An electric vehicle battery health assessment method and apparatus

Abstract

The application provides an electric vehicle battery health evaluation method and device, the method comprising: obtaining battery state big data of a target vehicle battery through Internet of Vehicles; obtaining state information of each single battery in the target vehicle battery according to the battery state big data; performing continuous modeling based on time sequence according to the state information to obtain a continuous state feature cloud model; determining a battery health change trend of the target vehicle battery according to the continuous state feature cloud model; and evaluating the battery health of the target vehicle battery according to the battery health change trend to obtain an evaluation result. It can be seen that the method and device can perform continuous modeling based on big data to obtain the health change trend of a healthy battery, and real-time monitor the health state of the battery, thereby realizing better battery management.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method and apparatus for assessing the health of electric vehicle batteries. Background Technology

[0002] Currently, electric vehicle manufacturers are required to upload certain status data of their operating electric vehicles to the National Testing and Management Center for New Energy Vehicles. Healthy battery cells should have consistent and stable state parameters that change slowly with age. However, if several cells malfunction for various reasons, the battery's health status will fluctuate significantly, posing a considerable risk to its use. Existing battery health status assessment methods typically employ offline physical testing, placing the battery in a pre-set test program to conduct physical experiments and thus estimate its health status offline. However, in practice, it has been found that existing methods cannot monitor battery health status in real time, thus hindering better battery management. Summary of the Invention

[0003] The purpose of this application is to provide a method and apparatus for assessing the health of electric vehicle batteries, which can perform continuous modeling based on big data to obtain the health change trend of healthy batteries, monitor the health status of batteries in real time, and thus achieve better battery management.

[0004] The first aspect of this application provides a method for assessing the health of an electric vehicle battery, including:

[0005] Big data on the battery status of the target vehicle battery can be obtained through vehicle-to-everything (V2X) networks.

[0006] Based on the battery status big data, obtain the status information of each individual battery cell in the target vehicle battery;

[0007] Based on the state information, a continuous state feature cloud model is obtained by performing time-series continuous modeling.

[0008] The battery health change trend of the target vehicle battery is determined based on the continuous state feature cloud model.

[0009] The battery health of the target vehicle battery is assessed based on the battery health change trend, and the assessment results are obtained.

[0010] In the above implementation process, this method can first acquire big data on the battery status of the target vehicle battery through the vehicle network; then, based on the big data on battery status, acquire the status information of each individual cell in the target vehicle battery; next, perform continuous modeling based on time sequence based on the status information to obtain a continuous state feature cloud model; then, determine the battery health change trend of the target vehicle battery based on the continuous state feature cloud model; finally, evaluate the battery health of the target vehicle battery based on the battery health change trend to obtain the evaluation result. It is evident that this method can perform continuous modeling based on big data to obtain the health change trend of a healthy battery, monitor the battery health status in real time, and thus achieve better battery management.

[0011] Furthermore, obtaining the state information of each individual cell in the target vehicle battery based on the battery state big data includes:

[0012] The battery status big data is clustered and divided according to the battery's working status to obtain multiple categories of processed data;

[0013] The processed data for each category is segmented into time segments to obtain time segment data for each category;

[0014] State identification is performed based on the time segment data to obtain the state information of each individual battery cell.

[0015] Further, determining the battery health change trend of the target vehicle battery based on the continuous state feature cloud model includes:

[0016] The state feature cloud model was analyzed, and the analysis results were obtained.

[0017] The battery health trend was determined based on the analysis results.

[0018] Furthermore, the assessment of the battery health of the target vehicle battery based on the battery health change trend, to obtain the assessment result, includes:

[0019] Determine a comparison time period group; wherein, the comparison time period group includes two time periods to be compared;

[0020] The cloud model parameters of the comparison time period group are analyzed based on the battery health change trend to obtain the analysis results;

[0021] Based on the analysis results, determine whether there are similar distance plotting point jumps;

[0022] If so, the assessment result is determined to be that the target vehicle battery has a cell abnormality;

[0023] If not, the assessment result is determined to be that the target vehicle battery does not have any cell abnormalities.

