Battery voltage fault diagnosis method and device, electronic equipment, medium and product

Abstract

The invention discloses a battery voltage fault diagnosis method. The method comprises the following steps: acquiring a voltage signal of each battery monomer; performing variational mode decomposition processing on the voltage signal of each battery monomer to obtain a plurality of mode signals corresponding to each battery monomer; performing high-frequency de-noising processing on each modal signal to obtain a de-noised modal signal corresponding to each battery monomer; performing local energy calculation on the de-noised modal signal by using a preset sliding window to obtain multiple pieces of single window signal energy corresponding to each battery monomer; calculating an energy difference mean value corresponding to each battery monomer according to the single window signal energy; and according to a preset energy difference threshold value and the energy difference mean value, determining an abnormal single battery. The method can solve the problems that an existing method is low in anomaly detection precision, prone to missed judgment, low in real-time performance and difficult to adapt to complex working conditions.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery voltage fault diagnosis method, device, electronic device, readable storage medium, and computer program product. Background Art

[0002] Driven by global energy conservation and emission reduction policies and growing consumer demand for green travel, electric vehicles (EVs), with their outstanding advantages such as cleanliness, environmental protection, and high energy efficiency, have rapidly emerged in the automotive market and achieved widespread popularity. Whether for urban commuting or long-distance travel, EVs are becoming increasingly common, becoming a key force in the green transformation of the transportation sector. In the operation of electric vehicles, battery safety is a core element in ensuring vehicle performance and user safety. In existing technologies, thresholds for battery voltage or other related parameters are usually set first. When a battery parameter exceeds the set threshold, the battery cell is judged to be abnormal. However, in practice, it has been found that with existing threshold determination methods, changes in battery voltage and other physical parameters may be small, making it difficult to reflect minor battery faults and easily missed. Furthermore, existing methods are difficult to adapt to complex operating conditions. Battery parameter fluctuations under different environments may exceed the normal range. Relying solely on static thresholds cannot accurately identify faults, posing a hidden danger to the safe operation of electric vehicles. Summary of the Invention

[0003] In view of the above problems, the present application provides a battery voltage fault diagnosis method, device, electronic device, readable storage medium and computer program product, which can solve the problems of low abnormality detection accuracy, easy missed detection, low real-time performance and difficulty in adapting to complex working conditions in existing methods.

[0004] In a first aspect, the present application provides a battery voltage fault diagnosis method, comprising: Obtain the voltage signal of each battery cell; Performing variational modal decomposition processing on the voltage signal of each battery cell to obtain multiple modal signals corresponding to each battery cell; Performing high-frequency denoising processing on each of the modal signals to obtain a denoised modal signal corresponding to each battery cell; Performing local energy calculation on the denoised modal signal using a preset sliding window to obtain multiple single-window signal energies corresponding to each battery cell; Calculating the energy difference mean corresponding to each battery cell according to the single window signal energy; According to the preset energy difference threshold and the energy difference mean, it is determined that there is an abnormal battery cell.

[0005] In the above technical solution, this method can effectively improve the accuracy of battery voltage fault diagnosis, reduce missed judgments, and enhance real-time performance, thereby better adapting to fault detection needs under complex working conditions.

[0006] In some embodiments, obtaining the voltage signal of each battery cell includes: Obtain the original voltage signal of each battery cell from the battery management system; The original voltage signal of each battery cell is preprocessed to obtain a voltage signal of each battery cell.

[0007] In the above technical solution, this method can improve the accuracy and reliability of voltage signal acquisition, thereby providing a high-quality data basis for subsequent accurate fault diagnosis.

[0008] In some embodiments, performing variational modal decomposition processing on the voltage signal of each battery cell to obtain multiple modal signals corresponding to each battery cell includes: Obtaining variational modal decomposition parameters; wherein the variational modal decomposition parameters include at least the number of modes, a regularization parameter, and an objective function; Performing variational modal decomposition processing on the voltage signal of each battery cell according to the variational modal decomposition parameter to obtain an original modal signal of the modal quantity corresponding to each battery cell; In order from front to back, a preset number of selected signals are selected from the original modal signals as multiple modal signals corresponding to each battery cell.

[0009] In the above technical solution, this method can effectively extract multi-scale characteristic modes in the battery cell voltage signal, providing richer and more discriminative signal components for subsequent fault diagnosis.

