Power battery self-discharge rate evaluation method, device and equipment based on big data

Abstract

The invention relates to the technical field of data processing, and provides a power battery self-discharge rate evaluation method, device and equipment based on big data, and the method comprises the steps: obtaining the initial operation data of a power battery, and carrying out the first preprocessing of the initial operation data, and obtaining the target data; wherein the target data represents voltage information of a target sampling point in a target time frame in a target data fragment of the initial operation data; calculating a self-discharge parameter of the power battery based on the target data; determining at least one self-discharge threshold value by using a preset rule based on the self-discharge parameter; and evaluating the self-discharge capability of the power battery according to a comparison result of the self-discharge parameter and the self-discharge threshold value. According to the technical scheme provided by one or more embodiments of the invention, the self-discharge rate evaluation cost and evaluation time can be reduced, and the timeliness and accuracy of the self-discharge rate evaluation result can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method, device and equipment for evaluating the self-discharge rate of a power battery based on big data. Background Art

[0002] The battery system in an electric vehicle is usually composed of multiple cells connected in series. In general, even if the cells are in an open circuit state, the battery system will produce spontaneous losses, resulting in a gradual decrease in the amount of charge. This phenomenon can be called battery self-discharge. Self-discharge may be caused by thermodynamic instabilities and kinetic factors within the battery. Ideally, the battery cells in a battery pack should have a good and consistent self-discharge rate due to their close production batches and similar operating conditions.

[0003] The self-discharge of batteries can generally be divided into reversible self-discharge and irreversible self-discharge. Self-discharge in which the power loss is within the designed range and does not cause the degradation of the battery system consistency indicators can be defined as reversible self-discharge, and its principle is similar to the normal discharge reaction of the battery. On the contrary, self-discharge that causes the degradation of the battery system consistency indicators can be defined as irreversible self-discharge, which may seriously affect the charge and discharge capabilities of the battery system and even cause the battery system or even the entire vehicle to spontaneously combust.

[0004] Therefore, in order to ensure the reliability and safety of the battery system, it is very necessary to evaluate the self-discharge rate of the power battery. However, the current self-discharge rate of power batteries is mostly evaluated through offline unpacking tests, which has high evaluation costs and long evaluation cycles. Summary of the invention

[0005] In view of this, one or more embodiments of the present disclosure provide a method, device, electronic device and readable storage medium for evaluating the self-discharge rate of a power battery based on big data, which can reduce the cost and time of self-discharge rate evaluation and improve the timeliness and accuracy of the self-discharge rate evaluation results.

[0006] On the one hand, the present disclosure provides a method for evaluating the self-discharge rate of a power battery based on big data, the method comprising: acquiring initial operating data of the power battery, and performing a first preprocessing on the initial operating data to obtain target data; wherein the target data represents voltage information of a target sampling point in a target time frame in a target data segment of the initial operating data; based on the target data, calculating a self-discharge parameter of the power battery; based on the self-discharge parameter, determining at least one self-discharge threshold; and evaluating the self-discharge capacity of the power battery according to a comparison result of the self-discharge parameter and the self-discharge threshold.

[0007] On the other hand, the present disclosure further provides a power battery self-discharge rate evaluation device based on big data, the device comprising: a data processing unit, used to obtain initial operating data of the power battery, and perform a first preprocessing on the initial operating data to obtain target data; wherein the target data represents the voltage information of a target sampling point in a target time frame in a target data segment of the initial operating data; a parameter determination unit, used to calculate the self-discharge parameters of the power battery based on the target data; a threshold determination unit, used to determine at least one self-discharge threshold based on the self-discharge parameters; and an evaluation unit, used to evaluate the self-discharge capacity of the power battery according to a comparison result between the self-discharge parameters and the self-discharge threshold.

[0008] On the other hand, the present disclosure further provides an electronic device, which includes a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the above-mentioned power battery self-discharge rate evaluation method based on big data is implemented.

[0009] On the other hand, the present disclosure further provides a computer-readable storage medium, which is used to store a computer program. When the computer program is executed by a processor, the above-mentioned power battery self-discharge rate evaluation method based on big data is implemented.

[0010] The technical solution provided by one or more embodiments of the present disclosure can extract target data containing voltage information after processing a large amount of power battery operation data. For the target data, key self-discharge parameters can be calculated. Then, under preset rules, the self-discharge threshold can be directly determined by the self-discharge parameters. By comparing the self-discharge parameters with the self-discharge threshold, the self-discharge capacity of the power battery can be evaluated.

