Battery consistency early warning method, system and equipment based on modal decomposition and medium

Abstract

The invention belongs to the technical field of power battery fault monitoring, and particularly relates to a battery consistency early warning method, system and device based on modal decomposition and a medium, and the method comprises the steps: firstly obtaining the charging and discharging time sequence data of a battery pack, and constructing a battery cell voltage matrix; a frequency domain-time domain coupled mode decomposition method is adopted, and multi-mode characteristics of each battery cell are extracted through discrete Fourier transform and an iterative optimization variational mode decomposition algorithm; performing anomaly detection on row vectors of the modal matrix by adopting a box plot method, and taking an intersection of detection results of each modal component to determine a target abnormal battery cell; and finally, giving out early warning according to the voltage and temperature values of the abnormal battery cell. The early consistency degradation of the battery can be effectively identified, the false alarm rate and the omission ratio are remarkably reduced, and the method is suitable for safety monitoring and fault early warning of the battery of the new energy automobile.

Description

Technical Field

[0001] The present invention belongs to the technical field of power battery fault monitoring, and particularly relates to a battery consistency early warning method, system, device and medium based on modal decomposition. Background Art

[0002] As a core component of new energy vehicles, the health state of power batteries directly affects the safety and reliability of vehicles. There may be huge differences between different battery packs due to factors such as actual temperature, aging rate, and internal resistance. Currently, the monitoring of battery pack consistency mainly uses threshold-based statistical methods or single-dimensional signal analysis techniques. For example, the invention patent with publication number CN115856692A discloses a power battery risk identification and traceability system based on the range voltage, which further identifies abnormal battery cells through the range voltage of power batteries; the invention patent with publication number CN119479219A discloses a new energy step-up transformer abnormal early warning system and method, which selects feature vectors through the wavelet transform algorithm and uses an improved artificial neural network to establish an abnormal location model of the step-up transformer to determine the abnormal location. In addition, some studies use clustering algorithms or machine learning models to analyze battery parameters, such as dividing the states of battery cells through K-means clustering or using an LSTM network to predict the decay trend of battery performance. Although these methods can achieve a certain degree of abnormal detection, they still face problems such as insufficient adaptability and single feature extraction in practical applications.

[0003] The above methods have significant deficiencies in practical applications: First, the traditional threshold method has a high false alarm rate for complex working conditions (such as fast charging and low temperature) and cannot distinguish normal fluctuations from real faults; second, single-modal analysis (such as only frequency domain decomposition) will lose time-domain dynamic features, resulting in missed detection of early tiny abnormalities. For example, although wavelet decomposition can extract high-frequency noise, it ignores the interaction between different frequency band modes; and the clustering algorithm is sensitive to data distribution and is prone to failure in the later stage of battery pack aging. These problems directly affect the safety and operation and maintenance efficiency of new energy vehicles, and there is an urgent need for a consistency early warning method that can integrate multi-dimensional features and adapt to working conditions. Summary of the Invention

[0004] The purpose of the present invention is to provide a battery consistency early warning method, system, device and medium based on modal decomposition, aiming to identify inconsistent battery cells by analyzing the voltage data of each battery cell in a power battery pack, so as to early warn potential faults in advance. Its core idea is to extract the frequency-domain and time-domain coupling features of the battery cell voltage through modal decomposition and combine the box plot method to detect abnormal battery cells.

[0005] The present invention realizes the above purpose through the following technical solutions: In the first aspect, the present invention proposes a battery consistency early warning method based on modal decomposition, and the method includes: Obtain the charge-discharge timing segments of the battery pack, including a voltage array and a temperature array; Obtain the cell voltage matrix constructed from multiple charge-discharge timing segments; Perform frequency-domain to time-domain coupled modal decomposition on each cell timing segment in the cell voltage matrix, extract the modal characteristics of each cell, and obtain the modal matrix; Among them, the modal decomposition separates modal components in different frequency bands through iterative optimization and extracts the maximum modal characteristics to characterize the cell state; Use the box plot method to identify inconsistent cell numbers for the row vectors of the modal matrix, and take the intersection of the identification results of each component to obtain the target abnormal cells; Determine the voltage value and temperature value of the target abnormal cells and send out a warning signal.

