Battery consistency calculation method and device, electronic equipment and computer program product

Abstract

The application relates to a battery consistency calculation method and device, electronic equipment and computer program product. The method comprises the following steps: obtaining battery data of a vehicle, and performing data processing on the battery data; dividing the battery data after data processing into non-overlapping time windows according to a time scale to construct a coarse-grained sequence, and calculating sample entropy of each coarse-grained sequence; distributing each coarse-grained sequence to each coarse sequence according to a preset distribution weight, calculating a weighted composite multi-scale entropy of each coarse-grained sequence based on the sample entropy value of each coarse-grained sequence, and evaluating the battery consistency of the vehicle based on the weighted composite multi-scale entropy. Thus, the problems that the prior art technical scheme for identifying the consistency of the battery cell is complicated, the calculation cost is large, a large amount of data is required, online data is not applicable, and an additional measuring device needs to be added are solved, the specific battery cell with consistency problems can be accurately identified, online data is directly used for calculation, and no external device is required.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a battery consistency calculation method, apparatus, electronic device, and computer program product. Background Technology

[0002] The widespread adoption of automobiles has greatly increased, with vehicle ownership and growth rates rising significantly in recent years, leading to rapid development in electric vehicle components. Among these, the battery directly provides the kinetic energy for vehicle operation, making the battery system the most crucial component, and its quality directly impacts the overall quality of the electric vehicle. A power battery is composed of multiple cells connected in parallel and series; the consistency between these cells directly affects the performance and safety of the entire battery pack. Therefore, researching cell consistency is essential.

[0003] Current methods for calculating consistency are relatively simple, using basic statistics such as standard deviation to quantify consistency, setting a threshold, and comparing two values ​​to determine consistency issues. Some methods also utilize external equipment for measurement. While the standard deviation method is commonly used in practical engineering, it requires manually setting thresholds, introducing subjectivity. Furthermore, cell consistency is a long-term process, and using only standard deviation calculates the current consistency status, failing to extend to different time scales. Moreover, standard deviation cannot reflect which specific cell has consistency issues, and equipment-based methods are only suitable for laboratory conditions and not for online data consistency assessment, a problem that urgently needs to be addressed. Summary of the Invention

[0004] This application provides a battery consistency calculation method, apparatus, electronic device, and computer program product to solve the problems of existing technical solutions for identifying cell consistency, such as complex calculations, high computational overhead, large data requirements, unsuitability for online data, and the need for additional measurement equipment.

[0005] The first aspect of this application provides a battery consistency calculation method, including the following steps: acquiring battery data of a vehicle and processing the battery data; dividing the processed battery data into non-overlapping time windows according to a time scale to construct coarse-grained sequences, and calculating the sample entropy of each coarse-grained sequence; allocating the coarse-grained sequence to each coarse sequence according to a preset allocation weight, calculating the weighted composite multi-scale entropy of the coarse-grained sequence based on the sample entropy of each coarse-grained sequence, and evaluating the battery consistency of the vehicle based on the weighted composite multi-scale entropy.

[0006] Optionally, the data processing of the battery data includes: identifying and deleting duplicate data and data whose field values ​​exceed the normal range in the battery data; using quantile and box plot techniques to identify outlier values ​​in the fields of the battery data, and deleting entire rows of data containing outlier values.

[0007] Optionally, calculating the sample entropy of each coarse-grained sequence includes: constructing a multidimensional vector and calculating the distance between the multidimensional vectors; statistically analyzing the proportion of similar vector pairs based on a similarity coefficient threshold; and calculating the sample entropy of each coarse-grained sequence based on the proportion of similar vector pairs using a preset sample entropy calculation formula, wherein the preset sample entropy calculation formula is:

[0008] ;

[0009] in, For the pattern dimension, For similarity coefficient threshold, For data length, This represents the proportion of similar vector pairs.

[0010] Optionally, calculating the weighted composite multiscale entropy of the coarse-grained sequence based on the sample entropy of each coarse-grained sequence includes: calculating the weighted composite multiscale entropy of the coarse-grained sequence using a preset weighted composite multiscale entropy calculation formula, wherein the preset weighted composite multiscale entropy calculation formula is:

[0011]

[0012] ;

[0013] in, , All are preset weight allocations. As a scale factor, This is a coarse-grained sequence, where M is the sequence length.

