Battery data management method, device, electronic device and computer program product

By converting battery data into images and using assembly extreme data for classification, combined with machine learning, the inaccuracy problems caused by isolated analysis and manual marking in existing battery data management are solved, and efficient and automated management of battery data is achieved and failure prediction.

CN114004288BActive Publication Date: 2024-11-01HANGZHOU HOPECHART
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111234274.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-10-22
Publication Date
2024-11-01
Estimated Expiration
2041-10-22

AI Technical Summary

Technical Problem

Existing battery data management methods lead to isolated analysis of single-body temperature data, single-body voltage data and assembly extreme value data through mathematical modeling and algorithmic analysis, resulting in inaccurate management, and relying on artificial markings with subjective factors, further reducing accuracy sex.

Method used

By analyzing the battery assembly single data stream, converting the single temperature data and voltage data into images, and using the assembly extreme data for overall classification, combining machine learning to predict faults, automating the classification process, and reducing manual participation.

Benefits of technology

It improves the accuracy and efficiency of battery data management, realizes automatic monitoring of battery status and fault prediction, and reduces the subjective error of manual marking.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114004288B_ABST
    Figure CN114004288B_ABST
Patent Text Reader

Abstract

The present application relates to the field of battery management technology, and provides a battery data management method, device, electronic device and computer program product, the method comprising: parsing the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list and an assembly extreme value data list; converting the single cell temperature data list and the single cell voltage data list into a single cell data image according to the battery system structure information; and classifying the single cell data image according to the assembly extreme value data list. The battery data management method provided in the embodiment of the present application converts single cell temperature data and single cell voltage data into single cell data images, and then manages the single cell data images as a whole through the assembly extreme value data, without isolating and analyzing the single cell temperature data, single cell voltage data and assembly extreme value data, thereby improving the accuracy of battery data management. Furthermore, the accuracy of battery data management is improved by automatically classifying the assembly extreme value data without manual intervention.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of battery management technology, and in particular to a battery data management method, device, electronic device and computer program product. Background Art

[0002] At present, the main method of battery data management is the analysis method of mathematical modeling + algorithm, that is, the battery data (cell temperature data, cell voltage data and assembly extreme value data) is analyzed by mathematical modeling first and then by algorithm. In the process of analyzing the cell temperature data, cell voltage data and assembly extreme value data, the above method splits and analyzes the cell temperature data, cell voltage data and assembly extreme value data, that is, the cell temperature data, cell voltage data and assembly extreme value data are analyzed in isolation and separately, so that the battery data cannot be managed as a whole, resulting in inaccurate battery data management. Furthermore, the battery data is manually marked during the analysis process. Due to the subjective factors in the manual marking process, the battery data management is further inaccurate. Summary of the invention

[0003] The present application provides a battery data management method, device, electronic device and computer program product, aiming to improve the accuracy of battery data management.

[0004] In a first aspect, the present application provides a battery data management method, comprising:

[0005] Parse the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list, and an assembly extreme value data list;

[0006] Converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information;

[0007] The monomer data images are classified according to the assembly extreme value data list.

[0008] In one embodiment, the step of converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information includes:

[0009] Converting each cell temperature data in the cell temperature data list and each cell voltage data in the cell voltage data list into a two-dimensional battery cell matrix according to the battery system structure information;

[0010] The two-dimensional battery cell matrix is ​​converted into a visual image to obtain the cell data image.

[0011] The step of converting each cell temperature data in the cell temperature data list and each cell voltage data in the cell voltage data list into a two-dimensional battery cell matrix according to the battery system structure information comprises:

[0012] Determine the number of longitudinal columns to be filled and the number of transverse columns to be filled according to the battery system structure information, and construct a two-dimensional matrix to be filled according to the number of longitudinal columns to be filled and the number of transverse columns to be filled;

[0013] Converting each cell temperature data in the cell temperature data list into a first color pixel value according to a preset color model, and converting each cell voltage data in the cell voltage data list into a second color pixel value according to the preset color model;

[0014] The to-be-filled position area in the to-be-filled two-dimensional matrix is ​​determined according to the battery system structure information, and the to-be-filled position area is filled based on each of the first color pixel values ​​and each of the second color pixel values ​​to obtain the two-dimensional battery cell matrix.