[0006] Furthermore, the obtaining of the charge-discharge timing segments of the battery pack includes: Parse the battery message data sent by the supervision platform; After sorting and de-duplicating the battery message data according to the acquisition time, obtain the voltage array and temperature array of the cells; Based on the charging, discharging, and static states of the battery pack, divide the array to obtain the charge-discharge timing segments of the battery pack.

[0007] Furthermore, the cell voltage matrix is constructed based on the following method: For a single charge-discharge timing segment, construct the cell voltage matrix : ; Among them, represents the number of cells, represents the timing data of the th cell.

[0008] Furthermore, the modal decomposition includes the following steps: Set the number of decomposition modes , the maximum number of iterations , and the tolerance error ; Based on the timing data in the cell voltage matrix initialize the modal component matrix , where is the timing length; Use the discrete Fourier transform to convert the timing data from the time domain to the frequency domain to obtain the transformed timing data ; Iteratively update the modal component matrix , gradually optimize each modal component until the termination condition is met; Extract the maximum modal feature from the iterated modal component matrix to obtain the modal feature vector of the battery cell , , denotes the th modal component of the th battery cell; Based on the modal feature vector construct a modal matrix , denotes the maximum modal vector of the th battery cell.

[0009] Furthermore, the iteratively updated modal component matrix is as follows: ; wherein, denotes the th modal component, denotes the original frequency domain signal, denotes the th modal component, denotes the th modal component updated last time.

[0010] Furthermore, the termination condition for the modal decomposition is: The number of iterations exceeds the maximum number of iterations ; or the error condition is satisfied, denotes the result of the modal component of the th iteration, denotes the result of the modal component of the th iteration.

[0011] Furthermore, the inconsistent battery cell numbers are identified for the row vectors of the modal matrix by using the box plot method, and the intersection of the identification results of each component is taken to obtain the target abnormal battery cells, including: For each row vector of the modal matrix , calculate the upper and lower quartiles and the interquartile range ; If the data point satisfies , mark the battery cell as an abnormal battery cell to obtain the abnormal battery cell set ; Take the logical intersection of the abnormal battery cell sets of the modal components to obtain the intersection And used as the target abnormal battery cell, as shown in the following formula: ; Second aspect, the present invention proposes a battery consistency warning system based on modal decomposition, which is applied to execute the steps of the battery consistency warning method as described above. The system includes: The first acquisition module is used to acquire the charge and discharge time sequence segments of the battery pack, including a voltage array and a temperature array; The second acquisition module is used to acquire the battery cell voltage matrix constructed by multiple charge and discharge time sequence segments; The modal decomposition module is used to perform frequency-domain to time-domain coupled modal decomposition on each battery cell time sequence segment in the battery cell voltage matrix, extract the modal characteristics of each battery cell, and obtain a modal matrix; Wherein, the modal decomposition separates modal components in different frequency bands through iterative optimization and extracts the maximum modal characteristics to characterize the state of the battery cell; The abnormal identification module is used to identify inconsistent battery cell numbers for the row vectors of the modal matrix by using the box plot method, and take the intersection of the identification results of each component to obtain the target abnormal battery cell; The warning module is used to determine the voltage value and temperature value of the target abnormal battery cell and issue a warning signal.

[0012] Third aspect, the present invention proposes an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it realizes the steps of the battery consistency warning method as described above.

[0013] Fourth aspect, the present invention proposes a computer-readable storage medium, storing a computer program, and when the computer program is executed by a processor, it realizes the steps of the battery consistency warning method as described above.

[0014] The beneficial effects of the present invention are as follows: The present invention proposes a frequency-domain to time-domain coupled analysis method, which realizes the deep feature extraction of the consistency state of the battery pack, and can effectively capture early minute abnormalities that are difficult to be found by traditional time-domain analysis methods; the discrete Fourier transform and the improved variational mode decomposition algorithm are organically combined, significantly improving the sensitivity and accuracy of fault detection. Secondly, an abnormal identification strategy combining multi-modal joint analysis and statistical test is adopted. After independently detecting each modal component by the box plot method and taking the intersection, it avoids misjudgment caused by a single detection standard and makes the warning result more reliable. Description of the Drawings