[0011] The technical solution provided by one or more embodiments of the present disclosure starts with the power battery operation data and can greatly reduce the evaluation cost and evaluation time of the power battery self-discharge rate evaluation through data analysis and evaluation, and can also improve the timeliness and accuracy of the power battery self-discharge rate evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The features and advantages of the embodiments of the present disclosure may be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the present disclosure in any way. In the accompanying drawings:

[0013] Figure 1 A schematic diagram showing the steps of a method for evaluating the self-discharge rate of a power battery based on big data in one embodiment of the present disclosure is shown;

[0014] Figure 2 A schematic diagram of a charging segment division method in one embodiment of the present disclosure is shown;

[0015] Figure 3 A schematic diagram showing the calculation results of the self-discharge rate index in one embodiment of the present disclosure is shown;

[0016] Figure 4 A schematic diagram of a normal state of self-discharge rate in one embodiment of the present disclosure is shown;

[0017] Figure 5 A schematic diagram of an abnormal state of self-discharge rate in one embodiment of the present disclosure is shown;

[0018] Figure 6 A schematic diagram of self-discharge capability evaluation results in one embodiment of the present disclosure is shown;

[0019] Figure 7 A schematic diagram of a process of evaluating a power battery self-discharge rate based on big data in one embodiment of the present disclosure is shown;

[0020] Figure 8 A schematic diagram of functional units of a power battery self-discharge rate evaluation device based on big data in one embodiment of the present disclosure is shown;

[0021] Fig. 9 A schematic structural diagram of an electronic device in one embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0023] See also Figure 1 , a method for evaluating the self-discharge rate of a power battery based on big data provided in one embodiment of the present disclosure may include the following steps.

[0024] S1: Acquire initial operation data of the power battery, and perform a first preprocessing on the initial operation data to obtain target data; wherein the target data represents voltage information of a target sampling point in a target time frame in a target data segment of the initial operation data.

[0025] In this embodiment, the long-term operation data of the power battery is mainly selected as the initial operation data. The initial operation data can be data of multiple dimensions and multiple application scenarios, and the content of the initial operation data can include but is not limited to voltage data, current data, temperature data, time data, vehicle startup status data, vehicle charging status data, etc.

[0026] In some embodiments, the first preprocessing of the initial operating data to obtain target data includes: using a start status mark and a charging status mark to mark the initial operating data to form a first data set; determining the target data based on the first data set; wherein the start status mark is used to mark the vehicle start status, and the vehicle start status includes vehicle start and vehicle shutdown; the charging status mark is used to mark the vehicle charging status, and the vehicle charging status includes at least one of parking charging, shutdown charging, not charging, and charging completion.

[0027] In a practical application example, the initial operation data can be divided into seven categories according to the vehicle data format and definition requirements in a certain industry standard (as shown in Table 1), and the vehicle status can be mainly divided into seven categories: vehicle start-up and parking charging, vehicle start-up and driving charging, vehicle start-up but not charging, vehicle start-up and charging completed, engine off and parking charging, engine off and not charging, and engine off and charging completed.

[0028] In a practical application example, considering that the initial operation data may be mixed with multiple states such as discharge, energy recovery, and no output, which increases the complexity of data processing, and the probability of parking discharge state data is relatively low, this application example can filter and mark the initial operation data. The specific filtering and marking method is: first filter the data according to the vehicle startup state, for example, filter out the vehicle startup state data, marked as 0×01, filter out the vehicle shutdown state data, marked as 0×02; then filter the data according to the vehicle charging state, for example, filter out the vehicle parking state data, marked as 0×01.

[0029] Table 1 Vehicle data format and definition table

[0030]

[0031]

[0032] By screening and marking the initial operation log, invalid or low-value data can be filtered out, data statistics and analysis can be facilitated, the efficiency and accuracy of data processing can be increased, and the efficiency and accuracy of self-discharge rate evaluation can be increased.

[0033] In some embodiments, the first preprocessing of the initial operation data to obtain the target data includes: determining at least one flameout data segment in the initial operation data according to the flameout state of the vehicle; determining the first parking charging state information frame in the flameout data segment as a fragment charging start frame; determining the previous information frame in the initial operation data that is not in the parking charging state and is sequentially connected to the fragment charging start frame as a conditional charging start frame; determining the last parking charging state information frame in the flameout data segment as a fragment charging end frame; determining the next information frame in the initial operation data that is not in the parking charging state and is sequentially connected to the fragment charging end frame as a conditional charging end frame; marking the initial operation data according to the fragment charging start frame, the conditional charging start frame, the fragment charging end frame and the conditional charging end frame to form a second data set; and determining the target data based on the second data set.

