A power battery monomer abnormality early warning method, system and electronic equipment

Abstract

The present invention provides an early warning method, system, electronic device and storage medium for abnormal power battery monomers. The method includes: obtaining recent historical data of the vehicle power battery and preprocessing it to obtain data of the battery in a static state; calculating the real SOC of each battery cell in each frame of battery cell data, and respectively calculating the real SOC median of each frame of battery cell data according to the real SOC of all battery cells in each frame of battery cell data; respectively calculating the difference between the real SOC of each battery cell in the current frame of battery cell data and the real SOC median, respectively calculating the Euclidean distance between each battery cell and all battery cells according to the difference, and calculating the average Euclidean distance between each battery cell and all battery cells according to the Euclidean distance calculation: comparing the average Euclidean distance with a preset threshold value to determine whether the current battery cell is abnormal. The present invention accurately identifies abnormal power battery conditions in advance and gives early warning, thereby replacing or repairing the battery pack module in advance, thereby improving vehicle safety.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicles, and more specifically, to an early warning method, system, electronic device and storage medium for abnormality of a power battery cell. Background Art

[0002] Under the current power battery technology level, power batteries are generally composed of dozens to hundreds of single cells connected in series and parallel. On the one hand, there are certain capacity differences between battery cells themselves. On the other hand, as the battery is continuously charged and discharged, the capacity differences between cells will gradually appear. The most intuitive manifestation of the inconsistency of cell capacity is the attenuation of power battery capacity, which affects the user's driving experience.

[0003] At present, the detection method of abnormal battery cells usually adopts the analysis of battery-related data during vehicle driving, mainly analyzing the internal resistance, voltage and other indicators of the battery, so as to locate the abnormal battery cells. However, this detection method is easily affected by the driving conditions of the vehicle, resulting in a high false alarm rate. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides a method, system, electronic device and storage medium for early warning of abnormality of power battery cells, so as to improve the accuracy of early warning of abnormality of power battery cells of electric vehicles, improve vehicle safety and enhance user driving experience.

[0005] According to a first aspect of the present invention, there is provided a method for early warning of abnormality of a power battery cell, comprising:

[0006] Acquire recent historical data of the vehicle's power battery and perform preprocessing to obtain multi-frame battery cell data in a static state;

[0007] Calculate the real SOC (SOC is the state of charge of the battery) of each battery cell in each frame of battery cell data, and calculate the real SOC median of each frame of battery cell data according to the real SOC of all battery cells in each frame of battery cell data; calculate the difference between the real SOC of each battery cell in the current frame of battery cell data and the real SOC median, calculate the Euclidean distance between each battery cell and all battery cells according to the difference, and calculate the average Euclidean distance between each battery cell and all battery cells according to the Euclidean distance:

[0008] The average value of the Euclidean distance is compared with a preset threshold value to determine whether the current battery cell is abnormal.

[0009] Based on the above technical solution, the present invention can also make the following improvements.

[0010] Optionally, the acquiring of recent historical data of the vehicle power battery and preprocessing to obtain data of the battery in a static state includes:

[0011] Select the national standard historical data of vehicle power batteries in a recent sampling period;

[0012] Abnormal data is screened out according to the voltage value and current value of each frame of battery cell data to obtain multiple frames of battery cell data in a static state.

[0013] Optionally, the method of filtering out abnormal data according to the voltage value and the current value of each frame of battery cell data to obtain multiple frames of battery cell data in a static state includes:

[0014] Compare the voltage value of a single cell in each frame of cell data with the voltage threshold, filter out cell data frames with abnormal voltage, and retain cell data frames with normal voltage;

[0015] The current values ​​of individual cells in the cell data frames with normal voltage are compared with the current thresholds respectively, and the cell data frames with abnormal current are screened out. The obtained multiple frames of cell data are the cell data in the static state.