[0014] A second aspect of this application provides a battery consistency calculation device, comprising: a processing module for acquiring battery data of a vehicle and processing the battery data; a first calculation module for dividing the processed battery data into non-overlapping time windows according to a time scale to construct coarse-grained sequences and calculating the sample entropy of each coarse-grained sequence; and a second calculation module for allocating the data to each coarse sequence and each coarse-grained sequence according to a preset allocation weight, calculating the weighted composite multi-scale entropy of the coarse-grained sequence based on the sample entropy of each coarse-grained sequence, and evaluating the battery consistency of the vehicle based on the weighted composite multi-scale entropy.

[0015] Optionally, the processing module is further configured to: identify and delete duplicate data and data whose field values ​​exceed the normal range in the battery data; identify outlier values ​​in the fields of the battery data using quantile and box plot techniques, and delete entire rows of data containing outlier values.

[0016] Optionally, the first calculation module is further configured to: construct multidimensional vectors and calculate the distance between the multidimensional vectors; statistically analyze the proportion of similar vector pairs according to a similarity coefficient threshold; and calculate the sample entropy of each coarse-grained sequence based on the proportion of similar vector pairs using a preset sample entropy calculation formula, wherein the preset sample entropy calculation formula is:

[0017] ;

[0018] in, For the pattern dimension, For similarity coefficient threshold, For data length, This represents the proportion of similar vector pairs.

[0019] Optionally, the second calculation module is further configured to: calculate the weighted composite multiscale entropy of the coarse-grained sequence using a preset weighted composite multiscale entropy calculation formula, wherein the preset weighted composite multiscale entropy calculation formula is:

[0020]

[0021] ;

[0022] in, , All are preset weight allocations. As a scale factor, This is a coarse-grained sequence, where M is the sequence length.

[0023] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the battery consistency calculation method as described in the above embodiments.

[0024] A fourth aspect of this application provides a computer program product having a computer program stored thereon, which is executed by a processor to implement the battery consistency calculation method as described in the above embodiments.

[0025] In the above embodiments, vehicle battery data is acquired and processed. The processed battery data is divided into non-overlapping time windows according to a time scale to construct coarse-grained sequences. The sample entropy of each coarse-grained sequence is calculated and assigned to each coarse sequence according to a preset weight. The weighted composite multi-scale entropy of each coarse-grained sequence is calculated based on the sample entropy of each coarse-grained sequence, and the battery consistency of the vehicle is evaluated based on the weighted composite multi-scale entropy. This solves the problems of existing technologies for identifying cell consistency, such as computational complexity, high computational overhead, large data requirements, inapplicability to online data, and the need for additional measurement equipment. It can accurately identify specific cells with consistency problems, directly utilize online data for calculation, eliminate the need for external equipment, and avoid the problems of computational complexity, high computational overhead, and large data requirements.

[0026] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0027] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0028] Figure 1 This is a flowchart of a battery consistency calculation method provided according to an embodiment of this application;

[0029] Figure 2 This is a flowchart of a battery consistency calculation method according to an embodiment of this application;

[0030] Figure 3 This is a schematic diagram of WMMSE of a vehicle at different time scales according to an embodiment of this application;

[0031] Figure 4 This is an example diagram of a battery consistency calculation device according to an embodiment of this application;

[0032] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Attached image description:

[0034] 10-Battery consistency calculation device; 100-Processing module; 200-First calculation module; 300-Second calculation module; 501-Memory; 502-Processor and 503-Communication interface. Detailed Implementation