[0024] Furthermore, the analysis of cloud model parameters for the comparison time period group based on the battery health change trend to obtain analysis results includes:

[0025] The parameters of the first cloud model and the second cloud model to be compared are determined based on the comparison time period group.

[0026] A first cloud droplet combination is generated based on the first cloud model parameters, and a second cloud droplet combination is generated based on the second cloud model parameters; wherein the number of cloud droplets in the first cloud droplet combination is the same as the number of cloud droplets in the second cloud droplet combination, and the number of cloud droplets in the first cloud droplet combination is greater than a preset number threshold.

[0027] The cloud droplet distances are calculated sequentially based on the first cloud droplet combination and the second cloud droplet combination;

[0028] Calculate the expected distance value of the cloud droplet distance;

[0029] The analysis results are determined based on the expected distance value.

[0030] A second aspect of this application provides an electric vehicle battery health assessment device, the electric vehicle battery health assessment device comprising:

[0031] The first acquisition unit is used to acquire big data on the battery status of the target vehicle battery through the vehicle network;

[0032] The second acquisition unit is used to acquire the status information of each individual cell in the target vehicle battery based on the battery status big data.

[0033] The modeling unit is used to perform continuous modeling based on the state information in a time sequence to obtain a continuous state feature cloud model.

[0034] A determining unit is used to determine the battery health change trend of the target vehicle battery based on the continuous state feature cloud model;

[0035] An evaluation unit is used to evaluate the battery health of the target vehicle battery based on the battery health change trend and obtain evaluation results.

[0036] In the above implementation process, the device can acquire big data on the battery status of the target vehicle battery through the vehicle network via a first acquisition unit; acquire state information of each individual cell in the target vehicle battery based on the big data on battery status via a second acquisition unit; perform continuous modeling based on time sequence based on the state information through a modeling unit to obtain a continuous state feature cloud model; determine the battery health change trend of the target vehicle battery based on the continuous state feature cloud model through a determination unit; and evaluate the battery health of the target vehicle battery based on the battery health change trend to obtain an evaluation result. It is evident that the device can perform continuous modeling based on big data to obtain the health change trend of a healthy battery, monitor the battery health status in real time, and thus achieve better battery management.

[0037] Furthermore, the second acquisition unit includes:

[0038] The first processing subunit is used to perform clustering and classification processing on the battery status big data according to the battery's working status to obtain multiple categories of processed data.

[0039] The second processing subunit is used to perform time segmentation processing on the processing data of each category to obtain time segment data of each category;

[0040] The state identification subunit is used to identify the state based on the time segment data to obtain the state information of each individual battery cell.

[0041] Furthermore, the determining unit includes:

[0042] The first analysis subunit is used to analyze the state feature cloud model and obtain the analysis results;

[0043] The first determining subunit is used to determine the battery health change trend based on the analysis results.

[0044] Furthermore, the evaluation unit includes:

[0045] The second determining subunit is used to determine a comparison time period group; wherein, the comparison time period group includes two time periods to be compared;

[0046] The second analysis subunit is used to analyze the cloud model parameters of the comparison time period group based on the battery health change trend, and obtain the analysis results;

[0047] The judgment subunit is used to determine whether there is a jump in similar distance plotted points based on the analysis results;

[0048] The second determining subunit is used to determine that the evaluation result indicates that the target car battery has a cell abnormality when there is a jump in the similar distance plotting point;

[0049] The second determining subunit is used to determine that the evaluation result is that the target car battery does not have cell abnormalities when there is no jump in similar distance plotting points.

