Abnormal sampling identification method, device and equipment of battery, medium and program product

Abstract

The invention relates to the technical field of power batteries, in particular to a battery abnormal sampling identification method, device and equipment, a medium and a program product, and the method comprises the steps: obtaining voltage data of a plurality of target single cells in a to-be-identified battery at a plurality of moments; determining a standard battery cell according to the voltage data of the plurality of target single battery cells at the plurality of moments, and making Pearson's correlation coefficients of the plurality of target single battery cells and the standard battery cell to obtain a Pearson's correlation coefficient array; and calculating a quartile distance of the Pearson's correlation coefficient array, and obtaining an abnormal sampling identification result of the to-be-identified battery according to the Pearson's correlation coefficient array and the quartile distance. Therefore, the voltage steady-state data is extracted through variational mode decomposition, and the sampling anomaly is identified based on the Pearson's correlation coefficient and the quartile distance, so that the problems of single abnormal sampling identification application range, difficulty in identifying various anomalies and the like in the related technology are solved, and false alarms are reduced.

Description

Technical Field

[0001] The present application relates to the technical field of power batteries, and in particular to a method, device, equipment, medium, and program product for sampling and identifying abnormal batteries. Background Art

[0002] There are many reasons for new energy vehicle accidents, and any of these issues will be reflected in the data. New energy vehicle accidents tend to have certain pattern characteristics, making it crucial to identify and recognize these patterns. Sampling anomalies are most likely caused by loose sampling cables or signal acquisition errors on the master and slave boards. These anomalies directly lead to data anomalies, impacting the vehicle's driving and charging performance.

[0003] In related technologies, the commonly used sampling anomaly recognition model mainly uses the absolute value of the difference between the voltage and the median voltage within the window time to extract the abstract features of vehicle data, and uses the global quantile and the frequency accumulation within a certain period of time to identify pairs of battery cells with sudden voltage increases; the advantage of this algorithm is that it does not focus on the voltage difference itself, but only on the change in the voltage difference relative to the median.

[0004] However, the feature selection in related technologies is more prominent, requiring adjacent cells to have one high and one low feature compared to the median cell. Although the recognition accuracy is very high, the scope of application is relatively single and it is unable to identify more sampling anomalies, which needs to be solved urgently. Summary of the Invention

[0005] The present application provides a battery abnormal sampling identification method, device, equipment, medium and program product to solve the problems of the related art in that the identification of sampling anomalies is limited in scope and difficult to identify multiple anomalies. It has high interpretability and reduces false alarms.

[0006] A first embodiment of the present application provides a method for identifying abnormal battery sampling, including the following steps:

[0007] Obtain voltage data of multiple target single cells in the battery to be identified at multiple times;

[0008] Determining a standard battery cell according to the voltage data of the plurality of target single battery cells at a plurality of moments, and performing Pearson correlation coefficient calculations on the plurality of target single battery cells and the standard battery cell respectively to obtain a Pearson correlation coefficient array;

[0009] The interquartile range of the Pearson correlation coefficient array is calculated, and an abnormal sampling identification result of the battery to be identified is obtained according to the Pearson correlation coefficient array and the interquartile range.

[0010] Optionally, obtaining the abnormal sampling identification result of the battery to be identified according to the Pearson correlation coefficient array and the interquartile range includes:

[0011] Obtaining an abnormal coefficient threshold value according to the product of the interquartile range and a preset multiple;

[0012] The battery cells in the Pearson correlation coefficient array that have a value greater than the abnormal coefficient threshold are marked, and an abnormal sampling identification result of the battery to be identified is obtained according to the marking result.

[0013] Optionally, obtaining the abnormal sampling identification result of the battery to be identified according to the marking result includes:

[0014] Determine the number of marked cells and the number of consecutive markings for each marked cell according to the marking result;

[0015] The abnormal sampling identification result is obtained according to the number of the marked battery cells and the number of consecutive markings of each marked battery cell.

[0016] Optionally, obtaining the abnormal sampling identification result according to the number of the marked cells and the number of consecutive markings of each marked cell includes:

[0017] Determine whether the number of marked cells is less than a preset number, and whether any marked cell has been marked continuously for more than a preset number of times;

[0018] If the number of the marked cells is less than the preset number, and the number of consecutive markings of any marked cell is greater than the preset number, it is determined that there is an abnormal sampling risk; otherwise, it is determined that there is no abnormal sampling risk.