[0015] Figure 1 It is a schematic flowchart of a battery consistency warning method based on modal decomposition in an embodiment of the present application; Figure 2Another schematic flowchart of the battery consistency warning method based on modal decomposition in an embodiment of the present application; Figure 3 A schematic flowchart of modal decomposition in an embodiment of the present application; Figure 4 A structural block diagram of the battery consistency warning system based on modal decomposition in an embodiment of the present application; Figure 5 A schematic structural diagram of an electronic device in an embodiment of the present application; Figure 6 A voltage curve graph of the battery cells with poor consistency in the case part of the specific implementation manner of the present application; Figure 7 A modal heat map of the battery cells in the case part of the specific implementation manner of the present application. Specific implementation manner

[0016] The present application will be further described in detail below with reference to the accompanying drawings. It is necessary to point out here that the following specific implementation manners are only used to further illustrate the present application and should not be construed as limiting the protection scope of the present application. Those skilled in the art can make some non-essential improvements and adjustments to the present application based on the above application content.

[0017] Please refer to Figures 1-3 , in an embodiment, a battery consistency warning method based on modal decomposition is proposed, and the method includes the following steps: S1. Obtain the charge and discharge time sequence segments of the battery pack, including a voltage array and a temperature array.

[0018] In the above step S1, specifically, it includes: parsing the battery message data sent by the supervision platform (or uploaded by the vehicle-mounted terminal), such as parsing the message in real time according to the data format of the GBT32960 protocol to obtain the original battery data; sorting and de-duplicating the battery message data by the collection time to obtain the voltage array and temperature array of the battery cells; de-duplication includes cleaning duplicate data and empty data; dividing the array based on the charging, discharging, and static states of the battery pack to obtain the charge and discharge time sequence segments of the battery pack.

[0019] In the above array division, according to the charging status code and the current direction feature, the continuous time sequence data is divided into charge and discharge segments with clear physical meanings. Specifically, when the charging pile connection signal is detected and the current is positive, it is marked as a charging segment; when the vehicle is in a driving state and the current is negative, it is marked as a discharging segment; when the absolute value of the current is less than the threshold and lasts for a set time, it is determined to be in a static state.

[0020] S2. Obtain the cell voltage matrix constructed by multiple charge-discharge timing segments; the cell voltage matrix is constructed based on the following method: for a single charge-discharge timing segment, construct the cell voltage matrix : ; wherein, represents the number of cells, represents the th cell's timing data.

[0021] In this embodiment, after obtaining the cell voltage matrix, the subsequent key modal decomposition step is performed, and this process realizes the multi-dimensional feature extraction of the battery health state through the frequency-domain and time-domain coupling analysis method.

[0022] S3. Perform frequency-domain and time-domain coupled modal decomposition on each cell timing segment in the cell voltage matrix, extract the modal features of each cell, and obtain the modal matrix; wherein, the modal decomposition separates the modal components of different frequency bands through iterative optimization and extracts the maximum modal feature to characterize the cell state.

[0023] More specifically, please refer to Figure 3 , the modal decomposition includes the following steps: S3.1. Set the number of decomposition modes , the maximum number of iterations , and the tolerance error .

[0024] It can be understood that in the modal decomposition process, parameter initialization is first performed, where the number of decomposition modes is dynamically configured according to the battery type, and the typical value is 3-5 modes; the maximum number of iterations is generally set to 100-200 times to ensure convergence; the tolerance error is recommended to take values of 0.001-0.01 to balance accuracy and efficiency.

[0025] S3.2. Initialize the modal component matrix based on the timing data in the cell voltage matrix , where is the timing length.

[0026] It can be understood that a modal component matrix with a dimension of is created for the timing data of each cell and is initialized to zero.

[0027] S3.3. Use the discrete Fourier transform to convert the timing data from the time domain to the frequency domain to obtain the transformed timing data ; among them, the discrete Fourier transform formula is as follows: ; where represents the value of the th time sampling point, is the time series data after transformation, is the value of the th time sampling point after conversion, is the imaginary unit.

[0028] It can be understood that in the frequency domain conversion stage, an optimized discrete Fourier transform algorithm is adopted, and efficient calculation is achieved through the fast Fourier transform (FFT), and the time domain voltage signal is converted into a frequency domain representation including real and imaginary parts.

[0029] S3.4. By iteratively updating the modal component matrix , gradually optimize each modal component until the termination condition is met.

[0030] In a preferred embodiment, the termination condition for modal decomposition is: the number of iterations exceeds the maximum number of iterations ; or the error condition is satisfied, represents the modal component result of the th iteration, represents the modal component result of the th iteration.