[0035] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0036] The following describes a battery consistency calculation method, apparatus, electronic device, and computer program product according to embodiments of this application with reference to the accompanying drawings. Addressing the problems mentioned in the background art regarding the complexity, high computational cost, large data requirements, inapplicability to online data, and the need for additional measurement equipment in existing cell consistency identification solutions, this application provides a battery consistency calculation method. In this method, vehicle battery data is acquired and processed. The processed battery data is divided into non-overlapping time windows according to a time scale to construct coarse-grained sequences. The sample entropy of each coarse-grained sequence is calculated and allocated to each coarse-grained sequence according to a preset weight. A weighted composite multi-scale entropy of the coarse-grained sequences is calculated based on the sample entropy of each sequence, and the battery consistency of the vehicle is evaluated based on the weighted composite multi-scale entropy. This solves the problems of computational complexity, high computational cost, large data requirements, inapplicability to online data, and the need for additional measurement equipment in existing cell consistency identification solutions. It can accurately identify specific cells with consistency issues, directly utilize online data for calculation, eliminate the need for external equipment, and avoid the problems of computational complexity, high computational cost, and large data requirements.

[0037] Specifically, Figure 1 This is a flowchart illustrating a battery consistency calculation method provided in an embodiment of this application.

[0038] like Figure 1 As shown, the battery consistency calculation method includes the following steps:

[0039] In step S101, the vehicle's battery data is acquired and processed.

[0040] Battery data includes voltage data (such as real-time voltage, average voltage, voltage change rate, etc.), capacity data, temperature data, SOC and SOH data, etc.

[0041] In step S102, the processed battery data is divided into non-overlapping time windows according to the time scale to construct coarse-grained sequences, and the sample entropy of each coarse-grained sequence is calculated.

[0042] Optionally, in some embodiments, the battery data is processed, including: identifying and deleting duplicate data and data whose field values ​​are outside the normal range; using quantile and box plot techniques to identify outliers in the battery data and deleting entire rows of data containing outliers.

[0043] Specifically, data cleaning and preprocessing of battery data fields can be performed using database query languages. PYTHON data processing and analysis are required, including fields such as VIN code, time, cell voltage list, and temperature list. Data acquisition requires database support (DBEAVER, SQLSERVER), while data processing and analysis require the support of PYTHON's pandas, numpy, and sklearn.

[0044] Dirty data in the battery database needs to be cleaned. Dirty data includes duplicate data, values ​​outside the normal range of field values, and outliers. The first two types of dirty data are handled by direct deletion. Outliers can be identified using quantiles and box plots, and the entire row containing the identified outlier is deleted. Data preprocessing is performed on the field definitions defined in the database, mainly including offset removal and unit conversion. Offset removal corrects the field value offsets set in the field definitions, and unit conversion addresses differences in field values ​​due to different unit settings.

[0045] In step S103, the coarse sequence and each coarse-grained sequence are assigned according to the preset allocation weights, and the weighted composite multi-scale entropy of the coarse-grained sequence is calculated based on the sample entropy of each coarse-grained sequence. The battery consistency of the vehicle is evaluated based on the weighted composite multi-scale entropy.

[0046] The preset allocation weight can be a threshold set by the user, a threshold obtained through a limited number of experiments, or a threshold obtained through a limited number of computer simulations; no specific limitation is made here.

[0047] The evaluation of vehicle battery consistency based on weighted composite multiscale entropy is as follows: if the weighted composite multiscale entropy of different batteries in a vehicle is closer at different time scales, it indicates that the battery pack consistency is better. If the weighted composite multiscale entropy of a battery deviates from that of other cells, it indicates that the battery has a consistency problem.

[0048] In some embodiments, calculating the sample entropy of each coarse-grained sequence includes: constructing a multidimensional vector and calculating the distance between the multidimensional vectors; statistically analyzing the proportion of similar vector pairs based on a similarity coefficient threshold; and calculating the sample entropy of each coarse-grained sequence based on the proportion of similar vector pairs using a preset sample entropy calculation formula, wherein the preset sample entropy calculation formula is:

[0049] ;

[0050] in, For the pattern dimension, For similarity coefficient threshold, For data length, This represents the proportion of similar vector pairs.

[0051] In some embodiments, calculating the weighted composite multiscale entropy of the coarse-grained sequence based on the sample entropy of each coarse-grained sequence includes: calculating the weighted composite multiscale entropy of the coarse-grained sequence using a preset weighted composite multiscale entropy calculation formula, wherein the preset weighted composite multiscale entropy calculation formula is:

[0052]

[0053] ;

[0054] in, , All are preset weight allocations. As a scale factor, This is a coarse-grained sequence, where M is the sequence length.