[0019] Optionally, obtaining voltage data of a plurality of target single cells in the battery to be identified at a plurality of times includes:

[0020] Obtaining initial voltage data of each single cell in the battery to be identified at the plurality of moments;

[0021] Cleaning the initial voltage data of each single cell at multiple moments to obtain intermediate voltage data of each single cell at multiple moments;

[0022] Based on a preset variational modal decomposition strategy, variational modal decomposition processing is performed on the intermediate voltage data of each single battery at multiple moments to obtain the voltage data of the multiple target single batteries at the multiple moments.

[0023] Optionally, determining the standard battery cell according to the voltage data of the plurality of target single battery cells at a plurality of moments includes:

[0024] Based on the voltage data of the multiple target single cells at multiple moments, averaging the voltages of all the target single cells at the same moment to obtain an average voltage of the multiple target single cells at each moment;

[0025] Based on the time sequence, the average voltage of the plurality of target single battery cells at each moment is used as the voltage value of the standard battery cell at each moment to obtain the standard battery cell.

[0026] A second embodiment of the present application provides a battery abnormality sampling and identification device, comprising:

[0027] An acquisition module is used to acquire voltage steady-state data of the battery to be identified, wherein the voltage steady-state data includes voltage data of multiple target single cells at multiple times;

[0028] a determination module, configured to determine a standard battery cell according to the voltage data of the plurality of target battery cells at a plurality of moments, and perform Pearson correlation coefficient calculations on the plurality of target battery cells and the standard battery cell to obtain a Pearson correlation coefficient array;

[0029] The calculation module is used to calculate the interquartile range of the Pearson correlation coefficient array, and obtain the abnormal sampling identification result of the battery to be identified based on the Pearson correlation coefficient array and the interquartile range.

[0030] Optionally, the calculation module is specifically configured to:

[0031] Obtaining an abnormal coefficient threshold value according to the product of the interquartile range and a preset multiple;

[0032] The battery cells in the Pearson correlation coefficient array that have a value greater than the abnormal coefficient threshold are marked, and an abnormal sampling identification result of the battery to be identified is obtained according to the marking result.

[0033] Optionally, the calculation module is specifically configured to:

[0034] Determine the number of marked cells and the number of consecutive markings for each marked cell according to the marking result;

[0035] The abnormal sampling identification result is obtained according to the number of the marked battery cells and the number of consecutive markings of each marked battery cell.

[0036] Optionally, the calculation module is specifically configured to:

[0037] Determine whether the number of marked cells is less than a preset number, and whether any marked cell has been marked continuously for more than a preset number of times;

[0038] If the number of the marked cells is less than the preset number, and the number of consecutive markings of any marked cell is greater than the preset number, it is determined that there is an abnormal sampling risk; otherwise, it is determined that there is no abnormal sampling risk.

[0039] Optionally, the acquisition module is specifically configured to:

[0040] Obtaining initial voltage data of each single cell in the battery to be identified at the plurality of moments;

[0041] Cleaning the initial voltage data of each single cell at multiple moments to obtain intermediate voltage data of each single cell at multiple moments;

[0042] Based on a preset variational modal decomposition strategy, variational modal decomposition processing is performed on the intermediate voltage data of each single battery at multiple moments to obtain the voltage data of the multiple target single batteries at the multiple moments.

[0043] Optionally, the determining module is specifically configured to:

[0044] Based on the voltage data of the multiple target single cells at multiple moments, averaging the voltages of all the target single cells at the same moment to obtain an average voltage of the multiple target single cells at each moment;

[0045] Based on the time sequence, the average voltage of the plurality of target single battery cells at each moment is used as the voltage value of the standard battery cell at each moment to obtain the standard battery cell.

[0046] A third aspect of the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the abnormal sampling and identification method for a battery as described in the above embodiment.

[0047] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the abnormal sampling and identification method for a battery as described in the above embodiment.

[0048] A fifth aspect of the present application provides a computer program product, which stores a computer program. When the program is executed by a processor, the abnormal sampling and identification method for a battery as described in the above embodiment is implemented.