[0034] For a practical example, see Figure 2 , the initial operation data can be segmented according to the number of charging times to form segmented data, which is convenient for subsequent data processing and calculation. The specific method for segmenting the initial operation data can be: in the data segment where status (indicating the vehicle startup status) is 2 (indicating the vehicle is turned off), the first information frame where c_stat (indicating the vehicle charging status) is 1 (indicating parking charging) is determined as the segment charging start frame; in the initial operation data, the previous information frame where c_stat is not 1 and is connected to the segment charging start frame sequence is determined as the conditional charging start frame; in the data segment where status is 2, the last information frame where c_stat is 1 is determined as the segment charging end frame; in the initial operation data, the next information frame where c_stat is not 1 and is connected to the segment charging end frame sequence is determined as the conditional charging end frame.

[0035] It should be noted that if there is a frame with c_stat not being 1 (eg c_stat=2, indicating driving charging; c_stat=3, indicating no charging) within the charging segment defined by the segment charging start frame and the segment charging end frame, it can be determined as an abnormal frame.

[0036] The initial operation data is marked by the fragment charging start frame, conditional charging start frame, fragment charging end frame and conditional charging end frame, which is conducive to dividing the charging data fragments in the initial operation data. Using the charging data fragments, the self-discharge parameters can be easily calculated to realize the self-discharge rate evaluation.

[0037] In some embodiments, determining the target data based on the second data set includes performing a second preprocessing on the second data set to obtain a third data set, and determining the target data based on the third data set.

[0038] Specifically, the second preprocessing of the second data set may be to determine, for a candidate data segment in the second data set, whether the charged power represented by the candidate data segment exceeds a predetermined power.

[0039] In a practical application example, the long-cycle initial operation data of the power battery is subjected to a second preprocessing, and the data of a certain time window can be selected for processing, so as to facilitate code deployment and periodic calculation. It can be determined whether the statistical charging power of all charging segments in the time window exceeds the predetermined power. Among them, the statistical charging power can be obtained by calculating the difference between the remaining battery power at the end of the time window and the remaining battery power at the beginning of the time window. If the statistical charging power does not exceed the predetermined power, the self-discharge rate status in the time window can be diagnosed as 0. For example, the daily operation data segment can be read and calculated to determine that the statistical charging power of the day is more than 30% of the total battery capacity. If it exceeds 30%, the self-discharge rate of the day can continue to be evaluated, otherwise the self-discharge rate status of the day can be set to 0.

[0040] The second preprocessing of the second data set may include screening the candidate data segments for data whose temperature information satisfies a preset temperature condition.

[0041] In an actual application example, data with battery temperature values ​​in a predetermined numerical range (eg, [-15, 60]) may be filtered.

[0042] The second preprocessing of the second data set may be to screen the candidate data segments whose initial power quantity meets a preset power quantity condition.

[0043] In a practical application example, data segments whose initial battery power is within a predetermined numerical range (eg, [0, 100]) may be filtered.

[0044] The second preprocessing of the second data set may be to correct the lowest voltage value of the battery cell, the highest voltage value of the battery cell, and the average voltage value of the battery cell for the candidate data segment.

[0045] In a practical application example, data of the battery cell minimum voltage value, the battery cell maximum voltage value, and the battery cell average voltage value outside a predetermined value range (eg, [1500 mV, 4500 mV]) may be replaced with null values.

[0046] The second preprocessing of the second data set may be to calculate the average voltage value of the battery cell for the candidate data segment.

[0047] In a practical application example, the average voltage value of the battery cells can be calculated based on the total voltage of the power battery and the number of battery cells.

[0048] The second preprocessing of the second data set may be to remove data of the candidate data segments, where the battery cell minimum voltage value, the battery cell maximum voltage value, and the battery cell average voltage value are all null values.

[0049] The second preprocessing of the second data set may be to correct the isolated point data according to the difference between the lowest voltage value of the battery cell and the highest voltage value of the battery cell for the candidate data segment.

[0050] In a practical application example, the difference between the lowest voltage value of a battery cell and the highest voltage value of the battery cell outside a predetermined value range (eg, [1500mV, 4500mV]) can be determined as isolated point data, and the value of the isolated point data can be replaced with a null value.