[0015] The step of classifying the monomer data images according to the assembly extreme value data list comprises:

[0016] Determining whether the battery assembly is in a normal state according to the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data in the assembly extreme value data list;

[0017] If the battery assembly is in a normal state, determining the single cell data image as a non-fault image;

[0018] If the battery assembly is in an abnormal state, the single cell data image is determined as a fault type image.

[0019] The step of determining whether the battery assembly is in a normal state according to the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data in the assembly extreme value data list comprises:

[0020] Determine whether the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data, and the minimum temperature data are all less than or equal to their corresponding preset thresholds;

[0021] If the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data are all less than or equal to their corresponding preset thresholds, it is determined that the battery assembly is in a normal state;

[0022] If any one or more of the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data is greater than its corresponding preset threshold value, it is determined that the battery assembly is in an abnormal state.

[0023] The step of parsing the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list and an assembly extreme value data list comprises:

[0024] Parsing the cell temperature data packets in the battery assembly cell data stream, and splicing the parsed cell temperature data to obtain the cell temperature data list;

[0025] Parsing the cell voltage data packets in the cell data stream of the battery assembly, and splicing the parsed cell voltage data to obtain the cell temperature data list;

[0026] The assembly extreme value data packets in the battery assembly single cell data stream are parsed to obtain the highest voltage data, the lowest voltage data, the highest temperature data and the lowest temperature data, which are associated with the total voltage data and the total current data to obtain the assembly extreme value data list.

[0027] After the step of classifying the monomer data images according to the assembly extreme value data list, the method further includes:

[0028] Perform machine learning on non-fault images and fault images to obtain a data model;

[0029] Inputting the image to be predicted into the data model and outputting a fault occurrence probability value;

[0030] If the probability of the fault occurring is less than or equal to the preset safety threshold, determining that the image to be predicted is a non-fault image;

[0031] If the probability of the fault occurring is greater than the preset safety threshold, the image to be predicted is determined to be a fault-type image, and a predictive alarm is issued.

[0032] In a second aspect, the present application also provides a battery data management device, including:

[0033] A parsing module is used to parse the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list and an assembly extreme value data list;

[0034] A conversion module, used for converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information;

[0035] A classification module is used to classify the monomer data image according to the assembly extreme value data list.

[0036] In a third aspect, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the battery data management method described in the first aspect when executing the program.

[0037] In a fourth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by the processor, the steps of the battery data management method described in the first aspect are implemented.

[0038] The battery data management method, device, electronic device and computer program product provided by the present application convert the single cell temperature data and single cell voltage data into single cell data images during the battery data management process, and then manage the single cell data images as a whole through the assembly extreme value data, without analyzing the single cell temperature data, single cell voltage data and assembly extreme value data in isolation, thereby improving the accuracy of battery data management. Furthermore, in the process of battery data management, automatic classification is achieved through the assembly extreme value data, without the need for manual participation, further improving the accuracy of battery data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 This is one of the flow charts of the battery data management method provided by this application;

[0041] Figure 2 This is the second flow chart of the battery data management method provided by this application;

[0042] Figure 3 It is a structural schematic diagram of the battery data management device provided by the present application;

[0043] Figure 4 It is a structural schematic diagram of the electronic device provided by this application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] Combine the following Figures 1 to 4 The present invention describes a battery data management method, device, electronic device, and computer program product.

[0046] Specifically, the present application provides a battery data management method, referring to Figure 1 , Figure 1 This is one of the flow charts of the battery data management method provided in this application.

[0047] The embodiments of the present application provide embodiments of a battery data management method. It should be noted that, although a logical order is shown in the flow chart, under certain data, the steps shown or described may be completed in a different order than that shown here.

[0048] The embodiments of the present application take an electronic device as an example of an execution subject. The embodiments of the present application take a data management system as one of the manifestations of the electronic device, but do not limit the electronic device.

[0049] The battery data management method provided in the embodiment of the present application includes:

[0050] Step S10, parsing the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list and an assembly extreme value data list.

[0051] It should be noted that the power battery system of electric vehicles generally adopts a closed structure and can be used continuously for several years. Therefore, the battery performance and structure of a single vehicle are considered to be long-term stable and will not be replaced frequently. In the case of charging by replacing the battery, the battery data can be collected and reported through the GB32960.2 protocol (GB / T32960.2-2016 Technical Specifications for Electric Vehicle Remote Service and Management System) by adding BMS (Battery Management System) terminal equipment to the energy storage battery hardware system.