[0016] Optionally, the calculating the real SOC of each battery cell in each frame of battery cell data includes:

[0017] Get the voltage value of each cell in each frame of cell data, and use the table lookup method to query the OCV-SOC table of the battery pack through the voltage value of each cell to get the real SOC of each cell, recorded as SOC_Real ij , i∈[1,m], j∈[1,n], where m is the number of frames of battery cell data obtained after preprocessing, and n is the number of battery cells in each frame of battery cell data.

[0018] Optionally, the real SOC median of each frame of battery cell data is calculated according to the real SOC of all battery cells in each frame of battery cell data, and the real SOC median of each frame of battery cell data is recorded as SOC_Median, which is calculated by formula (1):

[0019] SOC_Median i =median(SOC_Real i1 ,SOC_Real i2 ,…,SOC_Real ij ),

[0020] i∈[1,m],j∈[1,n](1),

[0021] Among them, SOC_Median iis the real SOC median of the cell data in the i-th frame, median is the median function, SOC_Real ij is the actual SOC of the jth battery cell in the i-th frame of battery cell data.

[0022] Optionally, the method of respectively calculating the difference between the real SOC of each battery cell in the battery cell data of the current frame and the median of the real SOC, respectively calculating the Euclidean distance between each battery cell and all the battery cells according to the difference, and obtaining the average value of the Euclidean distance between each battery cell and all the battery cells according to the Euclidean distance calculation; includes:

[0023] The difference between the actual SOC of each cell in each frame of cell data and the median of the actual SOC is calculated by formula (2), and the difference is recorded as ΔSOC ij :

[0024] ΔSOC ij =SOC_Real ij -SOC_Median i , i∈[1,m],j∈[1,n](2);

[0025] According to the difference between the actual SOC of each cell in each frame of cell data and the median of the actual SOC, the Euclidean distance D between each cell and all cells is calculated by formula (3): jk :

[0026]

[0027] Among them, D jk Indicates the Euclidean distance between the jth cell and the kth cell in the same frame of cell data, ΔSOC ij ΔSOC is the difference between the actual SOC of the jth cell in the i-th frame of cell data and the median of the actual SOC. ik is the difference between the real SOC of the kth cell in the i-th frame of cell data and the median of the real SOC. If the values ​​of j and k are the same, they represent the same cell.

[0028] According to the European distance D between each battery cell and all other batteries jk , calculate the average value D_AVG of the Euclidean distance between each cell and all cells using formula (4) j :

[0029] D_AVG j =(D j1 +D j2 +…+D jk ) / n,j∈[1,n],k∈[1,n](4).

[0030] Optionally, the threshold calculation process includes:

[0031] Obtain a sample data set of known abnormal cells, and calculate the corresponding mean value μ and standard deviation σ according to the sample data of each abnormal cell using formula (5) and formula (6):

[0032] μ=(D_AVG1+D_AVG2+…+D_AVGn) / n(5),

[0033]

[0034] Traverse all sample data of the sample data set and get the average value μ corresponding to each sample data p and standard deviation σ p , p∈[1,h], h is the number of samples;

[0035] According to the average value μ corresponding to each sample data p and standard deviation σ p , use formula (7) to calculate the threshold λ of abnormal cells:

[0036]

[0037] Optionally, the threshold calculation process further includes:

[0038] When a new abnormal cell is detected, data of the new abnormal cell is added to the sample data set to obtain an updated sample data set of the abnormal cell, and the threshold λ of the abnormal cell is recalculated using the new sample data set.

[0039] According to a second aspect of the present invention, there is provided an early warning system for abnormality of a power battery cell, comprising:

[0040] A preprocessing module is used to obtain the recent historical data of the vehicle power battery and perform preprocessing to obtain multi-frame battery cell data when the battery is in a static state;

[0041] The data calculation module calculates the real SOC of each battery cell in each frame of battery cell data, and calculates the real SOC median of each frame of battery cell data according to the real SOC of all battery cells in each frame of battery cell data; calculates the difference between the real SOC of each battery cell in the current frame of battery cell data and the real SOC median, calculates the Euclidean distance between each battery cell and all battery cells according to the difference, and calculates the average Euclidean distance between each battery cell and all battery cells according to the Euclidean distance:

[0042] The result detection module compares the Euclidean distance average value with a preset threshold value to determine whether the current battery cell is abnormal.