[0051] The second preprocessing of the second data set may be to calculate the target data for the candidate data segments and to establish a data matrix of the target data.

[0052] In a practical application example, the initial operation data can be processed in sections according to the charging and discharging process, taking a discharge and charging process as a section. Taking voltage data as an example, a data matrix of the i-th section voltage data can be established, and the formula is as follows:

[0053]

[0054] in, is the j-th frame voltage of the k-th sampling point in the i-th voltage matrix, m i is the number of rows of the voltage matrix of the i-th segment, n is the number of columns of the voltage matrix (the number of voltage sampling points), and p is the number of segmented voltage matrices. The voltage matrix data sample of the i-th segment can be referred to Table 2.

[0055] Table 2 Voltage matrix data sample table

[0056]

[0057]

[0058] Through the second preprocessing, the abnormal voltage data, abnormal current data and abnormal temperature data in the initial operation data can be corrected, and missing data can be filled and erroneous data can be deleted. In this way, the reliability of the data can be guaranteed, and the reliability of the self-discharge rate evaluation method can be guaranteed.

[0059] S2: Calculating the self-discharge parameters of the power battery based on the target data.

[0060] In this embodiment, the target data may represent voltage information of a target sampling point in a target time frame in a target data segment. Based on the target data, a self-discharge parameter for evaluating a self-discharge rate characteristic may be calculated.

[0061] In some embodiments, calculating the self-discharge parameter of the power battery based on the target data includes: determining a target voltage value of the target sampling point in the target time frame in the target data segment; determining an average voltage value of the target time frame in the target data segment; determining a consistency difference value based on a difference between the target voltage value and the average voltage value; filtering the consistency difference value to determine a voltage deviation from the average value sequence; averaging the voltage deviation from the average value sequence to determine an average deviation degree of each cell of the target sampling point in the target data segment; and calculating the self-discharge parameter based on the average deviation degree of each cell.

[0062] In a practical application example, the voltage matrix after segmentation can be used to obtain the voltage consistency difference index. For example, the voltage consistency difference of each voltage segment can be calculated based on the battery average-difference model. The formula of the battery average-difference model is described as follows:

[0063]

[0064] in, is the average value of the voltage sampling point of the jth frame in the i-th segment voltage matrix, For the consistency difference value. Gaussian filtering can be performed to reduce the calculation error of voltage consistency caused by factors such as data synchronization and sampling noise, so as to obtain the voltage fragment sequence of each voltage deviation from the average value after filtering. Then, the average value can be calculated for the sequence to obtain the average deviation of k monomers in the i segment.

[0065]

[0066] In a practical application example, the segment durations of all target data segments can be calculated to obtain a duration sequence T = [t1, t2, t3, ..., tn]. Subsequently, a relationship table containing segment durations and monomer average deviation degree information can be established, see Table 3.

[0067] Table 3 Average deviation information of charging segments

[0068]

[0069] In some embodiments, calculating the self-discharge parameter of the power battery includes: calculating the time length of the target data segment; linearly fitting the time length corresponding to the target sampling point and the average deviation degree of the monomer corresponding to the target sampling point to obtain a fitting expression; determining an intercept parameter according to the fitting expression; and determining a self-discharge rate index of the target sampling point according to the intercept parameter.

[0070] In some implementations, the calculating the self-discharge parameter of the power battery includes: determining a slope parameter according to the fitting expression; and determining a self-discharge rate index change rate of the target sampling point according to the slope parameter.

[0071] For a practical example, see Figure 3 , which can be obtained by taking the segment duration of k monomers and the average deviation of k monomers Perform linear fitting and obtain its intercept to obtain the self-discharge rate index sequence [b1, b2, b3, ..., bn] of k monomers.

[0072] Specifically, the duration of the k monomer segments can be used as the independent variable, and the average deviation of the k monomers can be used as the independent variable. As the dependent variable, a fitting formula of the form y=kx+b is established. Among them, x is the independent variable, y is the dependent variable, b is the intercept, and k is the slope. Subsequently, the values ​​of k intercepts can be calculated in sequence by solving the least squares method as the k monomer self-discharge rate indicators; the values ​​of k slopes can be calculated in sequence by solving the least squares method as the change rate of the k monomer self-discharge rate indicators.

