Battery cell anomaly identification method, device and electronic equipment based on multi-method fusion

Abstract

The present invention relates to the field of battery monitoring technology, and specifically to a method, device and electronic device for identifying abnormal cell behavior based on the fusion of multiple methods, including: calculating the internal resistance value of each cell at each moment; selecting the internal resistance value of each cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each cell; calculating the Pearson correlation coefficient value corresponding to each cell, the Euclidean distance value corresponding to each cell, the DTW value corresponding to each cell, the cosine similarity value and the standard deviation variation coefficient corresponding to each cell; using the 3σ principle and the outlier detection method to separately identify the Pearson correlation coefficient value, Euclidean distance value, DTW value, cosine similarity value and standard deviation variation coefficient of each cell, and determining the abnormal cell based on the identification result. The present invention identifies cell abnormalities by integrating multiple methods, thereby improving the identification effect of abnormal cells and effectively avoiding the limitations brought about by relying on a single method.

Description

Technical Field

[0001] The present invention relates to the field of battery monitoring technology, and in particular to a method, device and electronic equipment for identifying battery cell anomalies based on multi-method fusion. Background Art

[0002] In recent years, the number of electric vehicles has continued to rise, leading to widespread use of lithium-ion batteries. This has led to an increasing concern about battery cell consistency. Currently, assessment of power battery cell inconsistency is primarily accomplished using specialized equipment to measure battery capacity, voltage, internal resistance, and other performance characteristics. However, these three consistency measurement methods vary in practical operation, making it difficult to fully and repeatedly monitor batteries in service.

[0003] Currently, in addition to using specialized equipment for measurement, the industry's mainstream method for assessing battery inconsistency primarily relies on voltage differential and standard deviation. However, these methods cannot accurately reflect battery inconsistency and are significantly affected by the battery's State of Charge (SOC) and current. Furthermore, most existing technologies rely on manual measurement, which is cumbersome. Current cell identification models are limited and lack robustness. Summary of the Invention

[0004] The present invention provides a method, device and electronic device for identifying battery cell anomalies based on the fusion of multiple methods, so as to improve the recognition effect of battery cells and avoid the limitations brought by relying on a single method.

[0005] The embodiments of this specification provide a method for identifying battery cell anomalies based on the fusion of multiple methods, including:

[0006] Obtain the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle;

[0007] Calculating the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; selecting the internal resistance value of each battery cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell;

[0008] Based on the internal resistance value array of each battery cell, a Pearson correlation coefficient value of each battery cell, a Euclidean distance value of each battery cell, a DTW (Dynamic Time Warping, similarity between two time series of different lengths) value of each battery cell, and a cosine similarity value of each battery cell are calculated respectively;

[0009] Calculate the standard deviation coefficient of variation for each battery cell separately;

[0010] Using the 3σ principle, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell are respectively identified to obtain a first indicator identification result corresponding to each battery cell;

[0011] Using an outlier detection method, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell are respectively identified to obtain a second indicator identification result corresponding to each battery cell;

[0012] An abnormal battery cell is determined based on the first indicator identification result and the second indicator identification result.

[0013] Preferably, the obtaining of current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle includes:

[0014] Obtain voltage and current data for each vehicle during a preset time period;

[0015] Preprocessing the voltage data and the current data to obtain initial current data of each battery cell of each vehicle and initial voltage data of each battery cell of each vehicle;

[0016] The initial first current data of each battery cell of each vehicle and the initial first voltage data of each battery cell of each vehicle are cleaned to obtain current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle.

[0017] Preferably, the calculating the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle includes:

[0018] Calculate the voltage difference between two adjacent points in each battery cell of each vehicle at each moment and the current difference between two adjacent points in each battery cell of each vehicle at each moment according to the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle;

[0019] The internal resistance value of each battery cell at each moment is calculated according to the voltage difference between two adjacent points of each battery cell of each vehicle at each moment and the current difference between two adjacent points of each battery cell of each vehicle at each moment.

[0020] Preferably, the internal resistance value of each battery cell at each moment is selected according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell, including:

[0021] Take the median internal resistance value of each battery cell within the preset time window on a daily basis;

[0022] The median internal resistance value of each battery cell on each day within a preset time window is combined to obtain an internal resistance value array of each battery cell.