[0043] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the processor is configured to implement the steps of the above-mentioned method for early warning of abnormality of a power battery cell when executing a computer management program stored in the memory.

[0044] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer management program is stored, and when the computer management program is executed by a processor, the steps of the above-mentioned method for early warning of abnormality of a power battery cell are implemented.

[0045] The present invention provides a method, system, electronic device and storage medium for early warning of abnormal power battery cells. The method pre-processes the historical data of the power battery, extracts the data of the battery in a static state for analysis; based on the real SOC of the battery in a static state, the dispersion of the average Euclidean distance between any two cells is calculated within a period of time to screen abnormal cells. The present invention can identify abnormal power battery conditions in advance and issue early warnings, thereby replacing or repairing the battery pack module in advance. On the one hand, the accuracy of the abnormal power battery cell early warning is high, which improves the safety of the vehicle. On the other hand, it improves the user's driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flow chart of a method for early warning of abnormal power battery cells provided by the present invention;

[0047] Figure 2 A flow chart of the data preprocessing process of the method provided by the present invention;

[0048] Figure 3 A flow chart of the data calculation process of the method provided by the present invention;

[0049] Figure 4 A block diagram of a power battery cell abnormality early warning system provided by the present invention;

[0050] Figure 5 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0051] Figure 6 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0052] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0053] Terminology explanation: Battery SOC (State of charge), that is, the battery's state of charge, is used to reflect the remaining capacity of the battery. Its value is defined as the ratio of the remaining capacity to the battery capacity, usually expressed as a percentage. Its value range is 0 to 1. When SOC = 0, it means that the battery is fully discharged, and when SOC = 1, it means that the battery is fully charged.

[0054] Figure 1 A flow chart of an abnormal early warning method for a power battery cell provided by the present invention, such as Figure 1 As shown, the method includes:

[0055] S1, obtaining recent historical data of the vehicle power battery and preprocessing it to obtain multiple frames of battery cell data in a static state;

[0056] S2, calculating the real SOC of each battery cell in each frame of battery cell data, and calculating the real SOC median of each frame of battery cell data according to the real SOC of all battery cells in each frame of battery cell data; calculating the difference between the real SOC of each battery cell in the current frame of battery cell data and the real SOC median, calculating the Euclidean distance between each battery cell and all battery cells according to the difference, and calculating the average Euclidean distance between each battery cell and all battery cells according to the Euclidean distance;

[0057] S3, comparing the average value of the Euclidean distance between each battery cell and all battery cells with a preset threshold value to determine whether the current battery cell is abnormal.

[0058] It is understandable that, based on the defects in the background technology, the embodiment of the present invention proposes an early warning method for abnormal power battery cells. By preprocessing the historical data of the power battery, extracting the data of the battery in a static state for analysis, the interference of abnormal data on the detection results is reduced; based on the real SOC of the battery in a static state, the dispersion of the average Euclidean distance between any two cells is calculated within a period of time, and abnormal cells are screened, thereby achieving effective early warning of battery cell abnormalities.

[0059] The present invention can identify abnormal conditions of power batteries in advance and issue early warnings, thereby replacing or repairing the battery pack module in advance. Compared with the prior art, on the one hand, the embodiments of the present invention have a high accuracy rate in warning abnormalities of power battery cells and improve vehicle safety. On the other hand, it improves the user's driving experience and increases customer satisfaction.

[0060] In a possible embodiment, Figure 2 As shown, in step S1, the recent historical data of the vehicle power battery is obtained and preprocessed to obtain multiple frames of battery cell data in a static state, including:

[0061] S101, selecting continuous national standard historical data of vehicle power batteries in a recent sampling period, such as historical data for a continuous week;

[0062] S102, filtering out abnormal data according to the voltage value and the current value of each frame of battery cell data to obtain multiple frames of battery cell data in a static state.