[0073] In a practical application example, in order to avoid the uncertainty and false alarm rate of self-discharge assessment caused by a single indicator, especially the sampling method of different cells, or the situation where the self-discharge rate indicator [b1, b2, b3, ..., bn] fluctuates relatively greatly during the high and low end of charge and discharge, filtering can be performed on each calculated value. For example, the matrix [b1, b2, b3, ..., bn] is filtered for the monomer self-discharge rate in the time series dimension to obtain the filtered self-discharge rate indicator matrix

[0074] Similarly, according to the slope vector after fitting After filtering, the filtered self-discharge index change rate can be obtained. In this way, the above fitting formula can be modified as follows:

[0075] It should be noted that the median filtering method may be used to filter the self-discharge rate index or the slope vector.

[0076] In an actual application example, based on the filtered self-discharge rate indicator and the filtered self-discharge indicator change rate, a relationship table including segment duration, self-discharge rate indicator, and self-discharge indicator change rate can be established, see Table 4.

[0077] Table 4 Self-discharge parameter information table for charging segment

[0078]

[0079] S3: Based on the self-discharge parameter, at least one self-discharge threshold is determined using a preset rule.

[0080] S4: Evaluate the self-discharge capability of the power battery according to a comparison result between the self-discharge parameter and the self-discharge threshold.

[0081] In this embodiment, different alarm thresholds can be set according to the self-discharge rate, and a self-discharge fault threshold alarm table can be formed for different vehicle models, different battery types, different mileage stages, and other dimensions.

[0082] For a practical example, see Figure 4 ,In a normal self-discharge state, the value of the self-discharge rate represented by the green dot is lower than the alarm threshold represented by the yellow line.

[0083] For a practical example, see Figure 5 ,In a self-discharge abnormal state, the value of the self-discharge rate represented by the red dot is higher than the alarm threshold represented by the yellow line.

[0084] For a practical example, see Figure 6 , the self-discharge rate index and the self-discharge rate index change rate can be calculated first. According to the vehicle model, battery system type and current total mileage of the vehicle to be evaluated, the self-discharge threshold table can be consulted to determine the self-discharge threshold. Then, according to different threshold information, different fault levels or evaluation results can be output.

[0085] In some embodiments, the self-discharge threshold is mainly obtained by extracting thresholds of different risk levels for the self-discharge rate and the self-discharge change rate through the self-discharge abnormal sample set. For example, the first self-discharge threshold corresponding to the self-discharge rate index of the battery system at different risk stages can be obtained, including sd_sh1, sd_sh2, and sd_sh3. For another example, the second self-discharge threshold corresponding to the change rate of the self-discharge rate index of the battery system at different risk stages can be obtained, including α_sd_sh1, α_sd_sh2, and α_sd_sh3.

[0086] Generally, the self-discharge threshold can be obtained by using the self-discharge abnormal sample data set, and the self-discharge threshold can be automatically calculated by using the classification model based on the classification learning algorithm. The classification model can refer to the Bayesian classification, decision tree, support vector machine and K nearest neighbor models. These classification models need to be pre-trained using a large number of self-discharge abnormal vehicle samples, and also need to be verified by offline testing.

[0087] In some implementations, when the number of self-discharge abnormal samples is insufficient, the self-discharge threshold may be automatically acquired based on actual performance of the data.

[0088] Specifically, the self-discharge rate index of different mileage and different battery systems can be calculated based on the historical data of all vehicles on the platform. And the self-discharge rate index change rate Then we get the maximum and minimum single-cell deviations, and usually the distribution is skewed. For positive skewed distribution, that is, the maximum single-cell deviation of the battery cell is average, we can use 3 times the standard deviation as the self-discharge threshold, which can be adjusted according to the actual situation. The calculation formula of the self-discharge threshold can be expressed as: self-discharge threshold = mean ± (standard deviation × multiple).

[0089] In some embodiments, the first percentile of the self-discharge parameter can be determined as the first self-discharge threshold of the self-discharge parameter; the second percentile of the self-discharge parameter can be determined as the second self-discharge threshold of the self-discharge parameter; and the third percentile of the self-discharge parameter can be determined as the third self-discharge threshold of the self-discharge parameter.

[0090] In a practical application example, the calculation process of the target percentile can be as follows: First, sort the data in ascending or descending order. Secondly, calculate the position of the target percentile, which can be achieved through the formula "position = (target percentile / 100) × (total number of data + 1)". Among them, the total number of data is the size of the data set. If the position is an integer, the data value at that position is directly taken; if the position is a decimal, it means that the position is between two data points, and linear interpolation is usually used to estimate. Finally, according to the calculated position, the value of the corresponding position is obtained from the sorted data, which is the value of the target percentile.