[0052] There are multiple battery assemblies in the power battery system, and each battery assembly has several battery cells (monomers). Each battery assembly is independent of each other. Therefore, the embodiment of the present application performs data analysis and management on the battery assembly as a whole.

[0053] Therefore, before the data management system manages the battery data, the acquisition and control gateway needs to group the collected battery data (cell temperature data, cell voltage data and assembly extreme value data) in the GB32960.2 protocol according to the vehicle identification code, and store the grouped battery data in the data stream format of the data packet to the message queue topic of kafka (a high-throughput distributed publish-subscribe messaging system), where the topic of the assembly extreme value data packet is t_ne_limit; the topic of the cell temperature data packet is t_ne_temp; and the topic of the cell voltage data packet is t_ne_voltage.

[0054] It should be further explained that the battery data written to Kafka is packetized per second, and the same data item may have multiple data packets per second. The data packet message header structure is shown in Table 1, which is the data packet message header structure.

[0055] Table 1 Data packet message header structure

[0056] Location Fields Data Types illustrate 0 10-digit data number DWord As a unique identification code for terminal equipment 4 Data version Word Default is 0 6 Message body length N Word Message body length N 8 Data categories Byte 1-250 9 Data sub-category Byte 1-250 10 Message content Byte[N] Message content

[0057] The data management system obtains the battery assembly monomer data stream stored in kafka, wherein the battery assembly monomer data stream includes a monomer temperature data stream, a monomer voltage data stream, and an assembly extreme value data stream. Next, the data management system performs monomer temperature data parsing on the monomer temperature data stream, and obtains a monomer temperature data list based on the parsed monomer temperature data. At the same time, the data management system performs monomer voltage data parsing on the monomer voltage data stream, and obtains a monomer voltage data list based on the parsed monomer voltage data. At the same time, the data management system performs assembly extreme value data parsing on the assembly extreme value data stream, and obtains an assembly extreme value data list based on the parsed assembly extreme value data, as described in steps S101 to S103.

[0058] Further, steps S101 to S103 are described as follows:

[0059] Step S101, parsing the cell temperature data packets in the battery assembly cell data stream, and splicing the parsed cell temperature data to obtain a cell temperature data list;

[0060] Step S102, parsing the cell voltage data packets in the battery assembly cell data stream, and splicing the parsed cell voltage data to obtain a cell temperature data list;

[0061] Step S103, parsing the assembly extreme value data packets in the battery assembly single cell data stream, parsing out the highest voltage data, the lowest voltage data, the highest temperature data and the lowest temperature data, and associating them with the total voltage data and the total current data to obtain an assembly extreme value data list.

[0062] Specifically, the data management system consumes t_ne_temp in the topic of Kafka, that is, the cell temperature data packet in the battery assembly cell data stream, parses the cell temperature data packet, obtains the temperature data of each cell in the cell temperature data packet, and concatenates the temperature data of each cell to obtain a cell temperature data list. The structure of the cell temperature data packet is shown in Table 2. Table 2 is the structure of the cell temperature data packet.

[0063] Table 2 Monomer temperature data packet structure

[0064]

[0065]

[0066] The data management system consumes t_ne_voltage in the topic of Kafka, that is, the cell voltage data packet in the battery assembly cell data stream, parses the cell voltage data packet, obtains the individual cell voltage data in the cell voltage data packet, and concatenates the individual cell voltage data to obtain a cell voltage data list. The structure of the cell voltage data packet is shown in Table 3. Table 3 is the structure of the cell voltage data packet.

[0067] Table 3 Single cell voltage data packet structure

[0068]

[0069]

[0070] The data management system consumes t_ne_limit in the topic of Kafka, that is, the assembly extreme value data packet in the battery assembly monomer data stream, parses the assembly extreme value data packet, obtains the highest voltage data, the lowest voltage data, the highest temperature data and the lowest temperature data in the assembly extreme value data packet, and associates the highest voltage data, the lowest voltage data, the highest temperature data and the lowest temperature data with the total voltage data and the total current data to obtain the assembly extreme value data list. The structure of the assembly extreme value data packet is shown in Table 4. Table 4 is the structure of the assembly extreme value data packet.