[0050] Furthermore, the second analysis subunit includes:

[0051] The determination module is used to determine the parameters of the first cloud model and the second cloud model to be compared based on the comparison time period group;

[0052] The generation module is used to generate a first cloud droplet combination based on the first cloud model parameters and a second cloud droplet combination based on the second cloud model parameters; wherein the number of cloud droplets in the first cloud droplet combination is the same as the number of cloud droplets in the second cloud droplet combination, and the number of cloud droplets in the first cloud droplet combination is greater than a preset number threshold.

[0053] The calculation module is used to calculate the cloud droplet distance sequentially based on the first cloud droplet combination and the second cloud droplet combination;

[0054] The calculation module is also used to calculate the expected distance value of the cloud droplet distance;

[0055] The determining module is also used to determine the analysis result based on the expected distance value.

[0056] A third aspect of this application provides an electronic device including a memory and a processor, the memory storing a computer program, and the processor running the computer program to cause the electronic device to perform the electric vehicle battery health assessment method described in any one of the first aspects of this application.

[0057] The fourth aspect of this application provides a computer-readable storage medium storing computer program instructions, which, when read and executed by a processor, perform the electric vehicle battery health assessment method described in any one of the first aspects of this application.

[0058] The beneficial effects of this application are: the method and device can perform continuous modeling based on big data to obtain the health change trend of healthy batteries, monitor the health status of batteries in real time, and thus achieve better battery management. Attached Figure Description

[0059] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 A flowchart illustrating a method for assessing the health of an electric vehicle battery provided in an embodiment of this application;

[0061] Figure 2 A flowchart illustrating another method for assessing the health of an electric vehicle battery provided in this application embodiment;

[0062] Figure 3 This is a schematic diagram of the structure of an electric vehicle battery health assessment device provided in an embodiment of this application;

[0063] Figure 4 A schematic diagram of another electric vehicle battery health assessment device provided in this application embodiment;

[0064] Figure 5 A schematic diagram of a second-order circuit model provided in an embodiment of this application;

[0065] Figure 6 A schematic diagram of an equivalent circuit model provided in an embodiment of this application;

[0066] Figure 7 A cloud map of a battery cell of a vehicle at different life stages is provided as an embodiment of this application;

[0067] Figure 8 This is an example diagram illustrating a jump in the similar distance plotted points provided in an embodiment of this application. Detailed Implementation

[0068] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0069] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0070] Example 1

[0071] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a method for assessing the health of an electric vehicle battery provided in this embodiment. The method includes:

[0072] S101. Obtain big data on the battery status of the target vehicle battery through the Internet of Vehicles.

[0073] S102. Obtain the status information of each individual cell in the target vehicle battery based on the battery status big data.

[0074] S103. Perform continuous modeling based on time sequence according to the state information to obtain a continuous state feature cloud model.

[0075] S104. Determine the battery health change trend of the target vehicle battery based on the continuous state feature cloud model.

[0076] S105. Assess the battery health of the target vehicle battery based on the battery health change trend and obtain the assessment results.

[0077] In this embodiment, the theoretical basis of the method is as follows:

[0078] Firstly, in engineering, batteries are typically modeled using circuit models based on lumped parameters. Figure 5 The second-order circuit model shown is used as an example. For ease of analysis, this application uses Z-parameters to represent the circuit, thereby transforming it into an equivalent circuit. Figure 6 The equivalent circuit model is shown.

[0079] at this time, This can be further simplified to:

[0080]

[0081] Among these parameters, the terminal voltage U and current Is can be measured, while the internal impedance Z cannot be directly measured in engineering. It is a nonlinear time-varying function of SOC, SOH, current, and temperature, exhibiting randomness and uncertainty. However, this parameter is extremely important, as it is a key indicator of battery aging and health.

[0082] Therefore, if we can continuously monitor the internal impedance of a battery and obtain its current status and trends, we can monitor the current state of the battery and predict its future trends.