[0091] In an actual application example, the first percentile, the second percentile, and the third percentile may be the 95% percentile, the 97.35% percentile, and the 99.7% percentile, respectively.

[0092] In some embodiments, a self-discharge mean value of the self-discharge parameter and a self-discharge standard deviation of the self-discharge parameter can be calculated; a self-discharge difference between the self-discharge parameter and the self-discharge mean value can be calculated; a self-discharge deviation can be determined based on a quotient of the self-discharge difference and the self-discharge standard deviation; and the self-discharge capability can be evaluated based on the self-discharge deviation.

[0093] See also Figure 7 Another embodiment of the present disclosure provides a method for evaluating the self-discharge rate of a power battery based on big data. The method can use long-term operation data as processing input, and sequentially perform steps such as data screening, data segmentation, data preprocessing, parameter extraction, threshold calculation, and result output.

[0094] Among them, data screening corresponds to the process of determining the first data set above, data segmentation corresponds to the process of determining the second data set above, and data preprocessing corresponds to the process of determining the third data set above, which will not be repeated here. Parameter extraction corresponds to the process of determining the self-discharge parameter above, and threshold calculation corresponds to the process of determining the self-discharge threshold above, which will not be repeated here.

[0095] The technical solution provided by one or more embodiments of the present disclosure can extract target data containing voltage information after processing a large amount of power battery operation data. For the target data, key self-discharge parameters can be calculated. Then, under preset rules, the self-discharge threshold can be directly determined by the self-discharge parameters. By comparing the self-discharge parameters with the self-discharge threshold, the self-discharge capacity of the power battery can be evaluated.

[0096] The technical solution provided by one or more embodiments of the present disclosure starts with the power battery operation data and can greatly reduce the evaluation cost and evaluation time of the power battery self-discharge rate evaluation through data analysis and evaluation, and can also improve the timeliness and accuracy of the power battery self-discharge rate evaluation results.

[0097] See also Figure 8 The present disclosure also provides a power battery self-discharge rate evaluation device based on big data, the device comprising:

[0098] The data processing unit 100 is used to obtain the initial operation data of the power battery, and perform a first preprocessing on the initial operation data to obtain target data; wherein the target data represents the voltage information of a target sampling point in a target time frame in a target data segment of the initial operation data;

[0099] A parameter determination unit 200, configured to calculate a self-discharge parameter of the power battery based on the target data;

[0100] A threshold determination unit 300, configured to determine at least one self-discharge threshold based on the self-discharge parameter and using a preset rule;

[0101] The evaluation unit 400 is used to evaluate the self-discharge capability of the power battery according to the comparison result between the self-discharge parameter and the self-discharge threshold.

[0102] In one embodiment, the data processing unit 100 includes a first data processing subunit 101, which is specifically used to use a startup status mark and a charging status mark to mark the initial operation data to form a first data set; based on the first data set, the target data is determined; wherein the startup status mark is used to mark the vehicle startup status, and the vehicle startup status includes vehicle startup and vehicle shutdown; the charging status mark is used to mark the vehicle charging status, and the vehicle charging status includes at least one of parking charging, shutdown charging, not charging, and charging completion.

[0103] In one embodiment, the data processing unit 100 includes a second data processing subunit 102, which is specifically used to determine at least one flameout data segment in the initial operation data according to the flameout state of the vehicle; determine the first parking charging state information frame in the flameout data segment as a fragment charging start frame; determine the previous information frame in the initial operation data that is not in the parking charging state and is connected to the fragment charging start frame in sequence as a conditional charging start frame; determine the last parking charging state information frame in the flameout data segment as a fragment charging end frame; determine the next information frame in the initial operation data that is not in the parking charging state and is connected to the fragment charging end frame in sequence as a conditional charging end frame; mark the initial operation data according to the fragment charging start frame, the conditional charging start frame, the fragment charging end frame and the conditional charging end frame to form a second data set; and determine the target data based on the second data set.