[0031] In a preferred embodiment, the iterative update of the modal component matrix is as follows: ; where is the initial value of each mode, and the dimension is the same as the number of modes; represents the th modal component, represents the original frequency domain signal, represents the th modal component, represents the th modal component updated last time.

[0032] It is understandable that the iterative update process in step S3.4 uses an improved variational mode decomposition algorithm to achieve mode separation. In specific implementation, first, perform the Hilbert transform on the current mode component U[i,:] to extract its instantaneous frequency characteristics as the center frequency of the band-pass filter. Then, apply Gaussian window filtering centered on this frequency to the original signal û in the frequency domain to obtain the updated frequency-domain representation. Next, reconstruct the time-domain signal through the inverse Fourier transform to complete a single-mode update. During the iterative process, the system monitors the relative change in the Euclidean distance of the mode components between two adjacent iterations in real time. When this value is less than the preset tolerance error tol or reaches the maximum number of iterations iter, the optimization is terminated. The final obtained mode components can accurately reflect the battery state characteristics in different frequency bands.

[0033] S3.5. Extract the maximum mode feature from the iterated mode component matrix to obtain the mode feature vector of this battery cell , indicating the th battery cell's th mode component.

[0034] It is understandable that in the mode feature extraction stage, in specific implementation, perform time-domain analysis on the converged mode components, and extract the envelope extreme values of each component as feature points.

[0035] Specifically, select the dominant mode with the largest energy ratio for each battery cell, and record its maximum amplitude as the feature vector .

[0036] Arrange the feature vectors of all battery cells in rows to form a mode matrix . The row vectors of this matrix reflect the global state characteristics of each battery cell, and the column vectors show the distribution of different mode components in the entire battery pack.

[0037] S3.6. Based on the mode feature vector , construct a mode matrix : ; where is the number of decomposed modes, is the number of battery cells, is the maximum mode vector of the th battery cell, is the real part maximum value of the th battery cell's th mode component, .

[0038] Through modal decomposition, the above embodiments can effectively extract the characteristic performance of each battery cell in different frequency domains. For the time-series voltage data of each battery cell, after discrete Fourier transform, k modal components are separated by an iterative optimization method. During each iteration, the relative error between the current modal component and the result of the previous iteration is calculated in real time, and the optimization is terminated when the error is less than the preset tolerance value tol or the maximum number of iterations iter is reached. This dynamic adjustment mechanism ensures the convergence and stability of the decomposition process.

[0039] S4. Use the box plot method to identify inconsistent battery cell numbers for the row vectors of the modal matrix, and take the intersection of the identification results of each component to obtain the target abnormal battery cells.

[0040] In a preferred embodiment, using the box plot method to identify inconsistent battery cell numbers for the row vectors of the modal matrix, and taking the intersection of the identification results of each component to obtain the target abnormal battery cells, including: for each row vector of the modal matrix calculate the upper and lower quartiles and the interquartile range ; if the data point satisfies or , then mark this battery cell as an abnormal battery cell to obtain the abnormal battery cell set ; take the logical intersection of the abnormal battery cell sets of modal components to obtain the intersection A as the target abnormal battery cells, as shown in the following formula: .

[0041] When the above step S4 is specifically implemented, statistical analysis is performed on each row of the modal matrix M (i.e., all battery cell eigenvalues under each modal component). First, calculate the upper quartile Q3, lower quartile Q1, and interquartile range IQR of all battery cell eigenvalues under this modal component. By setting a threshold range of 1.5 times IQR, battery cells that perform abnormally under this modal component can be effectively identified. Considering the misjudgment risk that may exist in a single modal component, this solution further requires that the target abnormal battery cells must be determined to be abnormal in the detection of all k modal components, that is, take the logical intersection of the abnormal sets of each modal component, effectively reducing the false alarm rate. In practical applications, this method can accurately identify the phenomenon of deteriorated battery cell consistency caused by reasons such as aging, uneven temperature, or internal short circuit.

[0042] S5. Determine the voltage value and temperature value of the target abnormal battery cells and send out a warning signal; specifically implemented, the warning signal can include a complete report of the abnormal level, possible reasons, and maintenance suggestions.