[0083] Currently, electric vehicle manufacturers are typically required to upload certain status data of their operating electric vehicles to designated new energy vehicle testing and management centers. Among this data, information concerning battery operating characteristics often relies heavily on big data to significantly improve the performance of the Battery Management System (BMS).

[0084] A healthy battery cell should have consistent and stable state parameters that change slowly with age. However, if several cells become abnormal due to various reasons, the battery's health status will fluctuate significantly, posing a considerable risk to its use. Therefore, to identify these conditions as quickly as possible and take early intervention measures, this application proposes a method for identifying battery health status based on continuous monitoring using big data.

[0085] In this embodiment, the subject executing the method can be a computing device such as a computer or server, and no limitation is made in this embodiment.

[0086] In this embodiment, the subject executing the method can also be a smart device such as a smartphone or tablet, and no limitation is made in this embodiment.

[0087] As can be seen, the electric vehicle battery health assessment method described in this embodiment can adopt a cloud model, thereby better filtering out the influence of random errors and making abnormal information more prominent. It can also continuously model time-series data provided by big data, and analyze the continuous modeling results based on cloud similarity theory to obtain the health change trend of healthy batteries, which is conducive to quickly capturing the inflection point of anomalies and thus achieving better battery management.

[0088] Example 2

[0089] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating a method for assessing the health of an electric vehicle battery provided in this embodiment. The method includes:

[0090] S201. Obtain big data on the battery status of the target vehicle battery through the Internet of Vehicles.

[0091] S202. Based on the battery's working state, perform clustering and classification of the battery status big data to obtain multiple categories of processed data.

[0092] In this embodiment, the method can cluster and classify the big data about battery status obtained through the Internet of Vehicles according to the battery's working status, such as working cycle, SOC, temperature, etc.

[0093] S203. Perform time segmentation processing on the data of each category to obtain time segment data for each category.

[0094] In this embodiment, the method can further segment the data within the same type of data according to its transient changes and time segments.

[0095] S204. Based on the time segment data, perform state identification to obtain the state information of each individual battery cell.

[0096] In this embodiment, the method can identify the state information of each individual cell, such as internal impedance, through the segmented data (usually a time segment of data).

[0097] For example, linear regression is used here.

[0098] Based on the following assumptions:

[0099]

[0100] Among them, U—the voltage of a single cell, which is the time series data of the voltage of a single cell collected by the battery management system and uploaded to the big data system;

[0101] I—The real-time operating current of the battery is collected by the battery management system and uploaded to the big data system as time-series data;

[0102] OCV—Electromotive force of a single cell, which cannot be directly measured and is considered a parameter to be determined;

[0103] Z—The internal impedance of a single cell, which cannot be directly measured, is considered a parameter to be determined.

[0104] Based on the time series data U and I, which have already been classified and segmented through previous steps, this data can be denoted as:

[0105] U = (U1, U2, ..., U...) m );

[0106] I = (I1, I2, I3, ..., I m );

[0107] Among them, U i and I i A set of data of equal duration, occurring within the same time segment, is used to derive the battery's OCV for a specific time period through linear fitting for each such set of data. i and Z i Parameter value. Z i This is the internal impedance parameter that is the focus of this application.

[0108] S205. Perform continuous modeling based on time sequence according to the state information to obtain a continuous state feature cloud model.

[0109] In this embodiment, the method can perform mathematical modeling on the relevant parameters of each time segment in order to describe its overall state information; wherein, the method can perform mathematical modeling based on cloud theory model.

[0110] For example, this method demonstrates a process for modeling the internal resistance of a battery over a specific time segment using a cloud model. This process includes at least the following steps:

[0111] Step 1: Calculate Z i The average value, i.e., the expectation of the distribution of cloud droplets in the universe of discourse:

[0112]

[0113] Step 2: Calculate Zi Uncertainty, or entropy of cloud droplets, is represented by the first-order central moment:

[0114]

[0115] Step 3: Calculate the hyperentropy of cloud droplets to measure the uncertainty of entropy, revealing the cohesiveness of uncertainty and the relationship between fuzziness and randomness:

[0116]

[0117] Step 4: Based on digital features (Ez, En, He), generate cloud droplet maps using a forward cloud generator. Specifically, this step may include the following sub-steps:

[0118] ① Generate a normally distributed random number En' with expectation En and variance He;

[0119] ② Generate an image with Ez as the desired value, and... Let x be a normally distributed random number with variance.