[0049] Therefore, the embodiment of the present application obtains the voltage data of multiple target single cells in the battery to be identified at multiple times; determines the standard cell based on the voltage data of multiple target single cells at multiple times, and respectively performs Pearson correlation coefficients on the multiple target single cells and the standard cell to obtain a Pearson correlation coefficient array; calculates the interquartile range of the Pearson correlation coefficient array, and obtains the abnormal sampling identification result of the battery to be identified based on the Pearson correlation coefficient array and the interquartile range. Therefore, by extracting voltage steady-state data through variational mode decomposition and identifying sampling anomalies through Pearson correlation coefficient and interquartile range, the problems of single application of abnormal sampling identification and difficulty in identifying multiple anomalies in related technologies are solved, and the interpretability is high, which reduces false positives.

[0050] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0052] Figure 1 This is a flowchart of a battery abnormal sampling and identification method provided according to an embodiment of the present application;

[0053] Figure 2 This is a flowchart of a battery abnormal sampling and identification method provided according to one embodiment of the present application;

[0054] Figure 3 A schematic diagram of a battery abnormal sampling and identification device provided according to an embodiment of the present application;

[0055] Figure 4 A schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0057] The following describes an abnormal sampling identification method, device, equipment, medium and program product of a battery according to an embodiment of the present application with reference to the accompanying drawings. In response to the problem that the related art mentioned in the background art mentioned above has a single application scope for identifying sampling anomalies and is difficult to identify multiple anomalies, the present application provides a battery abnormal sampling identification method. In this method, the embodiment of the present application obtains voltage data of multiple target single cells in the battery to be identified at multiple times; determines a standard cell based on the voltage data of the multiple target single cells at multiple times, and performs Pearson correlation coefficients on the multiple target single cells and the standard cell respectively to obtain a Pearson correlation coefficient array; calculates the interquartile range of the Pearson correlation coefficient array, and obtains the abnormal sampling identification result of the battery to be identified based on the Pearson correlation coefficient array and the interquartile range. Therefore, by extracting voltage steady-state data through variational mode decomposition, and identifying sampling anomalies through Pearson correlation coefficient and interquartile range, the problem of the related art abnormal sampling identification having a single application scope and being difficult to identify multiple anomalies is solved, and the method has high interpretability and reduces false positives.

[0058] Specifically, Figure 1 A flowchart of a battery abnormality sampling and identification method provided in an embodiment of the present application is provided.

[0059] like Figure 1 As shown, the abnormal sampling and identification method of the battery includes the following steps:

[0060] In step S101 , voltage data of a plurality of target single cells in a battery to be identified at a plurality of times are obtained.

[0061] The target single cell refers to each individual battery unit in the battery pack to be identified, and each cell has its own independent working status and performance parameters.

[0062] Optionally, in some embodiments, obtaining the voltage steady-state data of the battery to be identified includes: obtaining the initial voltage data of each single cell in the battery to be identified at multiple times; performing data cleaning on the initial voltage data of each single cell at multiple times to obtain the intermediate voltage data of each single cell at multiple times; and performing variational modal decomposition processing on the intermediate voltage data of each single cell at multiple times based on a preset variational modal decomposition strategy to obtain voltage data of multiple target single cells at multiple times.

[0063] The preset variational mode decomposition strategy extracts steady-state components from the signal, removes high-frequency noise and small fluctuations, and obtains voltage data that reflects the battery's true operating state. It should be noted that in signal processing, variational mode decomposition is a signal decomposition and estimation method. By iteratively searching for the optimal solution of the variational model during the decomposition process to determine the frequency center and bandwidth of each component, it can adaptively achieve frequency domain decomposition of the signal and effective separation of its components.

[0064] It is understandable that the initial voltage data of each single cell at different time points is recorded through sensors or data acquisition equipment, and the data is stored in the form of a two-dimensional matrix, where rows represent time series and columns represent the initial voltage data of different single cells. The initial voltage data of each single cell at multiple times is cleaned to remove abnormal data and invalid records to ensure data quality and improve the accuracy of subsequent analysis; data records containing non-numeric characters (such as "NaN" or null values) are removed; partially missing or incomplete voltage data caused by collection problems are removed; data that does not conform to the physical range is removed, and data with voltage values ​​outside the reasonable range (such as greater than 5V or less than 1V) are deleted to avoid outliers interfering with the analysis; after cleaning, a reliable data set is obtained. The cleaned voltage data is processed using variational mode decomposition (VMD) technology, decomposing the complex signal into multiple intrinsic mode functions and extracting the core data reflecting the steady-state characteristics of the battery. The extracted steady-state data can effectively eliminate occasional abnormal data, thereby retaining data with multiple abnormalities and the true working state of the battery, and obtaining steady-state voltage data of multiple target single cells at multiple times for subsequent analysis.