[0055] Specifically, such as Figure 2 As shown, the first step is to obtain the online data uploaded by the vehicle: obtain the data uploaded by the vehicle from the vehicle manufacturer's data platform, which conforms to the national standard 32960, and obtain the relevant fields and their corresponding value ranges.

[0056] Data cleaning and preprocessing: Data cleaning and preprocessing are performed on the fields that will be used. Dirty data in the database needs to be cleaned, including duplicate data, values ​​outside the normal range of field values, and outliers. The first two types of dirty data mentioned above are handled by direct deletion. For outliers, outlier identification can be performed using quantiles and box plots, and the identified outlier fields are deleted entirely. Offset removal or unit conversion is performed on the field definitions defined in the database.

[0057] Further, the processed battery data is divided into non-overlapping time windows according to the time scale to construct a coarse-grained sequence. First, let the battery data be... Where N is the data length, the battery data sequence is divided into non-overlapping windows based on a time scale, referred to here as the scale factor τ, and then a coarse-grained sequence is established as follows:

[0058] ;

[0059] Further coarse-grained sequence sample entropy calculation: For coarse-grained sequences Where M is the sequence length, let M=j, then the sample entropy of the coarse-grained sequence is calculated as follows:

[0060] 1) Given a pattern dimension of m, then an m-dimensional vector is formed from the original sequence:

[0061] ;

[0062] 2) Define the distance between Y(i) and Y(j):

[0063] ;

[0064] 3) Given a similarity coefficient threshold r, perform statistical analysis. The quantity and the ratio of this quantity to the total quantity N-m+1 are denoted as The similarity coefficient threshold r is determined by the standard deviation of the original sequence.

[0065] ;

[0066] Furthermore, calculate the average of all i:

[0067] ;

[0068] Repeat steps 1) to 3) for m+1, denoted as :

[0069] ;

[0070] Then the sample entropy of this coarse-grained sequence can be obtained.

[0071] ;

[0072] When N takes finite values, the estimated value of the sample entropy is:

[0073] ;

[0074] The above formula can be used to calculate the subsequence entropy at each scale. Then, a function with scale τ as the independent variable and sample entropy SaEn as the dependent variable can be established to obtain the multi-scale entropy-scale factor curve:

[0075] ;

[0076] For each scaling factor, calculate each coarse sequence. The sample entropy is then used to calculate the weighted composite multiscale entropy (WMMSE) under the scale factor τ by allocating the k entropy values ​​according to a preset weighting:

[0077]

[0078] ;

[0079] Therefore, the embodiments of this application integrate information from all coarse-grained sequences and can amplify or reduce the importance of the analysis time scale according to weights, avoiding entropy fluctuations caused by moving averages.

[0080] In the actual verification process, such as Figure 3 As shown, Figure 3 By examining the WMMSE of a certain vehicle at different time scales, it can be observed that cell number 28 is significantly different from other cells, indicating that cell number 28 has a consistency problem.

[0081] In summary, the advantages of the embodiments of this application are as follows:

[0082] 1. It can perform calculations directly using online data, without the need for external equipment, making it more suitable for engineering implementation;

[0083] 2. Compared with traditional methods, this approach takes into account consistency analysis across multiple time scales, rather than being limited to calculating the consistency at the current instant.

[0084] 3. Data requirements: No complete charge-discharge cycle is required; any data segment can be used for calculation.

[0085] 4. Assign weights to different time scales. If you are more concerned about long-term consistency, you can assign higher weights to long-term time scales and the same applies to short-term time scales. This is more flexible than using the arithmetic mean directly.

[0086] 5. It is also a method that considers multiple time scales, without the need to build other correlation models, making the calculation simpler and less computationally expensive.