[0120] ③ Calculate the membership degree, which is also the degree of certainty.

[0121]

[0122] Here, (x, μ) is a cloud droplet relative to the universe of discourse.

[0123] ④ Repeat steps ① to ③ until enough cloud droplets are generated. Plot all the cloud droplets on the map to form a cloud map (i.e., a cloud droplet map).

[0124] S206. Analyze the state feature cloud model and obtain the analysis results.

[0125] S207. Determine the trend of battery health changes based on the analysis results.

[0126] Please refer to Figure 7 , Figure 7 The diagram shows cloud maps of individual battery cells in a vehicle at different stages of its lifespan. The upper part of the diagram (from left to right) shows cloud maps of normal batteries, batteries with individual abnormalities, and batteries with multiple abnormalities, respectively. The lower part of the diagram shows the results of fitting a normal distribution to the same data.

[0127] By comparing the two images, we can see that the normal distribution below is exactly the outline of the cloud map above. However, the cloud map is more sensitive and intuitive for uncertainty. For normal data, that is, data that perfectly follows a random distribution, the shapes of the cloud map and the normal distribution are almost identical. But once abnormal data appears, the cloud map can reveal it very clearly, indicating that the cloud model can reveal more abnormal information, while the normal distribution is powerless to do so.

[0128] S208. Determine the comparison time period group.

[0129] In this embodiment, the comparison time period group includes two time periods that need to be compared.

[0130] S209. Determine the parameters of the first cloud model and the second cloud model to be compared based on the comparison time period group.

[0131] S210. Generate a first cloud droplet combination based on the parameters of the first cloud model, and generate a second cloud droplet combination based on the parameters of the second cloud model.

[0132] In this embodiment, the number of cloud droplets in the first cloud droplet combination is the same as the number of cloud droplets in the second cloud droplet combination, and the number of cloud droplets in the first cloud droplet combination is greater than a preset number threshold.

[0133] S211. Calculate the cloud droplet distances sequentially based on the first cloud droplet combination and the second cloud droplet combination.

[0134] S212. Calculate the expected distance of the cloud droplet.

[0135] S213. Determine the analysis results based on the expected distance value.

[0136] S214. Based on the analysis results, determine whether there is a jump in the similar distance plotting points. If yes, proceed to step S215; otherwise, proceed to step S216.

[0137] S215. Confirm that the evaluation result indicates that the target vehicle battery has a cell abnormality, and end this process.

[0138] S216. Confirm that the evaluation result shows that there are no cell abnormalities in the target vehicle battery, and end this process.

[0139] In this embodiment, the method can continuously model time-series data provided by big data, and analyze the continuous modeling results based on cloud similarity theory to obtain the health change trend of healthy batteries. Based on this, the method can quickly capture the inflection point of anomalies, thereby achieving better battery management.

[0140] For any two comparison time periods, this method can preferentially assume that their cloud model parameters are as follows:

[0141] ①E z1 E n1 H e1 ;

[0142] ②E z2 E n2 H e2 ;

[0143] Based on this, the method can determine whether the battery cell is abnormal through the following multiple steps, among which,

[0144] Step 1: The cloud droplet combination generated based on parameter group ① is denoted as Drop1;

[0145]

[0146]

[0147] Step 2: The cloud droplet combination generated based on parameter group ② is denoted as Drop2;

[0148]

[0149]

[0150] Step 3: Ensure that the generated droplet combinations Drop1 and Drop2 have the same number, i.e., n=m, and the number of droplets is greater than 1000;

[0151] Step 4: Sort Drop1 and Drop2 in ascending order;

[0152] Step 5: Calculate cloud droplets sequentially and Distance(i);

[0153]

[0154] Step 6: Take the expected value of all distances, which is the similarity distance between the two cloud droplets.