[0071] Table 4 Assembly extreme value data packet structure

[0072]

[0073]

[0074] The embodiments of the present application parse the single-cell temperature data packet, the single-cell voltage data packet and the assembly extreme value data packet to obtain a single-cell temperature data list, a single-cell temperature data list and an assembly extreme value data list respectively. Since the data packet brings together all the data at the same time, the amount of data in the data packet is enriched, so that the parsed single-cell temperature data list, the single-cell temperature data list and the assembly extreme value data list have higher accuracy and representativeness.

[0075] Step S20 , converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information.

[0076] The data management system determines the battery system structure information, wherein the battery system structure information carries the battery coding information, and the matrix size and matrix distribution of the matrix to be converted are determined by the battery coding information. Next, the data management system converts each cell temperature data in the cell temperature data list into corresponding first filling information, and converts each cell voltage data in the cell voltage data list into corresponding second filling information, wherein the filling information includes but is not limited to the filling color and the filling color pixel value. Finally, the data management system fills the matrix to be converted according to the first filling information and the second filling information, and converts the filled matrix to be converted to obtain the cell data image corresponding to the cell temperature data list and the cell voltage data list, as described in steps S201 to S202.

[0077] Further, step S201 to step S202 are described as follows:

[0078] Step S201, converting each cell temperature data in the cell temperature data list and each cell voltage data in the cell voltage data list into a two-dimensional battery cell matrix according to the battery system structure information;

[0079] Step S202 converts the two-dimensional battery cell matrix into a visual image to obtain the cell data image.

[0080] Specifically, the data management system determines the matrix longitudinal number and matrix transverse number of the matrix to be converted according to the battery system structure information, and constructs a two-dimensional battery cell matrix consistent with the actual physical space structure distribution according to the matrix longitudinal number and the matrix transverse number. Next, the data management system fills the first filling information corresponding to each cell temperature data in the cell temperature data list, and the second filling information corresponding to each cell voltage data in the cell voltage data list into the two-dimensional battery cell matrix. Finally, the data management system performs a visual image conversion on the filled two-dimensional battery cell matrix to obtain a cell data image, wherein the process of visual image conversion is the process of visual image conversion of cell temperature data and cell voltage data. It should be noted that visual image conversion includes but is not limited to BMP visual image conversion, JPG visual image conversion and PNG visual image conversion.

[0081] The embodiment of the present application converts the monomer temperature data and the monomer voltage data from a data format to an image format, so that the monomer temperature data and the monomer voltage data can be analyzed more intuitively. At the same time, no intermediate processing is performed on the monomer temperature data and the monomer voltage data during the conversion process, which reduces the precision loss of the monomer temperature data and the monomer voltage data, thereby making the monomer data image more accurate. Furthermore, the visualized monomer data image provides an efficient training data set for subsequent machine learning.

[0082] Step S30, classifying the monomer data images according to the assembly extreme value data list.

[0083] The data management system determines the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data in the assembly extreme value data list, and classifies the monomer data images according to the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data, as specifically described in steps S301 to S303, wherein the monomer data images can be divided into non-fault monomer data images and fault monomer data images.

[0084] Further, the specific description of step S301 to step S303 is as follows:

[0085] Step S301, determining whether the battery assembly is in a normal state according to the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data in the assembly extreme value data list;

[0086] Step S302, if the battery assembly is in a normal state, determining the single cell data image as a non-fault image;

[0087] Step S303: if the battery assembly is in an abnormal state, the single cell data image is determined as a fault type image.

[0088] Specifically, the data management system determines whether the battery assembly is in a normal state based on the total voltage data, the total current data, the highest voltage data, the lowest voltage data, the highest temperature data, and the lowest temperature data, as described in steps S3011 to S3013. If it is determined that the battery assembly is in a normal state, the data management system determines the single cell data image as a non-fault image. If the battery assembly is in an abnormal state, the data management system determines the single cell data image as a fault image.

[0089] The embodiment of the present application realizes automatic classification of single cell data images according to voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data, without the need for human intervention, thereby improving the accuracy of battery data management.

[0090] Further, steps S3011 to S3013 are described as follows:

[0091] Step S3011, determining whether the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data are all less than or equal to their corresponding preset thresholds;

[0092] Step S3012: if the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data are all less than or equal to their corresponding preset thresholds, it is determined that the battery assembly is in a normal state;

[0093] Step S3013, if any one or more of the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data is greater than the corresponding preset threshold value, it is determined that the battery assembly is in an abnormal state.

