Vehicle battery cell consistency evaluation method, device, equipment and storage medium

Abstract

This application discloses a vehicle battery cell consistency assessment method, apparatus, device, and storage medium. The method comprises: obtaining vehicle operation data, filtering out valid cell data from the vehicle operation data according to a preset valid data standard; processing the valid cell data according to a preset cell consistency index processing method to obtain cell consistency index data; and determining a total index deviation value for all battery cells in the current vehicle based on the cell consistency index data. If the total index deviation value exceeds a preset deviation threshold, it is determined that the current vehicle has a consistency risk. This application comprehensively assesses each consistency index of the battery cells through the total index deviation value of the battery cells, achieving the technical effect of improving the accuracy of vehicle battery cell assessment.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicle technology, and in particular to a method, device, equipment and storage medium for evaluating the consistency of vehicle battery cells. Background Art

[0002] New energy vehicles are typically equipped with a BMS (Battery Management System) to monitor and control the battery. Battery cells are the basic units that make up a battery pack. Battery cell consistency refers to the convergence of key characteristic parameters across each cell. Poor cell consistency within a vehicle's battery pack triggers a BMS fault alarm, limiting some vehicle performance and reducing the user experience.

[0003] Currently, the typical approach for consistency monitoring of vehicle battery cells is to monitor the battery's SOC (State of Charge) and temperature using the vehicle's BMS. When the difference between the maximum and minimum values reaches a set threshold, an alarm is triggered. This method is simple to implement, but is prone to false alarms and missed alarms, resulting in low consistency assessment accuracy. Summary of the Invention

[0004] The main purpose of this application is to provide a vehicle battery cell consistency evaluation method, device, equipment and storage medium, aiming to solve the problem of low accuracy of battery cell consistency evaluation.

[0005] To achieve the above objectives, the present application provides a vehicle battery cell consistency assessment method, the method comprising:

[0006] Acquire vehicle operation data, and filter out valid individual data in the vehicle operation data according to preset valid data standards;

[0007] Processing the valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data;

[0008] A total index deviation value of all battery cells in the current vehicle is determined based on the cell consistency index data. If the total index deviation value exceeds a preset deviation threshold, it is determined that the current vehicle has a consistency risk.

[0009] Optionally, before the step of filtering out valid individual data from the vehicle operation data according to a preset valid data standard, the method further includes:

[0010] detecting whether there is abnormal data in the vehicle operation data;

[0011] If there is abnormal data, the abnormal data is filtered to obtain valid operation data.

[0012] Optionally, the step of filtering out valid single-unit data from the vehicle operation data according to a preset valid data standard includes:

[0013] Acquiring a current data standard and a charging state standard from the valid data standards;

[0014] Valid operating data that meets the current data standard and the charging state standard is screened out as the valid single cell data.

[0015] Optionally, the step of processing the valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data includes:

[0016] Classifying the valid monomer data to obtain initial consistency data of each monomer;

[0017] A monomer consistency index processing method corresponding to each monomer consistency initial data is obtained, and each monomer consistency initial data is processed according to the monomer consistency index processing method to obtain a characteristic vector of each monomer consistency index.

[0018] Optionally, the step of determining the total index deviation value of all battery cells in the current vehicle according to the consistency index deviation value of each cell includes:

[0019] Combining the monomer consistency feature vectors into a monomer index feature matrix, and determining a covariance matrix of the monomer index feature matrix;

[0020] The Mahalanobis distance of each battery cell is determined according to the cell index characteristic matrix and the covariance matrix, and the sum of the Mahalanobis distances of each battery cell is used as the total index deviation value.

[0021] Optionally, after the step of determining that the current vehicle has a consistency risk if the total index deviation value exceeds a preset deviation threshold, the method further includes:

[0022] Determining the standard deviation of the Mahalanobis distance of each battery cell;

[0023] Battery cells whose standard deviation of Mahalanobis distance from the battery cells exceeds a preset distance threshold are screened out as consistency risk cells.

[0024] Optionally, the vehicle battery cell consistency assessment method further includes:

[0025] Obtain a deviation threshold correction parameter, and correct the deviation threshold according to the deviation threshold correction parameter.