[0023] Preferably, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell are calculated based on the internal resistance value array of each battery cell;

[0024] Calculate the Pearson correlation coefficient, Euclidean distance, DTW value, and cosine similarity between the internal resistance array of each battery cell and the internal resistance arrays of other battery cells to generate the data structure of each battery cell;

[0025] The data structure of each battery cell is averaged to obtain a Pearson correlation coefficient value corresponding to each battery cell, a Euclidean distance value corresponding to each battery cell, a DTW value corresponding to each battery cell, and a cosine similarity value corresponding to each battery cell.

[0026] Preferably, calculating the standard deviation coefficient of variation of each battery cell separately includes:

[0027] The standard deviation coefficient of variation formula is used to calculate the standard deviation coefficient of variation of each battery cell. The formula is as follows:

[0028]

[0029] in, is the standard deviation coefficient of variation of the m-th cell, is the total number of days in the time window, j is the jth day in the time window, m is the mth battery cell, Indicates the maximum internal resistance of all cells on day j, Indicates the minimum internal resistance of all cells on day j, Indicates the resistance value of the mth battery cell on the jth day.

[0030] Preferably, determining the abnormal battery cell based on the first indicator identification result and the second indicator identification result includes:

[0031] When the number of abnormal indicators in the first indicator identification result and the second indicator identification result reaches or exceeds a preset abnormal indicator number, the internal resistance of the battery cell is inconsistent;

[0032] When the number of abnormal indicators in the first indicator identification result and the second indicator identification result corresponding to the battery cell is lower than the preset abnormal indicator number, the battery cell is normal.

[0033] The embodiments of this specification also provide a battery cell anomaly identification device based on multi-method fusion, including:

[0034] A data acquisition module is used to obtain the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle;

[0035] an internal resistance value calculation module, configured to calculate the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; and select the internal resistance value of each battery cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell;

[0036] A first indicator calculation module is used to calculate the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell based on the internal resistance value array of each battery cell;

[0037] The second indicator calculation module is used to calculate the standard deviation coefficient of variation of each battery cell;

[0038] A first indicator identification module is used to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell using the 3σ principle to obtain a first indicator identification result corresponding to each battery cell;

[0039] A second indicator identification module is used to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell by using an outlier detection method to obtain a second indicator identification result corresponding to each battery cell;

[0040] An abnormal cell determination module is configured to determine an abnormal cell based on the first indicator identification result and the second indicator identification result.

[0041] An electronic device, wherein the electronic device comprises:

[0042] A processor and a memory storing computer-executable instructions, wherein when the instructions are executed, the processor is caused to perform any of the above methods.

[0043] A computer-readable storage medium stores one or more instructions, and when the one or more instructions are executed by a processor, implements any of the above methods.

[0044] The present invention integrates multiple methods to identify battery cell anomalies, thereby improving the recognition effect of abnormal battery cells and effectively avoiding the limitations brought about by relying on a single method. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 This is a hardware structure block diagram of a mobile terminal for identifying abnormal cell behavior based on multi-method fusion according to an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of the principle of a battery cell anomaly identification method based on multi-method fusion provided in an embodiment of this specification;

[0048] Figure 3 This is a schematic diagram of the structure of a battery cell anomaly identification device based on multi-method fusion provided in an embodiment of this specification. DETAILED DESCRIPTION

[0049] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in various forms, and it should not be understood that the present invention is limited to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, making it easier to fully convey the inventive concept to those skilled in the art. In the figures, the same reference numerals represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0050] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0051] In the description of specific embodiments, the features, structures, characteristics, or other details of the present invention are described to enable those skilled in the art to fully understand the embodiments. However, this does not preclude those skilled in the art from practicing the technical solutions of the present invention without one or more of the specific features, structures, characteristics, or other details.

[0052] The figures shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be performed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0053] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0054] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0055] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware block diagram of a mobile terminal for identifying abnormal cell behavior based on multi-method fusion. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 (processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data. Optionally, the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0056] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the page layout method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0057] The transmission device 106 is used to receive or send data via a network. A specific example of the aforementioned network may include a wireless network provided by the mobile terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0058] Reference Figure 2 The schematic diagram of the principle of the battery cell abnormality identification method based on multi-method fusion provided in the embodiment of this specification includes:

[0059] S101: Acquire current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle;

[0060] Furthermore, the obtaining of current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle includes:

[0061] Obtain voltage and current data for each vehicle during a preset time period;

[0062] Preprocessing the voltage data and the current data to obtain initial current data of each battery cell of each vehicle and initial voltage data of each battery cell of each vehicle;

[0063] The initial first current data of each battery cell of each vehicle and the initial first voltage data of each battery cell of each vehicle are cleaned to obtain current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle.