[0155]

[0156] Step 7: If Similar is less than the similarity threshold, the two cloud maps are considered similar.

[0157] Please refer to Figure 8 , Figure 8 A schematic diagram of similar distance plotting points calculated according to the above algorithm is shown. At the position indicated by the circle in the diagram, it can be seen that a certain cell of the battery has an anomaly because the similar distance has changed significantly.

[0158] For example, this application, as a battery health status assessment based on time series similarity, can be summarized into the following steps:

[0159] (1) Obtain time-series data of battery cell voltage and load current based on big data;

[0160] (2) Divide the acquired data into segments according to certain time segments. The selection of time segments should conform to the characteristics of the working conditions used.

[0161] (3) Perform linear fitting on each data segment to solve for the internal resistance of a single cell;

[0162] (4) Establish cloud models based on the internal resistance of the same time period to characterize its state characteristics;

[0163] (5) Solve the similarity of different time periods based on the similarity theory of cloud models;

[0164] (6) When the similarity threshold is exceeded, it is considered that some individual cells have become abnormal.

[0165] In this embodiment, the subject executing the method can be a computing device such as a computer or server, and no limitation is made in this embodiment.

[0166] In this embodiment, the subject executing the method can also be a smart device such as a smartphone or tablet, and no limitation is made in this embodiment.

[0167] As can be seen, the electric vehicle battery health assessment method described in this embodiment can adopt a cloud model, thereby better filtering out the influence of random errors and making abnormal information more prominent. It can also continuously model time-series data provided by big data, and analyze the continuous modeling results based on cloud similarity theory to obtain the health change trend of healthy batteries, which is conducive to quickly capturing the inflection point of anomalies and thus achieving better battery management.

[0168] Example 3

[0169] Please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of an electric vehicle battery health assessment device provided in this embodiment. Figure 3 As shown, the electric vehicle battery health assessment device includes:

[0170] The first acquisition unit 310 is used to acquire big data on the battery status of the target vehicle battery through the vehicle network;

[0171] The second acquisition unit 320 is used to acquire the status information of each individual cell in the target car battery based on battery status big data.

[0172] Modeling unit 330 is used to perform continuous modeling based on time sequence according to state information to obtain a continuous state feature cloud model;

[0173] The determination unit 340 is used to determine the battery health change trend of the target vehicle battery based on the continuous state feature cloud model.

[0174] Evaluation unit 350 is used to evaluate the battery health of the target vehicle battery based on the battery health change trend and obtain the evaluation results.

[0175] In this embodiment, the explanation of the electric vehicle battery health assessment device can be referred to the description in Embodiment 1 or Embodiment 2, and will not be repeated here.

[0176] As can be seen, the electric vehicle battery health assessment device described in this embodiment can adopt a cloud model, thereby better filtering out the influence of random errors and making abnormal information more prominent. It can also continuously model time-series data provided by big data, and analyze the continuous modeling results based on cloud similarity theory to obtain the health change trend of healthy batteries, which is conducive to quickly capturing the inflection point of abnormalities and thus achieving better battery management.

[0177] Example 4

[0178] Please refer to Figure 4 , Figure 4 This is a schematic diagram of the structure of an electric vehicle battery health assessment device provided in this embodiment. Figure 4 As shown, the electric vehicle battery health assessment device includes:

[0179] The first acquisition unit 310 is used to acquire big data on the battery status of the target vehicle battery through the vehicle network;

[0180] The second acquisition unit 320 is used to acquire the status information of each individual cell in the target car battery based on battery status big data.