[0026] In addition, to achieve the above-mentioned purpose, the present application also provides a vehicle battery cell consistency evaluation device, the vehicle battery cell consistency evaluation device comprising:

[0027] An acquisition module is used to acquire vehicle operation data and filter out valid individual data in the vehicle operation data according to a preset valid data standard;

[0028] A processing module, configured to process the valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data;

[0029] The judgment module is used to determine the total index deviation value of all battery cells in the current vehicle based on the cell consistency index data, and if the total index deviation value exceeds a preset deviation threshold, it is determined that the current vehicle has a consistency risk.

[0030] In addition, to achieve the above-mentioned purpose, the present application also provides an electronic device, which includes: a memory, a processor, and a vehicle battery cell consistency evaluation program stored on the memory and runnable on the processor, wherein the vehicle battery cell consistency evaluation program is configured to implement the steps of the vehicle battery cell consistency evaluation method described above.

[0031] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which a vehicle battery cell consistency evaluation program is stored. When the vehicle battery cell consistency evaluation program is executed by a processor, the steps of the vehicle battery cell consistency evaluation method described above are implemented.

[0032] The present application obtains vehicle operation data, filters out valid cell data in the vehicle operation data according to a preset valid data standard, processes the valid cell data according to a preset cell consistency index processing method to obtain cell consistency index data, and determines the total index deviation value of all battery cells in the current vehicle based on the cell consistency index data. If the total index deviation value exceeds a preset deviation threshold, it is determined that the current vehicle has a consistency risk. The total index deviation value is used to comprehensively reflect the consistency index conditions of the battery cells, instead of performing threshold judgment on a single consistency indicator separately, making the evaluation process more comprehensive and improving the accuracy of the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 Schematic diagram of the vehicle battery cell consistency assessment scenario provided for this application;

[0034] Figure 2 This is a flow chart of the first embodiment of the vehicle battery cell consistency evaluation method of the present application;

[0035] Figure 3 This is a flow chart of the second embodiment of the vehicle battery cell consistency evaluation method of the present application;

[0036] Figure 4 This is a schematic diagram of the vehicle battery cell consistency evaluation device of the present application;

[0037] Figure 5 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiment of the present application.

[0038] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0039] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0040] Vehicle power battery packs are usually equipped with various sensors to monitor changes in battery pack voltage, current, temperature, battery state of charge and other indicators. The power management system often also sets many fault alarm strategies for different indicators, such as over-temperature alarms, over-voltage / under-voltage alarms, single cell SOC large difference alarms, etc. When certain alarms are triggered, the BMS will limit some of the vehicle's performance for safety reasons, such as limiting output power, limiting battery available power, etc. Among them, the poor consistency of battery cells will lead to large differences in battery cell SOC, resulting in a decrease in the available capacity of the battery pack (barrel effect), or cause large differences in battery cell temperature during charging and discharging, thereby affecting battery performance. Battery cell consistency is currently a concern of the industry and users.

[0041] At present, for the consistency monitoring of battery cells, the usual solution is to detect the SOC and temperature of the battery cells on the vehicle-side BMS. When the difference between the maximum SOC value and the minimum SOC value exceeds the threshold set at the factory, or the difference between the maximum temperature value and the minimum temperature value exceeds the threshold set at the factory, an alarm is triggered. However, if the alarm is triggered only by the threshold set at the factory, a false alarm may occur if the threshold is set too low, and a missed alarm may occur if it is set too high. In addition, adjusting the threshold requires an OTA (Over-the-Air Technology) upgrade or the vehicle entering the maintenance station to flash the new version of the software. The time period required to adjust the threshold is long and the operation is cumbersome. Most vehicle-side BMS only calculate the maximum, minimum and average values of the battery cell indicators, and cannot evaluate and monitor the changes of each battery cell, and usually cannot evaluate the consistency of the internal resistance of the cell.

[0042] In accordance with the requirements of GB / T 32960 of the Ministry of Industry and Information Technology, new energy vehicles will upload operating data to the big data platform established by the enterprise at a certain frequency. Figure 1 This is a schematic diagram of the scenario for evaluating the vehicle battery health status in this application, such as Figure 1 As shown, the vehicle can communicate with the cloud-based big data platform. The data transmitted by the vehicle to the big data platform can include measurements from various onboard sensors, providing a comprehensive view of the vehicle's operating conditions. The big data platform can then use this collected data to assess the consistency of the vehicle's battery cells.

