It should be noted that the above-mentioned first acquisition module 501, extraction module 502, second acquisition module 503 and analysis module 504 correspond to steps S201 to S204 in the method embodiment. The four modules are the same as the instances and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above-mentioned method embodiment.

[0120] It should be noted that the various modules mentioned in the above device embodiments can be implemented by software, hardware, or a combination of software and hardware. For example, when hardware is used to implement the above modules, the various modules can be set in the same processor, or the various modules can be set in different processors in any combination. For another example, the above modules can be hardware components or software components stored in a memory and processed by one or more processors, or the above modules can also be run as part of the device on a processor such as a processor. Figure 1 in the computing terminal shown.

[0121] According to an embodiment of the present invention, there is also provided an embodiment of a vehicle, which includes an on-board memory and an on-board processor, wherein a computer program is stored in the on-board memory, and the on-board processor is configured to run the computer program to implement the above-mentioned method.

[0122] According to an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to implement the above-mentioned method.

[0123] Optionally, the computer storage medium may include, but is not limited to, a hard disk drive (HDD), a solid state drive (SSD), a USB flash drive, an optical disk, a memory card, a cloud storage medium, and a network storage device (NAS).

[0124] Optionally, the computer-readable storage medium may be configured to store a computer program for executing the following steps: obtaining battery cell test data, wherein the battery cell test data is obtained by performing an electrochemical impedance test on a test battery cell with a known fault state; performing feature extraction on the battery cell test data to determine a characteristic frequency and an impedance characteristic value; obtaining real-time impedance data of a battery cell to be tested of a vehicle power battery at a characteristic frequency; and performing cluster analysis on the impedance characteristic value and the real-time impedance data to identify the fault state of the battery cell to be tested.

[0125] According to an embodiment of the present invention, a computer program product is also provided, which includes a computer program, and when the computer program is executed by a processor, the above method can be implemented.

[0126] Optionally, the above-mentioned computer program product can provide other services based on the above-mentioned other methods.

[0127] Optionally, in this embodiment, the computer program product may be a set of instructions and codes pre-written according to the above method. The computer program product may run on various computer platforms, including personal computers, servers, mobile devices, etc.

[0128] Optionally, in this embodiment, the instructions and codes corresponding to the computer program product are used to implement the following method steps: obtaining battery cell test data, wherein the battery cell test data is obtained by performing an electrochemical impedance test on a test battery cell with a known fault state; performing feature extraction on the battery cell test data to determine a characteristic frequency and an impedance characteristic value; obtaining real-time impedance data of a battery cell to be tested of a vehicle power battery at a characteristic frequency; performing cluster analysis on the impedance characteristic value and the real-time impedance data to identify the fault state of the battery cell to be tested.

[0129] In the above-mentioned multiple embodiments of the present application, the description of each embodiment has different emphases. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of multiple modules can be a logical function division, and there can be any other possible division methods when actually implemented in the application scenario; for another example, multiple modules (or units or components in the modules) can be combined with each other and can be integrated into another system. For example, some features in the method embodiments described above can be ignored or skipped.

[0131] It should be noted that in the above-mentioned embodiments, the modules, components or units described as separate parts can be physically separated or physically integrated. The parts displayed as modules or units can be physical modules or physical units, or virtual modules or virtual units, that is, multiple modules or multiple units can be in the same position, or distributed in multiple positions or multiple spaces. In the application scenario, according to the actual needs of the scenario, some or all of the multiple modules or multiple units can be selected to implement the technical solutions of the embodiments of the present application, thereby achieving the corresponding technical objectives.

[0132] In particular, for an integrated functional module or functional unit, if it is implemented in the form of a software functional unit and sold or used as an independent product, the module or functional unit can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0133] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A battery fault identification method, characterized in that: The battery fault identification method comprises: Acquiring battery cell test data, wherein the battery cell test data is obtained by performing an electrochemical impedance test on a test battery cell in a known fault state; Extracting features from the battery cell test data to determine characteristic frequencies and impedance characteristic values; Acquire real-time impedance data of the battery cell to be tested of the vehicle power battery at the characteristic frequency; Cluster analysis is performed on the impedance characteristic value and the real-time impedance data to identify the fault state of the battery cell to be tested.

2. The battery fault identification method according to claim 1, characterized in that: The test cells include normal cells and multiple fault cells corresponding to multiple fault types; The battery cell test data includes first test data corresponding to normal battery cells and second test data corresponding to the multiple faulty battery cells, wherein the first test data is obtained by performing an electrochemical impedance test on the normal battery cells based on multiple battery status indicators, and the second test data is obtained by performing an electrochemical impedance test on the multiple faulty battery cells based on the multiple fault types and test frequency ranges.

3. The battery fault identification method according to claim 1, characterized in that: Extracting features from the battery cell test data to determine the characteristic frequency and impedance characteristic value of the battery cell charge and discharge includes: Extracting impedance characteristics of the battery cell test data to obtain an impedance spectrum; Based on the impedance spectrum, a plurality of the characteristic frequencies are selected from a plurality of preset frequency bands, and the test impedance values ​​corresponding to the plurality of the characteristic frequencies are determined as the impedance characteristic values.

4. The battery fault identification method according to claim 1, characterized in that: Performing cluster analysis on the impedance characteristic value and the real-time impedance data to identify the fault state of the battery cell to be tested includes: Performing clustering processing on the impedance characteristic value and the real-time impedance data based on a target clustering algorithm to obtain a clustering result; Abnormal data analysis is performed based on the clustering result to identify the fault state.

5. The battery fault identification method according to claim 4, characterized in that: The target clustering algorithm is a mean clustering algorithm; The impedance characteristic value and the real-time impedance data are clustered based on a target clustering algorithm to obtain the clustering result including: Determine the number of cluster centers corresponding to the mean clustering algorithm based on the impedance characteristic value; The real-time impedance data is iteratively clustered for multiple rounds using the number of cluster centers to obtain the clustering result.

6. The battery fault identification method according to claim 5, characterized in that: Using the number of cluster centers, multiple rounds of iterative clustering are performed on the real-time impedance data to obtain the clustering results including: According to the number of cluster centers, selecting multiple random data points from the real-time impedance data as multiple cluster centers; According to the distance between the impedance data point in the real-time impedance data and the multiple cluster centers, the impedance data points are clustered and allocated in multiple rounds to obtain the clustering result.

7. The battery fault identification method according to claim 5 or 6, characterized in that: The battery fault identification method further includes: Based on the clustering results, calculating the sum of squared error data corresponding to multiple cluster centers; The number of cluster centers is updated according to the error sum-of-squares data and a preset optimization strategy.

8. The battery fault identification method according to claim 4, characterized in that: The clustering result includes a plurality of clustering groups corresponding to the battery cells to be tested; Performing abnormal data analysis based on the clustering result to identify the fault state includes: Based on the normal impedance value corresponding to the normal battery cell and the multiple abnormal impedance values ​​corresponding to the multiple faulty battery cells in the impedance characteristic value, performing impedance value deviation analysis on the multiple cluster groups to obtain analysis results; The fault state of the battery cell to be tested is determined according to the analysis result.

9. A vehicle, characterized in that: The invention comprises an on-board memory and an on-board processor, wherein the on-board memory stores a computer program, and the on-board processor is configured to run the computer program to execute the battery fault identification method according to any one of claims 1 to 8.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the battery fault identification method according to any one of claims 1 to 8 when being executed by a processor.

Images