[0094] Specifically, the data management system determines whether the total voltage data, the total current data, the highest voltage data, the lowest voltage data, the highest temperature data, and the lowest temperature data are all less than or equal to their corresponding preset thresholds, wherein each preset threshold is set according to actual conditions. If it is determined that the total voltage data, the total current data, the highest voltage data, the lowest voltage data, the highest temperature data, and the lowest temperature data are all less than or equal to their corresponding preset thresholds, the data management system determines that the battery assembly is in a normal state. If it is determined that any one or more of the total voltage data, the total current data, the highest voltage data, the lowest voltage data, the highest temperature data, and the lowest temperature data is greater than its corresponding preset threshold, the data management system determines that the battery assembly is in an abnormal state. It can be further understood that, among the total voltage data, the total current data, the highest voltage data, the lowest voltage data, the highest temperature data, and the lowest temperature data, there is mainly one that is greater than its corresponding preset threshold, and the data management system determines that the battery assembly is in an abnormal state.

[0095] The embodiment of the present application jointly determines whether the battery assembly is in a normal state or an abnormal state through total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data, thereby ensuring the accuracy of the battery assembly state.

[0096] Furthermore, after step S30, it is necessary to construct a data model based on the non-fault image and the fault image, and predict the image to be predicted based on the data model, as shown in steps S40 to S70.

[0097] Step S40, performing machine learning on the non-fault image and the fault image to obtain a data model;

[0098] Step S50, inputting the image to be predicted into the data model, and outputting a fault occurrence probability value;

[0099] Step S60: if the fault occurrence probability is less than or equal to a preset safety threshold, determining that the image to be predicted is a non-fault image;

[0100] Step S70: If the probability of the fault occurring is greater than the preset safety threshold, the image to be predicted is determined to be a fault-type image, and a predictive alarm is issued.

[0101] The data management system uses non-fault images and fault images as training data sets for machine learning to obtain a data model. When receiving the input image to be predicted, the data management system inputs the image to be predicted into the data model and outputs the fault probability value of the image to be predicted. Next, the data management system compares the fault probability value with the preset safety threshold to obtain a comparison result, wherein the comparison result may be that the fault probability value is greater than the preset safety threshold, or the comparison result may be that the fault probability value is less than or equal to the preset safety threshold. If the comparison result is determined to be that the fault probability value is less than or equal to the preset safety threshold, the data management system determines that the image to be predicted is a non-fault image, that is, the battery data corresponding to the image to be predicted is correct, and the battery corresponding to the battery data does not have a fault. If the comparison result is determined to be that the fault probability value is greater than the preset safety threshold, the data management system determines that the image to be predicted is a fault image, that is, the battery data corresponding to the image to be predicted is wrong, and the battery corresponding to the battery data has a fault, and a predictive alarm is issued. Further, if the assembly extreme value data, monomer temperature data, and monomer voltage data collected within the subsequent time range meet the fault judgment, it is determined that the fault is predicted successfully and the data model is strengthened. If the assembly extreme value data, monomer temperature data, and monomer voltage data collected within the subsequent time range do not conform to the fault judgment, it is determined that the predicted fault has failed and the data model is modified.

[0102] The embodiment of the present application performs machine learning on non-fault images and fault images, and the obtained data model has high accuracy. The ground prediction image is predicted by the high-accuracy data model, so as to improve the accuracy of the prediction result.

[0103] This embodiment provides a battery data management method. In the process of battery data management, the single cell temperature data and single cell voltage data are converted into single cell data images, and then the single cell data images are managed as a whole through the assembly extreme value data, without analyzing the single cell temperature data, single cell voltage data and assembly extreme value data in isolation, thereby improving the accuracy of battery data management. Furthermore, automatic classification is achieved through the assembly extreme value data, without the need for manual participation, further improving the accuracy of battery data management.