[0043] The present invention provides a method for evaluating the consistency of a vehicle battery cell. Figure 2 , Figure 2 This is a flow chart of a first embodiment of a vehicle battery cell consistency evaluation method of the present application.

[0044] In this embodiment, the vehicle battery cell consistency assessment method includes:

[0045] Step S10, acquiring vehicle operation data, and filtering out valid individual data in the vehicle operation data according to a preset valid data standard;

[0046] It should be noted that this embodiment is based on Figure 1 The big data platform shown is the execution entity. The big data platform acquires vehicle operation data uploaded by vehicles. According to GB / T 32960, the big data platform can collect daily vehicle operation data for new energy vehicles. Specifically, vehicle operation data may include vehicle frame number, message transmission time, battery pack total voltage, total current, charge status, insulation resistance, mileage, battery cell voltage, battery temperature probe temperature, and motor bus voltage.

[0047] Vehicle operation data contains various types of data that characterize the vehicle's operating status. For battery cell consistency assessment, valid cell data can be screened from the vehicle operation data and analyzed and evaluated based on this valid cell data. Battery cells are the basic units that make up a vehicle's battery pack. Temperature probes and sensors installed at the cells monitor their data, and cell data that meets pre-set valid data standards is considered valid.

[0048] As an example, before the step of filtering out valid individual data in the vehicle operation data according to the preset valid data standard, the following steps may also be included:

[0049] Step A1, detecting whether there is abnormal data in the vehicle operation data;

[0050] Step A2: If there is abnormal data, filter the abnormal data to obtain valid operation data.

[0051] There is a huge amount of vehicle operation data in the big data platform, which may include abnormal data of abnormal situations. The vehicle operation data can be screened and cleaned to retain the valid operation data that conforms to normal conditions.

[0052] Abnormal data can be divided into single cell abnormal data and transmission abnormal data. Single cell abnormal data is related to the conditions of each battery cell in the vehicle's power battery pack. Abnormal battery cell conditions may include the cell voltage exceeding the effective value range, the probe temperature exceeding the effective value range, the cell voltages being all equal, the probe temperatures being all equal, and the number of cells measured by the sensor being different from the actual number of cells. Cell voltage exceeding the effective value range indicates that the cell voltage is too high or too low, which may affect the normal operation of the battery pack. Probe temperature exceeding the effective value range indicates that the cell temperature is too high or too low, which may result in excessive charging current, reduced electrolyte, or improper connection of the probe. Generally, there are differences between the cell voltage and cell temperature detected by the sensor, and they will not be all equal. If they are all equal, it means that there may be a problem with the sensor used to measure the cell voltage or cell temperature. The situation where the number of cells is different is similar to this situation, and it may also be a problem with the sensor. Transmission abnormal data is related to data transmission between the vehicle and the big data platform. On some vehicles, the BMS may have entered sleep mode, but the T-BOX (Telematics Box) may still be active. During this time, the vehicle's sensors are no longer collecting or updating data, but the T-BOX will continue to repeatedly send data from the last moment before the BMS entered sleep mode. By filtering out this abnormal data, valid operating data can be obtained.

[0053] Screening and cleaning the vehicle operation data contained in the big data platform to obtain valid operation data that meets the usage requirements can improve the efficiency of subsequent data processing.

[0054] As an example, the step of filtering out valid individual data from the vehicle operation data according to a preset valid data standard may include:

[0055] Step B1, obtaining a current data standard and a charging state standard from the valid data standards;

[0056] Step B2: Filter out valid operating data that meets the current data standard and the charging state standard as the valid single cell data.

[0057] The effective operation data can be regarded as the original data before data screening. The monomer data in the effective operation data can be extracted first, and then different screening operations can be performed on the monomer data according to different effective data standards to obtain effective monomer data. The preset effective data standards can be adjusted according to the actual data analysis needs. The monomer consistency indicators selected in this embodiment are monomer SOC, monomer temperature and monomer internal resistance. The effective monomer data is associated with the monomer consistency index, and the effective data standards corresponding to each monomer consistency index may be different. The current data standard may include a current threshold range. It should be noted that before obtaining the effective monomer data corresponding to the monomer consistency index, data processing can also be performed, and the monomer data obtained by direct screening can be used as an intermediate quantity, and the data finally processed is the effective monomer data.