[0181] Modeling unit 330 is used to perform continuous modeling based on time sequence according to state information to obtain a continuous state feature cloud model;

[0182] The determination unit 340 is used to determine the battery health change trend of the target vehicle battery based on the continuous state feature cloud model.

[0183] Evaluation unit 350 is used to evaluate the battery health of the target vehicle battery based on the battery health change trend and obtain the evaluation results.

[0184] As an optional implementation, the second acquisition unit 320 includes:

[0185] The first processing subunit 321 is used to perform clustering and classification processing on the battery status big data according to the battery's working status to obtain multiple categories of processed data.

[0186] The second processing subunit 322 is used to perform time segmentation processing on the processing data of each category to obtain time segment data of each category;

[0187] The state identification subunit 323 is used to identify the state based on time segment data to obtain the state information of each individual battery cell.

[0188] As an optional implementation, the determining unit 340 includes:

[0189] The first analysis subunit 341 is used to analyze the state feature cloud model and obtain the analysis results;

[0190] The first determining subunit 342 is used to determine the trend of battery health changes based on the analysis results.

[0191] As an optional implementation, the evaluation unit 350 includes:

[0192] The second determining subunit 351 is used to determine the comparison time period group; wherein, the comparison time period group includes two time periods to be compared;

[0193] The second analysis subunit 352 is used to analyze the cloud model parameters of the comparison time period group according to the battery health change trend and obtain the analysis results;

[0194] Judgment subunit 353 is used to determine whether there is a jump in similar distance plotted points based on the analysis results;

[0195] The second determining subunit 351 is used to determine that the evaluation result is that the target car battery has a cell abnormality when there is a jump in the similar distance plotting point;

[0196] The second determining subunit 351 is used to determine that the evaluation result is that the target car battery does not have cell abnormalities when there is no similar distance plotting point jump.

[0197] As an optional implementation, the second analysis subunit 352 includes:

[0198] The determination module is used to determine the parameters of the first cloud model and the second cloud model to be compared based on the comparison time period group.

[0199] The generation module is used to generate a first cloud droplet combination based on the parameters of a first cloud model, and to generate a second cloud droplet combination based on the parameters of a second cloud model; wherein the number of cloud droplets in the first cloud droplet combination is the same as the number of cloud droplets in the second cloud droplet combination, and the number of cloud droplets in the first cloud droplet combination is greater than a preset number threshold.

[0200] The calculation module is used to calculate the cloud droplet distances sequentially based on the first cloud droplet combination and the second cloud droplet combination.

[0201] The calculation module is also used to calculate the expected distance of cloud droplets;

[0202] The determination module is also used to determine the analysis results based on the expected distance value.

[0203] In this embodiment, the explanation of the electric vehicle battery health assessment device can be referred to the description in Embodiment 1 or Embodiment 2, and will not be repeated here.

[0204] As can be seen, the electric vehicle battery health assessment device described in this embodiment can adopt a cloud model, thereby better filtering out the influence of random errors and making abnormal information more prominent. It can also continuously model time-series data provided by big data, and analyze the continuous modeling results based on cloud similarity theory to obtain the health change trend of healthy batteries, which is conducive to quickly capturing the inflection point of abnormalities and thus achieving better battery management.

[0205] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the electric vehicle battery health assessment method in embodiment 1 or embodiment 2 of this application.

[0206] This application provides a computer-readable storage medium storing computer program instructions, which are read and executed by a processor to perform the electric vehicle battery health assessment method in embodiment 1 or embodiment 2 of this application.

[0207] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0208] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0209] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0210] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0211] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0212] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for assessing the health of an electric vehicle battery, characterized in that, include: Big data on the battery status of the target vehicle battery can be obtained through vehicle-to-everything (V2X) networks. Based on the battery status big data, obtain the status information of each individual battery cell in the target vehicle battery; Based on the state information, a continuous state feature cloud model is obtained by performing time-series continuous modeling. The battery health change trend of the target vehicle battery is determined based on the continuous state feature cloud model. The battery health of the target vehicle battery is assessed based on the battery health change trend, and the assessment results are obtained.