[0087] According to the battery consistency calculation method proposed in this application, vehicle battery data is acquired and processed. The processed battery data is divided into non-overlapping time windows according to the time scale to construct coarse-grained sequences. The sample entropy of each coarse-grained sequence is calculated and allocated to each coarse-grained sequence according to a preset weight. The weighted composite multi-scale entropy of each coarse-grained sequence is calculated based on the sample entropy of each coarse-grained sequence, and the battery consistency of the vehicle is evaluated based on the weighted composite multi-scale entropy. This solves the problems of existing technologies for identifying cell consistency, such as computational complexity, high computational overhead, large data requirements, inapplicability to online data, and the need for additional measurement equipment. This method can accurately identify specific cells with consistency problems, directly utilize online data for calculation, eliminate the need for external equipment, and avoid the problems of computational complexity, high computational overhead, and large data requirements.

[0088] Next, the battery consistency calculation device proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0089] Figure 4 This is a block diagram of a battery consistency calculation device according to an embodiment of this application.

[0090] like Figure 4 As shown, the battery consistency calculation device 10 includes: a processing module 100, a first calculation module 200, and a second calculation module 300.

[0091] The system includes a processing module 100 for acquiring vehicle battery data and processing it; a first calculation module 200 for dividing the processed battery data into non-overlapping time windows to construct coarse-grained sequences and calculating the sample entropy of each coarse-grained sequence; and a second calculation module 300 for allocating the data to each coarse sequence and each coarse-grained sequence according to preset weights, calculating the weighted composite multi-scale entropy of each coarse-grained sequence based on the sample entropy of each coarse-grained sequence, and evaluating the battery consistency of the vehicle based on the weighted composite multi-scale entropy.

[0092] Optionally, in some embodiments, the processing module 100 is further configured to: identify and delete duplicate data and data whose field values ​​exceed the normal range in the battery data; identify outlier values ​​in the fields of the battery data using quantile and box plot techniques, and delete entire rows of data containing outlier values.

[0093] Optionally, in some embodiments, the first calculation module 200 is further configured to: construct multidimensional vectors, calculate the distance between multidimensional vectors; statistically analyze the proportion of similar vector pairs according to a similarity coefficient threshold, and calculate the sample entropy of each coarse-grained sequence based on the proportion of similar vector pairs using a preset sample entropy calculation formula, wherein the preset sample entropy calculation formula is:

[0094] ;

[0095] in, For the pattern dimension, For similarity coefficient threshold, For data length, This represents the proportion of similar vector pairs.

[0096] Optionally, in some embodiments, the second calculation module 300 is further configured to: calculate the weighted composite multiscale entropy of the coarse-grained sequence using a preset weighted composite multiscale entropy calculation formula, wherein the preset weighted composite multiscale entropy calculation formula is:

[0097]

[0098] ;

[0099] in, , All are preset weight allocations. As a scale factor, This is a coarse-grained sequence, where M is the sequence length.

[0100] It should be noted that the foregoing explanation of the battery consistency calculation method embodiment also applies to the battery consistency calculation device of this embodiment, and will not be repeated here.

[0101] According to the battery consistency calculation device proposed in this application, vehicle battery data is acquired and processed. The processed battery data is divided into non-overlapping time windows according to a time scale to construct coarse-grained sequences. The sample entropy of each coarse-grained sequence is calculated and allocated to each coarse-grained sequence according to a preset weight. The weighted composite multi-scale entropy of each coarse-grained sequence is calculated based on the sample entropy of each coarse-grained sequence, and the battery consistency of the vehicle is evaluated based on the weighted composite multi-scale entropy. This solves the problems of existing technologies for identifying cell consistency, such as computational complexity, high computational overhead, large data requirements, inapplicability to online data, and the need for additional measurement equipment. This device can accurately identify specific cells with consistency problems, directly utilize online data for calculation, eliminate the need for external equipment, and avoid the problems of computational complexity, high computational overhead, and large data requirements.

[0102] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0103] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0104] When the processor 502 executes the program, it implements the battery consistency calculation method provided in the above embodiments.

[0105] Furthermore, electronic devices also include:

[0106] Communication interface 503 is used for communication between memory 501 and processor 502.

[0107] The memory 501 is used to store computer programs that can run on the processor 502.

[0108] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0109] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0110] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0111] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0112] This application also provides a computer program product on which a computer program is stored, which, when executed by a processor, implements the battery consistency calculation method described above.