[0065] In step S102 , a standard cell is determined based on voltage data of a plurality of target single cells at a plurality of moments, and a Pearson correlation coefficient is calculated between the plurality of target single cells and the standard cell to obtain a Pearson correlation coefficient array.

[0066] Among them, the standard battery cell refers to the reference battery cell composed by averaging the voltage data of all single battery cells at the same time and arranged in chronological order; the Pearson Correlation Coefficient is a statistical indicator that measures the strength of the linear relationship between two variables and describes the degree of linear correlation between two sets of data.

[0067] Specifically, voltage data for each cell is collected at multiple time points (e.g., T1, T2, ..., Tm), and steady-state voltage data is extracted to make the data more stable and reflect the actual operating state. For multiple target cell voltage data at the same time, a standard cell is determined. The Pearson correlation coefficient between each target cell and the standard cell is calculated separately, and the correlation coefficient for each cell is stored in an array to generate a Pearson correlation coefficient array. This quantifies the similarity between each cell and the standard cell, thereby determining whether there is any abnormal behavior. The Pearson correlation coefficient array serves as important input data for subsequent anomaly identification, used to further screen and locate abnormal cells.

[0068] Optionally, in some embodiments, a standard battery cell is determined based on voltage data of multiple target single battery cells at multiple moments, including: based on the voltage data of multiple target single battery cells at multiple moments, respectively calculating the average voltage of all target single battery cells at the same moment to obtain the average voltage of the multiple target single battery cells at each moment; based on the time sequence, using the average voltage of the multiple target single battery cells at each moment as the voltage value of the standard battery cell at each moment to obtain the standard battery cell.

[0069] It can be understood that for each time point Ti (i = 1, 2, ..., m), the voltage values ​​of all target single cells at the same time are averaged, and an average voltage value is obtained for each time point Ti. The calculated average voltage values ​​of all moments are arranged in chronological order to form a time series. The time series represents the voltage values ​​of the standard cells at different time points, that is, the standard cells are obtained. By comparing the differences between each target single cell and the standard cell (such as using the Pearson correlation coefficient), cells that deviate from normal behavior are identified to help detect possible faults or abnormal conditions. The standard cell can also be used to assess the health status of the entire battery pack and track its changing trends over time.

[0070] In step S103, the interquartile range of the Pearson correlation coefficient array is calculated, and the abnormal sampling identification result of the battery to be identified is obtained according to the Pearson correlation coefficient array and the interquartile range.

[0071] Among them, the Pearson correlation coefficient array quantifies the similarity between each target single cell and the standard cell, reflecting whether the working status of the target single cell deviates from the overall trend; the interquartile range (IQR) is a method in statistics to measure the degree of data dispersion.

[0072] Optionally, in some embodiments, an abnormal sampling identification result of the battery to be identified is obtained based on the Pearson correlation coefficient array and the interquartile range, including: obtaining an abnormal coefficient threshold based on the product of the interquartile range and a preset multiple; marking the battery cells in the Pearson correlation coefficient array that are greater than the abnormal coefficient threshold, and obtaining the abnormal sampling identification result of the battery to be identified based on the marking result.

[0073] Optionally, in some embodiments, an abnormal sampling identification result of the battery to be identified is obtained based on the marking result, including: determining the number of marked battery cells and the number of consecutive markings of each marked battery cell based on the marking result; and obtaining the abnormal sampling identification result based on the number of marked battery cells and the number of consecutive markings of each marked battery cell.

[0074] Optionally, in some embodiments, an abnormal sampling identification result is obtained based on the number of marked battery cells and the number of consecutive markings of each marked battery cell, including: determining whether the number of marked battery cells is less than a preset number, and whether the number of consecutive markings of any marked battery cell is greater than the preset number; if the number of marked battery cells is less than the preset number, and the number of consecutive markings of any marked battery cell is greater than the preset number, then it is determined that there is an abnormal sampling risk; otherwise, it is determined that there is no abnormal sampling risk.