[0010] In some embodiments, performing high-frequency denoising on each modal signal to obtain a denoised modal signal corresponding to each battery cell includes: Acquire wavelet transform parameters; wherein the wavelet transform parameters include at least a mother wavelet function, a scale factor, and a translation factor; Perform wavelet transform processing on each of the modal signals according to the wavelet transform parameters to obtain a denoised modal signal corresponding to each battery cell.

[0011] In the above technical solution, this method can accurately remove the high-frequency noise components in the modal signal through wavelet transform, significantly improve the signal purity while retaining the fault characteristic information, and provide a more reliable modal signal basis for subsequent energy analysis.

[0012] In some embodiments, the performing local energy calculation on the denoised modal signal using a preset sliding window to obtain multiple single-window signal energies corresponding to each battery cell includes: On the denoised modal signal, gradually sliding a preset window from left to right; Calculating the signal energy value in the preset window after each sliding step to obtain the signal energy values ​​in multiple windows corresponding to each of the denoised modal signals; A plurality of single-window signal energies corresponding to each battery cell are determined according to the signal energy values ​​in the plurality of windows corresponding to each of the denoised modal signals.

[0013] In the above technical solution, this method can realize refined local analysis of signal energy through a sliding window mechanism, effectively capture the dynamic fluctuation characteristics of battery cell voltage in the time domain, and provide energy series data with high time resolution for subsequent energy difference calculation.

[0014] In some embodiments, calculating the energy difference mean corresponding to each battery cell based on the single window signal energy includes: Calculating the absolute value of the difference in single window signal energy between each battery cell and other battery cells based on the single window signal energy to obtain multiple absolute values ​​of the window signal energy differences corresponding to each battery cell; The average value is calculated based on the absolute value of the energy difference of the window signal to obtain the energy difference average value corresponding to each battery cell.

[0015] In the above technical solution, this method can effectively characterize the consistency of local energy fluctuations of the voltage signals of each cell in the battery pack by quantifying the energy differences between battery cells and calculating the average, thereby providing reliable quantitative indicators for subsequent fault diagnosis based on energy differences.

[0016] In some embodiments, determining the presence of an abnormal battery cell based on a preset energy difference threshold and the energy difference mean value includes: A battery cell with an energy difference mean value greater than a preset energy difference threshold is determined as an abnormal battery cell.

[0017] In the above technical solution, this method can quickly and accurately locate abnormal battery cells whose energy fluctuations significantly deviate from the normal range, and achieve efficient and reliable fault isolation and early warning.

[0018] In some embodiments, after determining that an abnormal battery cell exists based on the preset energy difference threshold and the energy difference mean, the method further includes: generating an abnormality detection result according to the abnormal battery cell; The abnormality detection result is fed back to the battery management system.

[0019] In the above technical solution, the method can realize closed-loop management of fault information by generating and feeding back abnormality detection results, and provide a real-time decision-making basis for the battery management system.

[0020] In some embodiments, after feeding back the abnormality detection result to the battery management system, the method further includes: After the battery management system receives the abnormality detection result, it determines an abnormality handling strategy according to the abnormality detection result; wherein the abnormality handling strategy includes a charge and discharge adjustment strategy and a backup battery switching strategy; The battery management system executes the corresponding operation process of the abnormality handling strategy.

[0021] In the above technical solution, the method can dynamically select processing strategies such as charge and discharge control or redundant switching according to the type of abnormality, thereby effectively improving the safe operation capability and fault tolerance level of electric vehicles under complex working conditions.

[0022] In a second aspect, the present application provides a battery voltage fault diagnosis device, comprising: An acquisition unit, used to acquire a voltage signal of each battery cell; a variational modal decomposition unit, configured to perform variational modal decomposition processing on the voltage signal of each battery cell to obtain a plurality of modal signals corresponding to each battery cell; a denoising unit, configured to perform high-frequency denoising processing on each of the modal signals to obtain a denoised modal signal corresponding to each battery cell; a first calculation unit, configured to perform local energy calculation on the denoised modal signal using a preset sliding window to obtain a plurality of single-window signal energies corresponding to each battery cell; a second calculation unit, configured to calculate an energy difference mean corresponding to each battery cell according to the single window signal energy; The determining unit is configured to determine a battery cell having an abnormality according to a preset energy difference threshold and the energy difference mean.

[0023] In the above technical solution, the device can effectively improve the accuracy of battery voltage fault diagnosis, reduce missed judgments, and enhance real-time performance, so as to better adapt to the fault detection needs under complex working conditions.