[0063] It is understandable that the national standard historical data of vehicle power batteries for a continuous sampling period includes the battery data of the vehicle in all states during this sampling period, such as steady driving, fast driving, static state, etc. When the vehicle is in operation, the battery data changes in real time according to the vehicle operation state, which is unstable and cannot be used as a basis for battery abnormality judgment. Therefore, in this embodiment, by judging the voltage and current values ​​of the battery data, abnormal data is screened out, and the data in the static state of the battery is screened out as the detection data of the method of the present invention to improve the accuracy of battery detection.

[0064] In a possible implementation manner, the method of filtering out abnormal data according to the voltage value and the current value of each frame of battery cell data to obtain multiple frames of battery cell data in a static state includes:

[0065] S1021, comparing the voltage value of a single battery cell in each frame of battery cell data with the voltage threshold value, filtering out battery cell data frames with abnormal voltage, and retaining battery cell data frames with normal voltage;

[0066] S1022, comparing the current values ​​of individual cells in the cell data frames with normal voltage with the current thresholds respectively, filtering out the cell data frames with abnormal currents, and the obtained multiple frames of cell data are the cell data in a static state.

[0067] It is understandable that when the battery is in a static state, its voltage and current values ​​are both in a stable state. Therefore, when screening each frame of battery cell data, it is necessary to preset the voltage threshold and current threshold. For example, the effective voltage threshold range is set to [0V, 5V], and the voltage value U of a single battery cell satisfies 0V≤U≤5V, that is, the voltage is judged to meet the requirements; the effective current threshold range is set to [-2A, 2A], and the current value I of a single battery cell satisfies -2A≤I≤2A, that is, the current is judged to meet the requirements. The multi-frame battery cell data with qualified voltage and current values ​​that are screened out are considered to be data when the battery is in a static state, and are used to participate in the calculation of subsequent steps. Assume that there are m frames of static data obtained after historical data preprocessing, and the number of single cells in each frame of battery cell data is n.

[0068] In a possible embodiment, Figure 3 As shown, in step S2, the calculation of the real SOC of each battery cell in each frame of battery cell data includes:

[0069] S201, obtain the voltage value of each battery cell in each frame of battery cell data, and use the table lookup method to query the OCV-SOC table of the battery pack through the voltage value of each battery cell to obtain the real SOC of each battery cell, which is recorded as SOC_Real ij , i∈[1,m], j∈[1,n], where m is the number of frames of battery cell data obtained after preprocessing, and n is the number of battery cells in each frame of battery cell data.

[0070] It is understandable that the SOC of a battery cannot be measured directly, and can only be estimated through parameters such as the battery terminal voltage, charge and discharge current, and internal resistance. These parameters are also affected by various uncertain factors such as battery aging, ambient temperature changes, and vehicle driving conditions. They are generally estimated through internal resistance measurement, linear model, and Kalman filtering. In this embodiment, the voltage value of a single battery cell is used as a known value to look up the OCV-SOC table of the battery cell, and the true SOC of a single battery cell is obtained through the OCV-SOC curve. The true SOC estimated by the OCV-SOC curve has a high accuracy and can be used as a basis for calculations in subsequent steps.

[0071] In a possible implementation manner, step S2 further includes:

[0072] S202, according to the real SOC of all the cells in each frame of the cell data, respectively calculate the real SOC median of each frame of the cell data, wherein the real SOC median of each frame of the cell data is recorded as SOC_Median and is calculated by formula (1):

[0073] SOC_Median i =median(SOC_Real i1 ,SOC_Real i2 ,…,SOC_Real ij ),

[0074] i∈[1,m],j∈[1,n](1),

[0075] Among them, SOC_Median i is the real SOC median of the cell data in the i-th frame, median is the median function, SOC_Real ij is the actual SOC of the jth battery cell in the i-th frame of battery cell data.

[0076] It can be understood that in this embodiment, the median operation is performed on the real SOC of all the battery cells in a single frame of battery cell data to obtain the real SOC median SOC_Median of each frame of battery cell data.