[0064] In a preferred embodiment of the present invention, the voltage data and current data of each vehicle for the past year are first obtained. Since we only need to obtain the voltage data and current data related to each battery cell of each vehicle, it is necessary to pre-process the voltage data and current data of each vehicle for the past year, filter out the valid data, and finally obtain the initial current data of each battery cell of each vehicle and the initial voltage data of each battery cell of each vehicle. Furthermore, since the initial current data of each battery cell of each vehicle and the initial voltage data of each battery cell of each vehicle may be incomplete, such as missing data and data duplication, the initial current data of each battery cell of each vehicle and the initial voltage data of each battery cell of each vehicle are improved by data cleaning, and finally the improved current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle are obtained, thereby improving the accuracy of subsequent related data calculations.

[0065] S102: Calculating the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; selecting the internal resistance value of each battery cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell;

[0066] Furthermore, the calculating the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle includes:

[0067] Calculate the voltage difference between two adjacent points in each battery cell of each vehicle at each moment and the current difference between two adjacent points in each battery cell of each vehicle at each moment according to the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle;

[0068] The internal resistance value of each battery cell at each moment is calculated according to the voltage difference between two adjacent points of each battery cell of each vehicle at each moment and the current difference between two adjacent points of each battery cell of each vehicle at each moment.

[0069] In a preferred embodiment of the present invention, the voltage difference between two adjacent points of each battery cell of each vehicle at each moment is calculated based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle. And the current difference between two adjacent points of each battery cell in each vehicle at each moment , in calculating the voltage difference and current difference When |>0, 、Time difference( ) At the same time, the SOC (State Of Charge) in each record is limited to between 30% and 90%, and then the voltage difference is calculated. and current difference Calculate the internal resistance of each cell at each moment , the calculation formula is as follows:

[0070]

[0071] in, is the internal resistance of the cell at a certain moment, is the voltage difference between two adjacent points of each battery cell of each vehicle at each moment, The current difference between two adjacent points in each battery cell of each vehicle at each moment. By limiting the above conditions, the calculation accuracy of the internal resistance value of each battery cell at each moment can be better improved, thus improving the use of data.

[0072] Furthermore, the internal resistance value of each battery cell at each moment is selected according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell, including:

[0073] Take the median internal resistance value of each battery cell within the preset time window on a daily basis;

[0074] The median internal resistance value of each battery cell on each day within a preset time window is combined to obtain an internal resistance value array of each battery cell.

[0075] In a preferred embodiment of the present invention, based on the internal resistance value of each battery cell at each moment calculated as above, the median internal resistance value of each battery cell is taken in units of days, and each battery cell has one median internal resistance value per day. The number of days included in the time window is used as the time length, and the median internal resistance value of each battery cell every day in the time window is combined to finally obtain an internal resistance value array of each battery cell. Subsequently, the numerical calculation of the corresponding indicator is realized through the internal resistance value array of each battery cell.

[0076] S103: Calculating the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell based on the internal resistance value array of each battery cell;

[0077] Furthermore, based on the internal resistance value array of each battery cell, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell are calculated respectively;

[0078] Calculate the Pearson correlation coefficient, Euclidean distance, DTW value, and cosine similarity between the internal resistance array of each battery cell and the internal resistance arrays of other battery cells to generate the data structure of each battery cell;

[0079] The data structure of each battery cell is averaged to obtain a Pearson correlation coefficient value corresponding to each battery cell, a Euclidean distance value corresponding to each battery cell, a DTW value corresponding to each battery cell, and a cosine similarity value corresponding to each battery cell.

[0080] In a preferred embodiment of the present invention, the Pearson correlation coefficient, Euclidean distance, DTW value and cosine similarity between the internal resistance value array of each battery cell and the internal resistance value array of other battery cells are calculated to generate a data structure for each battery cell, and then the mean of the Pearson correlation coefficient, Euclidean distance, DTW value and cosine similarity is calculated respectively, that is, for n The average of each row of data in the n data structure is calculated to finally obtain the Pearson correlation coefficient value, Euclidean distance value, DTW value, and cosine similarity value corresponding to each battery cell, providing a data basis for subsequent abnormality identification of battery cells.