[0024] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the battery voltage fault diagnosis method described in any one of the first aspects.

[0025] In a fourth aspect, the present application provides a readable storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor, the battery voltage fault diagnosis method described in any one of the first aspects is executed.

[0026] In a fifth aspect, the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it executes the battery voltage fault diagnosis method described in any one of the first aspects.

[0027] The beneficial effects of the present application are: it can achieve high-precision, high-adaptability and high-real-time detection of battery cell energy anomalies based on variational mode decomposition (VMD), wavelet transform, multimodal signal analysis, energy difference comparison and sliding window mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 Schematic diagram of a flow chart of a battery voltage fault diagnosis method in some embodiments of the present application; Figure 2 Schematic diagram of a flow chart of a battery voltage fault diagnosis method in some embodiments of the present application; Figure 3 This is a schematic structural diagram of a battery voltage fault diagnosis device in some embodiments of the present application; Figure 4 This is a schematic diagram of the structure of an electronic device in some embodiments of the present application. DETAILED DESCRIPTION

[0030] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0032] In the description of the embodiments of this application, technical terms such as "first" and "second" are used solely to distinguish between different objects and should not be understood to indicate or imply relative importance, or to implicitly indicate the quantity, specific order, or primary and secondary relationship of the technical features indicated. In the description of the embodiments of this application, "multiple" means two or more (including two). Similarly, "multiple groups" means two or more (including two groups), and "multiple sheets" means two or more (including two sheets), unless otherwise specifically defined.

[0033] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0034] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0035] Currently, battery management systems widely use anomaly detection methods based on physical parameters such as battery voltage, temperature, and internal impedance. These traditional methods generally include the following: (1) Threshold determination method: By setting the threshold of battery voltage or other related parameters, when a certain parameter of the battery exceeds the set threshold, the battery cell is judged to be abnormal.

[0036] While this approach is simple and easy to implement, it faces several practical challenges. For example, the battery's voltage and other physical parameters may fluctuate slightly, making it difficult to detect even minor faults, leading to low sensitivity and potential missed detections. Furthermore, batteries may experience complex fluctuations in different operating environments, making static thresholds ineffective for effectively identifying faults.

[0037] (2) Anomaly detection based on feature extraction: The frequency, amplitude and other features of the battery signal are extracted and anomaly detection is performed on these features using statistical analysis methods.

[0038] Although this method improves the accuracy of anomaly detection to a certain extent, it still relies on traditional signal processing methods such as Fourier transform, which makes it difficult to process nonlinear and non-stationary signals.

[0039] (3) Wavelet analysis: The characteristics of the battery signal are extracted through wavelet transform to analyze the battery status.

[0040] Although wavelet analysis can process non-stationary signals, it may not be as effective as more detailed signal decomposition methods, such as variational mode decomposition (VMD), in processing multimodal signals.

[0041] In summary, it can be seen that existing methods are prone to missed detections, especially when the battery operating state is more complex, making it difficult to accurately identify abnormal cells; at the same time, they are unable to fully utilize modern signal processing technologies (such as VMD) to extract complex signal features, resulting in the inability to accurately capture potential abnormalities in battery cells.

[0042] In response to the above technical problems, an embodiment of the present application provides a battery voltage fault diagnosis method, which can detect battery cell energy anomalies based on variational mode decomposition (VMD) and wavelet transform, and significantly improve the accuracy, real-time and adaptability of battery cell health status monitoring through multimodal signal analysis, energy difference detection and sliding window mechanism.

[0043] It can be seen that this method has broad application prospects in battery management systems, especially in electric vehicles, energy storage systems and other intelligent battery management systems, and can effectively improve battery safety, life and operating efficiency.

[0044] like Figure 1 As shown, some embodiments of the present application provide a battery voltage fault diagnosis method, which includes: S101, obtaining a voltage signal of each battery cell; S102, performing variational modal decomposition processing on the voltage signal of each battery cell to obtain multiple modal signals corresponding to each battery cell; S103, performing high-frequency denoising processing on each modal signal to obtain a denoised modal signal corresponding to each battery cell; S104, using a preset sliding window to perform local energy calculation on the denoised modal signal to obtain multiple single-window signal energies corresponding to each battery cell; S105. Calculate the energy difference mean corresponding to each battery cell based on the single window signal energy; S106 : Determine which battery cell has abnormality according to a preset energy difference threshold and an energy difference mean.