[0075] Among them, the preset multiple, preset number and preset number of times can be thresholds set in advance by the user, can be thresholds obtained through a limited number of experiments, or can be thresholds obtained through a limited number of computer simulations, and are not specifically limited here.

[0076] It can be understood that the Pearson correlation coefficient array is sorted, the 1 / 4 quantile and the 3 / 4 quantile are obtained and calculated, and the interquartile range is calculated based on the 1 / 4 quantile and the 3 / 4 quantile. The calculation formula is:

[0077] IQR = 3 / 4 quantile D - 1 / 4 quantile D;

[0078] Where IQR is the interquartile range and D is the Pearson correlation coefficient array.

[0079] Specifically, the preset multiple can be 3 times, therefore, the embodiment of the present application can use 3 times IQR as the abnormal coefficient threshold; compare each value in the Pearson correlation coefficient array with the abnormal coefficient threshold, and mark the battery cells that are greater than the abnormal coefficient threshold. The correlation coefficients of these battery cells deviate significantly from other battery cells and may be potential abnormal points; check whether the number of battery cells marked as abnormal is less than the preset number. If it is less than this number, it means that the abnormal situation may be relatively isolated and not common; at the same time, check whether there is any marked battery cell that is marked as abnormal in multiple consecutive time windows (or multiple consecutive samples) greater than the preset number of times; if the number of marked battery cells is less than the preset number, and there is at least one battery cell whose consecutive marking times exceed the preset number, it can be determined that the battery to be identified has an abnormality. Otherwise, the next round of data acquisition can be performed, and the step of obtaining the voltage steady-state data of the battery to be identified can be returned.

[0080] Furthermore, if the correlation coefficients of all target cells in the Pearson correlation coefficient array do not exceed the anomaly coefficient threshold, it means that no target cell exhibits behavior that significantly deviates from the overall trend. In this case, it can be directly determined that there is no anomaly in the battery to be identified, indicating that the working status of each target cell in the battery pack is highly consistent with the standard cell, with no obvious abnormal performance; if the number of marked cells in the array is zero, there is no need to make subsequent judgments on the number of markings or the number of consecutive markings, and the conclusion can be drawn directly, improving the efficiency of the algorithm; effectively avoiding false anomaly alarms caused by misjudgment or noise interference, ensuring more accurate anomaly identification results; it is suitable for situations where the overall state of the battery pack is relatively stable and the data fluctuations are small, and can quickly rule out the possibility of no anomaly.

[0081] It should be noted that if the number of target single cells whose correlation coefficient exceeds the abnormal coefficient threshold in the window exceeds 5 (i.e., the preset number), it means that there may be a battery replacement situation, or the voltage fluctuation is too large, or the current fluctuation is too large, etc., resulting in the sampling data cannot be used to determine whether the sampling is abnormal. Therefore, the window is slid to the next window to continue the calculation; if the number of target single cells whose correlation coefficient exceeds the abnormal coefficient threshold in the window does not exceed 5, and a certain target single cell exceeds the abnormal coefficient threshold in the window in two consecutive windows, it is determined that the battery to be identified is abnormal. It should be noted that the above 5 are not limitations of this application. Those skilled in the art can determine the preset number according to actual conditions, and no specific limitation is made here.

[0082] Therefore, the embodiment of the present application uses the 1 / 4 quantile and the 3 / 4 quantile to calculate the interquartile range, which can provide a relatively stable measure of dispersion. Even if there are outliers in the data set, the interquartile range is not easily affected by these values. Therefore, it can more accurately reflect the degree of dispersion in the middle part of the data and enhance the robustness of data analysis. In addition, the embodiment of the present application has verified through a large amount of data that the result is more accurate when the preset multiple is 3 times, which effectively improves the accuracy of abnormal battery sampling identification.

[0083] To facilitate those skilled in the art to further understand the abnormal sampling and identification method of the battery in the embodiment of the present application, the following is combined with Figure 2 The illustrated embodiment will be described in detail.