[0104] In one embodiment, the data processing unit 100 includes a third data processing subunit 103, and the third data processing subunit 103 is specifically used to perform a second preprocessing on the second data set to obtain a third data set, and determine the target data based on the third data set;

[0105] Among them, the second preprocessing of the second data set includes at least one of the following: for the candidate data segments in the second data set, judging whether the charged power represented by the candidate data segments exceeds the predetermined power; for the candidate data segments, screening the data whose temperature information meets the preset temperature condition; screening the candidate data segments whose initial power meets the preset power condition; for the candidate data segments, correcting the minimum voltage value of the battery cell, the maximum voltage value of the battery cell, and the average voltage value of the battery cell; for the candidate data segments, calculating the average voltage value of the battery cell; for the candidate data segments, removing the data whose minimum voltage value of the battery cell, the maximum voltage value of the battery cell, and the average voltage value of the battery cell are all null values; for the candidate data segments, correcting the isolated point data according to the difference between the minimum voltage value of the battery cell and the maximum voltage value of the battery cell; for the candidate data segments, calculating the target data and establishing a data matrix of the target data.

[0106] In one embodiment, the parameter determination unit 200 is specifically used to determine the target voltage value of the target sampling point in the target time frame in the target data segment; determine the average voltage value of the target time frame in the target data segment; determine the consistency difference value based on the difference between the target voltage value and the average voltage value; filter the consistency difference value to determine a voltage deviation from the average value sequence; average the voltage deviation from the average value sequence to determine the average deviation degree of the monomers of the target sampling point in the target data segment; calculate the self-discharge parameter based on the average deviation degree of the monomers.

[0107] In one embodiment, calculating the self-discharge parameter of the power battery includes: calculating the time length of the target data segment; linearly fitting the time length corresponding to the target sampling point and the average deviation degree of the monomer corresponding to the target sampling point to obtain a fitting expression; determining an intercept parameter according to the fitting expression; and determining a self-discharge rate index of the target sampling point according to the intercept parameter.

[0108] In one embodiment, calculating the self-discharge parameter of the power battery includes: determining a slope parameter according to the fitting expression; and determining a self-discharge rate index change rate of the target sampling point according to the slope parameter.

[0109] In one embodiment, the threshold determination unit 300 is specifically used to determine the first percentile of the self-discharge parameter as the first self-discharge threshold of the self-discharge parameter; determine the second percentile of the self-discharge parameter as the second self-discharge threshold of the self-discharge parameter; and determine the third percentile of the self-discharge parameter as the third self-discharge threshold of the self-discharge parameter.

[0110] In one embodiment, the evaluation unit 400 is further used to calculate the self-discharge mean of the self-discharge parameter and the self-discharge standard deviation of the self-discharge parameter; calculate the self-discharge difference between the self-discharge parameter and the self-discharge mean; determine the self-discharge deviation according to the quotient of the self-discharge difference and the self-discharge standard deviation; and evaluate the self-discharge capability according to the self-discharge deviation.

[0111] Each unit described in the above embodiments may be implemented by a computer chip or a product having a certain function. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0112] For the convenience of description, the above devices are described in terms of functions and are described separately in various units. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0113] See also Fig. 9 The present disclosure also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the above-mentioned power battery self-discharge rate evaluation method based on big data is implemented.

[0114] The present disclosure also provides a computer-readable storage medium, which is used to store a computer program. When the computer program is executed by a processor, the above-mentioned power battery self-discharge rate evaluation method based on big data is implemented.

[0115] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0116] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory, that is, implementing the method in the above method embodiment.

[0117] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0118] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0119] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, equipment, and storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0120] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0121] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for evaluating the self-discharge rate of a power battery based on big data, characterized in that: The method comprises: Acquire initial operation data of the power battery, and perform a first preprocessing on the initial operation data to obtain target data; wherein the target data represents voltage information of a target sampling point in a target time frame in a target data segment of the initial operation data; Based on the target data, calculating the self-discharge parameter of the power battery; Based on the self-discharge parameter, determining at least one self-discharge threshold value using a preset rule; The self-discharge capability of the power battery is evaluated according to a comparison result between the self-discharge parameter and the self-discharge threshold.

2. The method according to claim 1, characterized in that: The first preprocessing of the initial operation data to obtain target data includes: Using a startup state mark and a charging state mark, marking the initial operation data to form a first data set; Based on the first data set, determining the target data; Among them, the startup status mark is used to mark the vehicle startup status, and the vehicle startup status includes vehicle startup and vehicle shutdown; the charging status mark is used to mark the vehicle charging status, and the vehicle charging status includes at least one of parking charging, shutdown charging, not charging, and charging completed.