[0043] It is understandable that the generation of the warning signal is based on a comprehensive diagnosis of abnormal battery cells. This method not only records the numbers of the abnormal battery cells but also correlates and analyzes the historical change trends of their voltages and temperatures.

[0044] In a specific embodiment, the present invention proposes a battery consistency warning system based on modal decomposition, which is applied to perform the steps of the battery consistency warning method proposed in any of the above embodiments. Specifically in application, the battery consistency warning system of the present invention can be specifically implemented as an intelligent monitoring subsystem in a new energy vehicle battery management system (BMS) or as a core analysis module of a cloud battery health management platform. By integrating in-vehicle data acquisition terminals and cloud computing resources, the system constructs a complete set of battery state monitoring solutions. In actual application, the system can first collect the voltage and temperature data of each battery cell in the battery pack in real time through the in-vehicle CAN bus, and after standardizing and encapsulating them according to the GBT32960 protocol, transmit them to the processing unit. For vehicle models with edge computing capabilities, the system can directly complete modal decomposition and anomaly detection in the in-vehicle computing unit; for vehicle models with limited computing power, the raw data can be uploaded to the cloud server for centralized processing.

[0045] Please refer to Figure 4 , the system specifically includes: A first acquisition module, configured to acquire charge-discharge timing segments of the battery pack, including a voltage array and a temperature array; A second acquisition module, configured to acquire a battery cell voltage matrix constructed by a plurality of charge-discharge timing segments; A modal decomposition module, configured to perform frequency-domain to time-domain coupled modal decomposition on each battery cell timing segment in the battery cell voltage matrix, extract the modal features of each battery cell, and obtain a modal matrix; Among them, the modal decomposition separates modal components in different frequency bands through iterative optimization and extracts the maximum modal features to characterize the state of the battery cell; An anomaly recognition module, configured to use the box plot method to identify inconsistent battery cell numbers for the row vectors of the modal matrix, and take the intersection of the recognition results of each component to obtain the target abnormal battery cells; A warning module, configured to determine the voltage value and temperature value of the target abnormal battery cells and issue a warning signal.

[0046] Specifically in application, during the daily operation of the vehicle, the system can monitor the consistency state of the battery pack in real time. When abnormal battery cells are detected, a hierarchical warning can be sent to the driver through the in-vehicle display screen (such as a prompt warning, power limitation, or suggestion for immediate repair). In the charging scenario, the system can be linked with the charging pile to take protection measures such as adjusting the charging strategy for the abnormal battery.

[0047] Please refer to Figure 5, a computer device 21 is proposed. The computer device can be a terminal or a server. The computer device 21 includes a processor 23, a memory 24, and a network interface 25 connected through a system bus 22. Among them, the processor 23 of the computer device 21 is used to provide computing and control capabilities. The memory of the computer device 24 includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface 26 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the steps of the battery consistency warning method in any of the above embodiments.

[0048] In specific applications, the electronic device of the present invention can be specifically implemented as an in-vehicle computing unit (VCU) of a new energy vehicle, a main control module of a battery management system (BMS), or a dedicated battery health monitoring terminal device.

[0049] In a specific embodiment, the present invention proposes a computer-readable storage medium storing a computer program, which realizes the steps of the battery consistency warning method proposed in any of the above embodiments when executed by a processor.

[0050] To more clearly illustrate the present invention and its advantages, the following will further explain the battery consistency warning method provided by the present invention in combination with specific experimental cases and their related drawings.

[0051] Figure 6 is the voltage curve of the battery cell with poor consistency. According to the GBT32960 protocol, the voltage array of each battery cell at each time point can be obtained. After collecting data for a period of time, the voltage curve of each battery cell can be drawn according to each battery cell. Each line in the figure represents the voltage time series data of a certain battery cell monomer.

[0052] Figure 7 is the battery cell modal heat map, where modes 1, 2, and 3 are intermediate results calculated by the modal decomposition algorithm proposed in the above embodiment.