[0084] Specifically, if Figure 2 As shown, Figure 2 This is a flow chart of a method for identifying abnormal battery sampling according to one embodiment of the present application; the method includes the following steps:

[0085] S201: parse the original data message and extract the voltage data of each target single cell at multiple moments.

[0086] S202: Data collection and cleaning: Delete abnormal characters and invalid data such as NAN; delete incomplete data; remove voltage data greater than 5V and less than 1V; extract cell voltage data V1, V2, V3, ..., Vn and time T. Assume that after cleaning, the data contains n cells and m time points. The subscripts 1, 2, and 3 represent the cell numbers. The extracted data is sorted in chronological order from front to back.

[0087] S203: Select data within a specific time window from the cleaned data; extract a section of continuous data to form a calculation window, retain the corresponding T and single battery V, and the sliding window length M can be selected according to the actual application scenario.

[0088] S204: Due to the accuracy issues in sampling, they will inevitably be introduced into the calculation. However, the data fluctuations caused by this accuracy issue will not have a substantial impact on the performance of the vehicle, so such effects need to be eliminated. The variational mode decomposition method commonly used in signal processing is used to extract the voltage steady-state data.

[0089] S205: After the cell voltage data V is processed by the variational mode decomposition method, there are N columns, each column represents a battery cell, and there are N battery cells in total; the specific number of rows represents time, and the average value of all battery cells at the same time is calculated to form a standard battery cell in chronological order.

[0090] S206: Put the standard battery cells into V to form V1; perform Pearson correlation coefficient analysis on the matrix V1 and the standard battery cells in order according to the battery cell numbers to form a Pearson correlation coefficient array D.

[0091] S207: Sort the Pearson correlation coefficient array D to obtain the 1 / 4 quantile and the 3 / 4 quantile, and then obtain the IQR. The calculation formula is IQR = 3 / 4 quantile D - 1 / 4 quantile D, and 3 times the IQR is used as the threshold.

[0092] S208: Compare the cells in the Pearson correlation coefficient array D with 3 times the IQR in sequence.

[0093] S209: Determine the correlation coefficient of the target single cell. If the correlation coefficient of the target single cell is greater than 3IQR, execute step S210; otherwise, return to step S208.

[0094] S210: Mark the cells exceeding the threshold as abnormal, that is, cells greater than 3 times the IQR are determined to be abnormal and the marking information is stored in an array.

[0095] S211: Return all marked moments and their corresponding abnormal cell numbers.

[0096] Therefore, the embodiment of the present application starts from identifying more sampling anomalies. It does not perform specific data rule feature extraction, but instead finds abnormal changes that are different from the normal form of the big data battery. In the sampling anomaly identification algorithm, the variational mode decomposition method of signal processing is introduced to perform variational mode decomposition on the battery voltage of each vehicle, extract the steady-state voltage, and compare it with the constructed standard battery by Pearson correlation coefficient. Finally, the sampling abnormal battery is identified by the 3 times IQR method, which handles the sampling fluctuation problem of normal data and reduces the occurrence of false positives. The sampling anomaly forms identified by the embodiment of the present application are wide-ranging and are not limited to the traditional one-high-one-low regular sampling anomaly. The recognition accuracy of the embodiment of the present application is high. The variational mode decomposition method is used to smooth some data fluctuations in advance, reducing the occurrence of false positives. The application scope of the embodiment of the present application is wide. The sampling anomaly identification model method in the related art can only identify the "one high and one low" feature of adjacent battery cells. In addition to being able to identify the above-mentioned sampling anomalies, the embodiment of the present application can also identify irregular sampling anomalies. The embodiment of the present application is highly interpretable and does not require complex theories. Each step can have a clear theoretical basis.

[0097] According to the abnormal sampling identification method of the battery proposed in the embodiment of the present application, the embodiment of the present application obtains the voltage data of multiple target single cells in the battery to be identified at multiple times; determines the standard cell based on the voltage data of multiple target single cells at multiple times, and respectively performs Pearson correlation coefficient on the multiple target single cells and the standard cell to obtain a Pearson correlation coefficient array; calculates the interquartile range of the Pearson correlation coefficient array, and obtains the abnormal sampling identification result of the battery to be identified based on the Pearson correlation coefficient array and the interquartile range. Therefore, by extracting voltage steady-state data through variational mode decomposition, and identifying sampling anomalies through Pearson correlation coefficient and interquartile range, the problems of single application of abnormal sampling identification and difficulty in identifying multiple anomalies in related technologies are solved, and the interpretability is high, which reduces false positives.