[0077] In a possible embodiment, in step S2, respectively calculating the difference between the real SOC of each battery cell in the current frame battery cell data and the real SOC median, respectively calculating the Euclidean distance between each battery cell and all battery cells according to the difference, and obtaining the average value of the Euclidean distance between each battery cell and all battery cells according to the Euclidean distance calculation; including:

[0078] S203, calculating the difference between the actual SOC of each battery cell in each frame of battery cell data and the actual SOC median by formula (2), and the difference is recorded as ΔSOC ij :

[0079] ΔSOC ij =SOC_Real ij -SOC_Median i , i∈[1,m],j∈[1,n](2);

[0080] It can be understood that in step S203, the difference between the real SOC and the real SOC median of n single cells in the m-frame cell data can be calculated by formula (2), for example, the difference ΔSOC between the real SOC of the first single cell in the first frame and the real SOC median 11 , the difference between the actual SOC of the third single cell in the second frame and the median of the actual SOC ΔSOC 23 , ..., the difference between the actual SOC of the nth cell in the mth frame and the median of the actual SOC ΔSOC mn .

[0081] S204, according to the difference between the actual SOC of each battery cell in each frame of battery cell data and the median of the actual SOC, calculate the Euclidean distance D between each battery cell and all the battery cells by formula (3) jk :

[0082]

[0083] Among them, D jk Indicates the Euclidean distance between the jth cell and the kth cell in the same frame of cell data, ΔSOC ij ΔSOC is the difference between the actual SOC of the jth cell in the i-th frame of cell data and the median of the actual SOC. ik It is the difference between the actual SOC of the kth cell in the i-th frame of cell data and the median of the actual SOC. The values ​​of j and k do not interfere with each other. When the values ​​of j and k are the same, they represent the same cell.

[0084] It can be understood that in step S204, the Euclidean distance between any single cell and any single cell in the same frame of cell data can be calculated by formula (3). For example, when the values ​​of j and k are the same, it means that the Euclidean distance from a cell to itself is 0.

[0085] S205, based on the European distance D between each battery cell and all battery cells jk , calculate the average value D_AVG of the Euclidean distance between each cell and all cells using formula (4) j :

[0086] D_AVG j =(D j1 +D j2 +…+D jk ) / n,j∈[1,n],k∈[1,n](4).

[0087] It can be understood that in step S205, the average value D_AVG of the Euclidean distance between a certain battery cell and all the battery cells in the same frame data can be calculated by formula (4): j , the average value of the Euclidean distance D_AVG j It can reflect the dispersion of the average Euclidean distance between any two cells, so it can be used as a basis for judging whether a single cell is abnormal. Compare it with the preset threshold. If D_AVG j If it is greater than the preset threshold, the corresponding battery cell can be judged to be abnormal, and an early warning prompt will be issued.

[0088] In a possible embodiment, the calculation process of the threshold value for determining whether the battery cell is abnormal includes:

[0089] Obtain a sample data set of known abnormal cells, and calculate the corresponding mean value μ and standard deviation σ according to the sample data of each abnormal cell using formula (5) and formula (6):

[0090] μ=(D_AVG1+D_AVG2+…+D_AVGn) / n(5),

[0091]

[0092] Traverse all sample data of the sample data set and get the average value μ corresponding to each sample data p and standard deviation σ p , p∈[1,h], h is the number of samples;

[0093] According to the average value μ corresponding to each sample data p and standard deviation σ p , use formula (7) to calculate the threshold λ of abnormal cells:

[0094]

[0095] It is understandable that in this embodiment, multiple known abnormal battery cell data are analyzed to obtain an empirical value, which is used as a threshold value λ for judging battery abnormality. Since the calculated threshold value λ is based on samples of several known abnormal battery cells, it is based on the common rules of several abnormal battery cells and is referenceable.

[0096] In a possible implementation manner, in order to continuously improve the accuracy of cell abnormality judgment, the threshold λ may be continuously updated iteratively. For example, the threshold calculation process further includes:

[0097] When a new abnormal cell is detected, the data of the new abnormal cell is added to the sample data set, the value of p is updated to obtain an updated sample data set of the abnormal cell, and the threshold λ of the abnormal cell is recalculated using the new sample data set.