[0053] According to the above two experimental drawings, from Figure 7 it can be seen from mode 1 that there are significant abnormalities in battery cell #74, corresponding to Figure 6 the significant voltage drop of battery cell #74 in

[0054] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A battery consistency warning method based on modal decomposition, characterized in that The method includes: Obtaining the charge-discharge timing segments of the battery pack, including a voltage array and a temperature array; Obtaining a cell voltage matrix constructed from multiple charge-discharge timing segments; Performing frequency-domain to time-domain coupled modal decomposition on each cell timing segment in the cell voltage matrix, extracting the modal features of each cell, and obtaining a modal matrix; Wherein, the modal decomposition separates modal components in different frequency bands through iterative optimization and extracts the maximum modal features to characterize the cell state; Identifying inconsistent cell numbers for the row vectors of the modal matrix using the box plot method, and taking the intersection of the identification results of each component to obtain the target abnormal cells; Determining the voltage values and temperature values of the target abnormal cells and sending out a warning signal.

2. The battery consistency warning method based on modal decomposition according to claim 1, wherein The obtaining of the charge-discharge timing segments of the battery pack includes: Parsing the battery message data sent by the supervision platform; After sorting and de-duplicating the battery message data according to the acquisition time, obtaining the voltage array and temperature array of the cells; Dividing the arrays based on the charging, discharging, and static states of the battery pack to obtain the charge-discharge timing segments of the battery pack.

3. The battery consistency warning method based on modal decomposition according to claim 1, characterized in that The cell voltage matrix is constructed based on the following method: For a single charge-discharge timing segment, construct a cell voltage matrix : ； Among them, represents the number of battery cells, represents the timing data of the -th battery cell.

4. The battery consistency warning method based on modal decomposition according to claim 3, wherein The modal decomposition includes the following steps: Set the number of decomposition modes , the maximum number of iterations , the tolerance error ; Based on the cell voltage matrix in the timing data Initialize the modal component matrix , where is the timing length; Convert the time-series data using the discrete Fourier transform from the time domain to the frequency domain to obtain the transformed time-series data ; Updating the modal component matrix iteratively to gradually optimize each modal component until the termination condition is met Extract the maximum modal feature from the iterated modal component matrix to obtain the modal feature vector of the battery cell , , denotes the th modal component of the th battery cell; Based on the modal feature vector Construct a modal matrix , denote the maximum modal vector of the th power cell.

5. The battery consistency warning method based on modal decomposition according to claim 4, wherein The iteratively updated modal component matrix , as shown in the following formula: ； Among them, represents the th modal component, represents the original frequency-domain signal, represents the th modal component, represents the th modal component of the previous update.

6. The battery consistency warning method based on modal decomposition according to claim 4, wherein The termination condition of the modal decomposition is: The number of iterations exceeds the maximum number of iterations ; or satisfy the error condition , represents the modal component result of the th iteration, represents the modal component result of the th iteration.

7. The battery consistency warning method based on modal decomposition according to claim 4, wherein, The identifying of inconsistent cell numbers for the row vectors of the modal matrix using the box plot method and taking the intersection of the identification results of each component to obtain the target abnormal cells includes: For each row vector of the modal matrix calculate the upper and lower quartiles and the interquartile range , ; If the data point satisfies or , then mark this battery cell as an abnormal battery cell to obtain the abnormal battery cell set ; For the abnormal cell sets of the modal components, take the logical intersection to obtain the intersection A and use it as the target abnormal cell, as shown in the following formula: 。 8. A battery consistency warning system based on modal decomposition, which is applied to execute the steps of the battery consistency warning method according to any one of claims 1-7, characterized in that, The system includes: A first obtaining module, configured to obtain the charge-discharge timing segments of the battery pack, including a voltage array and a temperature array; A second obtaining module, configured to obtain a cell voltage matrix constructed from multiple charge-discharge timing segments; A modal decomposition module, configured to perform frequency-domain to time-domain coupled modal decomposition on each cell timing segment in the cell voltage matrix, extract the modal features of each cell, and obtain a modal matrix; Wherein, the modal decomposition separates modal components in different frequency bands through iterative optimization and extracts the maximum modal features to characterize the cell state; An abnormal identification module, configured to identify inconsistent cell numbers for the row vectors of the modal matrix using the box plot method and take the intersection of the identification results of each component to obtain the target abnormal cells; A warning module, configured to determine the voltage values and temperature values of the target abnormal cells and send out a warning signal.

9. An electronic device, characterized in that, Including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the battery consistency warning method according to any one of claims 1-7 are implemented.

10. A computer-readable storage medium, characterized in that, Stores a computer program, and when the computer program is executed by the processor, the steps of the battery consistency warning method according to any one of claims 1-7 are implemented.

Images