[0098] Next, the abnormal sampling and identification device for a battery according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0099] Figure 3 4 is a block diagram of a battery abnormality sampling and identification device according to an embodiment of the present application.

[0100] like Figure 3 As shown, the battery abnormal sampling and identification device 10 includes: an acquisition module 100 , a determination module 200 and a calculation module 300 .

[0101] The acquisition module 100 is used to acquire voltage data of multiple target single cells in the battery to be identified at multiple times;

[0102] The determination module 200 is configured to determine a standard cell based on voltage data of multiple target cells at multiple times, and to perform Pearson correlation coefficient calculations on the multiple target cells and the standard cell to obtain a Pearson correlation coefficient array.

[0103] The calculation module 300 is used to calculate the interquartile range of the Pearson correlation coefficient array and obtain the abnormal sampling identification result of the battery to be identified based on the Pearson correlation coefficient array and the interquartile range.

[0104] Optionally, the calculation module 300 is specifically used to: obtain an abnormal coefficient threshold according to the product of the interquartile range and a preset multiple; mark the battery cells in the Pearson correlation coefficient array that are greater than the abnormal coefficient threshold, and obtain an abnormal sampling identification result of the battery to be identified based on the marking result.

[0105] Optionally, the calculation module 300 is specifically used to: obtain an abnormal coefficient threshold according to the product of the interquartile range and a preset multiple; mark the battery cells in the Pearson correlation coefficient array that are greater than the abnormal coefficient threshold, and obtain an abnormal sampling identification result of the battery to be identified based on the marking result.

[0106] Optionally, the calculation module 300 is specifically used to: determine whether the number of marked battery cells is less than a preset number, and whether any marked battery cell has been marked continuously for more than a preset number of times; if the number of marked battery cells is less than a preset number, and any marked battery cell has been marked continuously for more than a preset number of times, then it is determined that there is an abnormal sampling risk; otherwise, it is determined that there is no abnormal sampling risk.

[0107] Optionally, the acquisition module 100 is specifically used to: obtain the initial voltage data of each single cell in the battery to be identified at multiple times; perform data cleaning on the initial voltage data of each single cell at multiple times to obtain the intermediate voltage data of each single cell at multiple times; based on a preset variational mode decomposition strategy, perform variational mode decomposition processing on the intermediate voltage data of each single cell at multiple times to obtain voltage data of multiple target single cells at multiple times.

[0108] Optionally, the determination module 200 is specifically used to: based on the voltage data of multiple target single cells at multiple moments, calculate the average value of the voltages of all target single cells at the same moment to obtain the average voltage of the multiple target single cells at each moment; based on the time sequence, use the average voltage of the multiple target single cells at each moment as the voltage value of the standard cell at each moment to obtain the standard cell.

[0109] It should be noted that the above explanations of the embodiment of the battery abnormality sampling and identification method are also applicable to the battery abnormality sampling and identification device of this embodiment, and will not be repeated here.

[0110] According to the abnormal sampling identification device for batteries proposed in the embodiment of the present application, the embodiment of the present application obtains the voltage data of multiple target single cells in the battery to be identified at multiple times; determines the standard cell based on the voltage data of multiple target single cells at multiple times, and respectively performs Pearson correlation coefficients on the multiple target single cells and the standard cell to obtain a Pearson correlation coefficient array; calculates the interquartile range of the Pearson correlation coefficient array through a calculation module, and obtains the abnormal sampling identification result of the battery to be identified based on the Pearson correlation coefficient array and the interquartile range. Therefore, by extracting voltage steady-state data through variational mode decomposition, and identifying sampling anomalies through Pearson correlation coefficient and interquartile range, the problems of single application of abnormal sampling identification and difficulty in identifying multiple anomalies in related technologies are solved, and the interpretability is high, which reduces false alarms.

[0111] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0112] Memory 401 , processor 402 , and computer programs stored in the memory 401 and executable on the processor 402 .

[0113] When the processor 402 executes the program, the abnormal sampling and identification method for the battery provided in the above embodiment is implemented.