[0045] In the above embodiment, the method can combine the precise energy features after VMD decomposition and wavelet denoising, effectively improving the reliability of anomaly detection and reducing misjudgments and missed judgments caused by factors such as signal instability and data noise.

[0046] In some embodiments, obtaining a voltage signal of each battery cell includes: Obtain the original voltage signal of each battery cell from the battery management system; The original voltage signal of each battery cell is preprocessed to obtain the voltage signal of each battery cell.

[0047] In some embodiments, the method may collect voltage signal data of the battery cells from a battery management system.

[0048] For example, assuming there are N battery cells, the voltage signal collected from each battery cell is V i (t), i = 1, 2, .... Where N represents the monomer number and t represents time.

[0049] In the above embodiment, the method can improve the accuracy and reliability of voltage signal acquisition, thereby providing a high-quality data basis for subsequent accurate fault diagnosis.

[0050] In some embodiments, a variational modal decomposition process is performed on the voltage signal of each battery cell to obtain multiple modal signals corresponding to each battery cell, including: Obtaining variational modal decomposition parameters; wherein the variational modal decomposition parameters include at least the number of modes, a regularization parameter, and an objective function; Performing variational modal decomposition processing on the voltage signal of each battery cell according to the variational modal decomposition parameters to obtain the original modal signal of the modal number corresponding to each battery cell; In order from front to back, a preset number of signals are selected from the original modal signals as multiple modal signals corresponding to each battery cell.

[0051] In some embodiments, the method may perform VMD decomposition on the acquired voltage sequence, with the goal of minimizing the following objective function: ; Among them, u k (t) is the Kth modal component; is the corresponding frequency domain representation; K is the number of modes, and α is the regularization parameter that controls the smoothness of the signal. The output of VMD is the original voltage signal v i (t) is decomposed into K modal signals u k (t) and the corresponding frequency ω k .

[0052] In some embodiments, the method can be used to calculate the voltage signal v of each battery cell. i (t) Perform VMD processing to obtain K modal components. This method selects the first M modes (usually 5 modes) for further processing.

[0053] Exemplarily, the method can obtain M modal signals corresponding to each battery monomer after processing.

[0054] In the above embodiment, the method can decompose the voltage signal of the battery monomer into multiple modes by using the variational mode decomposition (VMD), so as to effectively extract the frequency components in the signal and enhance the recognition ability of the complex fluctuations of the battery signal. Compared with the traditional single signal analysis method, the method can more accurately capture the energy change of the battery, especially in the case of nonlinear and non-stationary signals, and improves the sensitivity of the abnormal detection.

[0055] In some embodiments, each modal signal is subjected to high-frequency denoising processing to obtain a denoised modal signal corresponding to each battery monomer, comprising: obtaining wavelet transform parameters; wherein the wavelet transform parameters at least include a mother wavelet function, a scale factor and a translation factor; According to the wavelet transform parameters, each modal signal is subjected to wavelet transform processing to obtain a denoised modal signal corresponding to each battery monomer.

[0056] In some embodiments, the method can apply wavelet transform to each modal signal v k (t) obtained from VMD for denoising processing, use a higher frequency wavelet basis (such as Daubechies wavelet), and remove the noise component in the low-frequency approximation coefficient. The formula of wavelet denoising is: ; Wherein, f(t) is the signal to be analyzed, Ψ(t) is the mother wavelet function, a is the scale factor, and b is the translation factor.

[0057] ; Wherein, DWT represents the discrete wavelet transform, and IDWT represents the inverse discrete wavelet transform. In this way, the high-frequency noise in the signal can be effectively removed.

[0058] Exemplarily, the method can obtain M denoised modal signals corresponding to each battery monomer after wavelet transform.

[0059] In the above embodiment, the method can use wavelet transform to denoise each modal signal, effectively eliminate the interference of high-frequency noise, ensure the accuracy of signal analysis, and reduce the possibility of false judgment and missed judgment.

[0060] In the above embodiment, the method can greatly reduce the interference of noise in the signal on the final detection result through wavelet transform denoising processing, thereby improving the stability and reliability of the detection. By eliminating unnecessary signal fluctuations, the abnormal condition of the battery monomer can be accurately judged.