2. The method for assessing the health of electric vehicle batteries according to claim 1, characterized in that, The step of obtaining the state information of each individual cell in the target vehicle battery based on the battery state big data includes: The battery status big data is clustered and divided according to the battery's working status to obtain multiple categories of processed data; The processed data for each category is segmented into time segments to obtain time segment data for each category; State identification is performed based on the time segment data to obtain the state information of each individual battery cell.

3. The method for assessing the health of electric vehicle batteries according to claim 1, characterized in that, Determining the battery health trend of the target vehicle battery based on the continuous state feature cloud model includes: The state feature cloud model was analyzed, and the analysis results were obtained. The battery health trend was determined based on the analysis results.

4. The method for assessing the health of electric vehicle batteries according to claim 1, characterized in that, The assessment of the battery health of the target vehicle battery based on the battery health change trend, to obtain the assessment results, includes: Determine a comparison time period group; wherein, the comparison time period group includes two time periods to be compared; The cloud model parameters of the comparison time period group are analyzed based on the battery health change trend to obtain the analysis results; Based on the analysis results, determine whether there are similar distance plotting point jumps; If so, the assessment result is determined to be that the target vehicle battery has a cell abnormality; If not, the assessment result is determined to be that the target vehicle battery does not have any cell abnormalities.

5. The method for assessing the health of electric vehicle batteries according to claim 4, characterized in that, The analysis of cloud model parameters for the comparison time period group based on the battery health change trend yields the following results: The parameters of the first cloud model and the second cloud model to be compared are determined based on the comparison time period group. A first cloud droplet combination is generated based on the first cloud model parameters, and a second cloud droplet combination is generated based on the second cloud model parameters; wherein the number of cloud droplets in the first cloud droplet combination is the same as the number of cloud droplets in the second cloud droplet combination, and the number of cloud droplets in the first cloud droplet combination is greater than a preset number threshold. The cloud droplet distances are calculated sequentially based on the first cloud droplet combination and the second cloud droplet combination; Calculate the expected distance value of the cloud droplet distance; The analysis results are determined based on the expected distance value.

6. A battery health assessment device for electric vehicles, characterized in that, The electric vehicle battery health assessment device includes: The first acquisition unit is used to acquire big data on the battery status of the target vehicle battery through the vehicle network; The second acquisition unit is used to acquire the status information of each individual cell in the target vehicle battery based on the battery status big data. The modeling unit is used to perform continuous modeling based on the state information in a time sequence to obtain a continuous state feature cloud model. A determining unit is used to determine the battery health change trend of the target vehicle battery based on the continuous state feature cloud model; An evaluation unit is used to evaluate the battery health of the target vehicle battery based on the battery health change trend and obtain evaluation results.

7. The electric vehicle battery health assessment device according to claim 6, characterized in that, The second acquisition unit includes: The first processing subunit is used to perform clustering and classification processing on the battery status big data according to the battery's working status to obtain multiple categories of processed data. The second processing subunit is used to perform time segmentation processing on the processing data of each category to obtain time segment data of each category; The state identification subunit is used to identify the state based on the time segment data to obtain the state information of each individual battery cell.

8. The electric vehicle battery health assessment device according to claim 6, characterized in that, The determining unit includes: The first analysis subunit is used to analyze the state feature cloud model and obtain the analysis results; The first determining subunit is used to determine the battery health change trend based on the analysis results.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor running the computer program to enable the electronic device to perform the electric vehicle battery health assessment method according to any one of claims 1 to 5.

10. A readable storage medium, characterized in that, The readable storage medium stores computer program instructions, which are read and executed by a processor to perform the electric vehicle battery health assessment method according to any one of claims 1 to 5.

Images