Battery pack anomaly detection method and system based on average deviation and wavelet analysis

Abstract

The invention provides a battery pack anomaly detection method and system based on average deviation and wavelet analysis, and relates to the technical field of new energy vehicle power battery pack detection, and the method comprises the steps: obtaining the voltage data of each single battery in a power battery pack in real time, and carrying out the preprocessing; converting the preprocessed voltage data into a time sequence format, and compressing and storing by adopting a time partitioning strategy; calling the stored voltage time sequence data of each battery cell, and obtaining the average voltage deviation of each single battery cell by using a voltage deviation calculation method; carrying out wavelet transformation on the average voltage deviation of each single battery cell, carrying out multi-scale decomposition by adopting a wavelet basis function, obtaining high-frequency components of different frequency bands, analyzing energy distribution of the high-frequency components, calculating statistical characteristics of high-frequency energy, setting an energy threshold value of the single battery, and comparing the statistical characteristics with the energy threshold value, so as to obtain the high-frequency energy of the single battery cell. And determining whether the battery cell is abnormal or not.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of new energy vehicle power battery pack detection, in particular to a battery pack abnormality detection method and system based on average deviation and wavelet analysis. BACKGROUND

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

[0003] The battery management system (BMS) implements management and control of the power battery pack in new energy vehicles (such as electric vehicles and hybrid vehicles), which is directly related to the safety, endurance, performance and battery life of the vehicle. The battery management system monitors and tracks the voltage, current and temperature of each battery cell in real time, and realizes the management of the battery pack temperature and the control of the power. Therefore, how to monitor the voltage abnormality of the battery pack in real time has become one of the key points of the battery management control core and safe driving performance.

[0004] The current battery management system (BMS) mainly relies on the set voltage threshold to trigger an alarm, and only triggers an alarm when the voltage of a single battery cell exceeds the upper limit or is lower than the lower limit. However, the current system and method that mainly rely on fixed voltage thresholds to trigger an alarm cannot identify slow changes or potential abnormal trends in voltage, resulting in insufficient ability to capture early signs of failure. The system does not fully exploit and utilize historical time series voltage data, lacks modeling analysis of long-term voltage change patterns, and cannot carry out predictive maintenance or early intervention; the existing scheme only focuses on the instantaneous voltage value of the battery cell, lacks deep analysis and pattern recognition of historical voltage time series data, and cannot realize early warning of potential risks of the battery. SUMMARY

[0005] In order to solve the above problems, the present disclosure provides a battery pack abnormality detection method and system based on average deviation and wavelet analysis, a voltage deviation calculation method based on average deviation, which realizes accurate quantification of the consistency level of the battery monomer and the whole. At the same time, the voltage signal is decomposed by wavelet transform to effectively extract the feature information of the voltage signal in different frequency domains, and the accurate identification of the voltage abnormal fluctuation is realized.

[0006] According to some embodiments, the present disclosure adopts the following technical solutions: The battery pack abnormality detection method based on average deviation and wavelet analysis comprises: Real-time acquisition of voltage data of each battery monomer in the power battery pack, and preprocessing; Convert the preprocessed voltage data into a time series format, and compress the storage by using a time partition strategy; Retrieve the stored voltage time series data of each cell, and obtain the voltage average deviation of each single cell by using the voltage deviation calculation method; Wavelet transform is performed on the voltage average deviation of each single cell, multi-scale decomposition is performed by using a wavelet base function, high-frequency components of different frequency bands are obtained, energy distribution of the high-frequency components is analyzed, statistical features of the high-frequency energy are calculated, an energy threshold of the battery single cell is set, and whether the battery single cell is abnormal is determined by comparing the statistical features with the energy threshold.

[0007] According to some embodiments, the present disclosure adopts the technical solutions as follows: The battery pack abnormality detection system based on average deviation and wavelet analysis comprises: A data acquisition module is configured to acquire voltage data of each battery single cell in the power battery pack in real time, and perform preprocessing. A data storage module is configured to convert the preprocessed voltage data into a time series format, and compress the storage by using a time partition strategy. An average deviation calculation module is configured to retrieve the stored voltage time series data of each cell, and obtain the voltage average deviation of each single cell by using the voltage deviation calculation method. An abnormality detection module is configured to perform wavelet transform on the voltage average deviation of each single cell, perform multi-scale decomposition by using a wavelet base function, obtain high-frequency components of different frequency bands, analyze energy distribution of the high-frequency components, calculate statistical features of the high-frequency energy, set an energy threshold of the battery single cell, and determine whether the battery single cell is abnormal by comparing the statistical features with the energy threshold.