[0081] S104: Calculate the standard deviation coefficient of variation of each battery cell respectively;

[0082] In a preferred embodiment of the present invention, the Pearson correlation coefficient, Euclidean distance, DTW value and cosine similarity between the internal resistance array of each battery cell and the internal resistance array of other battery cells are calculated respectively to generate n Data Structure , use the standard deviation coefficient of variation formula to calculate the standard deviation coefficient of variation of each battery cell. The standard deviation coefficient of variation formula is: ,

[0083] in, is the standard deviation coefficient of variation of the m-th cell, is the total number of days in the time window, j is the jth day in the time window, m is the mth battery cell, Indicates the maximum internal resistance of all cells on day j, Indicates the minimum internal resistance of all cells on day j, Indicates the resistance value of the mth cell on the jth day

[0084] S105: Using the 3σ principle, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell are identified to obtain a first indicator identification result corresponding to each battery cell;

[0085] In a preferred embodiment of the present invention, the 3σ principle is to first assume that a group of detection data only contains random errors, calculate and process them to obtain the standard deviation, determine an interval according to a certain probability, and believe that any error exceeding this interval is not a random error but a gross error, and the data containing this error should be eliminated. Therefore, the 3σ principle can be used to identify abnormal values ​​in indicators such as the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation variation coefficient of each battery cell, thereby obtaining the first indicator identification result corresponding to each battery cell, and improving the battery cell abnormality identification effect by identifying multiple indicators.

[0086] S106: using an outlier detection method to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell, respectively, to obtain a second indicator identification result corresponding to each battery cell;

[0087] In a preferred embodiment of the present invention, LOF (Local Outlier Factor, outlier detection algorithm) is used to detect abnormal data or behaviors that are significantly different from normal data behaviors or characteristic attributes. Therefore, the outlier detection method can identify abnormal values ​​in indicators such as the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell, thereby obtaining the second indicator identification result corresponding to each battery cell, and improving the battery cell abnormality identification effect by identifying multiple indicators.

[0088] S107: Determine abnormal cells based on the first indicator identification result and the second indicator identification result.

[0089] Furthermore, the determining of abnormal cells based on the first indicator identification result and the second indicator identification result includes:

[0090] When the number of abnormal indicators in the first indicator identification result and the second indicator identification result reaches or exceeds a preset abnormal indicator number, the internal resistance of the battery cell is inconsistent;

[0091] When the number of abnormal indicators in the first indicator identification result and the second indicator identification result corresponding to the battery cell is lower than the preset abnormal indicator number, the battery cell is normal.

[0092] In a preferred embodiment of the present invention, the 3σ principle and the outlier detection method are used to perform abnormal identification on five indicators, namely, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell, to obtain 10 identification results for each battery cell. When the number of indicator abnormalities in the identification result reaches or exceeds the preset indicator abnormality number, it is considered that the internal resistance of the battery cell is inconsistent. When the number of indicator abnormalities in the identification result is lower than the preset indicator abnormality number, the battery cell is considered normal. The preset indicator abnormality number can be set to a specific value according to the specific situation, such as setting the preset indicator abnormality number to 5. By integrating multiple methods to identify battery cell abnormalities, the identification effect of abnormal batteries is improved, which can effectively avoid the limitations brought by relying on a single method.

[0093] In a preferred embodiment of the present invention, first, the voltage and current data of each vehicle for nearly one year are obtained, the obtained voltage and current data are cleaned, and the internal resistance value of each battery cell is calculated based on the cleaned data. Then, based on the number of days in the preset time window, the internal tissue median of each battery cell is taken for each day to generate an internal resistance value array of each battery cell in the preset time window; then, the Pearson correlation coefficient, Euclidean distance, DTW value and cosine similarity between the internal resistance value array of each battery cell and the internal resistance value array of other battery cells are calculated to generate a data structure for each battery cell, and the mean of the Pearson correlation coefficient, Euclidean distance, DTW value and cosine similarity is calculated for n The method calculates the mean of each row of data in the n data structure, ultimately obtaining the corresponding Pearson correlation coefficient, Euclidean distance, DTW value, and cosine similarity value for each battery cell. The standard deviation coefficient of variation is also calculated for each battery cell. The 3σ principle and outlier detection methods are used to identify anomalies in each of the five indicators: the Pearson correlation coefficient, Euclidean distance, DTW, cosine similarity, and standard deviation coefficient of variation. Ten identification results are obtained for each battery cell. When the number of anomalies in the identification results reaches or exceeds the preset number of anomalies, the battery cell is considered to have inconsistent internal resistance. When the number of anomalies in the identification results is lower than the preset number of anomalies, the battery cell is considered normal. By integrating multiple methods to identify abnormal cells, the identification of abnormal cells is improved, effectively avoiding the limitations of relying on a single method.