[0104] Further, refer to Figure 2 , Figure 2 This is the second flow chart of the battery data management method provided by the present application, and the step S201 includes:

[0105] Step S2011, determining the number of longitudinal lines to be filled and the number of transverse lines to be filled according to the battery system structure information, and constructing a two-dimensional matrix to be filled according to the number of longitudinal lines to be filled and the number of transverse lines to be filled;

[0106] Step S2012, converting each cell temperature data in the cell temperature data list into a first color pixel value according to a preset color model, and converting each cell voltage data in the cell voltage data list into a second color pixel value according to the preset color model;

[0107] Step S2013, determining the to-be-filled position area in the to-be-filled two-dimensional matrix according to the battery system structure information, and filling the to-be-filled position area based on each of the first color pixel values ​​and each of the second color pixel values ​​to obtain the two-dimensional battery cell matrix.

[0108] Specifically, the data management system determines the number of longitudinal columns to be filled and the number of transverse columns to be filled according to the battery coding information in the battery system structure information. In this embodiment, for example, the number of longitudinal columns to be filled in the battery coding information XN2021 is 16, and the number of transverse columns to be filled is 20; the number of longitudinal columns to be filled in the battery coding information YD2021 is 14, and the number of transverse columns to be filled is 17. Next, the data management system constructs a two-dimensional matrix to be filled according to the number of longitudinal columns to be filled and the number of transverse columns to be filled, that is, the number of rows of the two-dimensional matrix to be filled is the number of transverse columns to be filled, and the number of columns of the two-dimensional matrix to be filled is the number of longitudinal columns to be filled. Next, the data management system converts each cell temperature data in the cell temperature data list into a first color pixel value according to a preset color model, and converts each cell voltage data in the cell voltage data list into a second color pixel value according to a preset color model.

[0109] It should be noted that, in the present embodiment, different preset color models have different meanings of color pixel values. In the present embodiment, for example, when the preset color model is the HSV color model, the color pixel value is the hue value, saturation value or color brightness value; when the preset color model is the HSI color model, the color pixel value is the hue value, color saturation value or brightness value; when the preset color model is the RGB color model, the color pixel value is the red component value, the green component value or the blue component value; when the preset color model is the CMY color model, the color pixel value is the cyan component value, the magenta component value or the yellow component value.

[0110] In order to further clarify the embodiments of the present application, the RGB color model is taken as an example as a preset color model, which is described as follows:

[0111] The data management system converts each cell temperature data in the cell temperature data list into a first color pixel value according to the RGB color model, and converts each cell voltage data in the cell voltage data list into a second color pixel value according to the RGB color model. In this embodiment, the green component value is used as the first color pixel value, the blue component value is used as the second color pixel value, and the preset value is used as the preset red component value. The preset red component value in this embodiment is set to 0, wherein the value range of the cell temperature data is 0 to 250°C (degrees Celsius), the value offset is 40°C, that is, the effective range is -40°C to 210°C, and the value range of the cell voltage data is 0 to 200V (volts). Next, the data management system determines the to-be-filled position area of ​​the cell temperature data and the cell voltage data in the to-be-filled two-dimensional matrix according to the battery number information in the battery system structure information, and fills the to-be-filled position area according to each green component value, each blue component value and the preset red component value, and the remaining position area is filled with 0x00000 (white) to obtain a two-dimensional battery cell matrix. It should be noted that the size of the color pixel value is calculated by the built-in algorithm of the RGB color model and based on the monomer voltage data or the monomer temperature data. This embodiment does not limit this. For the sake of ease of understanding, this embodiment lists one of the algorithms. For example, for the monomer temperature data, -40°C to 210°C is measured in units of 1°C, and the corresponding green component value is 0x00000 to 0x00FEFE, that is, -40°C corresponds to 0x00000, and 210°C corresponds to 0x00FEFE.

[0112] It should be further explained that 0xFE in the cell temperature data indicates an abnormality, and 0xFF indicates invalidity. Similarly, 0xFE in the cell voltage data indicates an abnormality, and 0xFF indicates invalidity. Furthermore, the abnormal state 0xFE is kept as it is, and the invalid state 0xFF is replaced with 0.

[0113] The embodiment of the present application does not perform intermediate processing on the monomer temperature data and the monomer voltage data during the conversion process. Instead, the monomer temperature data and the monomer voltage data are converted through a preset color model, thereby reducing the precision loss of the monomer temperature data and the monomer voltage data, thereby making the monomer data image have higher accuracy.

[0114] Furthermore, the battery data management device provided in the present application is described below. The battery data management device described below and the battery data management method described above can be referred to in correspondence with each other.