[0114] Furthermore, the electronic device further includes:

[0115] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0116] The memory 401 is used to store computer programs that can be run on the processor 402 .

[0117] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0118] If the memory 401, the processor 402, and the communication interface 403 are implemented independently, the communication interface 403, the memory 401, and the processor 402 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0119] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0120] The processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0121] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the above-mentioned abnormal battery sampling and identification method is implemented.

[0122] An embodiment of the present application further provides a computer program product, which stores a computer program. When the program is executed by a processor, the above-mentioned abnormal battery sampling and identification method is implemented.

[0123] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0124] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0125] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0126] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0127] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

Claims

1. A battery abnormality sampling and identification method, characterized in that: The following steps are involved: Obtain voltage data of multiple target single cells in the battery to be identified at multiple times; Determining a standard battery cell according to the voltage data of the plurality of target single battery cells at a plurality of moments, and performing Pearson correlation coefficient calculations on the plurality of target single battery cells and the standard battery cell respectively to obtain a Pearson correlation coefficient array; The interquartile range of the Pearson correlation coefficient array is calculated, and an abnormal sampling identification result of the battery to be identified is obtained according to the Pearson correlation coefficient array and the interquartile range.

2. The method according to claim 1, characterized in that Obtaining the abnormal sampling identification result of the battery to be identified according to the Pearson correlation coefficient array and the interquartile range includes: Obtaining an abnormal coefficient threshold value according to the product of the interquartile range and a preset multiple; The battery cells in the Pearson correlation coefficient array that have a value greater than the abnormal coefficient threshold are marked, and an abnormal sampling identification result of the battery to be identified is obtained according to the marking result.

3. The method according to claim 2, characterized in that Obtaining the abnormal sampling identification result of the battery to be identified according to the marking result includes: Determine the number of marked cells and the number of consecutive markings for each marked cell according to the marking result; The abnormal sampling identification result is obtained according to the number of the marked battery cells and the number of consecutive markings of each marked battery cell.

4. The method according to claim 3, characterized in that Obtaining the abnormal sampling identification result according to the number of the marked cells and the number of consecutive markings of each marked cell includes: Determine whether the number of marked cells is less than a preset number, and whether any marked cell has been marked continuously for more than a preset number of times; If the number of the marked cells is less than the preset number, and the number of consecutive markings of any marked cell is greater than the preset number, it is determined that there is an abnormal sampling risk; otherwise, it is determined that there is no abnormal sampling risk.

5. The method according to claim 1, wherein The step of obtaining voltage data of a plurality of target single cells in the battery to be identified at a plurality of times includes: Obtaining initial voltage data of each single cell in the battery to be identified at the plurality of moments; Cleaning the initial voltage data of each single cell at multiple moments to obtain intermediate voltage data of each single cell at multiple moments; Based on a preset variational modal decomposition strategy, variational modal decomposition processing is performed on the intermediate voltage data of each single battery at multiple moments to obtain the voltage data of the multiple target single batteries at the multiple moments.

6. The method according to claim 5, characterized in that The determining of the standard battery cell according to the voltage data of the plurality of target single battery cells at a plurality of moments includes: Based on the voltage data of the multiple target single cells at multiple moments, averaging the voltages of all the target single cells at the same moment to obtain an average voltage of the multiple target single cells at each moment; Based on the time sequence, the average voltage of the plurality of target single battery cells at each moment is used as the voltage value of the standard battery cell at each moment to obtain the standard battery cell.

7. A battery abnormality sampling and identification device, characterized in that: include: An acquisition module is used to obtain voltage data of multiple target single cells in the battery to be identified at multiple times; a determination module, configured to determine a standard cell based on the voltage data of the plurality of target single cells at a plurality of moments, and perform Pearson correlation coefficient calculations on the plurality of target single cells and the standard cell to obtain a Pearson correlation coefficient array; A calculation module is used to calculate the interquartile range of the Pearson correlation coefficient array, and obtain the abnormal sampling identification result of the battery to be identified based on the Pearson correlation coefficient array and the interquartile range.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the abnormal sampling and identification method for a battery according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the abnormal sampling and identification method for a battery as claimed in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the abnormal sampling and identification method for a battery according to any one of claims 1 to 6 is implemented.

Images