[0008] According to some embodiments, the present disclosure adopts the technical solutions as follows: A computer program product comprises a computer program, and the computer program is executed by a processor to implement the battery pack abnormality detection method based on average deviation and wavelet analysis.

[0009] According to some embodiments, the present disclosure adopts the technical solutions as follows: A non-transitory computer readable storage medium is configured to store computer instructions, and the computer instructions are executed by a processor to implement the battery pack abnormality detection method based on average deviation and wavelet analysis.

[0010] According to some embodiments, the present disclosure adopts the technical solutions as follows: An electronic device includes: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the battery pack abnormality detection method based on mean deviation and wavelet analysis.

[0011] Compared with the prior art, the present invention has the following beneficial effects: The disclosed battery pack anomaly detection method based on mean deviation and wavelet analysis aims at the problem of voltage consistency evaluation of power battery packs during operation, and proposes a voltage deviation calculation method based on mean deviation. By calculating the difference between the current voltage value of each battery cell and the average voltage value of all battery cells at the current moment, the accurate quantification of the battery cell and the overall consistency level is achieved. At the same time, the wavelet transform is used to perform multi-scale decomposition of the voltage signal, effectively extracting the characteristic information of the voltage signal in different frequency domains, and realizing the accurate identification of abnormal voltage fluctuations. In the actual vehicle operation data verification, the method successfully identified multiple voltage outliers, and through in-depth analysis of the battery cells corresponding to these outliers, the potential problems inside the battery pack were discovered, which provides an important basis for the health status assessment and fault warning of the battery pack.

[0012] The battery pack abnormality detection method based on average deviation and wavelet analysis disclosed in the present invention retrieves the stored voltage time series data of each battery cell, uses the voltage deviation calculation method to obtain the average voltage deviation of each single battery cell, and obtains the deviation data of each battery cell at each time point, thereby realizing the accurate identification of abnormal voltage fluctuations.

[0013] The disclosed battery pack anomaly detection method based on mean deviation and wavelet analysis can quickly and effectively identify abnormal battery cells with voltage deviations from a large amount of new energy vehicle driving data, and intuitively display the analysis results through visualization methods such as scatter plots, providing reliable technical support for battery pack maintenance and replacement decisions. The system automatically records and extracts information about these abnormal battery cells, including battery cell number, abnormality occurrence time, high-frequency energy value, etc., to form a list of abnormal battery cells. Through continuous monitoring and analysis of these abnormal battery cells, potential problems in the battery pack can be discovered in a timely manner, providing a basis for battery pack maintenance and replacement decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings, which constitute a part of the present disclosure, are used to provide a further understanding of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation to the present disclosure.

[0015] Figure 1A flow chart of a battery pack abnormality detection method based on average deviation and wavelet analysis according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] The present disclosure is further illustrated below in conjunction with the accompanying drawings and embodiments.

[0017] It should be noted that the following detailed description is illustrative only and is intended to provide further description of the present disclosure. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs.

[0018] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, components, and / or groups thereof, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0019] Embodiment 1 In one embodiment of the present disclosure, a battery pack abnormality detection method based on average deviation and wavelet analysis is provided, comprising the following steps: Step 1: Real-time acquisition of voltage data of each battery cell in the power battery pack, and preprocessing; Step 2: Conversion of the preprocessed voltage data into time series format, and compression storage using time partitioning strategy; Step 3: Retrieval of the stored voltage time series data of each cell, and acquisition of the voltage average deviation of each single cell using the voltage deviation calculation method; Step 4: Wavelet transform of the voltage average deviation of each single cell, multi-scale decomposition using wavelet basis function, acquisition of high-frequency components in different frequency bands, analysis of the energy distribution of the high-frequency components, calculation of the statistical features of the high-frequency energy, setting of the energy threshold of the battery cell, comparison of the statistical features with the energy threshold, and determination of whether the battery cell is abnormal.