[0094] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0095] Figure 3 The schematic diagram of the structure of the battery cell abnormality identification device based on multi-method fusion provided in the embodiment of this specification includes:

[0096] A data acquisition module is used to obtain the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle;

[0097] an internal resistance value calculation module, configured to calculate the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; and select the internal resistance value of each battery cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell;

[0098] A first indicator calculation module is used to calculate the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell based on the internal resistance value array of each battery cell;

[0099] The second indicator calculation module is used to calculate the standard deviation coefficient of variation of each battery cell;

[0100] A first indicator identification module is used to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell using the 3σ principle to obtain a first indicator identification result corresponding to each battery cell;

[0101] A second indicator identification module is used to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell by using an outlier detection method to obtain a second indicator identification result corresponding to each battery cell;

[0102] An abnormal cell determination module is configured to determine an abnormal cell based on the first indicator identification result and the second indicator identification result.

[0103] The functions of the device in the embodiment of the present invention have been described in the above method embodiment. Therefore, for details not fully described in this embodiment, please refer to the relevant description in the above embodiment and will not be repeated here.

[0104] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0105] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0106] S101: Acquire current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle;

[0107] S102: Calculating the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; selecting the internal resistance value of each battery cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell;

[0108] S103: Calculating the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell based on the internal resistance value array of each battery cell;

[0109] S104: Calculate the standard deviation coefficient of variation of each battery cell respectively;

[0110] S105: Using the 3σ principle, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell are identified to obtain a first indicator identification result corresponding to each battery cell;

[0111] S106: using an outlier detection method to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell, respectively, to obtain a second indicator identification result corresponding to each battery cell;

[0112] S107: Determine abnormal cells based on the first indicator identification result and the second indicator identification result.

[0113] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0114] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0115] Furthermore, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0116] Furthermore, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0117] S101: Acquire current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle;

[0118] S102: Calculating the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; selecting the internal resistance value of each battery cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell;

[0119] S103: Calculating the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell based on the internal resistance value array of each battery cell;

[0120] S104: Calculate the standard deviation coefficient of variation of each battery cell respectively;

[0121] S105: Using the 3σ principle, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell are identified to obtain a first indicator identification result corresponding to each battery cell;

[0122] S106: using an outlier detection method to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell, respectively, to obtain a second indicator identification result corresponding to each battery cell;

[0123] S107: Determine abnormal cells based on the first indicator identification result and the second indicator identification result.

[0124] Furthermore, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0125] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, centralized on a single computing device, or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. In some cases, the steps shown or described can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0126] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A cell anomaly identification method based on multi-method fusion, characterized by: include: Obtain the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; Calculating the internal resistance of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; Selecting the internal resistance value of each battery cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell; Based on the internal resistance value array of each battery cell, respectively calculate the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell; The standard deviation coefficient of variation of each battery cell is calculated using the standard deviation coefficient of variation formula. The calculation formula for the standard deviation coefficient of variation is: in, is the standard deviation coefficient of variation of the mth cell, is the total number of days in the time window, j is the jth day in the time window, m is the mth battery cell, Indicates the maximum internal resistance of all cells on day j, Indicates the minimum internal resistance of all cells on day j, Indicates the resistance value of the mth battery cell on the jth day; Using the 3σ principle, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell are respectively identified to obtain a first indicator identification result corresponding to each battery cell; Using an outlier detection method, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell are respectively identified to obtain a second indicator identification result corresponding to each battery cell; An abnormal battery cell is determined based on the first indicator identification result and the second indicator identification result.