[0098] It is understandable that, as the abnormal cell sample data set continues to expand, each update of the sample data set corresponds to an update of the threshold λ, so that the threshold λ is continuously iterated and optimized, and the accuracy of the detection result is gradually improved.

[0099] Figure 4 A structural diagram of an abnormal early warning system for a power battery cell provided by an embodiment of the present invention, such as Figure 4 As shown, a power battery monomer abnormality early warning system includes a preprocessing module 401, a data calculation module 402 and a result detection module 403, wherein:

[0100] A preprocessing module 401 is used to obtain recent historical data of the vehicle power battery and perform preprocessing to obtain multiple frames of battery cell data in a static state;

[0101] The data calculation module 402 is used to calculate the real SOC of each battery cell in each frame of battery cell data, and calculate the real SOC median of each frame of battery cell data according to the real SOC of all battery cells in each frame of battery cell data; calculate the difference between the real SOC of each battery cell in the current frame of battery cell data and the real SOC median, calculate the Euclidean distance between each battery cell and all battery cells according to the difference, and calculate the average Euclidean distance between each battery cell and all battery cells according to the Euclidean distance calculation;

[0102] The result detection module 403 is used to compare the average value of the Euclidean distance with a preset threshold value to determine whether the current battery cell is abnormal.

[0103] It can be understood that the power battery cell abnormality warning system provided by the present invention corresponds to the power battery cell abnormality warning method provided by the aforementioned embodiments. The relevant technical features of the power battery cell abnormality warning system can refer to the relevant technical features of the power battery cell abnormality warning method, which will not be repeated here.

[0104] See also Figure 5 , Figure 5 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented:

[0105] Obtain the recent historical data of the vehicle power battery and perform preprocessing to obtain the data of the battery in a static state;

[0106] Calculate the real SOC of each battery cell in each frame of battery cell data, and calculate the real SOC median of each frame of battery cell data according to the real SOC of all battery cells in each frame of battery cell data; calculate the difference between the real SOC of each battery cell in the current frame of battery cell data and the real SOC median, calculate the Euclidean distance between each battery cell and all battery cells according to the difference, and calculate the average Euclidean distance between each battery cell and all battery cells according to the Euclidean distance:

[0107] The average value of the Euclidean distance is compared with a preset threshold value to determine whether the current battery cell is abnormal.

[0108] See also Figure 6 , Figure 6 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 6 As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented:

[0109] Obtain the recent historical data of the vehicle power battery and perform preprocessing to obtain the data of the battery in a static state;

[0110] Calculate the real SOC of each battery cell in each frame of battery cell data, and calculate the real SOC median of each frame of battery cell data according to the real SOC of all battery cells in each frame of battery cell data; calculate the difference between the real SOC of each battery cell in the current frame of battery cell data and the real SOC median, calculate the Euclidean distance between each battery cell and all battery cells according to the difference, and calculate the average Euclidean distance between each battery cell and all battery cells according to the Euclidean distance:

[0111] The average value of the Euclidean distance is compared with a preset threshold value to determine whether the current battery cell is abnormal.

[0112] The embodiments of the present invention provide a method, system and storage medium for early warning of abnormal power battery cells. The method pre-processes the historical data of the power battery, extracts the data of the battery in a static state for analysis; based on the real SOC of the battery in a static state, the dispersion of the average Euclidean distance between any two cells is calculated within a period of time to screen abnormal cells. The present invention can identify abnormal power battery conditions in advance and issue early warnings, thereby replacing or repairing the battery pack module in advance. On the one hand, the accuracy of the abnormal power battery cell early warning is high, which improves the safety of the vehicle. On the other hand, it improves the user's driving experience.