[0061] In some embodiments, a preset sliding window is used to perform local energy calculation on the denoised modal signal to obtain multiple single-window signal energies corresponding to each battery cell, including: On the denoised modal signal, the preset window is gradually slid from left to right; Calculate the signal energy value in the preset window after each sliding step to obtain the signal energy values ​​in multiple windows corresponding to each denoised modal signal; According to the signal energy values ​​in the multiple windows corresponding to each denoised modal signal, the signal energies of the multiple single windows corresponding to each battery cell are determined.

[0062] In some embodiments, a sliding window is configured to calculate local features of a signal by sliding a fixed-size window across the signal. The window size is set to w, and the window is progressively slid across the signal from left to right, one sample at a time, to calculate the energy within the current window.

[0063] In some embodiments, within the window [t, t+w], the battery cell signal u k Energy E of (t) k (t) is calculated as follows: ; Among them, u k (t) is the modal signal after wavelet transform denoising. Through this step, the energy value E of each battery cell signal in each sliding window is obtained. k (t).

[0064] For example, the method can perform corresponding calculations on each denoised modal signal to obtain multiple window signal energies E k (t). That is, each battery cell has corresponding multiple window energy E k (t).

[0065] In the above embodiment, the method uses a sliding window mechanism to calculate energy differences, responding to changes in battery status in real time. During battery operation, energy fluctuations between battery cells can vary dramatically. The sliding window technique can dynamically adjust the detection range, avoiding detection errors caused by static thresholds.

[0066] In the above embodiment, the method also enables real-time monitoring of battery cell energy through a sliding window, enabling timely detection of abnormal changes in battery status. Traditional methods often rely on static, periodic checks, which can result in delayed responses or missed detections. However, the sliding window approach used in this method enables rapid anomaly identification in real-time signal processing.

[0067] In some embodiments, calculating the energy difference mean corresponding to each battery cell based on the single window signal energy includes: Calculate the absolute value of the difference between the single window signal energy of each battery cell and other battery cells based on the single window signal energy, and obtain the absolute values ​​of the differences in the multiple window signal energies corresponding to each battery cell; The average value of the energy difference of each battery cell is obtained by calculating the average value according to the absolute value of the energy difference of the window signal.

[0068] In some embodiments, in order to detect abnormal cells, it is necessary to compare the energy differences between battery cells. Assume that at a certain time t, the energy difference ΔE between battery cell i and battery cell j is ij (t) is defined as: ; Among them, E i (t) and E j (t) are the energies of battery cells i and j at time t, respectively.

[0069] For example, the processed battery cell 1 has corresponding multiple window energies E k1 (t), the battery cell 2 after treatment also has multiple window energies E k2 (t). Based on this, when analyzing the energy difference between battery cell 1 and battery cell 2, you can choose any E k1 (t) and any E k2 (t) Calculate the absolute value of the difference.

[0070] In some embodiments, the average value of the energy difference is calculated. In order to comprehensively consider the energy difference between battery cells, the average value of the energy difference between each pair of battery cells is calculated: ; Where N is the total number of battery cells, and meandiff(t) is the average energy difference between all battery cells.

[0071] Exemplarily, the method may calculate the average of the absolute values ​​of all energy differences, and thus determine the obtained average as the average energy difference of the battery cell 1 .

[0072] In the above embodiment, the method can effectively characterize the consistency of local energy fluctuations of the voltage signals of each cell in the battery pack by quantifying the energy differences between battery cells and calculating the average, thereby providing a reliable quantitative indicator for subsequent fault diagnosis based on energy differences.

[0073] In some embodiments, determining that an abnormal battery cell exists according to a preset energy difference threshold and an energy difference mean value includes: A battery cell with an energy difference mean value greater than a preset energy difference threshold is determined as an abnormal battery cell.

[0074] In some embodiments, the method may set a threshold δ to determine abnormality.

[0075] In some embodiments, if the mean difference meandiff(t) at a certain time t exceeds a threshold δ, it is considered that battery cell i may be abnormal: if mean diff(t)>δ, then mark the cell as abnormal.

[0076] In the above embodiment, this method can better adapt to changes in the battery's complex operating environment by calculating the energy difference between each cell and other cells, rather than simply analyzing the energy value of a single cell. This relative difference-based detection method can not only identify anomalies in a single mode, but also capture the relative difference with other cells, providing more accurate anomaly judgment.

[0077] In some embodiments, after determining that an abnormal battery cell exists based on a preset energy difference threshold and an energy difference mean, the method further includes: Generate an abnormality detection result based on the abnormal battery cell; Feedback abnormality detection results to the battery management system.