[0113] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0114] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0115] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0116] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be specifically implemented in any computer program product for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer program product" can be any means that can contain, store, communicate, propagate, or transmit a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples of computer program products (a non-exhaustive list) include the following: an electrical connection having one or N wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). Furthermore, the computer program product can even be paper or other suitable medium on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0117] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0118] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer program product, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0119] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer program product.

[0120] The computer program product mentioned above may be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A battery uniformity calculation method characterized by comprising: The method comprises the following steps: acquiring battery data of a vehicle and performing data processing on the battery data; dividing the battery data after data processing into non-overlapping time windows according to a time scale to construct a coarse-grained sequence, and calculating sample entropy of each coarse-grained sequence; allocating a preset distribution weight to each coarse-grained sequence of each coarse sequence, calculating weighted composite multiscale entropy of the coarse-grained sequence based on the sample entropy of each coarse-grained sequence, and evaluating battery consistency of the vehicle based on the weighted composite multiscale entropy; the calculation of the sample entropy of each coarse-grained sequence comprises: constructing a multi-dimensional vector and calculating the distance between the multi-dimensional vectors; statistically determining the proportion of similar vector pairs according to a similarity coefficient threshold, and calculating the sample entropy of each coarse-grained sequence based on the proportion of similar vector pairs by using a preset sample entropy calculation formula, wherein the preset sample entropy calculation formula is: ； wherein, is the mode dimension, is the similarity coefficient threshold, is the data length, is the proportion of similar vector pairs; the calculation of the weighted composite multiscale entropy of the coarse-grained sequence based on the sample entropy of each coarse-grained sequence comprises: calculating the weighted composite multiscale entropy of the coarse-grained sequence by using a preset weighted composite multiscale entropy calculation formula, wherein the preset weighted composite multiscale entropy calculation formula is: wherein, , are both preset allocation weights, is a scale factor, is a coarse quantization sequence, and M is a sequence length.

2. The method of claim 1, wherein, the data processing on the battery data comprises: identifying and deleting repeated data and data with field values beyond a normal range in the battery data; identifying abnormal values of fields in the battery data by using quantile and box plot techniques, and deleting whole-row data containing abnormal values.

3. A battery uniformity calculation device characterized by comprising: comprise: a processing module configured to acquire battery data of a vehicle and perform data processing on the battery data; a first calculation module configured to divide the battery data after data processing into non-overlapping time windows according to a time scale to construct a coarse-grained sequence, and calculate sample entropy of each coarse-grained sequence; a second calculation module configured to allocate a preset distribution weight to each coarse-grained sequence of each coarse sequence, calculate weighted composite multiscale entropy of the coarse-grained sequence based on the sample entropy of each coarse-grained sequence, and evaluate battery consistency of the vehicle based on the weighted composite multiscale entropy; the first calculation module is further configured to: construct a multi-dimensional vector and calculate the distance between the multi-dimensional vectors; statistically determine the proportion of similar vector pairs according to a similarity coefficient threshold, and calculate the sample entropy of each coarse-grained sequence based on the proportion of similar vector pairs by using a preset sample entropy calculation formula, wherein the preset sample entropy calculation formula is: ； wherein, is the mode dimension, is the similarity coefficient threshold, is the data length, is the proportion of similar vector pairs; the second calculation module is further configured to: calculate the weighted composite multiscale entropy of the coarse-grained sequence by using a preset weighted composite multiscale entropy calculation formula, wherein the preset weighted composite multiscale entropy calculation formula is: wherein, , are both preset allocation weights, is a scale factor, is a coarse-grained sequence, and M is a sequence length.

4. The apparatus of claim 3, wherein, the processing module is further configured to: identify and delete repeated data and data with field values beyond a normal range in the battery data; identify abnormal values of fields in the battery data by using quantile and box plot techniques, and delete whole-row data containing abnormal values.

5. An electronic device, comprising: comprise a memory and a processor; The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the battery consistency calculation method as described in any one of claims 1-2.

6. A computer program product storing a computer program, characterized by, When executed by the processor, the program implements the battery consistency calculation method as described in any one of claims 1-2.

Images