[0113] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0114] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, 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 computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0119] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for early warning of abnormal power battery cells, characterized in that: include: Acquire recent historical data of the vehicle's power battery and perform preprocessing to obtain multi-frame battery cell data in a static state; Calculate the real SOC of each battery cell in each frame of battery cell data, and calculate the median of the real SOC of each frame of battery cell data based on the real SOC of all batteries in each frame of battery cell data; The difference between the real SOC and the median of the real SOC of each battery cell in the current frame battery cell data is calculated respectively, and the Euclidean distance between each battery cell and all the battery cells is calculated according to the difference, and the average value of the Euclidean distance between each battery cell and all the battery cells is obtained according to the Euclidean distance calculation: specifically including: The difference between the actual SOC of each cell in each frame of cell data and the median of the actual SOC is calculated by formula (2), and the difference is recorded as ΔSOC ij : ΔSOC ij =SOC_Real ij -SOC_Median i ,i∈[1,m], j∈[1,n] (2); Among them, SOC_Real ij The actual SOC of each battery cell, SOC_Median i is the real SOC median of each frame of battery cell data, m is the number of frames of battery cell data obtained after preprocessing, and n is the number of batteries in each frame of battery cell data; According to the difference between the actual SOC of each cell in each frame of cell data and the median of the actual SOC, the Euclidean distance D between each cell and all cells is calculated by formula (3): jk : Among them, D jk Indicates the Euclidean distance between the jth cell and the kth cell in the same frame of cell data, ΔSOC ij ΔSOC is the difference between the actual SOC of the jth cell in the i-th frame of cell data and the median of the actual SOC. ik is the difference between the real SOC of the kth cell in the i-th frame of cell data and the median of the real SOC. If the values ​​of j and k are the same, they represent the same cell. According to the European distance D between each battery cell and all other batteries jk , calculate the average value D_AVG of the Euclidean distance between each cell and all cells using formula (4) j : <h2 style=";text-align:left;direction:ltr">D_AVG<h2 style=";text-align:left;direction:ltr"> j <h2 style=";text-align:left;direction:ltr"> (D)<h2 style=";text-align:left;direction:ltr"> j1 <h2 style=";text-align:left;direction:ltr"> +D<h2 style=";text-align:left;direction:ltr"> j2 <h2 style=";text-align:left;direction:ltr"> +…+D<h2 style=";text-align:left;direction:ltr"> jk <h2 style=";text-align:left;direction:ltr"> ) / n, j∈[1,n], k∈[1,n] (4); The average value of the Euclidean distance is compared with a preset threshold value to determine whether the current battery cell is abnormal.

2. The method for early warning of abnormal power battery cells according to claim 1, characterized in that: The acquisition of recent historical data of the vehicle power battery and preprocessing to obtain data of the battery in a static state includes: Select the national standard historical data of vehicle power batteries in a recent sampling period; Abnormal data is screened out according to the voltage value and current value of each frame of battery cell data to obtain multiple frames of battery cell data in a static state.

3. The method for early warning of abnormality of a power battery cell according to claim 2, characterized in that: The method of filtering out abnormal data according to the voltage value and the current value of each frame of battery cell data to obtain multiple frames of battery cell data in a static state comprises: Compare the voltage value of a single cell in each frame of cell data with the voltage threshold, filter out cell data frames with abnormal voltage, and retain cell data frames with normal voltage; The current values ​​of individual cells in the cell data frames with normal voltage are compared with the current thresholds respectively, and the cell data frames with abnormal current are screened out. The obtained multiple frames of cell data are the cell data in the static state.

4. The method for early warning of abnormal power battery cells according to claim 1, characterized in that: The calculating of the real SOC of each battery cell in each frame of battery cell data includes: Get the voltage value of each cell in each frame of cell data, and use the table lookup method to query the OCV-SOC table of the battery pack through the voltage value of each cell to obtain the real SOC of each cell, recorded as SOC_Real ij , i∈[1,m], j∈[1,n], where m is the number of frames of battery cell data obtained after preprocessing, and n is the number of battery cells in each frame of battery cell data.