[0078] In the above embodiment, the method can quickly feed back the abnormal detection results of the battery cells to the battery management system (BMS), facilitating the system to make real-time decisions, such as adjusting the charging and discharging strategy, switching the backup battery, etc., thereby effectively avoiding the greater risks caused by battery failure.

[0079] In some embodiments, after feeding back the abnormality detection result to the battery management system, the method further includes: After receiving the abnormality detection result, the battery management system determines the abnormality handling strategy according to the abnormality detection result; wherein the abnormality handling strategy includes a charge and discharge adjustment strategy and a backup battery switching strategy; Execute the corresponding operation process of the abnormal handling strategy through the battery management system.

[0080] In the above embodiment, the method can dynamically select processing strategies such as charge and discharge control or redundant switching according to the abnormality type, thereby effectively improving the safe operation capability and fault tolerance level of electric vehicles under complex working conditions.

[0081] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be described clearly and completely below. In some embodiments, Figure 2As shown, the battery voltage fault diagnosis method includes: S201, signal acquisition and preprocessing: obtaining single cell voltage signal data.

[0082] In some embodiments, the method may obtain battery cell voltage signal data from a battery management system.

[0083] In some embodiments, the acquired battery cell voltage signal data needs to be pre-processed before use, wherein the pre-processing includes noise removal, standardization and other processing methods.

[0084] S202, Variational Mode Decomposition (VMD): Decompose the voltage signal into multiple modes.

[0085] In some embodiments, the method may perform VMD decomposition on the voltage signal of the battery cell to decompose the signal into multiple modes (IMFs).

[0086] In some embodiments, the method can separate multiple frequency components in the signal through VMD, thereby extracting the essential characteristics of the battery cell signal.

[0087] S203. Wavelet transform denoising: Apply wavelet transform to each modal signal.

[0088] In some embodiments, the method can remove the low-frequency approximate signal, retain the main energy components, eliminate the influence of noise, and improve signal quality.

[0089] S204, sliding window energy calculation: calculate the local energy of the battery cell signal.

[0090] In some embodiments, the method can use a sliding window technique to perform local energy calculations on the signals of the battery cells. By calculating the energy within each window, the fluctuation of battery energy can be dynamically monitored and abnormal changes can be detected.

[0091] S205. Energy difference analysis: Calculate the energy difference between monomers and take the average.

[0092] In some embodiments, the method can calculate the energy difference between each battery cell and the other cells. At the same time, by comparing the energy differences between each pair of cells and taking the average, cells with large energy fluctuation differences from other cells are identified as abnormal.

[0093] S206, abnormality determination: if the energy difference exceeds the threshold, it is marked as an abnormal monomer.

[0094] In some embodiments, if the energy difference of a cell exceeds a set threshold, the cell is marked as abnormal. The threshold can be dynamically adjusted based on the characteristics of different battery systems.

[0095] In the above embodiment, the method is not only applicable to conventional battery cell detection, but can also be extended to various types of battery systems, including lithium batteries, lead-acid batteries, etc., and has strong versatility.

[0096] In the above embodiment, the energy difference analysis and dynamic threshold setting of the method can enable the detection process to be flexibly adjusted according to different application scenarios, different battery models and environmental conditions to meet different safety detection requirements.

[0097] Figure 3 The schematic diagram of the structure of a battery voltage fault diagnosis device is shown. It should be understood that the device is Figure 1 The method executed in the embodiment corresponds to the embodiment, and the steps involved in the aforementioned method can be executed. The specific functions and effects of the device can be found in the description above. To avoid repetition, detailed description is appropriately omitted here.

[0098] The battery voltage fault diagnosis device includes: An acquisition unit 310 is configured to acquire a voltage signal of each battery cell; A variational modal decomposition unit 320 is configured to perform variational modal decomposition processing on the voltage signal of each battery cell to obtain multiple modal signals corresponding to each battery cell; A denoising unit 330 is configured to perform high-frequency denoising processing on each modal signal to obtain a denoised modal signal corresponding to each battery cell; A first calculation unit 340 is configured to perform local energy calculation on the denoised modal signal using a preset sliding window to obtain multiple single-window signal energies corresponding to each battery cell; A second calculation unit 350 is configured to calculate the energy difference mean corresponding to each battery cell based on the single window signal energy; The determining unit 360 is configured to determine an abnormal battery cell according to a preset energy difference threshold and an energy difference mean.