[0058] The following examples illustrate different valid data standards: When the cell consistency indicator is the cell SOC, the current data standard can be [-2, +2] A, the charging state standard can be "uncharged" or "charged" and maintained for more than 30 seconds, and then according to the OCV (Open Circuit Voltage)-SOC curve provided by the battery supplier, the cell voltage U i Convert to single SOC i , where i represents the cell number. When the cell consistency indicator is the cell temperature, the current data standard can be [-2, +2] A, and the charging state standard can be "uncharged" or "charged" and maintained for more than 30 seconds. When the cell consistency indicator is the cell internal resistance, the current data standard can be the current difference ΔI=I between two adjacent frames of cell data. k -I k-1 ≥0.2C, where 1C current represents the current required to fully charge the battery in 1 hour. For example, if the nominal capacity of a battery is 100Ah, then the current required to fully charge the battery in 1 hour is 100A. For this battery, 0.2C = 0.2 × 100 = 20A. k represents the current at time k, I k-1 Represents the current of the previous time step at time k, and then according to U k Indicates the cell voltage at the kth moment, I k Represents the single cell current at the kth moment, and calculates the internal resistance R of all cells i , i represents the monomer number.

[0059] Further data screening of effective operation data and elimination of effective operation data that does not meet the effective data standards can improve the reference value of effective individual data, reduce data processing volume, and improve data processing efficiency.

[0060] Step S20, processing the valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data;

[0061] The monomer consistency index data characterizes the consistency performance of each monomer in terms of consistency index. The median or average can be used as the center point of the valid monomer data, and the distance between each valid monomer data and the center point is calculated as the monomer consistency index data.

[0062] As an example, the step of processing valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data may include:

[0063] Step C1, classifying the valid monomer data to obtain initial consistency data of each monomer;

[0064] Step C2: obtaining a monomer consistency index processing method corresponding to each monomer consistency initial data, and processing each monomer consistency initial data according to the monomer consistency index processing method to obtain each monomer consistency index feature vector.

[0065] When screening valid monomer data, there may be situations where the valid data standards are the same. For example, the above-mentioned monomer SOC index and monomer temperature index, before data processing to obtain the final valid monomer data, the intermediate data obtained by the two are the same. At this time, the intermediate data can be classified according to the monomer consistency index to obtain the monomer SOC index consistency initial data and the monomer temperature index consistency initial data. The monomer consistency initial data of each category can correspond to different monomer consistency index processing methods, and finally obtain the characteristic vector of each monomer consistency index. The monomer consistency index characteristic vector can be used as the monomer consistency index data to represent the consistency deviation of the monomer index.

[0066] When the monomer consistency index is the monomer SOC, the corresponding monomer consistency index processing method flow can be: calculate the monomer SOC median SOC in each frame of monomer consistency initial data median Then use each monomer SOC i Subtract the median SOC of the single SOC of this frame of data median , get the deviation of each monomer SOC from the median in this frame of data, that is, diffSOC i =SOC i -SOC median , then calculate the average SOC deviation of each battery cell to obtain a single-cell SOC feature vector of size n×1, where n is the number of battery cells in the battery pack. This feature vector is the single-cell SOC consistency index data.

[0067]

[0068] m is the number of data frames that meet the valid data standard

[0069] feature SOC Represents the monomer SOC feature vector.

[0070] When the monomer consistency index is the monomer temperature, the corresponding monomer consistency index processing method flow can be: calculate the probe temperature median T in each frame of monomer consistency initial data median Then use each monomer T i Subtract the median probe temperature T of this frame of data median , get the deviation of each probe temperature from the median in this frame of data, that is, diffT i =T i -T median Calculate the average temperature deviation of each battery cell and obtain a cell temperature feature vector of size n×1, where n is the number of battery cells in the battery pack. This feature vector is the cell temperature consistency index data.

[0071]

[0072] m is the number of data frames that meet the valid data standard

[0073] When the cell consistency index is the cell internal resistance, the corresponding cell consistency index processing method flow can be: calculate the cell internal resistance median R in each frame of the initial cell consistency data median Then use each monomer R i Subtract the median internal resistance R of the monomer in this frame of data median , get the deviation of each monomer internal resistance from the median in this frame of data, that is, diffR i =R i -R median Calculate the average deviation of the internal resistance of each battery cell to obtain a cell internal resistance characteristic vector of size n×1, where n is the number of battery cells in the battery pack. This characteristic vector is the cell internal resistance consistency index data.