[0020] As an embodiment, the battery pack abnormality detection method based on average deviation and wavelet analysis according to the present disclosure, based on the voltage deviation calculation method of average deviation, realizes accurate quantification of the consistency level of the battery cell and the whole by calculating the difference between the current voltage value of each battery cell and the average voltage value of all battery cells at the current time. At the same time, multi-scale decomposition of the voltage signal using wavelet transform effectively extracts the feature information of the voltage signal in different frequency domains, and realizes accurate identification of the voltage abnormal fluctuation. The specific implementation process of the method is as follows: Step 1: Real-time acquisition of voltage data of each battery monomer in the power battery pack, and preprocessing; Specifically, real-time acquisition of voltage data of each battery monomer in the power battery pack includes: during the data acquisition process, the voltage data of each battery monomer in the power battery pack is collected in real time through the vehicle-mounted BMS system, and the collection is performed according to the set sampling frequency. The collected data includes battery monomer number, voltage value and collection timestamp information, and then transmitted to the vehicle terminal through the CAN bus and uploaded to the cloud server in real time.

[0021] Next, the data is stored. Before data storage, the voltage data is preprocessed, including data cleaning, outlier removal and timestamp alignment operation.

[0022] Further, the preprocessed voltage data is stored in time sequence format, each data point contains timestamp, battery monomer number and voltage value field, and the database adopts time partition storage strategy according to time range for database and table division, supports quick query and statistical analysis according to time range. At the same time, the system regularly compresses the storage of historical data, optimizes the storage space utilization efficiency.

[0023] Step 2: Call the stored voltage time sequence data of each cell, and use the voltage deviation calculation method to obtain the voltage average deviation of each monomer cell; Specifically, the process of calculating the voltage average deviation of the monomer cell includes: Let at any time t There are N Battery cells, whose voltages are respectively:

[0024] Then the average voltage of all battery cells at this time is:

[0025] The average deviation of the battery cell i is:

[0026] Step 3: Wavelet transform is performed on the voltage average deviation of each monomer cell, wavelet basis function is used for multi-scale decomposition, high-frequency components of different frequency bands are obtained, energy distribution of high-frequency components is analyzed, statistical characteristics of high-frequency energy are calculated, energy threshold of battery monomer is set, and whether the battery monomer is abnormal is determined by comparing the statistical characteristics with the energy threshold.

[0027] Specifically, first, the wavelet transform is performed on the voltage average deviation of each single cell by calling pywt.wavedec(series, wavelet), which decomposes the input time series into a set of different frequency components: Approximation Coefficients: Low-frequency part, representing overall trends or long-term changes.

[0028] Detail Coefficients: High-frequency part, representing short-term fluctuations at different levels. By default, db1 (Daubechies 1 wavelet) is used.

[0029] low_freq_component = coeffs[0]: Extract the lowest frequency approximation coefficient (overall trend).

[0030] selected_high_freq_component = coeffs[detail_level]: Extract a certain layer of high-frequency components. During the decomposition process, by setting appropriate decomposition levels and target time scales, we can effectively extract high-frequency and low-frequency feature information from the voltage signal.

[0031] where the number of layers is calculated as follows: With each additional layer of wavelet decomposition, the time resolution of the signal is halved. Therefore, in the selection of the number of layers, the following formula can be used to calculate:

[0032] As an example, if the sampling interval is 10 seconds (i.e., record a voltage data point every 10 seconds), then: 12 hours (43200 seconds) =

[0033] 24 hours (86400 seconds) =

[0034] Therefore, in wavelet decomposition, the 12th and 13th layers will contain approximately 12-hour and 24-hour periodic components. Selecting the detail coefficients of the 12th or 13th layer can help analyze the 12- to 24-hour periodic fluctuations in the data.

[0035] Further, calculate the low-frequency energy and high-frequency energy, including: Low-frequency energy:

[0036] where, is the approximation coefficient of the layer, For the coefficients are taken out from the wavelet decomposition result (the lowest frequency coefficient), each coefficient is squared to represent the energy contribution of the coefficient, and all square results are summed to obtain the total low-frequency energy.

[0037] High-frequency energy (layer 1):

[0038] Among them, the detail coefficient of the first layer represents the high-frequency (rapid fluctuation) part.

[0039] Furthermore, for the extracted high-frequency energy, its energy value is calculated. The energy calculation formula is:

[0040] Among them, c is the high-frequency coefficient.