[0099] In some embodiments, the acquisition unit 310 includes: A first acquisition subunit 311 is configured to acquire an original voltage signal of each battery cell from a battery management system; The pre-processing sub-unit 312 is configured to pre-process the original voltage signal of each battery cell to obtain the voltage signal of each battery cell.

[0100] In some embodiments, the variational mode decomposition unit 320 includes: The second acquisition subunit 321 is used to obtain variational modal decomposition parameters; wherein the variational modal decomposition parameters include at least the number of modes, regularization parameters and objective function; The variational modal decomposition subunit 322 is configured to perform variational modal decomposition on the voltage signal of each battery monomer according to the variational modal decomposition parameter, to obtain a raw modal signal corresponding to a modal number of each battery monomer. The selection subunit 323 is configured to select a preset number of signals from the raw modal signals in a front-to-back order as the modal signals corresponding to each battery monomer.

[0101] In some embodiments, the denoising unit 330 includes: The third acquisition subunit 331 is configured to acquire wavelet transform parameters, wherein the wavelet transform parameters at least include a mother wavelet function, a scale factor, and a translation factor. The wavelet transform processing 332 is configured to perform wavelet transform on each modal signal according to the wavelet transform parameters, to obtain a denoised modal signal corresponding to each battery monomer.

[0102] In some embodiments, the first calculation unit 340 includes: The sliding subunit 341 is configured to slide a preset window on the denoised modal signal in a left-to-right direction step by step. The calculation subunit 342 is configured to calculate a signal energy value in the preset window after each step of sliding, to obtain a plurality of window-in signal energy values corresponding to each denoised modal signal. The determination subunit 343 is configured to determine a single-window signal energy corresponding to each battery monomer according to the plurality of window-in signal energy values corresponding to each denoised modal signal.

[0103] In some embodiments, the second calculation unit 350 is specifically configured to calculate, according to the single-window signal energy, a difference absolute value of the single-window signal energy between each battery monomer and other battery monomers, to obtain a plurality of window signal energy difference absolute values corresponding to each battery monomer; and perform mean value calculation on the window signal energy difference absolute values, to obtain an energy difference mean value corresponding to each battery monomer.

[0104] In some embodiments, the determination unit 360 is specifically configured to determine, as the battery monomer with an anomaly, the battery monomer with the energy difference mean value greater than a preset energy difference threshold.

[0105] In some embodiments, the battery voltage fault diagnosis apparatus further includes: The generation unit 370 is configured to generate an anomaly detection result according to the battery monomer with an anomaly after the determination unit 360 determines the battery monomer with an anomaly. The feedback unit 380 is configured to feed back the anomaly detection result to a battery management system.

[0106] In some embodiments, the battery voltage fault diagnosis apparatus further includes: a determination unit 360 configured to feed back the abnormality detection result to the battery management system after the feedback unit 380 feeds back the abnormality detection result, and after the battery management system receives the abnormality detection result, determine an abnormality handling strategy based on the abnormality detection result; wherein the abnormality handling strategy includes a charge and discharge adjustment strategy and a backup battery switching strategy; The processing unit 390 is configured to execute an operation process corresponding to the abnormality handling strategy through the battery management system.

[0107] like Figure 4 As shown, the present application provides an electronic device 400, which includes a processor 401 and a memory 402. The processor 401 and the memory 402 are interconnected and communicate with each other through a communication bus 403 and / or other forms of connection mechanisms (not shown). The memory 402 stores a computer program executable by the processor 401. When the computing device is running, the processor 401 executes the computer program to perform the method in any of the aforementioned optional implementations.

[0108] The present application provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the method in any of the aforementioned optional implementations is executed.

[0109] Among them, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0110] The present application provides a computer program product, which includes computer programmability. When the computer program is executed by a processor, the method in any of the aforementioned optional implementations is executed.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A battery voltage fault diagnosis method, characterized in that: include: Obtain the voltage signal of each battery cell; Performing variational modal decomposition processing on the voltage signal of each battery cell to obtain multiple modal signals corresponding to each battery cell; Performing high-frequency denoising processing on each of the modal signals to obtain a denoised modal signal corresponding to each battery cell; Performing local energy calculation on the denoised modal signal using a preset sliding window to obtain multiple single-window signal energies corresponding to each battery cell; Calculating the energy difference mean corresponding to each battery cell according to the single window signal energy; According to the preset energy difference threshold and the energy difference mean, it is determined that there is an abnormal battery cell.