5. The method for early warning of abnormal power battery cells according to claim 4, characterized in that: The real SOC median of each frame of battery cell data is calculated based on the real SOC of all battery cells in each frame of battery cell data. The real SOC median of each frame of battery cell data is recorded as SOC_Median and is calculated by formula (1): SOC_Median i =median(SOC_Real i1 ,SOC_Real i2 ,…,SOC_Real ij ), i∈[1,m],j∈[1,n](1), Among them, SOC_Median i is the real SOC median of the cell data in the i-th frame, median is the median function, SOC_Real ij is the actual SOC of the jth battery cell in the i-th frame of battery cell data.

6. The method for early warning of abnormal power battery cells according to claim 5, characterized in that: The threshold calculation process includes: Obtain a sample data set of known abnormal cells, and calculate the corresponding mean value μ and standard deviation σ according to the sample data of each abnormal cell using formula (5) and formula (6): μ=(D_AVG1+ D_AVG2+…+D_AVGn) / n (5), Traverse all sample data of the sample data set and get the average value μ corresponding to each sample data p and standard deviation σ p , p∈[1,h], h is the number of samples; According to the average value μ corresponding to each sample data p and standard deviation σ p , use formula (7) to calculate the threshold λ of abnormal cells:

7. The method for early warning of abnormality of a power battery cell according to claim 6, characterized in that: The threshold calculation process also includes: When a new abnormal cell is detected, data of the new abnormal cell is added to the sample data set to obtain an updated sample data set of the abnormal cell, and the threshold λ of the abnormal cell is recalculated using the new sample data set.

8. An early warning system for abnormal power battery cells, characterized in that: include: A preprocessing module is used to obtain the recent historical data of the vehicle power battery and perform preprocessing to obtain multi-frame battery cell data when the battery is in a static state; The data calculation module calculates the real SOC of each battery cell in each frame of battery cell data, and calculates the real SOC median of each frame of battery cell data according to the real SOC of all batteries in each frame of battery cell data; The difference between the real SOC and the median of the real SOC of each battery cell in the current frame battery cell data is calculated respectively, and the Euclidean distance between each battery cell and all the battery cells is calculated according to the difference, and the average value of the Euclidean distance between each battery cell and all the battery cells is obtained according to the Euclidean distance calculation: specifically including: The difference between the actual SOC of each cell in each frame of cell data and the median of the actual SOC is calculated by formula (2), and the difference is recorded as ΔSOC ij : ΔSOC ij =SOC_Real ij -SOC_Median i ,i∈[1,m], j∈[1,n] (2); Among them, SOC_Real ij The actual SOC of each battery cell, SOC_Median i is the real SOC median of each frame of battery cell data, m is the number of frames of battery cell data obtained after preprocessing, and n is the number of batteries in each frame of battery cell data; According to the difference between the actual SOC of each cell in each frame of cell data and the median of the actual SOC, the Euclidean distance D between each cell and all cells is calculated by formula (3): jk : Among them, D jk Indicates the Euclidean distance between the jth cell and the kth cell in the same frame of cell data, ΔSOC ij ΔSOC is the difference between the actual SOC of the jth cell in the i-th frame of cell data and the median of the actual SOC. ik is the difference between the real SOC of the kth cell in the i-th frame of cell data and the median of the real SOC. If the values ​​of j and k are the same, they represent the same cell. According to the European distance D between each battery cell and all other batteries jk , calculate the average value D_AVG of the Euclidean distance between each cell and all cells using formula (4) j : <h2 style=";text-align:left;direction:ltr">D_AVG<h2 style=";text-align:left;direction:ltr"> j <h2 style=";text-align:left;direction:ltr"> (D)<h2 style=";text-align:left;direction:ltr"> j1 <h2 style=";text-align:left;direction:ltr"> +D<h2 style=";text-align:left;direction:ltr"> j2 <h2 style=";text-align:left;direction:ltr"> +…+D<h2 style=";text-align:left;direction:ltr"> jk <h2 style=";text-align:left;direction:ltr"> ) / n, j∈[1,n], k∈[1,n] (4); The result detection module compares the Euclidean distance average value with a preset threshold value to determine whether the current battery cell is abnormal.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the processor is used to implement the steps of a power battery cell abnormality early warning method as claimed in any one of claims 1 to 7 when executing a computer management program stored in the memory.

Images