[0074]

[0075] m is the number of data frames that meet the valid data standard

[0076] Using characteristic vectors to represent cell consistency index data facilitates the subsequent integration of each cell consistency index data and enhances the comprehensiveness of battery cell consistency evaluation.

[0077] Step S30 , determining a total index deviation value of all battery cells in the current vehicle based on the cell consistency index data, and if the total index deviation value exceeds a preset deviation threshold, determining that the current vehicle has a consistency risk.

[0078] The total index deviation value represents the comprehensive deviation value of each monomer consistency index. This embodiment uses the monomer SOC index, monomer temperature index and monomer internal resistance index to comprehensively evaluate the consistency deviation performance of the monomer. The preset deviation threshold can be adjusted through the big data platform. When it is determined that the deviation threshold needs to be adjusted according to the actual situation, the big data platform can obtain the deviation threshold correction parameter and correct the deviation threshold according to the deviation threshold correction parameter. Generally, the method of setting the deviation threshold between the maximum and minimum values of the monomer index data for the vehicle at the time of leaving the factory requires the deviation threshold data to be written into the hardware facilities such as chips inside the vehicle, and the threshold adjustment operation is cumbersome and time-consuming. This embodiment corrects the deviation threshold through the big data platform, which is easy to operate.

[0079] As an example, the step of determining the total index deviation value of all battery cells in the current vehicle based on the consistency index deviation value of each cell may include:

[0080] Step D1, combining the monomer consistency feature vectors into a monomer index feature matrix, and determining the covariance matrix of the monomer index feature matrix;

[0081] Step D2: determining the Mahalanobis distance of each battery cell according to the cell index characteristic matrix and the covariance matrix, and taking the sum of the Mahalanobis distances of each battery cell as the total index deviation value.

[0082] The single-cell SOC feature vector, single-cell temperature feature vector, and single-cell internal resistance feature vector are combined into a multi-parameter feature matrix Calculate the mean μ of the three indicators i And form the mean vector μ=[μ1,μ2,μ3], calculate the covariance matrix Σ of matrix X:

[0083]

[0084] According to the formula Calculate the Mahalanobis distance D(X i );

[0085] Find the sum of all monomer Mahalanobis distances As the total indicator deviation value. If the total indicator deviation value sum exceeds the threshold, it indicates that the current vehicle corresponding to the valid battery cell data has consistency risks. The big data platform can send consistency risk warning information to the current vehicle, prompting the user to perform vehicle maintenance before the vehicle's BMS restricts vehicle functions, avoiding the impact of poor battery cell consistency alarms on the vehicle experience.

[0086] As an example, after determining that the current vehicle has a consistency risk if the total index deviation value exceeds a preset deviation threshold, the following steps may also be performed:

[0087] Step E1, determining the mean Mahalanobis distance of each battery cell;

[0088] Step E2 , screening out battery cells whose Mahalanobis distances from the mean of the battery cells exceed a preset distance threshold as consistency risk cells.

[0089] Calculate the Mahalanobis distance D(X i ) Further through The standard deviation σ is calculated. The preset distance threshold can be 3σ, which is the mean of the Mahalanobis distance of all monomers. Cells with a difference exceeding 3σ are considered to have poor consistency and pose consistency risks. The big data platform can also send consistency risk warning information to the current vehicle, making it easier to quickly identify problematic cells during vehicle maintenance.

[0090] In this embodiment, vehicle operation data is obtained, valid cell data in the vehicle operation data is filtered out according to a preset valid data standard, the valid cell data is processed according to a preset cell consistency index processing method to obtain cell consistency index data, and the total index deviation value of all battery cells in the current vehicle is determined based on the cell consistency index data. If the total index deviation value exceeds the preset deviation threshold, it is determined that the current vehicle has a consistency risk. The total index deviation value is used to comprehensively reflect the consistency index conditions of the battery cells, instead of performing threshold judgment on each single consistency indicator. This makes the evaluation process more comprehensive and improves the accuracy of the evaluation results.