[0041] By analyzing the energy distribution of high-frequency components, mutations and abnormal fluctuations in voltage signals can be identified, including calculating the statistical characteristics of high-frequency energy, including the mean and standard deviation. When the low-frequency energy and high-frequency energy values ​​of a battery cell exceed three times the standard deviation, the battery cell is judged to be abnormal.

[0042] For each cell i, determine whether one of the following conditions is met:

[0043] Add the cells that meet the above conditions to the set S:

[0044] As an example, wavelet energy analysis of cell voltage_42 revealed a low-frequency energy of 18.67 and a high-frequency energy of 2.67. The high low-frequency energy (18.67) indicates that the cell voltage exhibits a significant trend or slow-changing process over a long time scale, reflecting voltage drift, load accumulation, or overall performance degradation during operation. High low-frequency energy typically indicates a strong slow-changing structure or steady-state offset in the system.

[0045] The high-frequency energy (2.67) is much higher than that of other cells, indicating that this cell has experienced rapid fluctuations or disturbances over a long period of 12–24 hours. This may be due to the following: frequent or abnormal charge and discharge operations; frequent external load fluctuations causing voltage instability; and internal physical or chemical anomalies such as uneven internal resistance, poor contact, or abnormal electrolyte distribution.

[0046] In combination with statistical analysis, if the high-frequency or low-frequency energy of a certain battery cell exceeds 3 times the standard deviation (3σ) of the average of the same type of battery cell, it can be preliminarily determined that the battery cell is in an atypical state or potential abnormal operation, and it is recommended to further track or warn the battery cell.

[0047] According to the judgment of each battery cell i whether one of the following conditions is met:

[0048] The battery cell meeting the above condition is added to the set S:

[0049] The high-frequency energy of the present disclosure focuses on "rapid disturbance", and the low-frequency energy focuses on "long-term trend", and the combination of the two can comprehensively depict the running state of the battery cell. High-frequency energy usually reflects rapid fluctuations in the signal, and long-period high-frequency energy is significantly higher than that of other battery cells, which may indicate that the voltage of voltage_42 is unstable for a long time and has abnormal fluctuations. Such instability may be caused by factors such as degradation, capacity imbalance, or increased internal impedance of the battery cell, which can cause greater voltage fluctuations during normal charging and discharging. The long-period high-frequency energy of voltage_42 is significantly higher than that of other battery cells, indicating that the battery cell has significant voltage fluctuations within a 12-24 hour period. Such fluctuations may be caused by internal instability or external environmental interference, or even early signs of degradation. According to the test results, subsequent health checks and monitoring of voltage_42 are recommended to ensure that it does not cause greater performance problems in future use.

[0050] Embodiment 2 In an embodiment of the present disclosure, a battery pack anomaly detection system based on average deviation and wavelet analysis is provided, comprising: A data acquisition module is used to acquire the voltage data of each battery cell in the power battery pack in real time and pre-process it. A data storage module is used to convert the pre-processed voltage data into a time series format and compress the storage using a time partitioning strategy. An average deviation calculation module is used to retrieve the stored voltage time series data of each battery cell and obtain the voltage average deviation of each battery cell using a voltage deviation calculation method. An anomaly detection module is used to perform wavelet transform on the voltage average deviation of each battery cell, perform multi-scale decomposition using a wavelet basis function, obtain high-frequency components of different frequency bands, analyze the energy distribution of the high-frequency components, calculate the statistical characteristics of the high-frequency energy, set the energy threshold of the battery cell, and determine whether the battery cell has an anomaly by comparing the statistical characteristics with the energy threshold.

[0051] Embodiment 3 In an embodiment of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the battery pack anomaly detection method based on average deviation and wavelet analysis.

[0052] Embodiment 4 In an embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, for storing computer instructions which, when executed by a processor, implement the battery pack anomaly detection method based on average deviation and wavelet analysis.

[0053] Embodiment 5 In an embodiment of the present disclosure, an electronic device is provided, comprising a processor, a memory, and a computer program; wherein the processor is connected with the memory, and the computer program is stored in the memory; when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device implements the battery pack anomaly detection method based on average deviation and wavelet analysis.

[0054] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to generate a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0056] Although the specific embodiments of the present disclosure are described above with reference to the accompanying drawings, the present disclosure is not limited to the specific embodiments described above. It should be understood by those skilled in the art that various modifications or changes can be made to the technical solutions of the present disclosure without the need for creative labor, and these modifications or changes are still within the protection scope of the present disclosure.