2. The battery voltage fault diagnosis method according to claim 1, characterized in that: The step of obtaining the voltage signal of each battery cell includes: Obtain the original voltage signal of each battery cell from the battery management system; The original voltage signal of each battery cell is preprocessed to obtain a voltage signal of each battery cell.

3. The battery voltage fault diagnosis method according to claim 1, characterized in that: The performing variational modal decomposition processing on the voltage signal of each battery cell to obtain multiple modal signals corresponding to each battery cell includes: Obtaining variational modal decomposition parameters; wherein the variational modal decomposition parameters include at least the number of modes, a regularization parameter, and an objective function; Performing variational modal decomposition processing on the voltage signal of each battery cell according to the variational modal decomposition parameter to obtain an original modal signal of the modal quantity corresponding to each battery cell; In order from front to back, a preset number of signals are selected from the original modal signals as multiple modal signals corresponding to each battery cell.

4. The battery voltage fault diagnosis method according to claim 1, characterized in that: The performing high-frequency denoising processing on each of the modal signals to obtain a denoised modal signal corresponding to each battery cell includes: Acquire wavelet transform parameters; wherein the wavelet transform parameters include at least a mother wavelet function, a scale factor, and a translation factor; Perform wavelet transform processing on each of the modal signals according to the wavelet transform parameters to obtain a denoised modal signal corresponding to each battery cell.

5. The battery voltage fault diagnosis method according to claim 1, characterized in that: The method of using a preset sliding window to perform local energy calculation on the denoised modal signal to obtain multiple single-window signal energies corresponding to each battery cell includes: On the denoised modal signal, gradually sliding a preset window from left to right; Calculating the signal energy value in the preset window after each sliding step to obtain the signal energy values ​​in multiple windows corresponding to each of the denoised modal signals; A plurality of single-window signal energies corresponding to each battery cell are determined according to the signal energy values ​​in the plurality of windows corresponding to each of the denoised modal signals.

6. The battery voltage fault diagnosis method according to claim 1, characterized in that: Calculating the energy difference mean corresponding to each battery cell according to the single window signal energy includes: Calculating the absolute value of the difference in single window signal energy between each battery cell and other battery cells based on the single window signal energy to obtain multiple absolute values ​​of the window signal energy differences corresponding to each battery cell; The average value is calculated based on the absolute value of the energy difference of the window signal to obtain the energy difference average value corresponding to each battery cell.

7. The battery voltage fault diagnosis method according to claim 1, characterized in that: The step of determining an abnormal battery cell according to a preset energy difference threshold and the energy difference mean value includes: A battery cell with an energy difference mean value greater than a preset energy difference threshold is determined as an abnormal battery cell.

8. The battery voltage fault diagnosis method according to claim 1, characterized in that: After determining that an abnormal battery cell exists based on the preset energy difference threshold and the energy difference mean, the method further includes: generating an abnormality detection result according to the abnormal battery cell; The abnormality detection result is fed back to the battery management system.

9. The battery voltage fault diagnosis method according to claim 8, characterized in that: After feeding back the abnormality detection result to the battery management system, the method further includes: After the battery management system receives the abnormality detection result, it determines an abnormality handling strategy according to the abnormality detection result; wherein the abnormality handling strategy includes a charge and discharge adjustment strategy and a backup battery switching strategy; The battery management system executes the corresponding operation process of the abnormality handling strategy.

10. A battery voltage fault diagnosis device, characterized in that: The battery voltage fault diagnosis device comprises: An acquisition unit, used to acquire a voltage signal of each battery cell; a variational modal decomposition unit, configured to perform variational modal decomposition processing on the voltage signal of each battery cell to obtain a plurality of modal signals corresponding to each battery cell; a denoising unit, configured to perform high-frequency denoising processing on each of the modal signals to obtain a denoised modal signal corresponding to each battery cell; a first calculation unit, configured to perform local energy calculation on the denoised modal signal using a preset sliding window to obtain a plurality of single-window signal energies corresponding to each battery cell; a second calculation unit, configured to calculate an energy difference mean corresponding to each battery cell according to the single window signal energy; The determining unit is configured to determine a battery cell having an abnormality according to a preset energy difference threshold and the energy difference mean.

11. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the battery voltage fault diagnosis method according to any one of claims 1 to 9.

12. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the battery voltage fault diagnosis method according to any one of claims 1 to 9 is executed.

13. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the battery voltage fault diagnosis method according to any one of claims 1 to 9 is executed.

Images