[0091] In the second embodiment of the vehicle battery cell consistency evaluation method of the present application, as shown in FIG. Figure 3As shown, the big data platform collects vehicle operation data, filters and cleans the vehicle operation data, removes abnormal data, and uses the filtered data to calculate the single-cell SOC consistency index, single-cell temperature consistency index and single-cell internal resistance consistency index respectively. The single-cell characteristic index is represented by a characteristic vector respectively, and the characteristic vectors are combined into a multi-parameter characteristic matrix. The Mahalanobis distance of each single cell and the sum of the Mahalanobis distances are calculated according to the Mahalanobis distance calculation formula, and it is judged whether the sum of the Mahalanobis distances is greater than the preset deviation threshold. If the sum of the Mahalanobis distances is greater than the preset deviation threshold, it means that the current vehicle corresponding to the current vehicle operation data has a consistency risk and is a risk vehicle. The single cell in the risk vehicle whose Mahalanobis distance difference with the mean of all single cells exceeds 3 times the standard deviation is a problem single cell. If the sum of the Mahalanobis distances is less than or equal to the preset deviation threshold, it means that there is no consistency risk for the current vehicle, and the big data platform can continue to perform battery cell and consistency evaluation on other vehicles.

[0092] The present application also provides a vehicle battery cell consistency evaluation device, such as Figure 4 As shown, the vehicle battery cell consistency evaluation device includes:

[0093] The acquisition module 101 is used to acquire vehicle operation data and filter out valid individual data in the vehicle operation data according to a preset valid data standard;

[0094] The processing module 102 is used to process the valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data;

[0095] The judgment module 103 is used to determine the total index deviation value of all battery cells in the current vehicle based on the cell consistency index data. If the total index deviation value exceeds a preset deviation threshold, it is determined that the current vehicle has a consistency risk.

[0096] Optionally, the acquisition module 101 is further configured to:

[0097] detecting whether there is abnormal data in the vehicle operation data;

[0098] If there is abnormal data, the abnormal data is filtered to obtain valid operation data.

[0099] Optionally, the acquisition module 101 is further configured to:

[0100] Acquiring a current data standard and a charging state standard from the valid data standards;

[0101] Valid operating data that meets the current data standard and the charging state standard is screened out as the valid single cell data.

[0102] Optionally, the processing module 102 is further configured to:

[0103] Classifying the valid monomer data to obtain initial consistency data of each monomer;

[0104] A monomer consistency index processing method corresponding to each monomer consistency initial data is obtained, and each monomer consistency initial data is processed according to the monomer consistency index processing method to obtain a characteristic vector of each monomer consistency index.

[0105] Optionally, the judgment module 103 is further configured to:

[0106] Combining the monomer consistency feature vectors into a monomer index feature matrix, and determining a covariance matrix of the monomer index feature matrix;

[0107] The Mahalanobis distance of each battery cell is determined according to the cell index characteristic matrix and the covariance matrix, and the sum of the Mahalanobis distances of each battery cell is used as the total index deviation value.

[0108] Optionally, the vehicle battery cell consistency assessment device further includes a screening module for:

[0109] Determining the standard deviation of the Mahalanobis distance of each battery cell;

[0110] Battery cells whose standard deviation of Mahalanobis distance from the battery cells exceeds a preset distance threshold are screened out as consistency risk cells.

[0111] Optionally, the vehicle battery cell consistency assessment device further includes a correction module, configured to:

[0112] Obtain a deviation threshold correction parameter, and correct the deviation threshold according to the deviation threshold correction parameter.

[0113] Figure 5 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiment of the present application.

[0114] like Figure 5As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0115] Those skilled in the art will understand that Figure 5 The structure shown in the figure does not constitute a limitation to the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0116] like Figure 5 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a vehicle battery cell consistency assessment program.

[0117] exist Figure 5 In the electronic device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the electronic device of the present application can be set in the electronic device, and the electronic device calls the vehicle battery cell consistency evaluation program stored in the memory 1005 through the processor 1001, and executes the vehicle battery cell consistency evaluation method provided in the embodiment of the present application.

[0118] An embodiment of the present application further provides a computer-readable storage medium, on which a vehicle battery cell consistency evaluation program is stored. When the vehicle battery cell consistency evaluation program is executed by a processor, the steps of the vehicle battery cell consistency evaluation method described above are implemented.