Claims

1. A battery pack anomaly detection method based on mean deviation and wavelet analysis, characterized in that: include: Real-time acquisition and pre-processing of voltage data of each battery cell in the power battery pack; The pre-processed voltage data is converted into a time series format and compressed and stored using a time partitioning strategy; Retrieve the stored voltage time series data of each battery cell and use the voltage deviation calculation method to obtain the average voltage deviation of each single battery cell; The average voltage deviation of each battery cell is subjected to wavelet transform, and multi-scale decomposition is performed using wavelet basis functions to obtain high-frequency components in different frequency bands. The energy distribution of the high-frequency components is analyzed, and the statistical characteristics of the high-frequency energy are calculated. The energy threshold of the battery cell is set, and by comparing the statistical characteristics with the energy threshold, it is determined whether the battery cell has an abnormality.

2. The battery pack abnormality detection method based on mean deviation and wavelet analysis according to claim 1, characterized in that: Real-time acquisition of voltage data of each battery cell in the power battery pack, including: during the data acquisition process, the voltage data of each battery cell in the power battery pack is collected in real time through the on-board BMS system, and the data is collected according to the set sampling frequency. The collected data includes battery cell number, voltage value and acquisition timestamp information, which is then transmitted to the on-board terminal via the CAN bus and uploaded to the cloud server in real time.

3. The battery pack abnormality detection method based on mean deviation and wavelet analysis according to claim 1, characterized in that: Before data storage, the voltage data is preprocessed, including data cleaning, outlier removal, and timestamp alignment. The preprocessed voltage data is stored in a time series format. Each data point contains a timestamp, battery cell number, and voltage value field. The database adopts a time partitioning storage strategy to support fast query and statistical analysis by time range.

4. The battery pack abnormality detection method based on mean deviation and wavelet analysis according to claim 1, characterized in that: The process of calculating the average deviation of the voltage of a single cell includes: assuming that at any time t have N The battery cells have voltages of , then the average voltage of all cells at that moment is: Battery Cell i The average deviation is: .

5. The battery pack abnormality detection method based on mean deviation and wavelet analysis according to claim 1, characterized in that: The voltage average deviation of each single cell is subjected to wavelet transform, and multi-scale decomposition is performed using the db4-order wavelet basis function to decompose the voltage average deviation into high-frequency and low-frequency components in different frequency bands. During the decomposition process, the number of decomposition layers and the target time scale are set to ensure that the high-frequency and low-frequency characteristic information in the voltage signal can be effectively extracted. With each additional layer of wavelet decomposition, the time resolution of the signal is halved.

6. The battery pack abnormality detection method based on mean deviation and wavelet analysis according to claim 1, characterized in that: For the extracted high-frequency energy, calculate its energy value. The energy calculation formula is: , where c is the high-frequency coefficient; by analyzing the energy distribution of the high-frequency component, mutations and abnormal fluctuations in the voltage signal are identified. At the same time, the statistical characteristics of the high-frequency energy, including the mean and standard deviation, are calculated. When the low-frequency energy and high-frequency energy values ​​of a battery cell exceed three times the standard deviation, the battery cell is determined to be abnormal.

7. A battery pack anomaly detection system based on mean deviation and wavelet analysis, characterized in that: include: The data acquisition module is used to obtain the voltage data of each battery cell in the power battery pack in real time and pre-process it; The data storage module is used to convert the pre-processed voltage data into a time series format and compress and store it using a time partitioning strategy; The average deviation calculation module is used to retrieve the stored voltage time series data of each battery cell and obtain the average voltage deviation of each single battery cell using the voltage deviation calculation method; The anomaly detection module is used to perform wavelet transform on the average voltage deviation of each battery cell, perform multi-scale decomposition using wavelet basis functions, obtain high-frequency components in different frequency bands, analyze the energy distribution of high-frequency components, calculate the statistical characteristics of high-frequency energy, set the energy threshold of the battery cell, and determine whether the battery cell has an abnormality by comparing the statistical characteristics with the energy threshold.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the battery pack abnormality detection method based on mean deviation and wavelet analysis according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the battery pack abnormality detection method based on mean deviation and wavelet analysis according to any one of claims 1 to 6 is implemented.

10. An electronic device, characterized in that: include: A processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the battery pack abnormality detection method based on mean deviation and wavelet analysis as described in any one of claims 1-6.

Images