3. The method according to claim 1 or 2, characterized in that: The first preprocessing of the initial operation data to obtain target data includes: Determining at least one flameout data segment in the initial operation data according to a flameout state of the vehicle; Determine the first parking charging state information frame in the shutdown data segment as a segment charging start frame; Determine the last information frame in the initial operation data that is not in the parking charging state and is connected to the fragment charging start frame timing as a conditional charging start frame; Determine the last parking charging state information frame in the shutdown data segment as a segment charging end frame; Determine the next information frame in the initial operation data that is not in the parking charging state and is connected to the fragment charging end frame timing as a conditional charging end frame; annotating the initial operation data according to the segment charging start frame, the conditional charging start frame, the segment charging end frame and the conditional charging end frame to form a second data set; Based on the second data set, the target data is determined.

4. The method according to claim 3, characterized in that: Determining the target data based on the second data set includes performing a second preprocessing on the second data set to obtain a third data set, and determining the target data based on the third data set; The performing a second preprocessing on the second data set includes at least one of the following: For the candidate data segments in the second data set, determining whether the charged power represented by the candidate data segments exceeds a predetermined power; For the candidate data segments, screening data whose temperature information meets a preset temperature condition; Screening the candidate data segments whose initial power quantity meets the preset power quantity condition; For the candidate data segment, correct the lowest voltage value of the battery cell, the highest voltage value of the battery cell, and the average voltage value of the battery cell; Calculating the average voltage value of the battery cell for the candidate data segment; For the candidate data segments, remove data in which the battery cell lowest voltage value, the battery cell highest voltage value, and the battery cell average voltage value are all null values; For the candidate data segment, correcting the isolated point data according to the difference between the lowest voltage value of the battery cell and the highest voltage value of the battery cell; For the candidate data segments, the target data is calculated, and a data matrix of the target data is established.

5. The method according to claim 1, characterized in that The calculating the self-discharge parameter of the power battery based on the target data includes: Determine a target voltage value of the target sampling point in the target time frame in the target data segment; Determining an average voltage value of the target time frame in the target data segment; Determining a consistency difference value based on a difference between the target voltage value and the average voltage value; Filtering the consistency difference value to determine a voltage deviation average value sequence; Calculating the mean of the voltage deviation average value sequence to determine the average deviation degree of the target sampling point in the target data segment; The self-discharge parameter is calculated based on the average deviation degree of the monomers.

6. The method according to claim 5, characterized in that The calculating the self-discharge parameter of the power battery includes: Calculating the time length of the target data segment; Performing a linear fit on the time length corresponding to the target sampling point and the average deviation degree of the monomers corresponding to the target sampling point to obtain a fitting expression; According to the fitting expression, an intercept parameter is determined; A self-discharge rate index of the target sampling point is determined according to the intercept parameter.

7. The method according to claim 6, characterized in that The calculating the self-discharge parameter of the power battery includes: Determine a slope parameter according to the fitting expression; The self-discharge rate index change rate of the target sampling point is determined according to the slope parameter.

8. The method according to claim 1, characterized in that The determining at least one self-discharge threshold value based on the self-discharge parameter and using a preset rule comprises: Determine the first percentile of the self-discharge parameter as the first self-discharge threshold of the self-discharge parameter; Determining the second percentile of the self-discharge parameter as a second self-discharge threshold of the self-discharge parameter; The third percentile of the self-discharge parameter is determined as a third self-discharge threshold of the self-discharge parameter.

9. The method according to claim 1, characterized in that: The method further comprises: Calculating a self-discharge mean value of the self-discharge parameter and a self-discharge standard deviation of the self-discharge parameter; Calculating a self-discharge difference between the self-discharge parameter and the self-discharge mean value; Determining a self-discharge deviation according to a quotient of the self-discharge difference and the self-discharge standard deviation; The self-discharge capability is evaluated according to the self-discharge deviation.

10. A power battery self-discharge rate evaluation device based on big data, characterized in that: The device comprises: A data processing unit, configured to obtain initial operation data of the power battery, and perform a first preprocessing on the initial operation data to obtain target data; wherein the target data represents voltage information of a target sampling point in a target time frame in a target data segment of the initial operation data; a parameter determination unit, configured to calculate a self-discharge parameter of the power battery based on the target data; A threshold determination unit, configured to determine at least one self-discharge threshold based on the self-discharge parameter and using a preset rule; An evaluation unit is used to evaluate the self-discharge capability of the power battery according to a comparison result between the self-discharge parameter and the self-discharge threshold.

11. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images