[0115] like Figure 3 As shown, Figure 3 : is a schematic diagram of the structure of the battery data management device provided by the present application, the battery data management device includes:

[0116] The parsing module 301 is used to parse the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list and an assembly extreme value data list;

[0117] A conversion module 302, configured to convert the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information;

[0118] The classification module 303 is used to classify the monomer data image according to the assembly extreme value data list.

[0119] Furthermore, the conversion module 302 is also used for:

[0120] Converting each cell temperature data in the cell temperature data list and each cell voltage data in the cell voltage data list into a two-dimensional battery cell matrix according to the battery system structure information;

[0121] The two-dimensional battery cell matrix is ​​converted into a visual image to obtain the cell data image.

[0122] Furthermore, the conversion module 302 is also used for:

[0123] Determine the number of longitudinal columns to be filled and the number of transverse columns to be filled according to the battery system structure information, and construct a two-dimensional matrix to be filled according to the number of longitudinal columns to be filled and the number of transverse columns to be filled;

[0124] Converting each cell temperature data in the cell temperature data list into a first color pixel value according to a preset color model, and converting each cell voltage data in the cell voltage data list into a second color pixel value according to the preset color model;

[0125] The to-be-filled position area in the to-be-filled two-dimensional matrix is ​​determined according to the battery system structure information, and the to-be-filled position area is filled based on each of the first color pixel values ​​and each of the second color pixel values ​​to obtain the two-dimensional battery cell matrix.

[0126] Furthermore, the classification module 303 is also used for:

[0127] Determining whether the battery assembly is in a normal state according to the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data in the assembly extreme value data list;

[0128] If the battery assembly is in a normal state, determining the single cell data image as a non-fault image;

[0129] If the battery assembly is in an abnormal state, the single cell data image is determined as a fault type image.

[0130] Furthermore, the classification module 303 is also used for:

[0131] Determine whether the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data, and the minimum temperature data are all less than or equal to their corresponding preset thresholds;

[0132] If the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data are all less than or equal to their corresponding preset thresholds, it is determined that the battery assembly is in a normal state;

[0133] If any one or more of the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data is greater than its corresponding preset threshold value, it is determined that the battery assembly is in an abnormal state.

[0134] Furthermore, the parsing module 301 is also used for:

[0135] Parsing the cell temperature data packets in the battery assembly cell data stream, and splicing the parsed cell temperature data to obtain the cell temperature data list;

[0136] Parsing the cell voltage data packets in the cell data stream of the battery assembly, and splicing the parsed cell voltage data to obtain the cell temperature data list;

[0137] The assembly extreme value data packets in the battery assembly single cell data stream are parsed to obtain the highest voltage data, the lowest voltage data, the highest temperature data and the lowest temperature data, which are associated with the total voltage data and the total current data to obtain the assembly extreme value data list.

[0138] Furthermore, the battery data management device further includes an analysis module, wherein the analysis module is used to:

[0139] Perform machine learning on non-fault images and fault images to obtain a data model;

[0140] Inputting the image to be predicted into the data model and outputting a fault occurrence probability value;

[0141] If the probability of the fault occurring is less than or equal to the preset safety threshold, determining that the image to be predicted is a non-fault image;

[0142] If the probability of the fault occurring is greater than the preset safety threshold, the image to be predicted is determined to be a fault-type image, and a predictive alarm is issued.

[0143] The specific embodiments of the battery data management device provided in this application are basically the same as the embodiments of the battery data management method described above, and will not be described in detail here.

[0144] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the battery data management method, which includes:

[0145] Parse the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list, and an assembly extreme value data list;

[0146] Converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information;

[0147] The monomer data images are classified according to the assembly extreme value data list.

[0148] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0149] On the other hand, the present application also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer can execute the battery data management method provided by the above methods, the method comprising:

[0150] Parse the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list, and an assembly extreme value data list;

[0151] Converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information;

[0152] The monomer data images are classified according to the assembly extreme value data list.

[0153] In another aspect, the present application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the battery data management method provided above is implemented, and the method includes:

[0154] Parse the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list, and an assembly extreme value data list;

[0155] Converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information;

[0156] The monomer data images are classified according to the assembly extreme value data list.