2. The method for identifying abnormality of battery cells based on multi-method fusion according to claim 1, characterized in that: The obtaining of current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle includes: Obtain voltage and current data for each vehicle during a preset time period; Preprocessing the voltage data and the current data to obtain initial current data of each battery cell of each vehicle and initial voltage data of each battery cell of each vehicle; The initial first current data of each battery cell of each vehicle and the initial first voltage data of each battery cell of each vehicle are cleaned to obtain current data of each battery cell of each vehicle and voltage data of each battery cell of each vehicle.

3. The method for identifying abnormality of battery cells based on multi-method fusion according to claim 1, characterized in that: The calculating the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle includes: Calculate the voltage difference between two adjacent points in each battery cell of each vehicle at each moment and the current difference between two adjacent points in each battery cell of each vehicle at each moment according to the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; The internal resistance value of each battery cell at each moment is calculated according to the voltage difference between two adjacent points of each battery cell of each vehicle at each moment and the current difference between two adjacent points of each battery cell of each vehicle at each moment.

4. The method for identifying abnormality of a battery cell based on multi-method fusion according to claim 1, characterized in that: The internal resistance value of each battery cell at each moment is selected according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell, including: Take the median internal resistance value of each battery cell within the preset time window on a daily basis; The median internal resistance value of each battery cell on each day within a preset time window is combined to obtain an internal resistance value array of each battery cell.

5. The method for identifying abnormality of battery cells based on multi-method fusion according to claim 1, characterized in that: The calculating, based on the internal resistance value array of each battery cell, the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell respectively includes: Calculate the Pearson correlation coefficient, Euclidean distance, DTW value, and cosine similarity between the internal resistance array of each battery cell and the internal resistance arrays of other battery cells to generate the data structure of each battery cell; The data structure of each battery cell is averaged to obtain a Pearson correlation coefficient value corresponding to each battery cell, a Euclidean distance value corresponding to each battery cell, a DTW value corresponding to each battery cell, and a cosine similarity value corresponding to each battery cell.

6. The method for identifying abnormality of battery cells based on multi-method fusion according to claim 1, characterized in that: The determining of abnormal cells based on the first indicator identification result and the second indicator identification result includes: When the number of abnormal indicators in the first indicator identification result and the second indicator identification result reaches or exceeds a preset abnormal indicator number, the internal resistance of the battery cell is inconsistent; When the number of abnormal indicators in the first indicator identification result and the second indicator identification result corresponding to the battery cell is lower than the preset abnormal indicator number, the battery cell is normal.

7. A battery cell anomaly identification device based on multi-method fusion, characterized in that: include: A data acquisition module is used to obtain the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; an internal resistance value calculation module, configured to calculate the internal resistance value of each battery cell at each moment based on the current data of each battery cell of each vehicle and the voltage data of each battery cell of each vehicle; Selecting the internal resistance value of each battery cell at each moment according to a preset internal resistance value selection rule to obtain an internal resistance value array of each battery cell; A first indicator calculation module is used to calculate the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, and the cosine similarity value corresponding to each battery cell based on the internal resistance value array of each battery cell; The second indicator calculation module is used to calculate the standard deviation coefficient of variation of each battery cell using the standard deviation coefficient of variation formula. The calculation formula of the standard deviation coefficient of variation is: in, is the standard deviation coefficient of variation of the mth cell, is the total number of days in the time window, j is the jth day in the time window, m is the mth battery cell, Indicates the maximum internal resistance of all cells on day j, Indicates the minimum internal resistance of all cells on day j, Indicates the resistance value of the mth battery cell on the jth day; A first indicator identification module is used to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell using the 3σ principle to obtain a first indicator identification result corresponding to each battery cell; A second indicator identification module is used to identify the Pearson correlation coefficient value corresponding to each battery cell, the Euclidean distance value corresponding to each battery cell, the DTW value corresponding to each battery cell, the cosine similarity value corresponding to each battery cell, and the standard deviation coefficient of variation of each battery cell by using an outlier detection method to obtain a second indicator identification result corresponding to each battery cell; An abnormal cell determination module is configured to determine an abnormal cell based on the first indicator identification result and the second indicator identification result.

8. An electronic device, wherein: The electronic device includes: A processor and a memory storing computer executable instructions, which when executed cause the processor to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more instructions, which, when executed by a processor, implement the method of any one of claims 1 to 6.

Images