[0119] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0120] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course 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 application 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) as described above, 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 application.

[0122] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle battery cell consistency assessment method, characterized in that: The vehicle battery cell consistency evaluation method comprises the following steps: Acquire vehicle operation data, and filter out valid individual data in the vehicle operation data according to preset valid data standards; Processing the valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data, wherein the monomer consistency index data represents the average value of the distance between each valid monomer data and a center point, and the center point is the median or average of each valid monomer data; Determining a total index deviation value of all battery cells in the current vehicle based on the cell consistency index data, and determining that the current vehicle has a consistency risk if the total index deviation value exceeds a preset deviation threshold; The step of processing the valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data includes: Classifying the valid monomer data to obtain initial consistency data of each monomer; Obtaining a monomer consistency index processing method corresponding to each monomer consistency initial data, and processing each monomer consistency initial data according to the monomer consistency index processing method to obtain a monomer consistency index feature vector; The step of determining the total index deviation value of all battery cells in the current vehicle based on the cell consistency index data includes: Combining the characteristic vectors of the monomer consistency indicators into a monomer indicator characteristic matrix, and determining the covariance matrix of the monomer indicator characteristic matrix; The Mahalanobis distance of each battery cell is determined according to the cell index characteristic matrix and the covariance matrix, and the sum of the Mahalanobis distances of each battery cell is used as the total index deviation value.

2. The vehicle battery cell consistency evaluation method according to claim 1, characterized in that: Before the step of filtering out valid individual data from the vehicle operation data according to a preset valid data standard, the method further includes: detecting whether there is abnormal data in the vehicle operation data; If there is abnormal data, the abnormal data is filtered to obtain valid operation data.

3. The vehicle battery cell consistency evaluation method according to claim 2, characterized in that: The step of filtering out valid single-unit data from the vehicle operation data according to a preset valid data standard includes: Acquiring a current data standard and a charging state standard from the valid data standards; Valid operating data that meets the current data standard and the charging state standard is screened out as the valid single cell data.

4. The vehicle battery cell consistency evaluation method according to claim 1, wherein: After the step of determining that the current vehicle has a consistency risk if the total index deviation value exceeds a preset deviation threshold, the method further includes: Determining the mean Mahalanobis distance of each battery cell; Battery cells whose Mahalanobis distances from the average of the battery cells exceed a preset distance threshold are selected as consistency risk cells.

5. The vehicle battery cell consistency evaluation method according to any one of claims 1 to 4, characterized in that: The vehicle battery cell consistency assessment method further includes: Obtain a deviation threshold correction parameter, and correct the deviation threshold according to the deviation threshold correction parameter.

6. A vehicle battery cell consistency evaluation device, characterized in that: The vehicle battery cell consistency assessment device comprises: An acquisition module is used to acquire vehicle operation data and filter out valid individual data in the vehicle operation data according to a preset valid data standard; A processing module, configured to process the valid monomer data according to a preset monomer consistency index processing method to obtain monomer consistency index data, wherein the monomer consistency index data represents the average value of the distance between each valid monomer data and a center point, and the center point is the median or average of each valid monomer data; classify the valid monomer data to obtain initial monomer consistency data; obtain a monomer consistency index processing method corresponding to each monomer consistency initial data, and process each monomer consistency initial data according to the monomer consistency index processing method to obtain a characteristic vector of each monomer consistency index; A judgment module is used to determine the total index deviation value of all battery cells in the current vehicle based on the cell consistency index data, and if the total index deviation value exceeds a preset deviation threshold, it is determined that the current vehicle has a consistency risk; combine the consistency index feature vectors of each cell into a cell index feature matrix, and determine the covariance matrix of the cell index feature matrix; determine the Mahalanobis distance of each battery cell based on the cell index feature matrix and the covariance matrix, and use the sum of the Mahalanobis distances of each battery cell as the total index deviation value.

7. An electronic device, characterized in that: The electronic device includes: a memory, a processor, and a vehicle battery cell consistency evaluation program stored in the memory and executable on the processor, wherein the vehicle battery cell consistency evaluation program is configured to implement the steps of the vehicle battery cell consistency evaluation method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a vehicle battery cell consistency evaluation program, which, when executed by a processor, implements the steps of the vehicle battery cell consistency evaluation method according to any one of claims 1 to 5.

Images