[0157] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0158] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0159] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A battery data management method, characterized in that: include: Parse the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list, and an assembly extreme value data list; Converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information; Classifying the monomer data images according to the assembly extreme value data list; The step of classifying the monomer data images according to the assembly extreme value data list comprises: Determining whether the battery assembly is in a normal state according to the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data in the assembly extreme value data list; If the battery assembly is in a normal state, determining the single cell data image as a non-fault image; If the battery assembly is in an abnormal state, the single cell data image is determined as a fault type image.

2. The battery data management method according to claim 1, characterized in that: The step of converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information comprises: Converting each cell temperature data in the cell temperature data list and each cell voltage data in the cell voltage data list into a two-dimensional battery cell matrix according to the battery system structure information; The two-dimensional battery cell matrix is ​​converted into a visual image to obtain the cell data image.

3. The battery data management method according to claim 2, characterized in that: The step of converting each cell temperature data in the cell temperature data list and each cell voltage data in the cell voltage data list into a two-dimensional battery cell matrix according to the battery system structure information comprises: Determine the number of longitudinal columns to be filled and the number of transverse columns to be filled according to the battery system structure information, and construct a two-dimensional matrix to be filled according to the number of longitudinal columns to be filled and the number of transverse columns to be filled; Converting each cell temperature data in the cell temperature data list into a first color pixel value according to a preset color model, and converting each cell voltage data in the cell voltage data list into a second color pixel value according to the preset color model; The to-be-filled position area in the to-be-filled two-dimensional matrix is ​​determined according to the battery system structure information, and the to-be-filled position area is filled based on each of the first color pixel values ​​and each of the second color pixel values ​​to obtain the two-dimensional battery cell matrix.

4. The battery data management method according to claim 1, characterized in that: The step of determining whether the battery assembly is in a normal state according to the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data in the assembly extreme value data list comprises: Determine whether the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data, and the minimum temperature data are all less than or equal to their corresponding preset thresholds; If the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data are all less than or equal to their corresponding preset thresholds, it is determined that the battery assembly is in a normal state; If any one or more of the total voltage data, the total current data, the maximum voltage data, the minimum voltage data, the maximum temperature data and the minimum temperature data is greater than its corresponding preset threshold value, it is determined that the battery assembly is in an abnormal state.

5. The battery data management method according to claim 1, characterized in that: The step of parsing the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list and an assembly extreme value data list comprises: Parsing the cell temperature data packets in the battery assembly cell data stream, and splicing the parsed cell temperature data to obtain the cell temperature data list; Parsing the cell voltage data packets in the cell data stream of the battery assembly, and splicing the parsed cell voltage data to obtain the cell temperature data list; The assembly extreme value data packets in the battery assembly single cell data stream are parsed to obtain the highest voltage data, the lowest voltage data, the highest temperature data and the lowest temperature data, which are associated with the total voltage data and the total current data to obtain the assembly extreme value data list.

6. The battery data management method according to any one of claims 1 to 5, characterized in that: After the step of classifying the monomer data images according to the assembly extreme value data list, the method further includes: Perform machine learning on non-fault images and fault images to obtain a data model; Inputting the image to be predicted into the data model and outputting a fault occurrence probability value; If the probability of the fault occurring is less than or equal to the preset safety threshold, determining that the image to be predicted is a non-fault image; If the probability of the fault occurring is greater than the preset safety threshold, the image to be predicted is determined to be a fault-type image, and a predictive alarm is issued.

7. A battery data management device, characterized in that: include: A parsing module is used to parse the battery assembly single cell data stream to obtain a single cell temperature data list, a single cell voltage data list and an assembly extreme value data list; A conversion module, used for converting the cell temperature data list and the cell voltage data list into a cell data image according to the battery system structure information; A classification module, used for classifying the monomer data image according to the assembly extreme value data list; The classification module is also used to: Determining whether the battery assembly is in a normal state according to the total voltage data, total current data, maximum voltage data, minimum voltage data, maximum temperature data and minimum temperature data in the assembly extreme value data list; If the battery assembly is in a normal state, determining the single cell data image as a non-fault image; If the battery assembly is in an abnormal state, the single cell data image is determined as a fault type image.

8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the battery data management method according to any one of claims 1 to 6 are implemented.

9. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of the battery data management method according to any one of claims 1 to 6 are implemented.